Timmerman, Marieke E; Ceulemans, Eva; De Roover, Kim; Van Leeuwen, Karla
2013-12-01
To achieve an insightful clustering of multivariate data, we propose subspace K-means. Its central idea is to model the centroids and cluster residuals in reduced spaces, which allows for dealing with a wide range of cluster types and yields rich interpretations of the clusters. We review the existing related clustering methods, including deterministic, stochastic, and unsupervised learning approaches. To evaluate subspace K-means, we performed a comparative simulation study, in which we manipulated the overlap of subspaces, the between-cluster variance, and the error variance. The study shows that the subspace K-means algorithm is sensitive to local minima but that the problem can be reasonably dealt with by using partitions of various cluster procedures as a starting point for the algorithm. Subspace K-means performs very well in recovering the true clustering across all conditions considered and appears to be superior to its competitor methods: K-means, reduced K-means, factorial K-means, mixtures of factor analyzers (MFA), and MCLUST. The best competitor method, MFA, showed a performance similar to that of subspace K-means in easy conditions but deteriorated in more difficult ones. Using data from a study on parental behavior, we show that subspace K-means analysis provides a rich insight into the cluster characteristics, in terms of both the relative positions of the clusters (via the centroids) and the shape of the clusters (via the within-cluster residuals).
Timmerman, Marieke E.; Ceulemans, Eva; De Roover, Kim; Van Leeuwen, Karla
2013-01-01
To achieve an insightful clustering of multivariate data, we propose subspace K-means. Its central idea is to model the centroids and cluster residuals in reduced spaces, which allows for dealing with a wide range of cluster types and yields rich interpretations of the clusters. We review the
3D Building Models Segmentation Based on K-Means++ Cluster Analysis
Zhang, C.; Mao, B.
2016-10-01
3D mesh model segmentation is drawing increasing attentions from digital geometry processing field in recent years. The original 3D mesh model need to be divided into separate meaningful parts or surface patches based on certain standards to support reconstruction, compressing, texture mapping, model retrieval and etc. Therefore, segmentation is a key problem for 3D mesh model segmentation. In this paper, we propose a method to segment Collada (a type of mesh model) 3D building models into meaningful parts using cluster analysis. Common clustering methods segment 3D mesh models by K-means, whose performance heavily depends on randomized initial seed points (i.e., centroid) and different randomized centroid can get quite different results. Therefore, we improved the existing method and used K-means++ clustering algorithm to solve this problem. Our experiments show that K-means++ improves both the speed and the accuracy of K-means, and achieve good and meaningful results.
3D BUILDING MODELS SEGMENTATION BASED ON K-MEANS++ CLUSTER ANALYSIS
Directory of Open Access Journals (Sweden)
C. Zhang
2016-10-01
Full Text Available 3D mesh model segmentation is drawing increasing attentions from digital geometry processing field in recent years. The original 3D mesh model need to be divided into separate meaningful parts or surface patches based on certain standards to support reconstruction, compressing, texture mapping, model retrieval and etc. Therefore, segmentation is a key problem for 3D mesh model segmentation. In this paper, we propose a method to segment Collada (a type of mesh model 3D building models into meaningful parts using cluster analysis. Common clustering methods segment 3D mesh models by K-means, whose performance heavily depends on randomized initial seed points (i.e., centroid and different randomized centroid can get quite different results. Therefore, we improved the existing method and used K-means++ clustering algorithm to solve this problem. Our experiments show that K-means++ improves both the speed and the accuracy of K-means, and achieve good and meaningful results.
Fatigue Feature Extraction Analysis based on a K-Means Clustering Approach
Directory of Open Access Journals (Sweden)
M.F.M. Yunoh
2015-06-01
Full Text Available This paper focuses on clustering analysis using a K-means approach for fatigue feature dataset extraction. The aim of this study is to group the dataset as closely as possible (homogeneity for the scattered dataset. Kurtosis, the wavelet-based energy coefficient and fatigue damage are calculated for all segments after the extraction process using wavelet transform. Kurtosis, the wavelet-based energy coefficient and fatigue damage are used as input data for the K-means clustering approach. K-means clustering calculates the average distance of each group from the centroid and gives the objective function values. Based on the results, maximum values of the objective function can be seen in the two centroid clusters, with a value of 11.58. The minimum objective function value is found at 8.06 for five centroid clusters. It can be seen that the objective function with the lowest value for the number of clusters is equal to five; which is therefore the best cluster for the dataset.
Effects of Group Size and Lack of Sphericity on the Recovery of Clusters in K-Means Cluster Analysis
de Craen, Saskia; Commandeur, Jacques J. F.; Frank, Laurence E.; Heiser, Willem J.
2006-01-01
K-means cluster analysis is known for its tendency to produce spherical and equally sized clusters. To assess the magnitude of these effects, a simulation study was conducted, in which populations were created with varying departures from sphericity and group sizes. An analysis of the recovery of clusters in the samples taken from these…
Cluster analysis of polymers using laser-induced breakdown spectroscopy with K-means
Yangmin, GUO; Yun, TANG; Yu, DU; Shisong, TANG; Lianbo, GUO; Xiangyou, LI; Yongfeng, LU; Xiaoyan, ZENG
2018-06-01
Laser-induced breakdown spectroscopy (LIBS) combined with K-means algorithm was employed to automatically differentiate industrial polymers under atmospheric conditions. The unsupervised learning algorithm K-means were utilized for the clustering of LIBS dataset measured from twenty kinds of industrial polymers. To prevent the interference from metallic elements, three atomic emission lines (C I 247.86 nm , H I 656.3 nm, and O I 777.3 nm) and one molecular line C–N (0, 0) 388.3 nm were used. The cluster analysis results were obtained through an iterative process. The Davies–Bouldin index was employed to determine the initial number of clusters. The average relative standard deviation values of characteristic spectral lines were used as the iterative criterion. With the proposed approach, the classification accuracy for twenty kinds of industrial polymers achieved 99.6%. The results demonstrated that this approach has great potential for industrial polymers recycling by LIBS.
Normalization based K means Clustering Algorithm
Virmani, Deepali; Taneja, Shweta; Malhotra, Geetika
2015-01-01
K-means is an effective clustering technique used to separate similar data into groups based on initial centroids of clusters. In this paper, Normalization based K-means clustering algorithm(N-K means) is proposed. Proposed N-K means clustering algorithm applies normalization prior to clustering on the available data as well as the proposed approach calculates initial centroids based on weights. Experimental results prove the betterment of proposed N-K means clustering algorithm over existing...
Lei, Yang; Yu, Dai; Bin, Zhang; Yang, Yang
2017-01-01
Clustering algorithm as a basis of data analysis is widely used in analysis systems. However, as for the high dimensions of the data, the clustering algorithm may overlook the business relation between these dimensions especially in the medical fields. As a result, usually the clustering result may not meet the business goals of the users. Then, in the clustering process, if it can combine the knowledge of the users, that is, the doctor's knowledge or the analysis intent, the clustering result can be more satisfied. In this paper, we propose an interactive K -means clustering method to improve the user's satisfactions towards the result. The core of this method is to get the user's feedback of the clustering result, to optimize the clustering result. Then, a particle swarm optimization algorithm is used in the method to optimize the parameters, especially the weight settings in the clustering algorithm to make it reflect the user's business preference as possible. After that, based on the parameter optimization and adjustment, the clustering result can be closer to the user's requirement. Finally, we take an example in the breast cancer, to testify our method. The experiments show the better performance of our algorithm.
Worst-case and smoothed analysis of k-means clustering with Bregman divergences
Manthey, Bodo; Röglin, H.
2013-01-01
The $k$-means method is the method of choice for clustering large-scale data sets and it performs exceedingly well in practice despite its exponential worst-case running-time. To narrow the gap between theory and practice, $k$-means has been studied in the semi-random input model of smoothed
Paternal age related schizophrenia (PARS): Latent subgroups detected by k-means clustering analysis.
Lee, Hyejoo; Malaspina, Dolores; Ahn, Hongshik; Perrin, Mary; Opler, Mark G; Kleinhaus, Karine; Harlap, Susan; Goetz, Raymond; Antonius, Daniel
2011-05-01
Paternal age related schizophrenia (PARS) has been proposed as a subgroup of schizophrenia with distinct etiology, pathophysiology and symptoms. This study uses a k-means clustering analysis approach to generate hypotheses about differences between PARS and other cases of schizophrenia. We studied PARS (operationally defined as not having any family history of schizophrenia among first and second-degree relatives and fathers' age at birth ≥ 35 years) in a series of schizophrenia cases recruited from a research unit. Data were available on demographic variables, symptoms (Positive and Negative Syndrome Scale; PANSS), cognitive tests (Wechsler Adult Intelligence Scale-Revised; WAIS-R) and olfaction (University of Pennsylvania Smell Identification Test; UPSIT). We conducted a series of k-means clustering analyses to identify clusters of cases containing high concentrations of PARS. Two analyses generated clusters with high concentrations of PARS cases. The first analysis (N=136; PARS=34) revealed a cluster containing 83% PARS cases, in which the patients showed a significant discrepancy between verbal and performance intelligence. The mean paternal and maternal ages were 41 and 33, respectively. The second analysis (N=123; PARS=30) revealed a cluster containing 71% PARS cases, of which 93% were females; the mean age of onset of psychosis, at 17.2, was significantly early. These results strengthen the evidence that PARS cases differ from other patients with schizophrenia. Hypothesis-generating findings suggest that features of PARS may include a discrepancy between verbal and performance intelligence, and in females, an early age of onset. These findings provide a rationale for separating these phenotypes from others in future clinical, genetic and pathophysiologic studies of schizophrenia and in considering responses to treatment. Copyright © 2011 Elsevier B.V. All rights reserved.
Rozumalski, Adam; Schwartz, Michael H
2009-08-01
In this study a gait classification method was developed and applied to subjects with Cerebral palsy who walk with excessive knee flexion at initial contact. Sagittal plane gait data, simplified using the gait features method, is used as input into a k-means cluster analysis to determine homogeneous groups. Several clinical domains were explored to determine if the clusters are related to underlying pathology. These domains included age, joint range-of-motion, strength, selective motor control, and spasticity. Principal component analysis is used to determine one overall score for each of the multi-joint domains (strength, selective motor control, and spasticity). The current study shows that there are five clusters among children with excessive knee flexion at initial contact. These clusters were labeled, in order of increasing gait pathology: (1) mild crouch with mild equinus, (2) moderate crouch, (3) moderate crouch with anterior pelvic tilt, (4) moderate crouch with equinus, and (5) severe crouch. Further analysis showed that age, range-of-motion, strength, selective motor control, and spasticity were significantly different between the clusters (p<0.001). The general tendency was for the clinical domains to worsen as gait pathology increased. This new classification tool can be used to define homogeneous groups of subjects in crouch gait, which can help guide treatment decisions and outcomes assessment.
Security and Correctness Analysis on Privacy-Preserving k-Means Clustering Schemes
Su, Chunhua; Bao, Feng; Zhou, Jianying; Takagi, Tsuyoshi; Sakurai, Kouichi
Due to the fast development of Internet and the related IT technologies, it becomes more and more easier to access a large amount of data. k-means clustering is a powerful and frequently used technique in data mining. Many research papers about privacy-preserving k-means clustering were published. In this paper, we analyze the existing privacy-preserving k-means clustering schemes based on the cryptographic techniques. We show those schemes will cause the privacy breach and cannot output the correct results due to the faults in the protocol construction. Furthermore, we analyze our proposal as an option to improve such problems but with intermediate information breach during the computation.
Performance Analysis of Entropy Methods on K Means in Clustering Process
Dicky Syahputra Lubis, Mhd.; Mawengkang, Herman; Suwilo, Saib
2017-12-01
K Means is a non-hierarchical data clustering method that attempts to partition existing data into one or more clusters / groups. This method partitions the data into clusters / groups so that data that have the same characteristics are grouped into the same cluster and data that have different characteristics are grouped into other groups.The purpose of this data clustering is to minimize the objective function set in the clustering process, which generally attempts to minimize variation within a cluster and maximize the variation between clusters. However, the main disadvantage of this method is that the number k is often not known before. Furthermore, a randomly chosen starting point may cause two points to approach the distance to be determined as two centroids. Therefore, for the determination of the starting point in K Means used entropy method where this method is a method that can be used to determine a weight and take a decision from a set of alternatives. Entropy is able to investigate the harmony in discrimination among a multitude of data sets. Using Entropy criteria with the highest value variations will get the highest weight. Given this entropy method can help K Means work process in determining the starting point which is usually determined at random. Thus the process of clustering on K Means can be more quickly known by helping the entropy method where the iteration process is faster than the K Means Standard process. Where the postoperative patient dataset of the UCI Repository Machine Learning used and using only 12 data as an example of its calculations is obtained by entropy method only with 2 times iteration can get the desired end result.
Worst-case and smoothed analysis of $k$-means clustering with Bregman divergences
Manthey, Bodo; Röglin, Heiko; Dong, Yingfei; Du, Dingzhu; Ibarra, Oscar
2009-01-01
The $k$-means algorithm is the method of choice for clustering large-scale data sets and it performs exceedingly well in practice. Most of the theoretical work is restricted to the case that squared Euclidean distances are used as similarity measure. In many applications, however, data is to be
K-means Clustering: Lloyd's algorithm
Indian Academy of Sciences (India)
First page Back Continue Last page Overview Graphics. K-means Clustering: Lloyd's algorithm. Refines clusters iteratively. Cluster points using Voronoi partitioning of the centers; Centroids of the clusters determine the new centers. Bad example k = 3, n =4.
Analysis of k-means clustering approach on the breast cancer Wisconsin dataset.
Dubey, Ashutosh Kumar; Gupta, Umesh; Jain, Sonal
2016-11-01
Breast cancer is one of the most common cancers found worldwide and most frequently found in women. An early detection of breast cancer provides the possibility of its cure; therefore, a large number of studies are currently going on to identify methods that can detect breast cancer in its early stages. This study was aimed to find the effects of k-means clustering algorithm with different computation measures like centroid, distance, split method, epoch, attribute, and iteration and to carefully consider and identify the combination of measures that has potential of highly accurate clustering accuracy. K-means algorithm was used to evaluate the impact of clustering using centroid initialization, distance measures, and split methods. The experiments were performed using breast cancer Wisconsin (BCW) diagnostic dataset. Foggy and random centroids were used for the centroid initialization. In foggy centroid, based on random values, the first centroid was calculated. For random centroid, the initial centroid was considered as (0, 0). The results were obtained by employing k-means algorithm and are discussed with different cases considering variable parameters. The calculations were based on the centroid (foggy/random), distance (Euclidean/Manhattan/Pearson), split (simple/variance), threshold (constant epoch/same centroid), attribute (2-9), and iteration (4-10). Approximately, 92 % average positive prediction accuracy was obtained with this approach. Better results were found for the same centroid and the highest variance. The results achieved using Euclidean and Manhattan were better than the Pearson correlation. The findings of this work provided extensive understanding of the computational parameters that can be used with k-means. The results indicated that k-means has a potential to classify BCW dataset.
Xu, Beijie; Recker, Mimi; Qi, Xiaojun; Flann, Nicholas; Ye, Lei
2013-01-01
This article examines clustering as an educational data mining method. In particular, two clustering algorithms, the widely used K-means and the model-based Latent Class Analysis, are compared, using usage data from an educational digital library service, the Instructional Architect (IA.usu.edu). Using a multi-faceted approach and multiple data…
Linear regression models and k-means clustering for statistical analysis of fNIRS data.
Bonomini, Viola; Zucchelli, Lucia; Re, Rebecca; Ieva, Francesca; Spinelli, Lorenzo; Contini, Davide; Paganoni, Anna; Torricelli, Alessandro
2015-02-01
We propose a new algorithm, based on a linear regression model, to statistically estimate the hemodynamic activations in fNIRS data sets. The main concern guiding the algorithm development was the minimization of assumptions and approximations made on the data set for the application of statistical tests. Further, we propose a K-means method to cluster fNIRS data (i.e. channels) as activated or not activated. The methods were validated both on simulated and in vivo fNIRS data. A time domain (TD) fNIRS technique was preferred because of its high performances in discriminating cortical activation and superficial physiological changes. However, the proposed method is also applicable to continuous wave or frequency domain fNIRS data sets.
Soil data clustering by using K-means and fuzzy K-means algorithm
Directory of Open Access Journals (Sweden)
E. Hot
2016-06-01
Full Text Available A problem of soil clustering based on the chemical characteristics of soil, and proper visual representation of the obtained results, is analysed in the paper. To that aim, K-means and fuzzy K-means algorithms are adapted for soil data clustering. A database of soil characteristics sampled in Montenegro is used for a comparative analysis of implemented algorithms. The procedure of setting proper values for control parameters of fuzzy K-means is illustrated on the used database. In addition, validation of clustering is made through visualisation. Classified soil data are presented on the static Google map and dynamic Open Street Map.
Lu, Chi-Jie; Chang, Chi-Chang
2014-01-01
Sales forecasting plays an important role in operating a business since it can be used to determine the required inventory level to meet consumer demand and avoid the problem of under/overstocking. Improving the accuracy of sales forecasting has become an important issue of operating a business. This study proposes a hybrid sales forecasting scheme by combining independent component analysis (ICA) with K-means clustering and support vector regression (SVR). The proposed scheme first uses the ICA to extract hidden information from the observed sales data. The extracted features are then applied to K-means algorithm for clustering the sales data into several disjoined clusters. Finally, the SVR forecasting models are applied to each group to generate final forecasting results. Experimental results from information technology (IT) product agent sales data reveal that the proposed sales forecasting scheme outperforms the three comparison models and hence provides an efficient alternative for sales forecasting.
A New Variable Weighting and Selection Procedure for K-Means Cluster Analysis
Steinley, Douglas; Brusco, Michael J.
2008-01-01
A variance-to-range ratio variable weighting procedure is proposed. We show how this weighting method is theoretically grounded in the inherent variability found in data exhibiting cluster structure. In addition, a variable selection procedure is proposed to operate in conjunction with the variable weighting technique. The performances of these…
Andersen, Erlend K F; Kristensen, Gunnar B; Lyng, Heidi; Malinen, Eirik
2011-08-01
Pharmacokinetic analysis of dynamic contrast enhanced magnetic resonance images (DCEMRI) allows for quantitative characterization of vascular properties of tumors. The aim of this study is twofold, first to determine if tumor regions with similar vascularization could be labeled by clustering methods, second to determine if the identified regions can be associated with local cancer relapse. Eighty-one patients with locally advanced cervical cancer treated with chemoradiotherapy underwent DCEMRI with Gd-DTPA prior to external beam radiotherapy. The median follow-up time after treatment was four years, in which nine patients had primary tumor relapse. By fitting a pharmacokinetic two-compartment model function to the temporal contrast enhancement in the tumor, two pharmacokinetic parameters, K(trans) and ύ(e), were estimated voxel by voxel from the DCEMR-images. Intratumoral regions with similar vascularization were identified by k-means clustering of the two pharmacokinetic parameter estimates over all patients. The volume fraction of each cluster was used to evaluate the prognostic value of the clusters. Three clusters provided a sufficient reduction of the cluster variance to label different vascular properties within the tumors. The corresponding median volume fraction of each cluster was 38%, 46% and 10%. The second cluster was significantly associated with primary tumor control in a log-rank survival test (p-value: 0.042), showing a decreased risk of treatment failure for patients with high volume fraction of voxels. Intratumoral regions showing similar vascular properties could successfully be labeled in three distinct clusters and the volume fraction of one cluster region was associated with primary tumor control.
International Nuclear Information System (INIS)
Andersen, Erlend K. F.; Kristensen, Gunnar B.; Lyng, Heidi; Malinen, Eirik
2011-01-01
Introduction. Pharmacokinetic analysis of dynamic contrast enhanced magnetic resonance images (DCEMRI) allows for quantitative characterization of vascular properties of tumors. The aim of this study is twofold, first to determine if tumor regions with similar vascularization could be labeled by clustering methods, second to determine if the identified regions can be associated with local cancer relapse. Materials and methods. Eighty-one patients with locally advanced cervical cancer treated with chemoradiotherapy underwent DCEMRI with Gd-DTPA prior to external beam radiotherapy. The median follow-up time after treatment was four years, in which nine patients had primary tumor relapse. By fitting a pharmacokinetic two-compartment model function to the temporal contrast enhancement in the tumor, two pharmacokinetic parameters, K trans and u e , were estimated voxel by voxel from the DCEMR-images. Intratumoral regions with similar vascularization were identified by k-means clustering of the two pharmacokinetic parameter estimates over all patients. The volume fraction of each cluster was used to evaluate the prognostic value of the clusters. Results. Three clusters provided a sufficient reduction of the cluster variance to label different vascular properties within the tumors. The corresponding median volume fraction of each cluster was 38%, 46% and 10%. The second cluster was significantly associated with primary tumor control in a log-rank survival test (p-value: 0.042), showing a decreased risk of treatment failure for patients with high volume fraction of voxels. Conclusions. Intratumoral regions showing similar vascular properties could successfully be labeled in three distinct clusters and the volume fraction of one cluster region was associated with primary tumor control
Energy Technology Data Exchange (ETDEWEB)
Andersen, Erlend K. F. (Dept. of Medical Physics, The Norwegian Radium Hospital, Oslo Univ. Hospital, Oslo (Norway)), e-mail: eirik.malinen@fys.uio.no; Kristensen, Gunnar B. (Section for Gynaecological Oncology, The Norwegian Radium Hospital, Oslo Univ. Hospital, Oslo (Norway)); Lyng, Heidi (Dept. of Radiation Biology, The Norwegian Radium Hospital, Oslo Univ. Hospital, Oslo (Norway)); Malinen, Eirik (Dept. of Medical Physics, The Norwegian Radium Hospital, Oslo Univ. Hospital, Oslo (Norway); Dept. of Physics, Univ. of Oslo, Oslo (Norway))
2011-08-15
Introduction. Pharmacokinetic analysis of dynamic contrast enhanced magnetic resonance images (DCEMRI) allows for quantitative characterization of vascular properties of tumors. The aim of this study is twofold, first to determine if tumor regions with similar vascularization could be labeled by clustering methods, second to determine if the identified regions can be associated with local cancer relapse. Materials and methods. Eighty-one patients with locally advanced cervical cancer treated with chemoradiotherapy underwent DCEMRI with Gd-DTPA prior to external beam radiotherapy. The median follow-up time after treatment was four years, in which nine patients had primary tumor relapse. By fitting a pharmacokinetic two-compartment model function to the temporal contrast enhancement in the tumor, two pharmacokinetic parameters, Ktrans and u{sub e}, were estimated voxel by voxel from the DCEMR-images. Intratumoral regions with similar vascularization were identified by k-means clustering of the two pharmacokinetic parameter estimates over all patients. The volume fraction of each cluster was used to evaluate the prognostic value of the clusters. Results. Three clusters provided a sufficient reduction of the cluster variance to label different vascular properties within the tumors. The corresponding median volume fraction of each cluster was 38%, 46% and 10%. The second cluster was significantly associated with primary tumor control in a log-rank survival test (p-value: 0.042), showing a decreased risk of treatment failure for patients with high volume fraction of voxels. Conclusions. Intratumoral regions showing similar vascular properties could successfully be labeled in three distinct clusters and the volume fraction of one cluster region was associated with primary tumor control
Adya Zizwan, Putra; Zarlis, Muhammad; Budhiarti Nababan, Erna
2017-12-01
The determination of Centroid on K-Means Algorithm directly affects the quality of the clustering results. Determination of centroid by using random numbers has many weaknesses. The GenClust algorithm that combines the use of Genetic Algorithms and K-Means uses a genetic algorithm to determine the centroid of each cluster. The use of the GenClust algorithm uses 50% chromosomes obtained through deterministic calculations and 50% is obtained from the generation of random numbers. This study will modify the use of the GenClust algorithm in which the chromosomes used are 100% obtained through deterministic calculations. The results of this study resulted in performance comparisons expressed in Mean Square Error influenced by centroid determination on K-Means method by using GenClust method, modified GenClust method and also classic K-Means.
International Nuclear Information System (INIS)
Zhou, Hongming; Soh, Yeng Chai; Wu, Xiaoying
2015-01-01
Maintaining a desired comfort level while minimizing the total energy consumed is an interesting optimization problem in Heating, ventilating and air conditioning (HVAC) system control. This paper proposes a localized control strategy that uses Computational Fluid Dynamics (CFD) simulation results and K-means clustering algorithm to optimally partition an air-conditioned room into different zones. The temperature and air velocity results from CFD simulation are combined in two ways: 1) based on the relationship indicated in predicted mean vote (PMV) formula; 2) based on the relationship extracted from ASHRAE RP-884 database using extreme learning machine (ELM). Localized control can then be effected in which each of the zones can be treated individually and an optimal control strategy can be developed based on the partitioning result. - Highlights: • The paper provides a visual guideline for thermal comfort analysis. • CFD, K-means, PMV and ELM are used to analyze thermal conditions within a room. • Localized control strategy could be developed based on our clustering results
Lu, Siqi; Wang, Xiaorong; Wu, Junyong
2018-01-01
The paper presents a method to generate the planning scenarios, which is based on K-means clustering analysis algorithm driven by data, for the location and size planning of distributed photovoltaic (PV) units in the network. Taken the power losses of the network, the installation and maintenance costs of distributed PV, the profit of distributed PV and the voltage offset as objectives and the locations and sizes of distributed PV as decision variables, Pareto optimal front is obtained through the self-adaptive genetic algorithm (GA) and solutions are ranked by a method called technique for order preference by similarity to an ideal solution (TOPSIS). Finally, select the planning schemes at the top of the ranking list based on different planning emphasis after the analysis in detail. The proposed method is applied to a 10-kV distribution network in Gansu Province, China and the results are discussed.
A Variable-Selection Heuristic for K-Means Clustering.
Brusco, Michael J.; Cradit, J. Dennis
2001-01-01
Presents a variable selection heuristic for nonhierarchical (K-means) cluster analysis based on the adjusted Rand index for measuring cluster recovery. Subjected the heuristic to Monte Carlo testing across more than 2,200 datasets. Results indicate that the heuristic is extremely effective at eliminating masking variables. (SLD)
ANALISIS CLUSTER K-MEANS DALAM PENGELOMPOKAN KEMAMPUAN MAHASISWA
Directory of Open Access Journals (Sweden)
B. Poerwanto
2016-12-01
Full Text Available Abstract. Cluster Analysis, K-Means Algorithm, Student Classification. This study aims to classify students based on learning outcomes for subject the basic of statistics (DDS, which is measured based on attendance, task, midterm (UTS, and final exams (UAS to further used to evaluate learning for subjects that require analysis of quantitative . This study uses k-means cluster analysis to classify the students into three groups based on learning outcomes. After grouped, there are 3 people in the low category, 27 in the medium category and over 70% in the high category.Abstrak. Analisis Cluster K-Means dalam Pengelompokan Kemampuan Mahasiswa. Pene-litian ini bertujuan untuk mengelompokkan mahasiswa berdasarkan hasil belajar mata kuliah dasar-dasar statistika (DDS yang diukur berdasarkan variabel nilai kehadiran, tugas, ujian tengah semester (UTS, dan ujian akhir semester (UAS untuk selanjutnya digunakan untuk mengevaluasi pembelajaran untuk mata kuliah yang membutuhkan kemampuan analisis kuantititatif yang baik. Penelitian ini menggunakan analisis cluster k-means dalam mengelompokkan mahasiswa ke dalam tiga kelompok berdasarkan hasil belajarnya. Seteleh dikelompokkan, terdapat 3 orang yang masuk pada kategori rendah, 27 orang pada kategori sedang dan lebih dari 70% pada kategori tinggi.Kata Kunci: Cluster Analysis, K-Means Algoritma, Klasifikasi Mahasiswa, Universitas Cokroaminoto Palopo
Choosing the Number of Clusters in K-Means Clustering
Steinley, Douglas; Brusco, Michael J.
2011-01-01
Steinley (2007) provided a lower bound for the sum-of-squares error criterion function used in K-means clustering. In this article, on the basis of the lower bound, the authors propose a method to distinguish between 1 cluster (i.e., a single distribution) versus more than 1 cluster. Additionally, conditional on indicating there are multiple…
Finding reproducible cluster partitions for the k-means algorithm.
Lisboa, Paulo J G; Etchells, Terence A; Jarman, Ian H; Chambers, Simon J
2013-01-01
K-means clustering is widely used for exploratory data analysis. While its dependence on initialisation is well-known, it is common practice to assume that the partition with lowest sum-of-squares (SSQ) total i.e. within cluster variance, is both reproducible under repeated initialisations and also the closest that k-means can provide to true structure, when applied to synthetic data. We show that this is generally the case for small numbers of clusters, but for values of k that are still of theoretical and practical interest, similar values of SSQ can correspond to markedly different cluster partitions. This paper extends stability measures previously presented in the context of finding optimal values of cluster number, into a component of a 2-d map of the local minima found by the k-means algorithm, from which not only can values of k be identified for further analysis but, more importantly, it is made clear whether the best SSQ is a suitable solution or whether obtaining a consistently good partition requires further application of the stability index. The proposed method is illustrated by application to five synthetic datasets replicating a real world breast cancer dataset with varying data density, and a large bioinformatics dataset.
Performance Evaluation of Incremental K-means Clustering Algorithm
Chakraborty, Sanjay; Nagwani, N. K.
2014-01-01
The incremental K-means clustering algorithm has already been proposed and analysed in paper [Chakraborty and Nagwani, 2011]. It is a very innovative approach which is applicable in periodically incremental environment and dealing with a bulk of updates. In this paper the performance evaluation is done for this incremental K-means clustering algorithm using air pollution database. This paper also describes the comparison on the performance evaluations between existing K-means clustering and i...
*K-means and Cluster Models for Cancer Signatures
Kakushadze, Zura; Yu, Willie
2017-01-01
We present *K-means clustering algorithm and source code by expanding statistical clustering methods applied in https://ssrn.com/abstract=2802753 to quantitative finance. *K-means is statistically deterministic without specifying initial centers, etc. We apply *K-means to extracting cancer signatures from genome data without using nonnegative matrix factorization (NMF). *K-means’ computational cost is a fraction of NMF’s. Using 1389 published samples for 14 cancer types, we find that 3 cancer...
Single pass kernel k-means clustering method
Indian Academy of Sciences (India)
paper proposes a simple and faster version of the kernel k-means clustering ... It has been considered as an important tool ... On the other hand, kernel-based clustering methods, like kernel k-means clus- ..... able at the UCI machine learning repository (Murphy 1994). ... All the data sets have only numeric valued features.
*K-means and cluster models for cancer signatures.
Kakushadze, Zura; Yu, Willie
2017-09-01
We present *K-means clustering algorithm and source code by expanding statistical clustering methods applied in https://ssrn.com/abstract=2802753 to quantitative finance. *K-means is statistically deterministic without specifying initial centers, etc. We apply *K-means to extracting cancer signatures from genome data without using nonnegative matrix factorization (NMF). *K-means' computational cost is a fraction of NMF's. Using 1389 published samples for 14 cancer types, we find that 3 cancers (liver cancer, lung cancer and renal cell carcinoma) stand out and do not have cluster-like structures. Two clusters have especially high within-cluster correlations with 11 other cancers indicating common underlying structures. Our approach opens a novel avenue for studying such structures. *K-means is universal and can be applied in other fields. We discuss some potential applications in quantitative finance.
Smoothed analysis of the k-means method
Arthur, David; Manthey, Bodo; Röglin, Heiko
2011-01-01
The k-means method is one of the most widely used clustering algorithms, drawing its popularity from its speed in practice. Recently, however, it was shown to have exponential worst-case running time. In order to close the gap between practical performance and theoretical analysis, the k-means
Armstrong, Joshua J; Zhu, Mu; Hirdes, John P; Stolee, Paul
2012-12-01
To examine the heterogeneity of home care clients who use rehabilitation services by using the K-means algorithm to identify previously unknown patterns of clinical characteristics. Observational study of secondary data. Home care system. Assessment information was collected on 150,253 home care clients using the provincially mandated Resident Assessment Instrument-Home Care (RAI-HC) data system. Not applicable. Assessment information from every long-stay (>60 d) home care client that entered the home care system between 2005 and 2008 and used rehabilitation services within 3 months of their initial assessment was analyzed. The K-means clustering algorithm was applied using 37 variables from the RAI-HC assessment. The K-means cluster analysis resulted in the identification of 7 relatively homogeneous subgroups that differed on characteristics such as age, sex, cognition, and functional impairment. Client profiles were created to illustrate the diversity of this geriatric population. The K-means algorithm provided a useful way to segment a heterogeneous rehabilitation client population into more homogeneous subgroups. This analysis provides an enhanced understanding of client characteristics and needs, and could enable more appropriate targeting of rehabilitation services for home care clients. Copyright © 2012 American Congress of Rehabilitation Medicine. Published by Elsevier Inc. All rights reserved.
Zou, Ling; Guo, Qian; Xu, Yi; Yang, Biao; Jiao, Zhuqing; Xiang, Jianbo
2016-04-29
Functional magnetic resonance imaging (fMRI) is an important tool in neuroscience for assessing connectivity and interactions between distant areas of the brain. To find and characterize the coherent patterns of brain activity as a means of identifying brain systems for the cognitive reappraisal of the emotion task, both density-based k-means clustering and independent component analysis (ICA) methods can be applied to characterize the interactions between brain regions involved in cognitive reappraisal of emotion. Our results reveal that compared with the ICA method, the density-based k-means clustering method provides a higher sensitivity of polymerization. In addition, it is more sensitive to those relatively weak functional connection regions. Thus, the study concludes that in the process of receiving emotional stimuli, the relatively obvious activation areas are mainly distributed in the frontal lobe, cingulum and near the hypothalamus. Furthermore, density-based k-means clustering method creates a more reliable method for follow-up studies of brain functional connectivity.
Android Malware Classification Using K-Means Clustering Algorithm
Hamid, Isredza Rahmi A.; Syafiqah Khalid, Nur; Azma Abdullah, Nurul; Rahman, Nurul Hidayah Ab; Chai Wen, Chuah
2017-08-01
Malware was designed to gain access or damage a computer system without user notice. Besides, attacker exploits malware to commit crime or fraud. This paper proposed Android malware classification approach based on K-Means clustering algorithm. We evaluate the proposed model in terms of accuracy using machine learning algorithms. Two datasets were selected to demonstrate the practicing of K-Means clustering algorithms that are Virus Total and Malgenome dataset. We classify the Android malware into three clusters which are ransomware, scareware and goodware. Nine features were considered for each types of dataset such as Lock Detected, Text Detected, Text Score, Encryption Detected, Threat, Porn, Law, Copyright and Moneypak. We used IBM SPSS Statistic software for data classification and WEKA tools to evaluate the built cluster. The proposed K-Means clustering algorithm shows promising result with high accuracy when tested using Random Forest algorithm.
An extended k-means technique for clustering moving objects
Directory of Open Access Journals (Sweden)
Omnia Ossama
2011-03-01
Full Text Available k-means algorithm is one of the basic clustering techniques that is used in many data mining applications. In this paper we present a novel pattern based clustering algorithm that extends the k-means algorithm for clustering moving object trajectory data. The proposed algorithm uses a key feature of moving object trajectories namely, its direction as a heuristic to determine the different number of clusters for the k-means algorithm. In addition, we use the silhouette coefficient as a measure for the quality of our proposed approach. Finally, we present experimental results on both real and synthetic data that show the performance and accuracy of our proposed technique.
Lee, Yii-Ching; Huang, Shian-Chang; Huang, Chih-Hsuan; Wu, Hsin-Hung
2016-01-01
This study uses kernel k-means cluster analysis to identify medical staffs with high burnout. The data collected in October to November 2014 are from the emotional exhaustion dimension of the Chinese version of Safety Attitudes Questionnaire in a regional teaching hospital in Taiwan. The number of effective questionnaires including the entire staffs such as physicians, nurses, technicians, pharmacists, medical administrators, and respiratory therapists is 680. The results show that 8 clusters are generated by kernel k-means method. Employees in clusters 1, 4, and 5 are relatively in good conditions, whereas employees in clusters 2, 3, 6, 7, and 8 need to be closely monitored from time to time because they have relatively higher degree of burnout. When employees with higher degree of burnout are identified, the hospital management can take actions to improve the resilience, reduce the potential medical errors, and, eventually, enhance the patient safety. This study also suggests that the hospital management needs to keep track of medical staffs' fatigue conditions and provide timely assistance for burnout recovery through employee assistance programs, mindfulness-based stress reduction programs, positivity currency buildup, and forming appreciative inquiry groups. © The Author(s) 2016.
Directory of Open Access Journals (Sweden)
Yii-Ching Lee PhD
2016-11-01
Full Text Available This study uses kernel k-means cluster analysis to identify medical staffs with high burnout. The data collected in October to November 2014 are from the emotional exhaustion dimension of the Chinese version of Safety Attitudes Questionnaire in a regional teaching hospital in Taiwan. The number of effective questionnaires including the entire staffs such as physicians, nurses, technicians, pharmacists, medical administrators, and respiratory therapists is 680. The results show that 8 clusters are generated by kernel k-means method. Employees in clusters 1, 4, and 5 are relatively in good conditions, whereas employees in clusters 2, 3, 6, 7, and 8 need to be closely monitored from time to time because they have relatively higher degree of burnout. When employees with higher degree of burnout are identified, the hospital management can take actions to improve the resilience, reduce the potential medical errors, and, eventually, enhance the patient safety. This study also suggests that the hospital management needs to keep track of medical staffs’ fatigue conditions and provide timely assistance for burnout recovery through employee assistance programs, mindfulness-based stress reduction programs, positivity currency buildup, and forming appreciative inquiry groups.
Zhang, Jingjing; Dennis, Todd E.
2015-01-01
We present a simple framework for classifying mutually exclusive behavioural states within the geospatial lifelines of animals. This method involves use of three sequentially applied statistical procedures: (1) behavioural change point analysis to partition movement trajectories into discrete bouts of same-state behaviours, based on abrupt changes in the spatio-temporal autocorrelation structure of movement parameters; (2) hierarchical multivariate cluster analysis to determine the number of different behavioural states; and (3) k-means clustering to classify inferred bouts of same-state location observations into behavioural modes. We demonstrate application of the method by analysing synthetic trajectories of known ‘artificial behaviours’ comprised of different correlated random walks, as well as real foraging trajectories of little penguins (Eudyptula minor) obtained by global-positioning-system telemetry. Our results show that the modelling procedure correctly classified 92.5% of all individual location observations in the synthetic trajectories, demonstrating reasonable ability to successfully discriminate behavioural modes. Most individual little penguins were found to exhibit three unique behavioural states (resting, commuting/active searching, area-restricted foraging), with variation in the timing and locations of observations apparently related to ambient light, bathymetry, and proximity to coastlines and river mouths. Addition of k-means clustering extends the utility of behavioural change point analysis, by providing a simple means through which the behaviours inferred for the location observations comprising individual movement trajectories can be objectively classified. PMID:25922935
Directory of Open Access Journals (Sweden)
Jingjing Zhang
Full Text Available We present a simple framework for classifying mutually exclusive behavioural states within the geospatial lifelines of animals. This method involves use of three sequentially applied statistical procedures: (1 behavioural change point analysis to partition movement trajectories into discrete bouts of same-state behaviours, based on abrupt changes in the spatio-temporal autocorrelation structure of movement parameters; (2 hierarchical multivariate cluster analysis to determine the number of different behavioural states; and (3 k-means clustering to classify inferred bouts of same-state location observations into behavioural modes. We demonstrate application of the method by analysing synthetic trajectories of known 'artificial behaviours' comprised of different correlated random walks, as well as real foraging trajectories of little penguins (Eudyptula minor obtained by global-positioning-system telemetry. Our results show that the modelling procedure correctly classified 92.5% of all individual location observations in the synthetic trajectories, demonstrating reasonable ability to successfully discriminate behavioural modes. Most individual little penguins were found to exhibit three unique behavioural states (resting, commuting/active searching, area-restricted foraging, with variation in the timing and locations of observations apparently related to ambient light, bathymetry, and proximity to coastlines and river mouths. Addition of k-means clustering extends the utility of behavioural change point analysis, by providing a simple means through which the behaviours inferred for the location observations comprising individual movement trajectories can be objectively classified.
Zhang, Jingjing; O'Reilly, Kathleen M; Perry, George L W; Taylor, Graeme A; Dennis, Todd E
2015-01-01
We present a simple framework for classifying mutually exclusive behavioural states within the geospatial lifelines of animals. This method involves use of three sequentially applied statistical procedures: (1) behavioural change point analysis to partition movement trajectories into discrete bouts of same-state behaviours, based on abrupt changes in the spatio-temporal autocorrelation structure of movement parameters; (2) hierarchical multivariate cluster analysis to determine the number of different behavioural states; and (3) k-means clustering to classify inferred bouts of same-state location observations into behavioural modes. We demonstrate application of the method by analysing synthetic trajectories of known 'artificial behaviours' comprised of different correlated random walks, as well as real foraging trajectories of little penguins (Eudyptula minor) obtained by global-positioning-system telemetry. Our results show that the modelling procedure correctly classified 92.5% of all individual location observations in the synthetic trajectories, demonstrating reasonable ability to successfully discriminate behavioural modes. Most individual little penguins were found to exhibit three unique behavioural states (resting, commuting/active searching, area-restricted foraging), with variation in the timing and locations of observations apparently related to ambient light, bathymetry, and proximity to coastlines and river mouths. Addition of k-means clustering extends the utility of behavioural change point analysis, by providing a simple means through which the behaviours inferred for the location observations comprising individual movement trajectories can be objectively classified.
Clustering Using Boosted Constrained k-Means Algorithm
Directory of Open Access Journals (Sweden)
Masayuki Okabe
2018-03-01
Full Text Available This article proposes a constrained clustering algorithm with competitive performance and less computation time to the state-of-the-art methods, which consists of a constrained k-means algorithm enhanced by the boosting principle. Constrained k-means clustering using constraints as background knowledge, although easy to implement and quick, has insufficient performance compared with metric learning-based methods. Since it simply adds a function into the data assignment process of the k-means algorithm to check for constraint violations, it often exploits only a small number of constraints. Metric learning-based methods, which exploit constraints to create a new metric for data similarity, have shown promising results although the methods proposed so far are often slow depending on the amount of data or number of feature dimensions. We present a method that exploits the advantages of the constrained k-means and metric learning approaches. It incorporates a mechanism for accepting constraint priorities and a metric learning framework based on the boosting principle into a constrained k-means algorithm. In the framework, a metric is learned in the form of a kernel matrix that integrates weak cluster hypotheses produced by the constrained k-means algorithm, which works as a weak learner under the boosting principle. Experimental results for 12 data sets from 3 data sources demonstrated that our method has performance competitive to those of state-of-the-art constrained clustering methods for most data sets and that it takes much less computation time. Experimental evaluation demonstrated the effectiveness of controlling the constraint priorities by using the boosting principle and that our constrained k-means algorithm functions correctly as a weak learner of boosting.
Elangasinghe, M. A.; Singhal, N.; Dirks, K. N.; Salmond, J. A.; Samarasinghe, S.
2014-09-01
This paper uses artificial neural networks (ANN), combined with k-means clustering, to understand the complex time series of PM10 and PM2.5 concentrations at a coastal location of New Zealand based on data from a single site. Out of available meteorological parameters from the network (wind speed, wind direction, solar radiation, temperature, relative humidity), key factors governing the pattern of the time series concentrations were identified through input sensitivity analysis performed on the trained neural network model. The transport pathways of particulate matter under these key meteorological parameters were further analysed through bivariate concentration polar plots and k-means clustering techniques. The analysis shows that the external sources such as marine aerosols and local sources such as traffic and biomass burning contribute equally to the particulate matter concentrations at the study site. These results are in agreement with the results of receptor modelling by the Auckland Council based on Positive Matrix Factorization (PMF). Our findings also show that contrasting concentration-wind speed relationships exist between marine aerosols and local traffic sources resulting in very noisy and seemingly large random PM10 concentrations. The inclusion of cluster rankings as an input parameter to the ANN model showed a statistically significant (p advanced air dispersion models.
Ckmeans.1d.dp: Optimal k-means Clustering in One Dimension by Dynamic Programming.
Wang, Haizhou; Song, Mingzhou
2011-12-01
The heuristic k -means algorithm, widely used for cluster analysis, does not guarantee optimality. We developed a dynamic programming algorithm for optimal one-dimensional clustering. The algorithm is implemented as an R package called Ckmeans.1d.dp . We demonstrate its advantage in optimality and runtime over the standard iterative k -means algorithm.
K-means clustering for support construction in diffractive imaging.
Hattanda, Shunsuke; Shioya, Hiroyuki; Maehara, Yosuke; Gohara, Kazutoshi
2014-03-01
A method for constructing an object support based on K-means clustering of the object-intensity distribution is newly presented in diffractive imaging. This releases the adjustment of unknown parameters in the support construction, and it is well incorporated with the Gerchberg and Saxton diagram. A simple numerical simulation reveals that the proposed method is effective for dynamically constructing the support without an initial prior support.
K-Means Clustering for Problems with Periodic Attributes
Czech Academy of Sciences Publication Activity Database
Vejmelka, Martin; Musílek, P.; Paluš, Milan; Pelikán, Emil
2009-01-01
Roč. 23, č. 4 (2009), s. 721-743 ISSN 0218-0014 R&D Projects: GA AV ČR 1ET400300513 EU Projects: European Commission(XE) 517133 - BRACCIA Institutional research plan: CEZ:AV0Z10300504 Keywords : clustering algorithms * similarity measures * K- means * periodic attributes Subject RIV: BB - Applied Statistics, Operational Research Impact factor: 0.512, year: 2009
Stricker, M D; Onland-Moret, N C; Boer, J M A; van der Schouw, Y T; Verschuren, W M M; May, A M; Peeters, P H M; Beulens, J W J
2013-03-01
Studies comparing dietary patterns derived from different a posteriori methods in view of predicting disease risk are scarce. We aimed to explore differences between dietary patterns derived from principal component- (PCA) and k-means cluster analysis (KCA) in relation to their food group composition and ability to predict CHD and stroke risk. The study was conducted in the EPIC-NL cohort that consists of 40,011 men and women. Baseline dietary intake was measured using a validated food-frequency questionnaire. Food items were consolidated into 31 food groups. Occurrence of CHD and stroke was assessed through linkage with registries. After 13 years of follow-up, 1,843 CHD and 588 stroke cases were documented. Both PCA and KCA extracted a prudent pattern (high intakes of fish, high-fiber products, raw vegetables, wine) and a western pattern (high consumption of French fries, fast food, low-fiber products, other alcoholic drinks, soft drinks with sugar) with small variation between components and clusters. The prudent component was associated with a reduced risk of CHD (HR for extreme quartiles: 0.87; 95%-CI: 0.75-1.00) and stroke (0.68; 0.53-0.88). The western component was not related to any outcome. The prudent cluster was related with a lower risk of CHD (0.91; 0.82-1.00) and stroke (0.79; 0.67-0.94) compared to the western cluster. PCA and KCA found similar underlying patterns with comparable associations with CHD and stroke risk. A prudent pattern reduced the risk of CHD and stroke. Copyright © 2012 Elsevier B.V. All rights reserved.
Syakur, M. A.; Khotimah, B. K.; Rochman, E. M. S.; Satoto, B. D.
2018-04-01
Clustering is a data mining technique used to analyse data that has variations and the number of lots. Clustering was process of grouping data into a cluster, so they contained data that is as similar as possible and different from other cluster objects. SMEs Indonesia has a variety of customers, but SMEs do not have the mapping of these customers so they did not know which customers are loyal or otherwise. Customer mapping is a grouping of customer profiling to facilitate analysis and policy of SMEs in the production of goods, especially batik sales. Researchers will use a combination of K-Means method with elbow to improve efficient and effective k-means performance in processing large amounts of data. K-Means Clustering is a localized optimization method that is sensitive to the selection of the starting position from the midpoint of the cluster. So choosing the starting position from the midpoint of a bad cluster will result in K-Means Clustering algorithm resulting in high errors and poor cluster results. The K-means algorithm has problems in determining the best number of clusters. So Elbow looks for the best number of clusters on the K-means method. Based on the results obtained from the process in determining the best number of clusters with elbow method can produce the same number of clusters K on the amount of different data. The result of determining the best number of clusters with elbow method will be the default for characteristic process based on case study. Measurement of k-means value of k-means has resulted in the best clusters based on SSE values on 500 clusters of batik visitors. The result shows the cluster has a sharp decrease is at K = 3, so K as the cut-off point as the best cluster.
Li, Chunhui; Sun, Lian; Jia, Junxiang; Cai, Yanpeng; Wang, Xuan
2016-07-01
Source water areas are facing many potential water pollution risks. Risk assessment is an effective method to evaluate such risks. In this paper an integrated model based on k-means clustering analysis and set pair analysis was established aiming at evaluating the risks associated with water pollution in source water areas, in which the weights of indicators were determined through the entropy weight method. Then the proposed model was applied to assess water pollution risks in the region of Shiyan in which China's key source water area Danjiangkou Reservoir for the water source of the middle route of South-to-North Water Diversion Project is located. The results showed that eleven sources with relative high risk value were identified. At the regional scale, Shiyan City and Danjiangkou City would have a high risk value in term of the industrial discharge. Comparatively, Danjiangkou City and Yunxian County would have a high risk value in terms of agricultural pollution. Overall, the risk values of north regions close to the main stream and reservoir of the region of Shiyan were higher than that in the south. The results of risk level indicated that five sources were in lower risk level (i.e., level II), two in moderate risk level (i.e., level III), one in higher risk level (i.e., level IV) and three in highest risk level (i.e., level V). Also risks of industrial discharge are higher than that of the agricultural sector. It is thus essential to manage the pillar industry of the region of Shiyan and certain agricultural companies in the vicinity of the reservoir to reduce water pollution risks of source water areas. Copyright © 2016 Elsevier B.V. All rights reserved.
Enhanced K-means clustering with encryption on cloud
Singh, Iqjot; Dwivedi, Prerna; Gupta, Taru; Shynu, P. G.
2017-11-01
This paper tries to solve the problem of storing and managing big files over cloud by implementing hashing on Hadoop in big-data and ensure security while uploading and downloading files. Cloud computing is a term that emphasis on sharing data and facilitates to share infrastructure and resources.[10] Hadoop is an open source software that gives us access to store and manage big files according to our needs on cloud. K-means clustering algorithm is an algorithm used to calculate distance between the centroid of the cluster and the data points. Hashing is a algorithm in which we are storing and retrieving data with hash keys. The hashing algorithm is called as hash function which is used to portray the original data and later to fetch the data stored at the specific key. [17] Encryption is a process to transform electronic data into non readable form known as cipher text. Decryption is the opposite process of encryption, it transforms the cipher text into plain text that the end user can read and understand well. For encryption and decryption we are using Symmetric key cryptographic algorithm. In symmetric key cryptography are using DES algorithm for a secure storage of the files. [3
Rajab, Maher I
2011-11-01
Since the introduction of epiluminescence microscopy (ELM), image analysis tools have been extended to the field of dermatology, in an attempt to algorithmically reproduce clinical evaluation. Accurate image segmentation of skin lesions is one of the key steps for useful, early and non-invasive diagnosis of coetaneous melanomas. This paper proposes two image segmentation algorithms based on frequency domain processing and k-means clustering/fuzzy k-means clustering. The two methods are capable of segmenting and extracting the true border that reveals the global structure irregularity (indentations and protrusions), which may suggest excessive cell growth or regression of a melanoma. As a pre-processing step, Fourier low-pass filtering is applied to reduce the surrounding noise in a skin lesion image. A quantitative comparison of the techniques is enabled by the use of synthetic skin lesion images that model lesions covered with hair to which Gaussian noise is added. The proposed techniques are also compared with an established optimal-based thresholding skin-segmentation method. It is demonstrated that for lesions with a range of different border irregularity properties, the k-means clustering and fuzzy k-means clustering segmentation methods provide the best performance over a range of signal to noise ratios. The proposed segmentation techniques are also demonstrated to have similar performance when tested on real skin lesions representing high-resolution ELM images. This study suggests that the segmentation results obtained using a combination of low-pass frequency filtering and k-means or fuzzy k-means clustering are superior to the result that would be obtained by using k-means or fuzzy k-means clustering segmentation methods alone. © 2011 John Wiley & Sons A/S.
Robust K-Median and K-Means Clustering Algorithms for Incomplete Data
Directory of Open Access Journals (Sweden)
Jinhua Li
2016-01-01
Full Text Available Incomplete data with missing feature values are prevalent in clustering problems. Traditional clustering methods first estimate the missing values by imputation and then apply the classical clustering algorithms for complete data, such as K-median and K-means. However, in practice, it is often hard to obtain accurate estimation of the missing values, which deteriorates the performance of clustering. To enhance the robustness of clustering algorithms, this paper represents the missing values by interval data and introduces the concept of robust cluster objective function. A minimax robust optimization (RO formulation is presented to provide clustering results, which are insensitive to estimation errors. To solve the proposed RO problem, we propose robust K-median and K-means clustering algorithms with low time and space complexity. Comparisons and analysis of experimental results on both artificially generated and real-world incomplete data sets validate the robustness and effectiveness of the proposed algorithms.
Optimasi Pusat Cluster Awal K-Means dengan Algoritma Genetika Pada Pengelompokan Dokumen
Fauzi, Muhammad
2017-01-01
147038065 Clustering a data set of documents based on certain data points in documents are an easy way to organize document for extension to work. K-Means clustering algorithm is one of iterative cluster algorithm to partition a set of entities into K cluster. Unfortunately, resulting in K?Means cluster is depending on the initial cluster center that generally assigned randomly. In this reserach, determining initial cluster center K-Means for documents clustering are investi...
k-Means Clustering with Hölder Divergences
Nielsen, Frank; Sun, Ke; Marchand-Maillet, Sté phane
2017-01-01
We introduced two novel classes of Hölder divergences and Hölder pseudo-divergences that are both invariant to rescaling, and that both encapsulate the Cauchy-Schwarz divergence and the skew Bhattacharyya divergences. We review the elementary concepts of those parametric divergences, and perform a clustering analysis on two synthetic datasets. It is shown experimentally that the symmetrized Hölder divergences consistently outperform significantly the Cauchy-Schwarz divergence in clustering tasks.
k-Means Clustering with Hölder Divergences
Nielsen, Frank
2017-10-24
We introduced two novel classes of Hölder divergences and Hölder pseudo-divergences that are both invariant to rescaling, and that both encapsulate the Cauchy-Schwarz divergence and the skew Bhattacharyya divergences. We review the elementary concepts of those parametric divergences, and perform a clustering analysis on two synthetic datasets. It is shown experimentally that the symmetrized Hölder divergences consistently outperform significantly the Cauchy-Schwarz divergence in clustering tasks.
A hybridized K-means clustering approach for high dimensional ...
African Journals Online (AJOL)
International Journal of Engineering, Science and Technology ... Due to incredible growth of high dimensional dataset, conventional data base querying methods are inadequate to extract useful information, so researchers nowadays ... Recently cluster analysis is a popularly used data analysis method in number of areas.
Clustering performance comparison using K-means and expectation maximization algorithms.
Jung, Yong Gyu; Kang, Min Soo; Heo, Jun
2014-11-14
Clustering is an important means of data mining based on separating data categories by similar features. Unlike the classification algorithm, clustering belongs to the unsupervised type of algorithms. Two representatives of the clustering algorithms are the K -means and the expectation maximization (EM) algorithm. Linear regression analysis was extended to the category-type dependent variable, while logistic regression was achieved using a linear combination of independent variables. To predict the possibility of occurrence of an event, a statistical approach is used. However, the classification of all data by means of logistic regression analysis cannot guarantee the accuracy of the results. In this paper, the logistic regression analysis is applied to EM clusters and the K -means clustering method for quality assessment of red wine, and a method is proposed for ensuring the accuracy of the classification results.
Bagged K-means clustering of metabolome data
Hageman, J. A.; van den Berg, R. A.; Westerhuis, J. A.; Hoefsloot, H. C. J.; Smilde, A. K.
2006-01-01
Clustering of metabolomics data can be hampered by noise originating from biological variation, physical sampling error and analytical error. Using data analysis methods which are not specially suited for dealing with noisy data will yield sub optimal solutions. Bootstrap aggregating (bagging) is a
On the Equivalence of Nonnegative Matrix Factorization and K-means- Spectral Clustering
Energy Technology Data Exchange (ETDEWEB)
Ding, Chris; He, Xiaofeng; Simon, Horst D.; Jin, Rong
2005-12-04
We provide a systematic analysis of nonnegative matrix factorization (NMF) relating to data clustering. We generalize the usual X = FG{sup T} decomposition to the symmetric W = HH{sup T} and W = HSH{sup T} decompositions. We show that (1) W = HH{sup T} is equivalent to Kernel K-means clustering and the Laplacian-based spectral clustering. (2) X = FG{sup T} is equivalent to simultaneous clustering of rows and columns of a bipartite graph. We emphasizes the importance of orthogonality in NMF and soft clustering nature of NMF. These results are verified with experiments on face images and newsgroups.
Unsupervised Cryo-EM Data Clustering through Adaptively Constrained K-Means Algorithm.
Xu, Yaofang; Wu, Jiayi; Yin, Chang-Cheng; Mao, Youdong
2016-01-01
In single-particle cryo-electron microscopy (cryo-EM), K-means clustering algorithm is widely used in unsupervised 2D classification of projection images of biological macromolecules. 3D ab initio reconstruction requires accurate unsupervised classification in order to separate molecular projections of distinct orientations. Due to background noise in single-particle images and uncertainty of molecular orientations, traditional K-means clustering algorithm may classify images into wrong classes and produce classes with a large variation in membership. Overcoming these limitations requires further development on clustering algorithms for cryo-EM data analysis. We propose a novel unsupervised data clustering method building upon the traditional K-means algorithm. By introducing an adaptive constraint term in the objective function, our algorithm not only avoids a large variation in class sizes but also produces more accurate data clustering. Applications of this approach to both simulated and experimental cryo-EM data demonstrate that our algorithm is a significantly improved alterative to the traditional K-means algorithm in single-particle cryo-EM analysis.
Order-Constrained Solutions in K-Means Clustering: Even Better than Being Globally Optimal
Steinley, Douglas; Hubert, Lawrence
2008-01-01
This paper proposes an order-constrained K-means cluster analysis strategy, and implements that strategy through an auxiliary quadratic assignment optimization heuristic that identifies an initial object order. A subsequent dynamic programming recursion is applied to optimally subdivide the object set subject to the order constraint. We show that…
Optimized data fusion for K-means Laplacian clustering
Yu, Shi; Liu, Xinhai; Tranchevent, Léon-Charles; Glänzel, Wolfgang; Suykens, Johan A. K.; De Moor, Bart; Moreau, Yves
2011-01-01
Motivation: We propose a novel algorithm to combine multiple kernels and Laplacians for clustering analysis. The new algorithm is formulated on a Rayleigh quotient objective function and is solved as a bi-level alternating minimization procedure. Using the proposed algorithm, the coefficients of kernels and Laplacians can be optimized automatically. Results: Three variants of the algorithm are proposed. The performance is systematically validated on two real-life data fusion applications. The proposed Optimized Kernel Laplacian Clustering (OKLC) algorithms perform significantly better than other methods. Moreover, the coefficients of kernels and Laplacians optimized by OKLC show some correlation with the rank of performance of individual data source. Though in our evaluation the K values are predefined, in practical studies, the optimal cluster number can be consistently estimated from the eigenspectrum of the combined kernel Laplacian matrix. Availability: The MATLAB code of algorithms implemented in this paper is downloadable from http://homes.esat.kuleuven.be/~sistawww/bioi/syu/oklc.html. Contact: shiyu@uchicago.edu Supplementary information: Supplementary data are available at Bioinformatics online. PMID:20980271
Implementasi KD-Tree K-Means Clustering untuk Klasterisasi Dokumen
Directory of Open Access Journals (Sweden)
Eric Budiman Gosno
2013-09-01
Full Text Available Klasterisasi dokumen adalah suatu proses pengelompokan dokumen secara otomatis dan unsupervised. Klasterisasi dokumen merupakan permasalahan yang sering ditemui dalam berbagai bidang seperti text mining dan sistem temu kembali informasi. Metode klasterisasi dokumen yang memiliki akurasi dan efisiensi waktu yang tinggi sangat diperlukan untuk meningkatkan hasil pada mesin pencari web, dan untuk proses filtering. Salah satu metode klasterisasi yang telah dikenal dan diaplikasikan dalam klasterisasi dokumen adalah K-Means Clustering. Tetapi K-Means Clustering sensitif terhadap pemilihan posisi awal dari titik tengah klaster sehingga pemilihan posisi awal dari titik tengah klaster yang buruk akan mengakibatkan K-Means Clustering terjebak dalam local optimum. KD-Tree K-Means Clustering merupakan perbaikan dari K-Means Clustering. KD-Tree K-Means Clustering menggunakan struktur data K-Dimensional Tree dan nilai kerapatan pada proses inisialisasi titik tengah klaster. Pada makalah ini diimplementasikan algoritma KD-Tree K-Means Clustering untuk permasalahan klasterisasi dokumen. Performa klasterisasi dokumen yang dihasilkan oleh metode KD-Tree K-Means Clustering pada data set 20 newsgroup memiliki nilai distorsi 3×105 lebih rendah dibandingkan dengan nilai rerata distorsi K-Means Clustering dan nilai NIG 0,09 lebih baik dibandingkan dengan nilai NIG K-Means Clustering.
Improved smoothed analysis of the k-means method
Manthey, Bodo; Röglin, Heiko; Mathieu, C.
2009-01-01
The k-means method is a widely used clustering algorithm. One of its distinguished features is its speed in practice. Its worst-case running-time, however, is exponential, leaving a gap between practical and theoretical performance. Arthur and Vassilvitskii [3] aimed at closing this gap, and they
Single pass kernel k-means clustering method
Indian Academy of Sciences (India)
In unsupervised classiﬁcation, kernel -means clustering method has been shown to perform better than conventional -means clustering method in ... 518501, India; Department of Computer Science and Engineering, Jawaharlal Nehru Technological University, Anantapur College of Engineering, Anantapur 515002, India ...
The global kernel k-means algorithm for clustering in feature space.
Tzortzis, Grigorios F; Likas, Aristidis C
2009-07-01
Kernel k-means is an extension of the standard k -means clustering algorithm that identifies nonlinearly separable clusters. In order to overcome the cluster initialization problem associated with this method, we propose the global kernel k-means algorithm, a deterministic and incremental approach to kernel-based clustering. Our method adds one cluster at each stage, through a global search procedure consisting of several executions of kernel k-means from suitable initializations. This algorithm does not depend on cluster initialization, identifies nonlinearly separable clusters, and, due to its incremental nature and search procedure, locates near-optimal solutions avoiding poor local minima. Furthermore, two modifications are developed to reduce the computational cost that do not significantly affect the solution quality. The proposed methods are extended to handle weighted data points, which enables their application to graph partitioning. We experiment with several data sets and the proposed approach compares favorably to kernel k -means with random restarts.
Iswandhani, N.; Muhajir, M.
2018-03-01
This research was conducted in Department of Statistics Islamic University of Indonesia. The data used are primary data obtained by post @explorejogja instagram account from January until December 2016. In the @explorejogja instagram account found many tourist destinations that can be visited by tourists both in the country and abroad, Therefore it is necessary to form a cluster of existing tourist destinations based on the number of likes from user instagram assumed as the most popular. The purpose of this research is to know the most popular distribution of tourist spot, the cluster formation of tourist destinations, and central popularity of tourist destinations based on @explorejogja instagram account in 2016. Statistical analysis used is descriptive statistics, k-means clustering, and social network analysis. The results of this research were obtained the top 10 most popular destinations in Yogyakarta, map of html-based tourist destination distribution consisting of 121 tourist destination points, formed 3 clusters each consisting of cluster 1 with 52 destinations, cluster 2 with 9 destinations and cluster 3 with 60 destinations, and Central popularity of tourist destinations in the special region of Yogyakarta by district.
K-means clustering versus validation measures: a data-distribution perspective.
Xiong, Hui; Wu, Junjie; Chen, Jian
2009-04-01
K-means is a well-known and widely used partitional clustering method. While there are considerable research efforts to characterize the key features of the K-means clustering algorithm, further investigation is needed to understand how data distributions can have impact on the performance of K-means clustering. To that end, in this paper, we provide a formal and organized study of the effect of skewed data distributions on K-means clustering. Along this line, we first formally illustrate that K-means tends to produce clusters of relatively uniform size, even if input data have varied "true" cluster sizes. In addition, we show that some clustering validation measures, such as the entropy measure, may not capture this uniform effect and provide misleading information on the clustering performance. Viewed in this light, we provide the coefficient of variation (CV) as a necessary criterion to validate the clustering results. Our findings reveal that K-means tends to produce clusters in which the variations of cluster sizes, as measured by CV, are in a range of about 0.3-1.0. Specifically, for data sets with large variation in "true" cluster sizes (e.g., CV > 1.0), K-means reduces variation in resultant cluster sizes to less than 1.0. In contrast, for data sets with small variation in "true" cluster sizes (e.g., CV K-means increases variation in resultant cluster sizes to greater than 0.3. In other words, for the earlier two cases, K-means produces the clustering results which are away from the "true" cluster distributions.
Jamali, Jamshid; Ayatollahi, Seyyed Mohammad Taghi
2015-10-01
Nurses constitute the most providers of health care systems. Their mental health can affect the quality of services and patients' satisfaction. General Health Questionnaire (GHQ-12) is a general screening tool used to detect mental disorders. Scoring method and determining thresholds for this questionnaire are debatable and the cut-off points can vary from sample to sample. This study was conducted to estimate the prevalence of mental disorders among Iranian nurses using GHQ-12 and also compare Latent Class Analysis (LCA) and K-means clustering with traditional scoring method. A cross-sectional study was carried out in Fars and Bushehr provinces of southern Iran in 2014. Participants were 771 Iranian nurses, who filled out the GHQ-12 questionnaire. Traditional scoring method, LCA and K-means were used to estimate the prevalence of mental disorder among Iranian nurses. Cohen's kappa statistic was applied to assess the agreement between the LCA and K-means with traditional scoring method of GHQ-12. The nurses with mental disorder by scoring method, LCA and K-mean were 36.3% (n=280), 32.2% (n=248), and 26.5% (n=204), respectively. LCA and logistic regression revealed that the prevalence of mental disorder in females was significantly higher than males. Mental disorder in nurses was in a medium level compared to other people living in Iran. There was a little difference between prevalence of mental disorder estimated by scoring method, K-means and LCA. According to the advantages of LCA than K-means and different results in scoring method, we suggest LCA for classification of Iranian nurses according to their mental health outcomes using GHQ-12 questionnaire.
An improved K-means clustering algorithm in agricultural image segmentation
Cheng, Huifeng; Peng, Hui; Liu, Shanmei
Image segmentation is the first important step to image analysis and image processing. In this paper, according to color crops image characteristics, we firstly transform the color space of image from RGB to HIS, and then select proper initial clustering center and cluster number in application of mean-variance approach and rough set theory followed by clustering calculation in such a way as to automatically segment color component rapidly and extract target objects from background accurately, which provides a reliable basis for identification, analysis, follow-up calculation and process of crops images. Experimental results demonstrate that improved k-means clustering algorithm is able to reduce the computation amounts and enhance precision and accuracy of clustering.
Sarrafzadeh, Omid; Dehnavi, Alireza Mehri
2015-01-01
Segmentation of leukocytes acts as the foundation for all automated image-based hematological disease recognition systems. Most of the time, hematologists are interested in evaluation of white blood cells only. Digital image processing techniques can help them in their analysis and diagnosis. The main objective of this paper is to detect leukocytes from a blood smear microscopic image and segment them into their two dominant elements, nucleus and cytoplasm. The segmentation is conducted using two stages of applying K-means clustering. First, the nuclei are segmented using K-means clustering. Then, a proposed method based on region growing is applied to separate the connected nuclei. Next, the nuclei are subtracted from the original image. Finally, the cytoplasm is segmented using the second stage of K-means clustering. The results indicate that the proposed method is able to extract the nucleus and cytoplasm regions accurately and works well even though there is no significant contrast between the components in the image. In this paper, a method based on K-means clustering and region growing is proposed in order to detect leukocytes from a blood smear microscopic image and segment its components, the nucleus and the cytoplasm. As region growing step of the algorithm relies on the information of edges, it will not able to separate the connected nuclei more accurately in poor edges and it requires at least a weak edge to exist between the nuclei. The nucleus and cytoplasm segments of a leukocyte can be used for feature extraction and classification which leads to automated leukemia detection.
Profiling Local Optima in K-Means Clustering: Developing a Diagnostic Technique
Steinley, Douglas
2006-01-01
Using the cluster generation procedure proposed by D. Steinley and R. Henson (2005), the author investigated the performance of K-means clustering under the following scenarios: (a) different probabilities of cluster overlap; (b) different types of cluster overlap; (c) varying samples sizes, clusters, and dimensions; (d) different multivariate…
Reducing Earth Topography Resolution for SMAP Mission Ground Tracks Using K-Means Clustering
Rizvi, Farheen
2013-01-01
The K-means clustering algorithm is used to reduce Earth topography resolution for the SMAP mission ground tracks. As SMAP propagates in orbit, knowledge of the radar antenna footprints on Earth is required for the antenna misalignment calibration. Each antenna footprint contains a latitude and longitude location pair on the Earth surface. There are 400 pairs in one data set for the calibration model. It is computationally expensive to calculate corresponding Earth elevation for these data pairs. Thus, the antenna footprint resolution is reduced. Similar topographical data pairs are grouped together with the K-means clustering algorithm. The resolution is reduced to the mean of each topographical cluster called the cluster centroid. The corresponding Earth elevation for each cluster centroid is assigned to the entire group. Results show that 400 data points are reduced to 60 while still maintaining algorithm performance and computational efficiency. In this work, sensitivity analysis is also performed to show a trade-off between algorithm performance versus computational efficiency as the number of cluster centroids and algorithm iterations are increased.
Analysis of Home Energy Consumption by K-Mean
Directory of Open Access Journals (Sweden)
Fahad Razaque
2017-10-01
Full Text Available The smart meter offered exceptional chances to well comprehend energy consumption manners in which quantity of data being generated. One request was the separation of energy load-profiles into clusters of related conduct. The Research measured the resemblance between groups them together and load-profiles into clusters by k-means clustering algorithm. The cluster met, also called “Gender (Male/Female, House (Rented/Owned and customers status (Satisfied/Unsatisfied” display methods of consuming energy. It provided value information aimed at utilities to generate specific electricity charges and healthier aim energy efficiency programs. The results show that 43% extremely dissatisfied of energy customer is achieved by using energy consumption.
Long-term surface EMG monitoring using K-means clustering and compressive sensing
Balouchestani, Mohammadreza; Krishnan, Sridhar
2015-05-01
In this work, we present an advanced K-means clustering algorithm based on Compressed Sensing theory (CS) in combination with the K-Singular Value Decomposition (K-SVD) method for Clustering of long-term recording of surface Electromyography (sEMG) signals. The long-term monitoring of sEMG signals aims at recording of the electrical activity produced by muscles which are very useful procedure for treatment and diagnostic purposes as well as for detection of various pathologies. The proposed algorithm is examined for three scenarios of sEMG signals including healthy person (sEMG-Healthy), a patient with myopathy (sEMG-Myopathy), and a patient with neuropathy (sEMG-Neuropathr), respectively. The proposed algorithm can easily scan large sEMG datasets of long-term sEMG recording. We test the proposed algorithm with Principal Component Analysis (PCA) and Linear Correlation Coefficient (LCC) dimensionality reduction methods. Then, the output of the proposed algorithm is fed to K-Nearest Neighbours (K-NN) and Probabilistic Neural Network (PNN) classifiers in order to calclute the clustering performance. The proposed algorithm achieves a classification accuracy of 99.22%. This ability allows reducing 17% of Average Classification Error (ACE), 9% of Training Error (TE), and 18% of Root Mean Square Error (RMSE). The proposed algorithm also reduces 14% clustering energy consumption compared to the existing K-Means clustering algorithm.
Satria, Fiqih; Aziz, R Z Abdul
2016-01-01
This research aims to determine the steps cluster analysis method with Ward method and K-Means method, and compare the results of the analysis of the two methods for clustering student data related decision-making to determine the students are eligible to receive a Peningkatan PrestasiAkademik (PPA) scholarship and Bantuan Biaya Akademik (BBA) scholarship in STMIK Pringsewu. Cluster analysis was performed using IBM SPSS Version 23. Cluster Analysis results of both methods were compared using ...
Privacy-Preserving k-Means Clustering under Multiowner Setting in Distributed Cloud Environments
Directory of Open Access Journals (Sweden)
Hong Rong
2017-01-01
Full Text Available With the advent of big data era, clients who lack computational and storage resources tend to outsource data mining tasks to cloud service providers in order to improve efficiency and reduce costs. It is also increasingly common for clients to perform collaborative mining to maximize profits. However, due to the rise of privacy leakage issues, the data contributed by clients should be encrypted using their own keys. This paper focuses on privacy-preserving k-means clustering over the joint datasets encrypted under multiple keys. Unfortunately, existing outsourcing k-means protocols are impractical because not only are they restricted to a single key setting, but also they are inefficient and nonscalable for distributed cloud computing. To address these issues, we propose a set of privacy-preserving building blocks and outsourced k-means clustering protocol under Spark framework. Theoretical analysis shows that our scheme protects the confidentiality of the joint database and mining results, as well as access patterns under the standard semihonest model with relatively small computational overhead. Experimental evaluations on real datasets also demonstrate its efficiency improvements compared with existing approaches.
[Automatic Sleep Stage Classification Based on an Improved K-means Clustering Algorithm].
Xiao, Shuyuan; Wang, Bei; Zhang, Jian; Zhang, Qunfeng; Zou, Junzhong
2016-10-01
Sleep stage scoring is a hotspot in the field of medicine and neuroscience.Visual inspection of sleep is laborious and the results may be subjective to different clinicians.Automatic sleep stage classification algorithm can be used to reduce the manual workload.However,there are still limitations when it encounters complicated and changeable clinical cases.The purpose of this paper is to develop an automatic sleep staging algorithm based on the characteristics of actual sleep data.In the proposed improved K-means clustering algorithm,points were selected as the initial centers by using a concept of density to avoid the randomness of the original K-means algorithm.Meanwhile,the cluster centers were updated according to the‘Three-Sigma Rule’during the iteration to abate the influence of the outliers.The proposed method was tested and analyzed on the overnight sleep data of the healthy persons and patients with sleep disorders after continuous positive airway pressure(CPAP)treatment.The automatic sleep stage classification results were compared with the visual inspection by qualified clinicians and the averaged accuracy reached 76%.With the analysis of morphological diversity of sleep data,it was proved that the proposed improved K-means algorithm was feasible and valid for clinical practice.
A hybrid sequential approach for data clustering using K-Means and ...
African Journals Online (AJOL)
Experiments on four kinds of data sets have been conducted. The obtained results are compared with K-Means, PSO, Hybrid, K-Means+Genetic Algorithm and it has been found that the proposed algorithm generates more accurate, robust and better clustering results. International Journal of Engineering, Science and ...
The effect of mining data k-means clustering toward students profile model drop out potential
Purba, Windania; Tamba, Saut; Saragih, Jepronel
2018-04-01
The high of student success and the low of student failure can reflect the quality of a college. One of the factors of fail students was drop out. To solve the problem, so mining data with K-means Clustering was applied. K-Means Clustering method would be implemented to clustering the drop out students potentially. Firstly the the result data would be clustering to get the information of all students condition. Based on the model taken was found that students who potentially drop out because of the unexciting students in learning, unsupported parents, diffident students and less of students behavior time. The result of process of K-Means Clustering could known that students who more potentially drop out were in Cluster 1 caused Credit Total System, Quality Total, and the lowest Grade Point Average (GPA) compared between cluster 2 and 3.
Merging K-means with hierarchical clustering for identifying general-shaped groups.
Peterson, Anna D; Ghosh, Arka P; Maitra, Ranjan
2018-01-01
Clustering partitions a dataset such that observations placed together in a group are similar but different from those in other groups. Hierarchical and K -means clustering are two approaches but have different strengths and weaknesses. For instance, hierarchical clustering identifies groups in a tree-like structure but suffers from computational complexity in large datasets while K -means clustering is efficient but designed to identify homogeneous spherically-shaped clusters. We present a hybrid non-parametric clustering approach that amalgamates the two methods to identify general-shaped clusters and that can be applied to larger datasets. Specifically, we first partition the dataset into spherical groups using K -means. We next merge these groups using hierarchical methods with a data-driven distance measure as a stopping criterion. Our proposal has the potential to reveal groups with general shapes and structure in a dataset. We demonstrate good performance on several simulated and real datasets.
Zhang, Junfeng; Chen, Wei; Gao, Mingyi; Shen, Gangxiang
2017-10-30
In this work, we proposed two k-means-clustering-based algorithms to mitigate the fiber nonlinearity for 64-quadrature amplitude modulation (64-QAM) signal, the training-sequence assisted k-means algorithm and the blind k-means algorithm. We experimentally demonstrated the proposed k-means-clustering-based fiber nonlinearity mitigation techniques in 75-Gb/s 64-QAM coherent optical communication system. The proposed algorithms have reduced clustering complexity and low data redundancy and they are able to quickly find appropriate initial centroids and select correctly the centroids of the clusters to obtain the global optimal solutions for large k value. We measured the bit-error-ratio (BER) performance of 64-QAM signal with different launched powers into the 50-km single mode fiber and the proposed techniques can greatly mitigate the signal impairments caused by the amplified spontaneous emission noise and the fiber Kerr nonlinearity and improve the BER performance.
Canonical PSO Based K-Means Clustering Approach for Real Datasets.
Dey, Lopamudra; Chakraborty, Sanjay
2014-01-01
"Clustering" the significance and application of this technique is spread over various fields. Clustering is an unsupervised process in data mining, that is why the proper evaluation of the results and measuring the compactness and separability of the clusters are important issues. The procedure of evaluating the results of a clustering algorithm is known as cluster validity measure. Different types of indexes are used to solve different types of problems and indices selection depends on the kind of available data. This paper first proposes Canonical PSO based K-means clustering algorithm and also analyses some important clustering indices (intercluster, intracluster) and then evaluates the effects of those indices on real-time air pollution database, wholesale customer, wine, and vehicle datasets using typical K-means, Canonical PSO based K-means, simple PSO based K-means, DBSCAN, and Hierarchical clustering algorithms. This paper also describes the nature of the clusters and finally compares the performances of these clustering algorithms according to the validity assessment. It also defines which algorithm will be more desirable among all these algorithms to make proper compact clusters on this particular real life datasets. It actually deals with the behaviour of these clustering algorithms with respect to validation indexes and represents their results of evaluation in terms of mathematical and graphical forms.
Clustering for Binary Data Sets by Using Genetic Algorithm-Incremental K-means
Saharan, S.; Baragona, R.; Nor, M. E.; Salleh, R. M.; Asrah, N. M.
2018-04-01
This research was initially driven by the lack of clustering algorithms that specifically focus in binary data. To overcome this gap in knowledge, a promising technique for analysing this type of data became the main subject in this research, namely Genetic Algorithms (GA). For the purpose of this research, GA was combined with the Incremental K-means (IKM) algorithm to cluster the binary data streams. In GAIKM, the objective function was based on a few sufficient statistics that may be easily and quickly calculated on binary numbers. The implementation of IKM will give an advantage in terms of fast convergence. The results show that GAIKM is an efficient and effective new clustering algorithm compared to the clustering algorithms and to the IKM itself. In conclusion, the GAIKM outperformed other clustering algorithms such as GCUK, IKM, Scalable K-means (SKM) and K-means clustering and paves the way for future research involving missing data and outliers.
Directory of Open Access Journals (Sweden)
Fahmida Afrin
2015-08-01
Full Text Available Abstract Data mining is the process of analyzing data and discovering useful information. Sometimes it is called knowledge Discovery. Clustering refers to groups whereas data are grouped in such a way that the data in one cluster are similar data in different clusters are dissimilar. Many data mining technologies are developed for customer segmentation. PCA is working as a preprocessor of Fuzzy C means and K- means for reducing the high dimensional and noisy data. There are many clustering method apply on customer segmentation. In this paper the performance of Fuzzy C means and K-means after implementing Principal Component Analysis is analyzed. We analyze the performance on a standard dataset for these algorithms. The results indicate that PCA based fuzzy clustering produces better results than PCA based K-means and is a more stable method for customer segmentation.
Automatic classification of canine PRG neuronal discharge patterns using K-means clustering.
Zuperku, Edward J; Prkic, Ivana; Stucke, Astrid G; Miller, Justin R; Hopp, Francis A; Stuth, Eckehard A
2015-02-01
Respiratory-related neurons in the parabrachial-Kölliker-Fuse (PB-KF) region of the pons play a key role in the control of breathing. The neuronal activities of these pontine respiratory group (PRG) neurons exhibit a variety of inspiratory (I), expiratory (E), phase spanning and non-respiratory related (NRM) discharge patterns. Due to the variety of patterns, it can be difficult to classify them into distinct subgroups according to their discharge contours. This report presents a method that automatically classifies neurons according to their discharge patterns and derives an average subgroup contour of each class. It is based on the K-means clustering technique and it is implemented via SigmaPlot User-Defined transform scripts. The discharge patterns of 135 canine PRG neurons were classified into seven distinct subgroups. Additional methods for choosing the optimal number of clusters are described. Analysis of the results suggests that the K-means clustering method offers a robust objective means of both automatically categorizing neuron patterns and establishing the underlying archetypical contours of subtypes based on the discharge patterns of group of neurons. Published by Elsevier B.V.
Automated spike sorting algorithm based on Laplacian eigenmaps and k-means clustering.
Chah, E; Hok, V; Della-Chiesa, A; Miller, J J H; O'Mara, S M; Reilly, R B
2011-02-01
This study presents a new automatic spike sorting method based on feature extraction by Laplacian eigenmaps combined with k-means clustering. The performance of the proposed method was compared against previously reported algorithms such as principal component analysis (PCA) and amplitude-based feature extraction. Two types of classifier (namely k-means and classification expectation-maximization) were incorporated within the spike sorting algorithms, in order to find a suitable classifier for the feature sets. Simulated data sets and in-vivo tetrode multichannel recordings were employed to assess the performance of the spike sorting algorithms. The results show that the proposed algorithm yields significantly improved performance with mean sorting accuracy of 73% and sorting error of 10% compared to PCA which combined with k-means had a sorting accuracy of 58% and sorting error of 10%.A correction was made to this article on 22 February 2011. The spacing of the title was amended on the abstract page. No changes were made to the article PDF and the print version was unaffected.
Balanced Cluster Head Selection Based on Modified k-Means in a Distributed Wireless Sensor Network
Periyasamy, Sasikumar; Khara, Sibaram; Thangavelu, Shankar
2016-01-01
A major problem with Wireless Sensor Networks (WSNs) is the maximization of effective network lifetime through minimization of energy usage in the network nodes. A modified k-means (Mk-means) algorithm for clustering was proposed which includes three cluster heads (simultaneously chosen) for each cluster. These cluster heads (CHs) use a load sharing mechanism to rotate as the active cluster head, which conserves residual energy of the nodes, thereby extending network lifetime. Moreover, it re...
DEFF Research Database (Denmark)
Hedegaard, Martin; Krafft, Christoph; Ditzel, Henrik J
2010-01-01
level of a few proteins and genes. Raman maps were recorded of single cells after fixation and drying using 785 nm laser excitation. K-means clustering reduced the amount of data from each cell and improved the signal-to-noise ratio of cluster-averaged spectra. Spectra representing the nucleus were...
Automatic detection of erythemato-squamous diseases using k-means clustering.
Ubeyli, Elif Derya; Doğdu, Erdoğan
2010-04-01
A new approach based on the implementation of k-means clustering is presented for automated detection of erythemato-squamous diseases. The purpose of clustering techniques is to find a structure for the given data by finding similarities between data according to data characteristics. The studied domain contained records of patients with known diagnosis. The k-means clustering algorithm's task was to classify the data points, in this case the patients with attribute data, to one of the five clusters. The algorithm was used to detect the five erythemato-squamous diseases when 33 features defining five disease indications were used. The purpose is to determine an optimum classification scheme for this problem. The present research demonstrated that the features well represent the erythemato-squamous diseases and the k-means clustering algorithm's task achieved high classification accuracies for only five erythemato-squamous diseases.
Directory of Open Access Journals (Sweden)
Irene Erlyn Wina Rachmawan
2015-06-01
Full Text Available Deforestration is one of the crucial issues in Indonesia because now Indonesia has world's highest deforestation rate. In other hand, multispectral image delivers a great source of data for studying spatial and temporal changeability of the environmental such as deforestration area. This research present differential image processing methods for detecting nature change of deforestration. Our differential image processing algorithms extract and indicating area automatically. The feature of our proposed idea produce extracted information from multiband satellite image and calculate the area of deforestration by years with calculating data using temporal dataset. Yet, multiband satellite image consists of big data size that were difficult to be handled for segmentation. Commonly, K- Means clustering is considered to be a powerfull clustering algorithm because of its ability to clustering big data. However K-Means has sensitivity of its first generated centroids, which could lead into a bad performance. In this paper we propose a new approach to optimize K-Means clustering using Reinforcement Programming in order to clustering multispectral image. We build a new mechanism for generating initial centroids by implementing exploration and exploitation knowledge from Reinforcement Programming. This optimization will lead a better result for K-means data cluster. We select multispectral image from Landsat 7 in past ten years in Medawai, Borneo, Indonesia, and apply two segmentation areas consist of deforestration land and forest field. We made series of experiments and compared the experimental results of K-means using Reinforcement Programming as optimizing initiate centroid and normal K-means without optimization process. Keywords: Deforestration, Multispectral images, landsat, automatic clustering, K-means.
Sleep stages identification in patients with sleep disorder using k-means clustering
Fadhlullah, M. U.; Resahya, A.; Nugraha, D. F.; Yulita, I. N.
2018-05-01
Data mining is a computational intelligence discipline where a large dataset processed using a certain method to look for patterns within the large dataset. This pattern then used for real time application or to develop some certain knowledge. This is a valuable tool to solve a complex problem, discover new knowledge, data analysis and decision making. To be able to get the pattern that lies inside the large dataset, clustering method is used to get the pattern. Clustering is basically grouping data that looks similar so a certain pattern can be seen in the large data set. Clustering itself has several algorithms to group the data into the corresponding cluster. This research used data from patients who suffer sleep disorders and aims to help people in the medical world to reduce the time required to classify the sleep stages from a patient who suffers from sleep disorders. This study used K-Means algorithm and silhouette evaluation to find out that 3 clusters are the optimal cluster for this dataset which means can be divided to 3 sleep stages.
GLOBAL CLASSIFICATION OF DERMATITIS DISEASE WITH K-MEANS CLUSTERING IMAGE SEGMENTATION METHODS
Prafulla N. Aerkewar1 & Dr. G. H. Agrawal2
2018-01-01
The objective of this paper to presents a global technique for classification of different dermatitis disease lesions using the process of k-Means clustering image segmentation method. The word global is used such that the all dermatitis disease having skin lesion on body are classified in to four category using k-means image segmentation and nntool of Matlab. Through the image segmentation technique and nntool can be analyze and study the segmentation properties of skin lesions occurs in...
Efficient privacy preserving K-means clustering in a three-party setting
Beye, Michael; Erkin, Zekeriya; Erkin, Zekeriya; Lagendijk, Reginald L.
2011-01-01
User clustering is a common operation in online social networks, for example to recommend new friends. In previous work [5], Erkin et al. proposed a privacy-preserving K-means clustering algorithm for the semi-honest model, using homomorphic encryption and multi-party computation. This paper makes
Hybrid K-means Dan Particle Swarm Optimization Untuk Clustering Nasabah Kredit
Directory of Open Access Journals (Sweden)
Yusuf Priyo Anggodo
2017-05-01
Credit is the biggest revenue for the bank. However, banks have to be selective in deciding which clients can receive the credit. This issue is becoming increasingly complex because when the bank was wrong to give credit to customers can do harm, apart of that a large number of deciding parameter in determining customer credit. Clustering is one way to be able to resolve this issue. K-means is a simple and popular method for solving clustering. However, K-means pure can’t provide optimum solutions so that needs to be done to get the optimum solution to improve. One method of optimization that can solve the problems of optimization with particle swarm optimization is good (PSO. PSO is very helpful in the process of clustering to perform optimization on the central point of each cluster. To improve better results on PSO there are some that do improve. The first use of time-variant inertia to make the dynamic value of inertial w each iteration. Both control the speed of the particle velocity or clamping to get the best position. Besides to overcome premature convergence do hybrid PSO with random injection. The results of this research provide the optimum results for solving clustering of customer credits. The test results showed the hybrid PSO K-means provide the greatest results than K-means and PSO K-means, where the silhouette of the K-means, PSO K-means, and hybrid PSO K-means respectively 0.57343, 0.792045, 1. Keywords: Credit, Clustering, PSO, K-means, Random Injection
MULTI-K: accurate classification of microarray subtypes using ensemble k-means clustering
Directory of Open Access Journals (Sweden)
Ashlock Daniel
2009-08-01
Full Text Available Abstract Background Uncovering subtypes of disease from microarray samples has important clinical implications such as survival time and sensitivity of individual patients to specific therapies. Unsupervised clustering methods have been used to classify this type of data. However, most existing methods focus on clusters with compact shapes and do not reflect the geometric complexity of the high dimensional microarray clusters, which limits their performance. Results We present a cluster-number-based ensemble clustering algorithm, called MULTI-K, for microarray sample classification, which demonstrates remarkable accuracy. The method amalgamates multiple k-means runs by varying the number of clusters and identifies clusters that manifest the most robust co-memberships of elements. In addition to the original algorithm, we newly devised the entropy-plot to control the separation of singletons or small clusters. MULTI-K, unlike the simple k-means or other widely used methods, was able to capture clusters with complex and high-dimensional structures accurately. MULTI-K outperformed other methods including a recently developed ensemble clustering algorithm in tests with five simulated and eight real gene-expression data sets. Conclusion The geometric complexity of clusters should be taken into account for accurate classification of microarray data, and ensemble clustering applied to the number of clusters tackles the problem very well. The C++ code and the data sets tested are available from the authors.
MULTI-K: accurate classification of microarray subtypes using ensemble k-means clustering.
Kim, Eun-Youn; Kim, Seon-Young; Ashlock, Daniel; Nam, Dougu
2009-08-22
Uncovering subtypes of disease from microarray samples has important clinical implications such as survival time and sensitivity of individual patients to specific therapies. Unsupervised clustering methods have been used to classify this type of data. However, most existing methods focus on clusters with compact shapes and do not reflect the geometric complexity of the high dimensional microarray clusters, which limits their performance. We present a cluster-number-based ensemble clustering algorithm, called MULTI-K, for microarray sample classification, which demonstrates remarkable accuracy. The method amalgamates multiple k-means runs by varying the number of clusters and identifies clusters that manifest the most robust co-memberships of elements. In addition to the original algorithm, we newly devised the entropy-plot to control the separation of singletons or small clusters. MULTI-K, unlike the simple k-means or other widely used methods, was able to capture clusters with complex and high-dimensional structures accurately. MULTI-K outperformed other methods including a recently developed ensemble clustering algorithm in tests with five simulated and eight real gene-expression data sets. The geometric complexity of clusters should be taken into account for accurate classification of microarray data, and ensemble clustering applied to the number of clusters tackles the problem very well. The C++ code and the data sets tested are available from the authors.
Directory of Open Access Journals (Sweden)
Simon Fong
2014-01-01
Full Text Available Traditional K-means clustering algorithms have the drawback of getting stuck at local optima that depend on the random values of initial centroids. Optimization algorithms have their advantages in guiding iterative computation to search for global optima while avoiding local optima. The algorithms help speed up the clustering process by converging into a global optimum early with multiple search agents in action. Inspired by nature, some contemporary optimization algorithms which include Ant, Bat, Cuckoo, Firefly, and Wolf search algorithms mimic the swarming behavior allowing them to cooperatively steer towards an optimal objective within a reasonable time. It is known that these so-called nature-inspired optimization algorithms have their own characteristics as well as pros and cons in different applications. When these algorithms are combined with K-means clustering mechanism for the sake of enhancing its clustering quality by avoiding local optima and finding global optima, the new hybrids are anticipated to produce unprecedented performance. In this paper, we report the results of our evaluation experiments on the integration of nature-inspired optimization methods into K-means algorithms. In addition to the standard evaluation metrics in evaluating clustering quality, the extended K-means algorithms that are empowered by nature-inspired optimization methods are applied on image segmentation as a case study of application scenario.
Group analyses of connectivity-based cortical parcellation using repeated k-means clustering.
Nanetti, Luca; Cerliani, Leonardo; Gazzola, Valeria; Renken, Remco; Keysers, Christian
2009-10-01
K-means clustering has become a popular tool for connectivity-based cortical segmentation using Diffusion Weighted Imaging (DWI) data. A sometimes ignored issue is, however, that the output of the algorithm depends on the initial placement of starting points, and that different sets of starting points therefore could lead to different solutions. In this study we explore this issue. We apply k-means clustering a thousand times to the same DWI dataset collected in 10 individuals to segment two brain regions: the SMA-preSMA on the medial wall, and the insula. At the level of single subjects, we found that in both brain regions, repeatedly applying k-means indeed often leads to a variety of rather different cortical based parcellations. By assessing the similarity and frequency of these different solutions, we show that approximately 256 k-means repetitions are needed to accurately estimate the distribution of possible solutions. Using nonparametric group statistics, we then propose a method to employ the variability of clustering solutions to assess the reliability with which certain voxels can be attributed to a particular cluster. In addition, we show that the proportion of voxels that can be attributed significantly to either cluster in the SMA and preSMA is relatively higher than in the insula and discuss how this difference may relate to differences in the anatomy of these regions.
Fong, Simon; Deb, Suash; Yang, Xin-She; Zhuang, Yan
2014-01-01
Traditional K-means clustering algorithms have the drawback of getting stuck at local optima that depend on the random values of initial centroids. Optimization algorithms have their advantages in guiding iterative computation to search for global optima while avoiding local optima. The algorithms help speed up the clustering process by converging into a global optimum early with multiple search agents in action. Inspired by nature, some contemporary optimization algorithms which include Ant, Bat, Cuckoo, Firefly, and Wolf search algorithms mimic the swarming behavior allowing them to cooperatively steer towards an optimal objective within a reasonable time. It is known that these so-called nature-inspired optimization algorithms have their own characteristics as well as pros and cons in different applications. When these algorithms are combined with K-means clustering mechanism for the sake of enhancing its clustering quality by avoiding local optima and finding global optima, the new hybrids are anticipated to produce unprecedented performance. In this paper, we report the results of our evaluation experiments on the integration of nature-inspired optimization methods into K-means algorithms. In addition to the standard evaluation metrics in evaluating clustering quality, the extended K-means algorithms that are empowered by nature-inspired optimization methods are applied on image segmentation as a case study of application scenario.
Deb, Suash; Yang, Xin-She
2014-01-01
Traditional K-means clustering algorithms have the drawback of getting stuck at local optima that depend on the random values of initial centroids. Optimization algorithms have their advantages in guiding iterative computation to search for global optima while avoiding local optima. The algorithms help speed up the clustering process by converging into a global optimum early with multiple search agents in action. Inspired by nature, some contemporary optimization algorithms which include Ant, Bat, Cuckoo, Firefly, and Wolf search algorithms mimic the swarming behavior allowing them to cooperatively steer towards an optimal objective within a reasonable time. It is known that these so-called nature-inspired optimization algorithms have their own characteristics as well as pros and cons in different applications. When these algorithms are combined with K-means clustering mechanism for the sake of enhancing its clustering quality by avoiding local optima and finding global optima, the new hybrids are anticipated to produce unprecedented performance. In this paper, we report the results of our evaluation experiments on the integration of nature-inspired optimization methods into K-means algorithms. In addition to the standard evaluation metrics in evaluating clustering quality, the extended K-means algorithms that are empowered by nature-inspired optimization methods are applied on image segmentation as a case study of application scenario. PMID:25202730
What to Do When K-Means Clustering Fails: A Simple yet Principled Alternative Algorithm.
Raykov, Yordan P; Boukouvalas, Alexis; Baig, Fahd; Little, Max A
The K-means algorithm is one of the most popular clustering algorithms in current use as it is relatively fast yet simple to understand and deploy in practice. Nevertheless, its use entails certain restrictive assumptions about the data, the negative consequences of which are not always immediately apparent, as we demonstrate. While more flexible algorithms have been developed, their widespread use has been hindered by their computational and technical complexity. Motivated by these considerations, we present a flexible alternative to K-means that relaxes most of the assumptions, whilst remaining almost as fast and simple. This novel algorithm which we call MAP-DP (maximum a-posteriori Dirichlet process mixtures), is statistically rigorous as it is based on nonparametric Bayesian Dirichlet process mixture modeling. This approach allows us to overcome most of the limitations imposed by K-means. The number of clusters K is estimated from the data instead of being fixed a-priori as in K-means. In addition, while K-means is restricted to continuous data, the MAP-DP framework can be applied to many kinds of data, for example, binary, count or ordinal data. Also, it can efficiently separate outliers from the data. This additional flexibility does not incur a significant computational overhead compared to K-means with MAP-DP convergence typically achieved in the order of seconds for many practical problems. Finally, in contrast to K-means, since the algorithm is based on an underlying statistical model, the MAP-DP framework can deal with missing data and enables model testing such as cross validation in a principled way. We demonstrate the simplicity and effectiveness of this algorithm on the health informatics problem of clinical sub-typing in a cluster of diseases known as parkinsonism.
Breast Cancer Image Segmentation Using K-Means Clustering Based on GPU Cuda Parallel Computing
Directory of Open Access Journals (Sweden)
Andika Elok Amalia
2018-02-01
Full Text Available Image processing technology is now widely used in the health area, one example is to help the radiologist to analyze the result of MRI (Magnetic Resonance Imaging, CT Scan and Mammography. Image segmentation is a process which is intended to obtain the objects contained in the image by dividing the image into several areas that have similarity attributes on an object with the aim of facilitating the analysis process. The increasing amount of patient data and larger image size are new challenges in segmentation process to use time efficiently while still keeping the process quality. Research on the segmentation of medical images have been done but still few that combine with parallel computing. In this research, K-Means clustering on the image of mammography result is implemented using two-way computation which are serial and parallel. The result shows that parallel computing gives faster average performance execution up to twofold.
Spadone, Sara; de Pasquale, Francesco; Mantini, Dante; Della Penna, Stefania
2012-09-01
Independent component analysis (ICA) is typically applied on functional magnetic resonance imaging, electroencephalographic and magnetoencephalographic (MEG) data due to its data-driven nature. In these applications, ICA needs to be extended from single to multi-session and multi-subject studies for interpreting and assigning a statistical significance at the group level. Here a novel strategy for analyzing MEG independent components (ICs) is presented, Multivariate Algorithm for Grouping MEG Independent Components K-means based (MAGMICK). The proposed approach is able to capture spatio-temporal dynamics of brain activity in MEG studies by running ICA at subject level and then clustering the ICs across sessions and subjects. Distinctive features of MAGMICK are: i) the implementation of an efficient set of "MEG fingerprints" designed to summarize properties of MEG ICs as they are built on spatial, temporal and spectral parameters; ii) the implementation of a modified version of the standard K-means procedure to improve its data-driven character. This algorithm groups the obtained ICs automatically estimating the number of clusters through an adaptive weighting of the parameters and a constraint on the ICs independence, i.e. components coming from the same session (at subject level) or subject (at group level) cannot be grouped together. The performances of MAGMICK are illustrated by analyzing two sets of MEG data obtained during a finger tapping task and median nerve stimulation. The results demonstrate that the method can extract consistent patterns of spatial topography and spectral properties across sessions and subjects that are in good agreement with the literature. In addition, these results are compared to those from a modified version of affinity propagation clustering method. The comparison, evaluated in terms of different clustering validity indices, shows that our methodology often outperforms the clustering algorithm. Eventually, these results are
Segmentation of Mushroom and Cap width Measurement using Modified K-Means Clustering Algorithm
Directory of Open Access Journals (Sweden)
Eser Sert
2014-01-01
Full Text Available Mushroom is one of the commonly consumed foods. Image processing is one of the effective way for examination of visual features and detecting the size of a mushroom. We developed software for segmentation of a mushroom in a picture and also to measure the cap width of the mushroom. K-Means clustering method is used for the process. K-Means is one of the most successful clustering methods. In our study we customized the algorithm to get the best result and tested the algorithm. In the system, at first mushroom picture is filtered, histograms are balanced and after that segmentation is performed. Results provided that customized algorithm performed better segmentation than classical K-Means algorithm. Tests performed on the designed software showed that segmentation on complex background pictures is performed with high accuracy, and 20 mushrooms caps are measured with 2.281 % relative error.
Knops, Z.F.; Maintz, J.B.A.; Viergever, M.A.; Pluim, J.P.W.; Gee, J.C.; Maintz, J.B.A.; Vannier, M.W.
2003-01-01
A method for the efficient re-binning and shading based correction of intensity distributions of the images prior to normalized mutual information based registration is presented. Our intensity distribution re-binning method is based on the K-means clustering algorithm as opposed to the generally
Group analyses of connectivity-based cortical parcellation using repeated k-means clustering
Nanetti, Luca; Cerliani, Leonardo; Gazzola, Valeria; Renken, Remco; Keysers, Christian
2009-01-01
K-means clustering has become a popular tool for connectivity-based cortical segmentation using Diffusion Weighted Imaging (DWI) data. A sometimes ignored issue is, however, that the output of the algorithm depends on the initial placement of starting points, and that different sets of starting
An improved K-means clustering method for cDNA microarray image segmentation.
Wang, T N; Li, T J; Shao, G F; Wu, S X
2015-07-14
Microarray technology is a powerful tool for human genetic research and other biomedical applications. Numerous improvements to the standard K-means algorithm have been carried out to complete the image segmentation step. However, most of the previous studies classify the image into two clusters. In this paper, we propose a novel K-means algorithm, which first classifies the image into three clusters, and then one of the three clusters is divided as the background region and the other two clusters, as the foreground region. The proposed method was evaluated on six different data sets. The analyses of accuracy, efficiency, expression values, special gene spots, and noise images demonstrate the effectiveness of our method in improving the segmentation quality.
The k-means clustering technique: General considerations and implementation in Mathematica
Directory of Open Access Journals (Sweden)
Laurence Morissette
2013-02-01
Full Text Available Data clustering techniques are valuable tools for researchers working with large databases of multivariate data. In this tutorial, we present a simple yet powerful one: the k-means clustering technique, through three different algorithms: the Forgy/Lloyd, algorithm, the MacQueen algorithm and the Hartigan and Wong algorithm. We then present an implementation in Mathematica and various examples of the different options available to illustrate the application of the technique.
CLUSTERING PENENTUAN POTENSI KEJAHATAN DAERAH DI KOTA BANJARBARU DENGAN METODE K-MEANS
Directory of Open Access Journals (Sweden)
Sri Rahayu
2016-09-01
Full Text Available Abstract Within the scope of the police, the data held in the database can be used to make a crime report, the presumption of evil to come, and so on. With the data mining based on the amount of data stored so much, these data can be processed to find the useful knowledge for police. One technique that is known in the data mining clustering techniques. The purpose of the job grouping (clustering the data can be divided into two, namely grouping for understanding and grouping to use. Methods K-Means clustering is a method for engineering the most simple and common. KMeans clustering is one method of data non-hierarchy (partition which seeks to partition the existing data in the form of two or more groups. This method of partitioning data into groups so that the same characteristic of data put into the same group and a different characteristic data are grouped into another group. The purpose of this grouping is to minimize the objective function is set in the grouping process, which generally seek to minimize the variation within a group and maximize the variation between groups. The data mined to determine the potential clustering of crime in the city area of crime data Banjarbaru is owned by the city police in the Police Banjarbaru. Thus this study aims to assess the stage of clustering techniques and build clustering determination of potential crime areas in the city Banjarbaru. Keywords:Clustering, Data mining, K-Means, K-Means Clustering ABSTRAK Dalam ruang lingkup kepolisian, data-data yang dimiliki pada basis data dapat dimanfaatkan untuk pembuatan laporan kejahatan, praduga kejahatan yang akan datang, dan sebagainya.Dengan adanya data mining yang didasarkan pada jumlah data yang tersimpan begitu banyak, data-data tersebut dapat diproses untuk menemukan suatu pengetahuan yang berguna bagi pihak kepolisian.Salah satu teknik yang dikenal dalam data mining yaitu teknik clustering.Tujuan pekerjaan pengelompokan (clustering data dapat dibedakan
Support Vector Data Descriptions and k-Means Clustering: One Class?
Gornitz, Nico; Lima, Luiz Alberto; Muller, Klaus-Robert; Kloft, Marius; Nakajima, Shinichi
2017-09-27
We present ClusterSVDD, a methodology that unifies support vector data descriptions (SVDDs) and k-means clustering into a single formulation. This allows both methods to benefit from one another, i.e., by adding flexibility using multiple spheres for SVDDs and increasing anomaly resistance and flexibility through kernels to k-means. In particular, our approach leads to a new interpretation of k-means as a regularized mode seeking algorithm. The unifying formulation further allows for deriving new algorithms by transferring knowledge from one-class learning settings to clustering settings and vice versa. As a showcase, we derive a clustering method for structured data based on a one-class learning scenario. Additionally, our formulation can be solved via a particularly simple optimization scheme. We evaluate our approach empirically to highlight some of the proposed benefits on artificially generated data, as well as on real-world problems, and provide a Python software package comprising various implementations of primal and dual SVDD as well as our proposed ClusterSVDD.
Hopfield-K-Means clustering algorithm: A proposal for the segmentation of electricity customers
Energy Technology Data Exchange (ETDEWEB)
Lopez, Jose J.; Aguado, Jose A.; Martin, F.; Munoz, F.; Rodriguez, A.; Ruiz, Jose E. [Department of Electrical Engineering, University of Malaga, C/ Dr. Ortiz Ramos, sn., Escuela de Ingenierias, 29071 Malaga (Spain)
2011-02-15
Customer classification aims at providing electric utilities with a volume of information to enable them to establish different types of tariffs. Several methods have been used to segment electricity customers, including, among others, the hierarchical clustering, Modified Follow the Leader and K-Means methods. These, however, entail problems with the pre-allocation of the number of clusters (Follow the Leader), randomness of the solution (K-Means) and improvement of the solution obtained (hierarchical algorithm). Another segmentation method used is Hopfield's autonomous recurrent neural network, although the solution obtained only guarantees that it is a local minimum. In this paper, we present the Hopfield-K-Means algorithm in order to overcome these limitations. This approach eliminates the randomness of the initial solution provided by K-Means based algorithms and it moves closer to the global optimun. The proposed algorithm is also compared against other customer segmentation and characterization techniques, on the basis of relative validation indexes. Finally, the results obtained by this algorithm with a set of 230 electricity customers (residential, industrial and administrative) are presented. (author)
Hopfield-K-Means clustering algorithm: A proposal for the segmentation of electricity customers
International Nuclear Information System (INIS)
Lopez, Jose J.; Aguado, Jose A.; Martin, F.; Munoz, F.; Rodriguez, A.; Ruiz, Jose E.
2011-01-01
Customer classification aims at providing electric utilities with a volume of information to enable them to establish different types of tariffs. Several methods have been used to segment electricity customers, including, among others, the hierarchical clustering, Modified Follow the Leader and K-Means methods. These, however, entail problems with the pre-allocation of the number of clusters (Follow the Leader), randomness of the solution (K-Means) and improvement of the solution obtained (hierarchical algorithm). Another segmentation method used is Hopfield's autonomous recurrent neural network, although the solution obtained only guarantees that it is a local minimum. In this paper, we present the Hopfield-K-Means algorithm in order to overcome these limitations. This approach eliminates the randomness of the initial solution provided by K-Means based algorithms and it moves closer to the global optimun. The proposed algorithm is also compared against other customer segmentation and characterization techniques, on the basis of relative validation indexes. Finally, the results obtained by this algorithm with a set of 230 electricity customers (residential, industrial and administrative) are presented. (author)
Nidheesh, N; Abdul Nazeer, K A; Ameer, P M
2017-12-01
Clustering algorithms with steps involving randomness usually give different results on different executions for the same dataset. This non-deterministic nature of algorithms such as the K-Means clustering algorithm limits their applicability in areas such as cancer subtype prediction using gene expression data. It is hard to sensibly compare the results of such algorithms with those of other algorithms. The non-deterministic nature of K-Means is due to its random selection of data points as initial centroids. We propose an improved, density based version of K-Means, which involves a novel and systematic method for selecting initial centroids. The key idea of the algorithm is to select data points which belong to dense regions and which are adequately separated in feature space as the initial centroids. We compared the proposed algorithm to a set of eleven widely used single clustering algorithms and a prominent ensemble clustering algorithm which is being used for cancer data classification, based on the performances on a set of datasets comprising ten cancer gene expression datasets. The proposed algorithm has shown better overall performance than the others. There is a pressing need in the Biomedical domain for simple, easy-to-use and more accurate Machine Learning tools for cancer subtype prediction. The proposed algorithm is simple, easy-to-use and gives stable results. Moreover, it provides comparatively better predictions of cancer subtypes from gene expression data. Copyright © 2017 Elsevier Ltd. All rights reserved.
An improved initialization center k-means clustering algorithm based on distance and density
Duan, Yanling; Liu, Qun; Xia, Shuyin
2018-04-01
Aiming at the problem of the random initial clustering center of k means algorithm that the clustering results are influenced by outlier data sample and are unstable in multiple clustering, a method of central point initialization method based on larger distance and higher density is proposed. The reciprocal of the weighted average of distance is used to represent the sample density, and the data sample with the larger distance and the higher density are selected as the initial clustering centers to optimize the clustering results. Then, a clustering evaluation method based on distance and density is designed to verify the feasibility of the algorithm and the practicality, the experimental results on UCI data sets show that the algorithm has a certain stability and practicality.
Evaluation of stability of k-means cluster ensembles with respect to random initialization.
Kuncheva, Ludmila I; Vetrov, Dmitry P
2006-11-01
Many clustering algorithms, including cluster ensembles, rely on a random component. Stability of the results across different runs is considered to be an asset of the algorithm. The cluster ensembles considered here are based on k-means clusterers. Each clusterer is assigned a random target number of clusters, k and is started from a random initialization. Here, we use 10 artificial and 10 real data sets to study ensemble stability with respect to random k, and random initialization. The data sets were chosen to have a small number of clusters (two to seven) and a moderate number of data points (up to a few hundred). Pairwise stability is defined as the adjusted Rand index between pairs of clusterers in the ensemble, averaged across all pairs. Nonpairwise stability is defined as the entropy of the consensus matrix of the ensemble. An experimental comparison with the stability of the standard k-means algorithm was carried out for k from 2 to 20. The results revealed that ensembles are generally more stable, markedly so for larger k. To establish whether stability can serve as a cluster validity index, we first looked at the relationship between stability and accuracy with respect to the number of clusters, k. We found that such a relationship strongly depends on the data set, varying from almost perfect positive correlation (0.97, for the glass data) to almost perfect negative correlation (-0.93, for the crabs data). We propose a new combined stability index to be the sum of the pairwise individual and ensemble stabilities. This index was found to correlate better with the ensemble accuracy. Following the hypothesis that a point of stability of a clustering algorithm corresponds to a structure found in the data, we used the stability measures to pick the number of clusters. The combined stability index gave best results.
An Enhanced K-Means Algorithm for Water Quality Analysis of The Haihe River in China.
Zou, Hui; Zou, Zhihong; Wang, Xiaojing
2015-11-12
The increase and the complexity of data caused by the uncertain environment is today's reality. In order to identify water quality effectively and reliably, this paper presents a modified fast clustering algorithm for water quality analysis. The algorithm has adopted a varying weights K-means cluster algorithm to analyze water monitoring data. The varying weights scheme was the best weighting indicator selected by a modified indicator weight self-adjustment algorithm based on K-means, which is named MIWAS-K-means. The new clustering algorithm avoids the margin of the iteration not being calculated in some cases. With the fast clustering analysis, we can identify the quality of water samples. The algorithm is applied in water quality analysis of the Haihe River (China) data obtained by the monitoring network over a period of eight years (2006-2013) with four indicators at seven different sites (2078 samples). Both the theoretical and simulated results demonstrate that the algorithm is efficient and reliable for water quality analysis of the Haihe River. In addition, the algorithm can be applied to more complex data matrices with high dimensionality.
A novel intrusion detection method based on OCSVM and K-means recursive clustering
Directory of Open Access Journals (Sweden)
Leandros A. Maglaras
2015-01-01
Full Text Available In this paper we present an intrusion detection module capable of detecting malicious network traffic in a SCADA (Supervisory Control and Data Acquisition system, based on the combination of One-Class Support Vector Machine (OCSVM with RBF kernel and recursive k-means clustering. Important parameters of OCSVM, such as Gaussian width o and parameter v affect the performance of the classifier. Tuning of these parameters is of great importance in order to avoid false positives and over fitting. The combination of OCSVM with recursive k- means clustering leads the proposed intrusion detection module to distinguish real alarms from possible attacks regardless of the values of parameters o and v, making it ideal for real-time intrusion detection mechanisms for SCADA systems. Extensive simulations have been conducted with datasets extracted from small and medium sized HTB SCADA testbeds, in order to compare the accuracy, false alarm rate and execution time against the base line OCSVM method.
Sa, Qila; Wang, Zhihui
2018-03-01
At present, content-based video retrieval (CBVR) is the most mainstream video retrieval method, using the video features of its own to perform automatic identification and retrieval. This method involves a key technology, i.e. shot segmentation. In this paper, the method of automatic video shot boundary detection with K-means clustering and improved adaptive dual threshold comparison is proposed. First, extract the visual features of every frame and divide them into two categories using K-means clustering algorithm, namely, one with significant change and one with no significant change. Then, as to the classification results, utilize the improved adaptive dual threshold comparison method to determine the abrupt as well as gradual shot boundaries.Finally, achieve automatic video shot boundary detection system.
IP2P K-means: an efficient method for data clustering on sensor networks
Directory of Open Access Journals (Sweden)
Peyman Mirhadi
2013-03-01
Full Text Available Many wireless sensor network applications require data gathering as the most important parts of their operations. There are increasing demands for innovative methods to improve energy efficiency and to prolong the network lifetime. Clustering is considered as an efficient topology control methods in wireless sensor networks, which can increase network scalability and lifetime. This paper presents a method, IP2P K-means – Improved P2P K-means, which uses efficient leveling in clustering approach, reduces false labeling and restricts the necessary communication among various sensors, which obviously saves more energy. The proposed method is examined in Network Simulator Ver.2 (NS2 and the preliminary results show that the algorithm works effectively and relatively more precisely.
2015-03-26
clustering is an algorithm that has been used in data mining applications such as machine learning applications , pattern recognition, hyper-spectral imagery...42 3.7.2 Application of K-means Clustering . . . . . . . . . . . . . . . . . 42 3.8 Experiment Design...Tomographic Imaging WLAN Wireless Local Area Networks WSN Wireless Sensor Network xx ESTIMATING SINGLE AND MULTIPLE TARGET LOCATIONS USING K-MEANS CLUSTERING
K-mean clustering algorithm for processing signals from compound semiconductor detectors
International Nuclear Information System (INIS)
Tada, Tsutomu; Hitomi, Keitaro; Wu, Yan; Kim, Seong-Yun; Yamazaki, Hiromichi; Ishii, Keizo
2011-01-01
The K-mean clustering algorithm was employed for processing signal waveforms from TlBr detectors. The signal waveforms were classified based on its shape reflecting the charge collection process in the detector. The classified signal waveforms were processed individually to suppress the pulse height variation of signals due to the charge collection loss. The obtained energy resolution of a 137 Cs spectrum measured with a 0.5 mm thick TlBr detector was 1.3% FWHM by employing 500 clusters.
A comparison of latent class, K-means, and K-median methods for clustering dichotomous data.
Brusco, Michael J; Shireman, Emilie; Steinley, Douglas
2017-09-01
The problem of partitioning a collection of objects based on their measurements on a set of dichotomous variables is a well-established problem in psychological research, with applications including clinical diagnosis, educational testing, cognitive categorization, and choice analysis. Latent class analysis and K-means clustering are popular methods for partitioning objects based on dichotomous measures in the psychological literature. The K-median clustering method has recently been touted as a potentially useful tool for psychological data and might be preferable to its close neighbor, K-means, when the variable measures are dichotomous. We conducted simulation-based comparisons of the latent class, K-means, and K-median approaches for partitioning dichotomous data. Although all 3 methods proved capable of recovering cluster structure, K-median clustering yielded the best average performance, followed closely by latent class analysis. We also report results for the 3 methods within the context of an application to transitive reasoning data, in which it was found that the 3 approaches can exhibit profound differences when applied to real data. (PsycINFO Database Record (c) 2017 APA, all rights reserved).
Implementation of K-Means Clustering Method for Electronic Learning Model
Latipa Sari, Herlina; Suranti Mrs., Dewi; Natalia Zulita, Leni
2017-12-01
Teaching and Learning process at SMK Negeri 2 Bengkulu Tengah has applied e-learning system for teachers and students. The e-learning was based on the classification of normative, productive, and adaptive subjects. SMK Negeri 2 Bengkulu Tengah consisted of 394 students and 60 teachers with 16 subjects. The record of e-learning database was used in this research to observe students’ activity pattern in attending class. K-Means algorithm in this research was used to classify students’ learning activities using e-learning, so that it was obtained cluster of students’ activity and improvement of student’s ability. Implementation of K-Means Clustering method for electronic learning model at SMK Negeri 2 Bengkulu Tengah was conducted by observing 10 students’ activities, namely participation of students in the classroom, submit assignment, view assignment, add discussion, view discussion, add comment, download course materials, view article, view test, and submit test. In the e-learning model, the testing was conducted toward 10 students that yielded 2 clusters of membership data (C1 and C2). Cluster 1: with membership percentage of 70% and it consisted of 6 members, namely 1112438 Anggi Julian, 1112439 Anis Maulita, 1112441 Ardi Febriansyah, 1112452 Berlian Sinurat, 1112460 Dewi Anugrah Anwar and 1112467 Eka Tri Oktavia Sari. Cluster 2:with membership percentage of 30% and it consisted of 4 members, namely 1112463 Dosita Afriyani, 1112471 Erda Novita, 1112474 Eskardi and 1112477 Fachrur Rozi.
Directory of Open Access Journals (Sweden)
Susan Worner
2013-09-01
Full Text Available For greater preparedness, pest risk assessors are required to prioritise long lists of pest species with potential to establish and cause significant impact in an endangered area. Such prioritization is often qualitative, subjective, and sometimes biased, relying mostly on expert and stakeholder consultation. In recent years, cluster based analyses have been used to investigate regional pest species assemblages or pest profiles to indicate the risk of new organism establishment. Such an approach is based on the premise that the co-occurrence of well-known global invasive pest species in a region is not random, and that the pest species profile or assemblage integrates complex functional relationships that are difficult to tease apart. In other words, the assemblage can help identify and prioritise species that pose a threat in a target region. A computational intelligence method called a Kohonen self-organizing map (SOM, a type of artificial neural network, was the first clustering method applied to analyse assemblages of invasive pests. The SOM is a well known dimension reduction and visualization method especially useful for high dimensional data that more conventional clustering methods may not analyse suitably. Like all clustering algorithms, the SOM can give details of clusters that identify regions with similar pest assemblages, possible donor and recipient regions. More important, however SOM connection weights that result from the analysis can be used to rank the strength of association of each species within each regional assemblage. Species with high weights that are not already established in the target region are identified as high risk. However, the SOM analysis is only the first step in a process to assess risk to be used alongside or incorporated within other measures. Here we illustrate the application of SOM analyses in a range of contexts in invasive species risk assessment, and discuss other clustering methods such as k-means
Anthropometric typology of male and female rowers using k-means clustering.
Forjasz, Justyna
2011-06-01
The aim of this paper is to present the morphological features of rowers. The objective is to establish the type of body build best suited to the present requirements of this sports discipline through the determination of the most important morphological features in rowing with regard to the type of racing boat. The subjects of this study included competitors who practise rowing and were members of the Junior National Team. The considered variables included a group of 32 anthropometric measurements of body composition determined using the BIA method among male and female athletes, while also including rowing boat categories. In order to determine the analysed structures of male and female rowers, an observation analysis was taken into consideration and performed by the k-means clustering method. In the group of male and female rowers using long paddles, higher mean values for the analysed features were observed, with the exception of fat-free mass, and water content in both genders, and trunk length and horizontal reach in women who achieved higher means in the short-paddle group. On the men's team, both groups differed significantly in body mass, longitudinal features, horizontal reach, hand width and body circumferences, while on the women's, they differed in body mass, width and length of the chest, body circumferences and fat content. The method of grouping used in this paper confirmed morphological differences in the competitors with regard to the type of racing boat.
Are judgments a form of data clustering? Reexamining contrast effects with the k-means algorithm.
Boillaud, Eric; Molina, Guylaine
2015-04-01
A number of theories have been proposed to explain in precise mathematical terms how statistical parameters and sequential properties of stimulus distributions affect category ratings. Various contextual factors such as the mean, the midrange, and the median of the stimuli; the stimulus range; the percentile rank of each stimulus; and the order of appearance have been assumed to influence judgmental contrast. A data clustering reinterpretation of judgmental relativity is offered wherein the influence of the initial choice of centroids on judgmental contrast involves 2 combined frequency and consistency tendencies. Accounts of the k-means algorithm are provided, showing good agreement with effects observed on multiple distribution shapes and with a variety of interaction effects relating to the number of stimuli, the number of response categories, and the method of skewing. Experiment 1 demonstrates that centroid initialization accounts for contrast effects obtained with stretched distributions. Experiment 2 demonstrates that the iterative convergence inherent to the k-means algorithm accounts for the contrast reduction observed across repeated blocks of trials. The concept of within-cluster variance minimization is discussed, as is the applicability of a backward k-means calculation method for inferring, from empirical data, the values of the centroids that would serve as a representation of the judgmental context. (c) 2015 APA, all rights reserved.
A new locally weighted K-means for cancer-aided microarray data analysis.
Iam-On, Natthakan; Boongoen, Tossapon
2012-11-01
Cancer has been identified as the leading cause of death. It is predicted that around 20-26 million people will be diagnosed with cancer by 2020. With this alarming rate, there is an urgent need for a more effective methodology to understand, prevent and cure cancer. Microarray technology provides a useful basis of achieving this goal, with cluster analysis of gene expression data leading to the discrimination of patients, identification of possible tumor subtypes and individualized treatment. Amongst clustering techniques, k-means is normally chosen for its simplicity and efficiency. However, it does not account for the different importance of data attributes. This paper presents a new locally weighted extension of k-means, which has proven more accurate across many published datasets than the original and other extensions found in the literature.
AN EFFICIENT INITIALIZATION METHOD FOR K-MEANS CLUSTERING OF HYPERSPECTRAL DATA
Directory of Open Access Journals (Sweden)
A. Alizade Naeini
2014-10-01
Full Text Available K-means is definitely the most frequently used partitional clustering algorithm in the remote sensing community. Unfortunately due to its gradient decent nature, this algorithm is highly sensitive to the initial placement of cluster centers. This problem deteriorates for the high-dimensional data such as hyperspectral remotely sensed imagery. To tackle this problem, in this paper, the spectral signatures of the endmembers in the image scene are extracted and used as the initial positions of the cluster centers. For this purpose, in the first step, A Neyman–Pearson detection theory based eigen-thresholding method (i.e., the HFC method has been employed to estimate the number of endmembers in the image. Afterwards, the spectral signatures of the endmembers are obtained using the Minimum Volume Enclosing Simplex (MVES algorithm. Eventually, these spectral signatures are used to initialize the k-means clustering algorithm. The proposed method is implemented on a hyperspectral dataset acquired by ROSIS sensor with 103 spectral bands over the Pavia University campus, Italy. For comparative evaluation, two other commonly used initialization methods (i.e., Bradley & Fayyad (BF and Random methods are implemented and compared. The confusion matrix, overall accuracy and Kappa coefficient are employed to assess the methods’ performance. The evaluations demonstrate that the proposed solution outperforms the other initialization methods and can be applied for unsupervised classification of hyperspectral imagery for landcover mapping.
Implementasi Pendekatan Rule-Of-Thumb untuk Optimasi Algoritma K-Means Clustering
Directory of Open Access Journals (Sweden)
M Nishom
2018-05-01
Full Text Available In the big data era, the clustering of data or so-called clustering has attracted great interest or attention from researchers in conducting various studies, many grouping algorithms have been proposed in recent times. However, as technology evolves, data volumes continue to grow and data formats are increasingly varied, thus making massive data grouping into a huge and challenging task. To overcome this problem, various research related methods for data grouping have been done, among them is K-Means. However, this method still has some shortcomings, among them is the sensitivity issue in determining the value of cluster (K. In this paper we discuss the implementation of the rule-of-thumb approach and the normalization of data on the K-Means method to determine the number of clusters or K values dynamically in the data groupings. The results show that the implementation of the approach has a significant impact (related to time, number of iterations, and no outliers in the data grouping.
Directory of Open Access Journals (Sweden)
Liling Sun
2015-01-01
Full Text Available An improved multiobjective ABC algorithm based on K-means clustering, called CMOABC, is proposed. To fasten the convergence rate of the canonical MOABC, the way of information communication in the employed bees’ phase is modified. For keeping the population diversity, the multiswarm technology based on K-means clustering is employed to decompose the population into many clusters. Due to each subcomponent evolving separately, after every specific iteration, the population will be reclustered to facilitate information exchange among different clusters. Application of the new CMOABC on several multiobjective benchmark functions shows a marked improvement in performance over the fast nondominated sorting genetic algorithm (NSGA-II, the multiobjective particle swarm optimizer (MOPSO, and the multiobjective ABC (MOABC. Finally, the CMOABC is applied to solve the real-world optimal power flow (OPF problem that considers the cost, loss, and emission impacts as the objective functions. The 30-bus IEEE test system is presented to illustrate the application of the proposed algorithm. The simulation results demonstrate that, compared to NSGA-II, MOPSO, and MOABC, the proposed CMOABC is superior for solving OPF problem, in terms of optimization accuracy.
Guo, Lei; Abbosh, Amin
2018-05-01
For any chance for stroke patients to survive, the stroke type should be classified to enable giving medication within a few hours of the onset of symptoms. In this paper, a microwave-based stroke localization and classification framework is proposed. It is based on microwave tomography, k-means clustering, and a support vector machine (SVM) method. The dielectric profile of the brain is first calculated using the Born iterative method, whereas the amplitude of the dielectric profile is then taken as the input to k-means clustering. The cluster is selected as the feature vector for constructing and testing the SVM. A database of MRI-derived realistic head phantoms at different signal-to-noise ratios is used in the classification procedure. The performance of the proposed framework is evaluated using the receiver operating characteristic (ROC) curve. The results based on a two-dimensional framework show that 88% classification accuracy, with a sensitivity of 91% and a specificity of 87%, can be achieved. Bioelectromagnetics. 39:312-324, 2018. © 2018 Wiley Periodicals, Inc. © 2018 Wiley Periodicals, Inc.
Findings in resting-state fMRI by differences from K-means clustering.
Chyzhyk, Darya; Graña, Manuel
2014-01-01
Resting state fMRI has growing number of studies with diverse aims, always centered on some kind of functional connectivity biomarker obtained from correlation regarding seed regions, or by analytical decomposition of the signal towards the localization of the spatial distribution of functional connectivity patterns. In general, studies are computationally costly and very sensitive to noise and preprocessing of data. In this paper we consider clustering by K-means as a exploratory procedure which can provide some results with little computational effort, due to efficient implementations that are readily available. We demonstrate the approach on a dataset of schizophrenia patients, finding differences between patients with and without auditory hallucinations.
Biswas, Dwaipayan; Cranny, Andy; Gupta, Nayaab; Maharatna, Koushik; Achner, Josy; Klemke, Jasmin; Jöbges, Michael; Ortmann, Steffen
2015-04-01
In this paper we present a methodology for recognizing three fundamental movements of the human forearm (extension, flexion and rotation) using pattern recognition applied to the data from a single wrist-worn, inertial sensor. We propose that this technique could be used as a clinical tool to assess rehabilitation progress in neurodegenerative pathologies such as stroke or cerebral palsy by tracking the number of times a patient performs specific arm movements (e.g. prescribed exercises) with their paretic arm throughout the day. We demonstrate this with healthy subjects and stroke patients in a simple proof of concept study in which these arm movements are detected during an archetypal activity of daily-living (ADL) - 'making-a-cup-of-tea'. Data is collected from a tri-axial accelerometer and a tri-axial gyroscope located proximal to the wrist. In a training phase, movements are initially performed in a controlled environment which are represented by a ranked set of 30 time-domain features. Using a sequential forward selection technique, for each set of feature combinations three clusters are formed using k-means clustering followed by 10 runs of 10-fold cross validation on the training data to determine the best feature combinations. For the testing phase, movements performed during the ADL are associated with each cluster label using a minimum distance classifier in a multi-dimensional feature space, comprised of the best ranked features, using Euclidean or Mahalanobis distance as the metric. Experiments were performed with four healthy subjects and four stroke survivors and our results show that the proposed methodology can detect the three movements performed during the ADL with an overall average accuracy of 88% using the accelerometer data and 83% using the gyroscope data across all healthy subjects and arm movement types. The average accuracy across all stroke survivors was 70% using accelerometer data and 66% using gyroscope data. We also use a Linear
Abualhaj, Bedor; Weng, Guoyang; Ong, Melissa; Attarwala, Ali Asgar; Molina, Flavia; Büsing, Karen; Glatting, Gerhard
2017-01-01
Dynamic [ 18 F]fluoro-ethyl-L-tyrosine positron emission tomography ([ 18 F]FET-PET) is used to identify tumor lesions for radiotherapy treatment planning, to differentiate glioma recurrence from radiation necrosis and to classify gliomas grading. To segment different regions in the brain k-means cluster analysis can be used. The main disadvantage of k-means is that the number of clusters must be pre-defined. In this study, we therefore compared different cluster validity indices for automated and reproducible determination of the optimal number of clusters based on the dynamic PET data. The k-means algorithm was applied to dynamic [ 18 F]FET-PET images of 8 patients. Akaike information criterion (AIC), WB, I, modified Dunn's and Silhouette indices were compared on their ability to determine the optimal number of clusters based on requirements for an adequate cluster validity index. To check the reproducibility of k-means, the coefficients of variation CVs of the objective function values OFVs (sum of squared Euclidean distances within each cluster) were calculated using 100 random centroid initialization replications RCI 100 for 2 to 50 clusters. k-means was performed independently on three neighboring slices containing tumor for each patient to investigate the stability of the optimal number of clusters within them. To check the independence of the validity indices on the number of voxels, cluster analysis was applied after duplication of a slice selected from each patient. CVs of index values were calculated at the optimal number of clusters using RCI 100 to investigate the reproducibility of the validity indices. To check if the indices have a single extremum, visual inspection was performed on the replication with minimum OFV from RCI 100 . The maximum CV of OFVs was 2.7 × 10 -2 from all patients. The optimal number of clusters given by modified Dunn's and Silhouette indices was 2 or 3 leading to a very poor segmentation. WB and I indices suggested in
Botía, Juan A; Vandrovcova, Jana; Forabosco, Paola; Guelfi, Sebastian; D'Sa, Karishma; Hardy, John; Lewis, Cathryn M; Ryten, Mina; Weale, Michael E
2017-04-12
Weighted Gene Co-expression Network Analysis (WGCNA) is a widely used R software package for the generation of gene co-expression networks (GCN). WGCNA generates both a GCN and a derived partitioning of clusters of genes (modules). We propose k-means clustering as an additional processing step to conventional WGCNA, which we have implemented in the R package km2gcn (k-means to gene co-expression network, https://github.com/juanbot/km2gcn ). We assessed our method on networks created from UKBEC data (10 different human brain tissues), on networks created from GTEx data (42 human tissues, including 13 brain tissues), and on simulated networks derived from GTEx data. We observed substantially improved module properties, including: (1) few or zero misplaced genes; (2) increased counts of replicable clusters in alternate tissues (x3.1 on average); (3) improved enrichment of Gene Ontology terms (seen in 48/52 GCNs) (4) improved cell type enrichment signals (seen in 21/23 brain GCNs); and (5) more accurate partitions in simulated data according to a range of similarity indices. The results obtained from our investigations indicate that our k-means method, applied as an adjunct to standard WGCNA, results in better network partitions. These improved partitions enable more fruitful downstream analyses, as gene modules are more biologically meaningful.
Conveyor Performance based on Motor DC 12 Volt Eg-530ad-2f using K-Means Clustering
Arifin, Zaenal; Artini, Sri DP; Much Ibnu Subroto, Imam
2017-04-01
To produce goods in industry, a controlled tool to improve production is required. Separation process has become a part of production process. Separation process is carried out based on certain criteria to get optimum result. By knowing the characteristics performance of a controlled tools in separation process the optimum results is also possible to be obtained. Clustering analysis is popular method for clustering data into smaller segments. Clustering analysis is useful to divide a group of object into a k-group in which the member value of the group is homogeny or similar. Similarity in the group is set based on certain criteria. The work in this paper based on K-Means method to conduct clustering of loading in the performance of a conveyor driven by a dc motor 12 volt eg-530-2f. This technique gives a complete clustering data for a prototype of conveyor driven by dc motor to separate goods in term of height. The parameters involved are voltage, current, time of travelling. These parameters give two clusters namely optimal cluster with center of cluster 10.50 volt, 0.3 Ampere, 10.58 second, and unoptimal cluster with center of cluster 10.88 volt, 0.28 Ampere and 40.43 second.
Surface EMG decomposition based on K-means clustering and convolution kernel compensation.
Ning, Yong; Zhu, Xiangjun; Zhu, Shanan; Zhang, Yingchun
2015-03-01
A new approach has been developed by combining the K-mean clustering (KMC) method and a modified convolution kernel compensation (CKC) method for multichannel surface electromyogram (EMG) decomposition. The KMC method was first utilized to cluster vectors of observations at different time instants and then estimate the initial innervation pulse train (IPT). The CKC method, modified with a novel multistep iterative process, was conducted to update the estimated IPT. The performance of the proposed K-means clustering-Modified CKC (KmCKC) approach was evaluated by reconstructing IPTs from both simulated and experimental surface EMG signals. The KmCKC approach successfully reconstructed all 10 IPTs from the simulated surface EMG signals with true positive rates (TPR) of over 90% with a low signal-to-noise ratio (SNR) of -10 dB. More than 10 motor units were also successfully extracted from the 64-channel experimental surface EMG signals of the first dorsal interosseous (FDI) muscles when a contraction force was held at 8 N by using the KmCKC approach. A "two-source" test was further conducted with 64-channel surface EMG signals. The high percentage of common MUs and common pulses (over 92% at all force levels) between the IPTs reconstructed from the two independent groups of surface EMG signals demonstrates the reliability and capability of the proposed KmCKC approach in multichannel surface EMG decomposition. Results from both simulated and experimental data are consistent and confirm that the proposed KmCKC approach can successfully reconstruct IPTs with high accuracy at different levels of contraction.
Nguyen, Huyen T; Jia, Guang; Shah, Zarine K; Pohar, Kamal; Mortazavi, Amir; Zynger, Debra L; Wei, Lai; Yang, Xiangyu; Clark, Daniel; Knopp, Michael V
2015-05-01
To apply k-means clustering of two pharmacokinetic parameters derived from 3T dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to predict the chemotherapeutic response in bladder cancer at the mid-cycle timepoint. With the predetermined number of three clusters, k-means clustering was performed on nondimensionalized Amp and kep estimates of each bladder tumor. Three cluster volume fractions (VFs) were calculated for each tumor at baseline and mid-cycle. The changes of three cluster VFs from baseline to mid-cycle were correlated with the tumor's chemotherapeutic response. Receiver-operating-characteristics curve analysis was used to evaluate the performance of each cluster VF change as a biomarker of chemotherapeutic response in bladder cancer. The k-means clustering partitioned each bladder tumor into cluster 1 (low kep and low Amp), cluster 2 (low kep and high Amp), cluster 3 (high kep and low Amp). The changes of all three cluster VFs were found to be associated with bladder tumor response to chemotherapy. The VF change of cluster 2 presented with the highest area-under-the-curve value (0.96) and the highest sensitivity/specificity/accuracy (96%/100%/97%) with a selected cutoff value. The k-means clustering of the two DCE-MRI pharmacokinetic parameters can characterize the complex microcirculatory changes within a bladder tumor to enable early prediction of the tumor's chemotherapeutic response. © 2014 Wiley Periodicals, Inc.
White blood cell segmentation by color-space-based k-means clustering.
Zhang, Congcong; Xiao, Xiaoyan; Li, Xiaomei; Chen, Ying-Jie; Zhen, Wu; Chang, Jun; Zheng, Chengyun; Liu, Zhi
2014-09-01
White blood cell (WBC) segmentation, which is important for cytometry, is a challenging issue because of the morphological diversity of WBCs and the complex and uncertain background of blood smear images. This paper proposes a novel method for the nucleus and cytoplasm segmentation of WBCs for cytometry. A color adjustment step was also introduced before segmentation. Color space decomposition and k-means clustering were combined for segmentation. A database including 300 microscopic blood smear images were used to evaluate the performance of our method. The proposed segmentation method achieves 95.7% and 91.3% overall accuracy for nucleus segmentation and cytoplasm segmentation, respectively. Experimental results demonstrate that the proposed method can segment WBCs effectively with high accuracy.
Niukkanen, Anton; Arponen, Otso; Nykänen, Aki; Masarwah, Amro; Sutela, Anna; Liimatainen, Timo; Vanninen, Ritva; Sudah, Mazen
2017-10-18
Mammographic breast density (MBD) is the most commonly used method to assess the volume of fibroglandular tissue (FGT). However, MRI could provide a clinically feasible and more accurate alternative. There were three aims in this study: (1) to evaluate a clinically feasible method to quantify FGT with MRI, (2) to assess the inter-rater agreement of MRI-based volumetric measurements and (3) to compare them to measurements acquired using digital mammography and 3D tomosynthesis. This retrospective study examined 72 women (mean age 52.4 ± 12.3 years) with 105 disease-free breasts undergoing diagnostic 3.0-T breast MRI and either digital mammography or tomosynthesis. Two observers analyzed MRI images for breast and FGT volumes and FGT-% from T1-weighted images (0.7-, 2.0-, and 4.0-mm-thick slices) using K-means clustering, data from histogram, and active contour algorithms. Reference values were obtained with Quantra software. Inter-rater agreement for MRI measurements made with 2-mm-thick slices was excellent: for FGT-%, r = 0.994 (95% CI 0.990-0.997); for breast volume, r = 0.985 (95% CI 0.934-0.994); and for FGT volume, r = 0.979 (95% CI 0.958-0.989). MRI-based FGT-% correlated strongly with MBD in mammography (r = 0.819-0.904, P K-means clustering-based assessments of the proportion of the fibroglandular tissue in the breast at MRI are highly reproducible. In the future, quantitative assessment of FGT-% to complement visual estimation of FGT should be performed on a more regular basis as it provides a component which can be incorporated into the individual's breast cancer risk stratification.
Energy Technology Data Exchange (ETDEWEB)
Sanchez Almeida, J.; Allende Prieto, C., E-mail: jos@iac.es, E-mail: callende@iac.es [Instituto de Astrofisica de Canarias, E-38205 La Laguna, Tenerife (Spain)
2013-01-20
Large spectroscopic surveys require automated methods of analysis. This paper explores the use of k-means clustering as a tool for automated unsupervised classification of massive stellar spectral catalogs. The classification criteria are defined by the data and the algorithm, with no prior physical framework. We work with a representative set of stellar spectra associated with the Sloan Digital Sky Survey (SDSS) SEGUE and SEGUE-2 programs, which consists of 173,390 spectra from 3800 to 9200 A sampled on 3849 wavelengths. We classify the original spectra as well as the spectra with the continuum removed. The second set only contains spectral lines, and it is less dependent on uncertainties of the flux calibration. The classification of the spectra with continuum renders 16 major classes. Roughly speaking, stars are split according to their colors, with enough finesse to distinguish dwarfs from giants of the same effective temperature, but with difficulties to separate stars with different metallicities. There are classes corresponding to particular MK types, intrinsically blue stars, dust-reddened, stellar systems, and also classes collecting faulty spectra. Overall, there is no one-to-one correspondence between the classes we derive and the MK types. The classification of spectra without continuum renders 13 classes, the color separation is not so sharp, but it distinguishes stars of the same effective temperature and different metallicities. Some classes thus obtained present a fairly small range of physical parameters (200 K in effective temperature, 0.25 dex in surface gravity, and 0.35 dex in metallicity), so that the classification can be used to estimate the main physical parameters of some stars at a minimum computational cost. We also analyze the outliers of the classification. Most of them turn out to be failures of the reduction pipeline, but there are also high redshift QSOs, multiple stellar systems, dust-reddened stars, galaxies, and, finally, odd
Khan, Fouad
2016-01-01
K-means is one of the most widely used clustering algorithms in various disciplines, especially for large datasets. However the method is known to be highly sensitive to initial seed selection of cluster centers. K-means++ has been proposed to overcome this problem and has been shown to have better accuracy and computational efficiency than k-means. In many clustering problems though -such as when classifying georeferenced data for mapping applications- standardization of clustering methodolo...
Chang, Ni-Bin; Wimberly, Brent; Xuan, Zhemin
2012-03-01
This study presents an integrated k-means clustering and gravity model (IKCGM) for investigating the spatiotemporal patterns of nutrient and associated dissolved oxygen levels in Tampa Bay, Florida. By using a k-means clustering analysis to first partition the nutrient data into a user-specified number of subsets, it is possible to discover the spatiotemporal patterns of nutrient distribution in the bay and capture the inherent linkages of hydrodynamic and biogeochemical features. Such patterns may then be combined with a gravity model to link the nutrient source contribution from each coastal watershed to the generated clusters in the bay to aid in the source proportion analysis for environmental management. The clustering analysis was carried out based on 1 year (2008) water quality data composed of 55 sample stations throughout Tampa Bay collected by the Environmental Protection Commission of Hillsborough County. In addition, hydrological and river water quality data of the same year were acquired from the United States Geological Survey's National Water Information System to support the gravity modeling analysis. The results show that the k-means model with 8 clusters is the optimal choice, in which cluster 2 at Lower Tampa Bay had the minimum values of total nitrogen (TN) concentrations, chlorophyll a (Chl-a) concentrations, and ocean color values in every season as well as the minimum concentration of total phosphorus (TP) in three consecutive seasons in 2008. The datasets indicate that Lower Tampa Bay is an area with limited nutrient input throughout the year. Cluster 5, located in Middle Tampa Bay, displayed elevated TN concentrations, ocean color values, and Chl-a concentrations, suggesting that high values of colored dissolved organic matter are linked with some nutrient sources. The data presented by the gravity modeling analysis indicate that the Alafia River Basin is the major contributor of nutrients in terms of both TP and TN values in all seasons
Directory of Open Access Journals (Sweden)
WANG Huixian
2015-05-01
Full Text Available In order to adapt different scale land cover segmentation, an optimized approach under the guidance of k-means clustering for multi-scale segmentation is proposed. At first, small scale segmentation and k-means clustering are used to process the original images; then the result of k-means clustering is used to guide objects merging procedure, in which Otsu threshold method is used to automatically select the impact factor of k-means clustering; finally we obtain the segmentation results which are applicable to different scale objects. FNEA method is taken for an example and segmentation experiments are done using a simulated image and a real remote sensing image from GeoEye-1 satellite, qualitative and quantitative evaluation demonstrates that the proposed method can obtain high quality segmentation results.
Vertebra identification using template matching modelmp and K-means clustering.
Larhmam, Mohamed Amine; Benjelloun, Mohammed; Mahmoudi, Saïd
2014-03-01
Accurate vertebra detection and segmentation are essential steps for automating the diagnosis of spinal disorders. This study is dedicated to vertebra alignment measurement, the first step in a computer-aided diagnosis tool for cervical spine trauma. Automated vertebral segment alignment determination is a challenging task due to low contrast imaging and noise. A software tool for segmenting vertebrae and detecting subluxations has clinical significance. A robust method was developed and tested for cervical vertebra identification and segmentation that extracts parameters used for vertebra alignment measurement. Our contribution involves a novel combination of a template matching method and an unsupervised clustering algorithm. In this method, we build a geometric vertebra mean model. To achieve vertebra detection, manual selection of the region of interest is performed initially on the input image. Subsequent preprocessing is done to enhance image contrast and detect edges. Candidate vertebra localization is then carried out by using a modified generalized Hough transform (GHT). Next, an adapted cost function is used to compute local voted centers and filter boundary data. Thereafter, a K-means clustering algorithm is applied to obtain clusters distribution corresponding to the targeted vertebrae. These clusters are combined with the vote parameters to detect vertebra centers. Rigid segmentation is then carried out by using GHT parameters. Finally, cervical spine curves are extracted to measure vertebra alignment. The proposed approach was successfully applied to a set of 66 high-resolution X-ray images. Robust detection was achieved in 97.5 % of the 330 tested cervical vertebrae. An automated vertebral identification method was developed and demonstrated to be robust to noise and occlusion. This work presents a first step toward an automated computer-aided diagnosis system for cervical spine trauma detection.
IMPLEMENTASI ALGORITMA K-MEANS CLUSTERING UNTUK MENENTUKAN STRATEGI MARKETING PRESIDENT UNIVERSITY
Directory of Open Access Journals (Sweden)
Johan Oscar Ong
2013-06-01
Full Text Available Information technology advances very rapidly at this time to generate thousands or even millions of data from various aspect of life. However, what can be done with that much data?. In this research, we start from calculation of data set of students who have graduated from President University using k-means clustering algorithm, namely by classifying the data of students into several clusters based on the characteristics of this data in order to discover the information hidden from the data set of student who have graduated from President University. The attribute data that is used in this study is hometown, major and GPA. The purpose of this study is to help the President University's marketing department in predicting promotion strategies undertaken in the cities in Indonesia. Information gained in this study can be used as a references in determining the proper strategy for marketing team in their promotion activities in the cities in Indonesia so that the campaign will be more effective and efficient.
Mathavan, Senthan; Kumar, Akash; Kamal, Khurram; Nieminen, Michael; Shah, Hitesh; Rahman, Mujib
2016-09-01
Thousands of pavement images are collected by road authorities daily for condition monitoring surveys. These images typically have intensity variations and texture nonuniformities that make their segmentation challenging. The automated segmentation of such pavement images is crucial for accurate, thorough, and expedited health monitoring of roads. In the pavement monitoring area, well-known texture descriptors, such as gray-level co-occurrence matrices and local binary patterns, are often used for surface segmentation and identification. These, despite being the established methods for texture discrimination, are inherently slow. This work evaluates Laws texture energy measures as a viable alternative for pavement images for the first time. k-means clustering is used to partition the feature space, limiting the human subjectivity in the process. Data classification, hence image segmentation, is performed by the k-nearest neighbor method. Laws texture energy masks are shown to perform well with resulting accuracy and precision values of more than 80%. The implementations of the algorithm, in both MATLAB® and OpenCV/C++, are extensively compared against the state of the art for execution speed, clearly showing the advantages of the proposed method. Furthermore, the OpenCV-based segmentation shows a 100% increase in processing speed when compared to the fastest algorithm available in literature.
Vessel Segmentation in Retinal Images Using Multi-scale Line Operator and K-Means Clustering.
Saffarzadeh, Vahid Mohammadi; Osareh, Alireza; Shadgar, Bita
2014-04-01
Detecting blood vessels is a vital task in retinal image analysis. The task is more challenging with the presence of bright and dark lesions in retinal images. Here, a method is proposed to detect vessels in both normal and abnormal retinal fundus images based on their linear features. First, the negative impact of bright lesions is reduced by using K-means segmentation in a perceptive space. Then, a multi-scale line operator is utilized to detect vessels while ignoring some of the dark lesions, which have intensity structures different from the line-shaped vessels in the retina. The proposed algorithm is tested on two publicly available STARE and DRIVE databases. The performance of the method is measured by calculating the area under the receiver operating characteristic curve and the segmentation accuracy. The proposed method achieves 0.9483 and 0.9387 localization accuracy against STARE and DRIVE respectively.
Quick detection of QRS complexes and R-waves using a wavelet transform and K-means clustering.
Xia, Yong; Han, Junze; Wang, Kuanquan
2015-01-01
Based on the idea of telemedicine, 24-hour uninterrupted monitoring on electrocardiograms (ECG) has started to be implemented. To create an intelligent ECG monitoring system, an efficient and quick detection algorithm for the characteristic waveforms is needed. This paper aims to give a quick and effective method for detecting QRS-complexes and R-waves in ECGs. The real ECG signal from the MIT-BIH Arrhythmia Database is used for the performance evaluation. The method proposed combined a wavelet transform and the K-means clustering algorithm. A wavelet transform is adopted in the data analysis and preprocessing. Then, based on the slope information of the filtered data, a segmented K-means clustering method is adopted to detect the QRS region. Detection of the R-peak is based on comparing the local amplitudes in each QRS region, which is different from other approaches, and the time cost of R-wave detection is reduced. Of the tested 8 records (total 18201 beats) from the MIT-BIH Arrhythmia Database, an average R-peak detection sensitivity of 99.72 and a positive predictive value of 99.80% are gained; the average time consumed detecting a 30-min original signal is 5.78s, which is competitive with other methods.
Mustaniroh, S. A.; Effendi, U.; Silalahi, R. L. R.; Sari, T.; Ala, M.
2018-03-01
The purposes of this research were to determine the grouping of apples dodol small and medium enterprises (SMEs) in Batu City and to determine an appropriate development strategy for each cluster. The methods used for clustering SMEs was k-means. The Analytical Hierarchy Process (AHP) approach was then applied to determine the development strategy priority for each cluster. The variables used in grouping include production capacity per month, length of operation, investment value, average sales revenue per month, amount of SMEs assets, and the number of workers. Several factors were considered in AHP include industry cluster, government, as well as related and supporting industries. Data was collected using the methods of questionaire and interviews. SMEs respondents were selected among SMEs appels dodol in Batu City using purposive sampling. The result showed that two clusters were formed from five apples dodol SMEs. The 1stcluster of apples dodol SMEs, classified as small enterprises, included SME A, SME C, and SME D. The 2ndcluster of SMEs apples dodol, classified as medium enterprises, consisted of SME B and SME E. The AHP results indicated that the priority development strategy for the 1stcluster of apples dodol SMEs was improving quality and the product standardisation, while for the 2nd cluster was increasing the marketing access.
Re-weighted Discriminatively Embedded K-Means for Multi-view Clustering.
Xu, Jinglin; Han, Junwei; Nie, Feiping; Li, Xuelong
2017-02-08
Recent years, more and more multi-view data are widely used in many real world applications. This kind of data (such as image data) are high dimensional and obtained from different feature extractors, which represents distinct perspectives of the data. How to cluster such data efficiently is a challenge. In this paper, we propose a novel multi-view clustering framework, called Re-weighted Discriminatively Embedded KMeans (RDEKM), for this task. The proposed method is a multiview least-absolute residual model which induces robustness to efficiently mitigates the influence of outliers and realizes dimension reduction during multi-view clustering. Specifically, the proposed model is an unsupervised optimization scheme which utilizes Iterative Re-weighted Least Squares to solve leastabsolute residual and adaptively controls the distribution of multiple weights in a re-weighted manner only based on its own low-dimensional subspaces and a common clustering indicator matrix. Furthermore, theoretical analysis (including optimality and convergence analysis) and the optimization algorithm are also presented. Compared to several state-of-the-art multi-view clustering methods, the proposed method substantially improves the accuracy of the clustering results on widely used benchmark datasets, which demonstrates the superiority of the proposed work.
Variance-Based Cluster Selection Criteria in a K-Means Framework for One-Mode Dissimilarity Data.
Vera, J Fernando; Macías, Rodrigo
2017-06-01
One of the main problems in cluster analysis is that of determining the number of groups in the data. In general, the approach taken depends on the cluster method used. For K-means, some of the most widely employed criteria are formulated in terms of the decomposition of the total point scatter, regarding a two-mode data set of N points in p dimensions, which are optimally arranged into K classes. This paper addresses the formulation of criteria to determine the number of clusters, in the general situation in which the available information for clustering is a one-mode [Formula: see text] dissimilarity matrix describing the objects. In this framework, p and the coordinates of points are usually unknown, and the application of criteria originally formulated for two-mode data sets is dependent on their possible reformulation in the one-mode situation. The decomposition of the variability of the clustered objects is proposed in terms of the corresponding block-shaped partition of the dissimilarity matrix. Within-block and between-block dispersion values for the partitioned dissimilarity matrix are derived, and variance-based criteria are subsequently formulated in order to determine the number of groups in the data. A Monte Carlo experiment was carried out to study the performance of the proposed criteria. For simulated clustered points in p dimensions, greater efficiency in recovering the number of clusters is obtained when the criteria are calculated from the related Euclidean distances instead of the known two-mode data set, in general, for unequal-sized clusters and for low dimensionality situations. For simulated dissimilarity data sets, the proposed criteria always outperform the results obtained when these criteria are calculated from their original formulation, using dissimilarities instead of distances.
CLASSIFICATION OF LIDAR DATA OVER BUILDING ROOFS USING K-MEANS AND PRINCIPAL COMPONENT ANALYSIS
Directory of Open Access Journals (Sweden)
Renato César dos Santos
Full Text Available Abstract: The classification is an important step in the extraction of geometric primitives from LiDAR data. Normally, it is applied for the identification of points sampled on geometric primitives of interest. In the literature there are several studies that have explored the use of eigenvalues to classify LiDAR points into different classes or structures, such as corner, edge, and plane. However, in some works the classes are defined considering an ideal geometry, which can be affected by the inadequate sampling and/or by the presence of noise when using real data. To overcome this limitation, in this paper is proposed the use of metrics based on eigenvalues and the k-means method to carry out the classification. So, the concept of principal component analysis is used to obtain the eigenvalues and the derived metrics, while the k-means is applied to cluster the roof points in two classes: edge and non-edge. To evaluate the proposed method four test areas with different levels of complexity were selected. From the qualitative and quantitative analyses, it could be concluded that the proposed classification procedure gave satisfactory results, resulting in completeness and correctness above 92% for the non-edge class, and between 61% to 98% for the edge class.
Directory of Open Access Journals (Sweden)
Iin Parlina
2018-01-01
Full Text Available Data mining merupakan teknik pengolahan data dalam jumlah besar untuk pengelompokan. Teknik Data mining mempunyai beberapa metode dalam mengelompokkan salah satu teknik yang dipakai penulis saat ini adalah K-Means. Dalam hal ini penulis mengelompokan data daftar program SDP tahun 2017 untuk mengetahui manakah pegawai yang layak lolos dalam program SDP sehingga dapat melakukan Registrasi Asessment Center. Pengelompokan tersebut berdasarkan kriteria – kriteria data Program SDP. Pada penelitian ini, penulis menerapkan algoritma K-Means Clustering untuk pengelompokan data Program SDP di PT.Bank Syariah. Dalam hal ini, pada umumnya untuk memamasuki program SDP tersebut disesuaikan dengan ketentuan dan parameter Program SDP saja, namun dalam penelitian ini pengelompokan disesuaikan dengan kriteria – kriteria Program SDP seperti kedisiplinan pegawai, Target Kerja Pegawai, Kepatuhan Program SDP. Penulis menggunakan beberapa kriteria tersebut agar pengelompokan yang dihasilkan menjadi lebih optimal. Tujuan dari pengelompokan ini adalah terbentuknya kelompok SDP pada Program SDP yang menggunakan algoritma K-Means clustering. Hasil dari pengelompokan tersebut diperoleh tiga kelompok yaitu kelompok Lolos, Hampir Lolos dan Tidak Lolos. Terdapat pusat cluster dengan Cluster-1= 8;66;13, Cluster-2= 10;71;14 dan Cluster-3=7;60;12. Pusat cluster tersebut didapat dari beberapa iterasi sehingga mengahasilakan pusat cluster yang optimal.
Srinivasan, A; Galbán, C J; Johnson, T D; Chenevert, T L; Ross, B D; Mukherji, S K
2010-04-01
Does the K-means algorithm do a better job of differentiating benign and malignant neck pathologies compared to only mean ADC? The objective of our study was to analyze the differences between ADC partitions to evaluate whether the K-means technique can be of additional benefit to whole-lesion mean ADC alone in distinguishing benign and malignant neck pathologies. MR imaging studies of 10 benign and 10 malignant proved neck pathologies were postprocessed on a PC by using in-house software developed in Matlab. Two neuroradiologists manually contoured the lesions, with the ADC values within each lesion clustered into 2 (low, ADC-ADC(L); high, ADC-ADC(H)) and 3 partitions (ADC(L); intermediate, ADC-ADC(I); ADC(H)) by using the K-means clustering algorithm. An unpaired 2-tailed Student t test was performed for all metrics to determine statistical differences in the means of the benign and malignant pathologies. A statistically significant difference between the mean ADC(L) clusters in benign and malignant pathologies was seen in the 3-cluster models of both readers (P = .03 and .022, respectively) and the 2-cluster model of reader 2 (P = .04), with the other metrics (ADC(H), ADC(I); whole-lesion mean ADC) not revealing any significant differences. ROC curves demonstrated the quantitative differences in mean ADC(H) and ADC(L) in both the 2- and 3-cluster models to be predictive of malignancy (2 clusters: P = .008, area under curve = 0.850; 3 clusters: P = .01, area under curve = 0.825). The K-means clustering algorithm that generates partitions of large datasets may provide a better characterization of neck pathologies and may be of additional benefit in distinguishing benign and malignant neck pathologies compared with whole-lesion mean ADC alone.
Supplier Risk Assessment Based on Best-Worst Method and K-Means Clustering: A Case Study
Directory of Open Access Journals (Sweden)
Merve Er Kara
2018-04-01
Full Text Available Supplier evaluation and selection is one of the most critical strategic decisions for developing a competitive and sustainable organization. Companies have to consider supplier related risks and threats in their purchasing decisions. In today’s competitive and risky business environment, it is very important to work with reliable suppliers. This study proposes a clustering based approach to group suppliers based on their risk profile. Suppliers of a company in the heavy-machinery sector are assessed based on 17 qualitative and quantitative risk types. The weights of the criteria are determined by using the Best-Worst method. Four factors are extracted by applying Factor Analysis to the supplier risk data. Then k-means clustering algorithm is applied to group core suppliers of the company based on the four risk factors. Three clusters are created with different risk exposure levels. The interpretation of the results provides insights for risk management actions and supplier development programs to mitigate supplier risk.
Energy Technology Data Exchange (ETDEWEB)
2017-04-04
A parallelization of the k-means++ seed selection algorithm on three distinct hardware platforms: GPU, multicore CPU, and multithreaded architecture. K-means++ was developed by David Arthur and Sergei Vassilvitskii in 2007 as an extension of the k-means data clustering technique. These algorithms allow people to cluster multidimensional data, by attempting to minimize the mean distance of data points within a cluster. K-means++ improved upon traditional k-means by using a more intelligent approach to selecting the initial seeds for the clustering process. While k-means++ has become a popular alternative to traditional k-means clustering, little work has been done to parallelize this technique. We have developed original C++ code for parallelizing the algorithm on three unique hardware architectures: GPU using NVidia's CUDA/Thrust framework, multicore CPU using OpenMP, and the Cray XMT multithreaded architecture. By parallelizing the process for these platforms, we are able to perform k-means++ clustering much more quickly than it could be done before.
Directory of Open Access Journals (Sweden)
Xiangbing Zhou
2017-12-01
Full Text Available Rapidly growing Global Positioning System (GPS data plays an important role in trajectory and their applications (e.g., GPS-enabled smart devices. In order to employ K-means to mine the better origins and destinations (OD behind the GPS data and overcome its shortcomings including slowness of convergence, sensitivity to initial seeds selection, and getting stuck in a local optimum, this paper proposes and focuses on a novel niche genetic algorithm (NGA with density and noise for K-means clustering (NoiseClust. In NoiseClust, an improved noise method and K-means++ are proposed to produce the initial population and capture higher quality seeds that can automatically determine the proper number of clusters, and also handle the different sizes and shapes of genes. A density-based method is presented to divide the number of niches, with its aim to maintain population diversity. Adaptive probabilities of crossover and mutation are also employed to prevent the convergence to a local optimum. Finally, the centers (the best chromosome are obtained and then fed into the K-means as initial seeds to generate even higher quality clustering results by allowing the initial seeds to readjust as needed. Experimental results based on taxi GPS data sets demonstrate that NoiseClust has high performance and effectiveness, and easily mine the city’s situations in four taxi GPS data sets.
Directory of Open Access Journals (Sweden)
Saatchi Mahdi
2011-11-01
Full Text Available Abstract Background Genomic selection is a recently developed technology that is beginning to revolutionize animal breeding. The objective of this study was to estimate marker effects to derive prediction equations for direct genomic values for 16 routinely recorded traits of American Angus beef cattle and quantify corresponding accuracies of prediction. Methods Deregressed estimated breeding values were used as observations in a weighted analysis to derive direct genomic values for 3570 sires genotyped using the Illumina BovineSNP50 BeadChip. These bulls were clustered into five groups using K-means clustering on pedigree estimates of additive genetic relationships between animals, with the aim of increasing within-group and decreasing between-group relationships. All five combinations of four groups were used for model training, with cross-validation performed in the group not used in training. Bivariate animal models were used for each trait to estimate the genetic correlation between deregressed estimated breeding values and direct genomic values. Results Accuracies of direct genomic values ranged from 0.22 to 0.69 for the studied traits, with an average of 0.44. Predictions were more accurate when animals within the validation group were more closely related to animals in the training set. When training and validation sets were formed by random allocation, the accuracies of direct genomic values ranged from 0.38 to 0.85, with an average of 0.65, reflecting the greater relationship between animals in training and validation. The accuracies of direct genomic values obtained from training on older animals and validating in younger animals were intermediate to the accuracies obtained from K-means clustering and random clustering for most traits. The genetic correlation between deregressed estimated breeding values and direct genomic values ranged from 0.15 to 0.80 for the traits studied. Conclusions These results suggest that genomic estimates
Saatchi, Mahdi; McClure, Mathew C; McKay, Stephanie D; Rolf, Megan M; Kim, JaeWoo; Decker, Jared E; Taxis, Tasia M; Chapple, Richard H; Ramey, Holly R; Northcutt, Sally L; Bauck, Stewart; Woodward, Brent; Dekkers, Jack C M; Fernando, Rohan L; Schnabel, Robert D; Garrick, Dorian J; Taylor, Jeremy F
2011-11-28
Genomic selection is a recently developed technology that is beginning to revolutionize animal breeding. The objective of this study was to estimate marker effects to derive prediction equations for direct genomic values for 16 routinely recorded traits of American Angus beef cattle and quantify corresponding accuracies of prediction. Deregressed estimated breeding values were used as observations in a weighted analysis to derive direct genomic values for 3570 sires genotyped using the Illumina BovineSNP50 BeadChip. These bulls were clustered into five groups using K-means clustering on pedigree estimates of additive genetic relationships between animals, with the aim of increasing within-group and decreasing between-group relationships. All five combinations of four groups were used for model training, with cross-validation performed in the group not used in training. Bivariate animal models were used for each trait to estimate the genetic correlation between deregressed estimated breeding values and direct genomic values. Accuracies of direct genomic values ranged from 0.22 to 0.69 for the studied traits, with an average of 0.44. Predictions were more accurate when animals within the validation group were more closely related to animals in the training set. When training and validation sets were formed by random allocation, the accuracies of direct genomic values ranged from 0.38 to 0.85, with an average of 0.65, reflecting the greater relationship between animals in training and validation. The accuracies of direct genomic values obtained from training on older animals and validating in younger animals were intermediate to the accuracies obtained from K-means clustering and random clustering for most traits. The genetic correlation between deregressed estimated breeding values and direct genomic values ranged from 0.15 to 0.80 for the traits studied. These results suggest that genomic estimates of genetic merit can be produced in beef cattle at a young age but
Srinivasan, A.; Galbán, C.J.; Johnson, T.D.; Chenevert, T.L.; Ross, B.D.; Mukherji, S.K.
2014-01-01
Purpose The objective of our study was to analyze the differences between apparent diffusion coefficient (ADC) partitions (created using the K-Means algorithm) between benign and malignant neck lesions and evaluate its benefit in distinguishing these entities. Material and methods MRI studies of 10 benign and 10 malignant proven neck pathologies were post-processed on a PC using in-house software developed in MATLAB (The MathWorks, Inc., Natick, MA). Lesions were manually contoured by two neuroradiologists with the ADC values within each lesion clustered into two (low ADC-ADCL, high ADC-ADCH) and three partitions (ADCL, intermediate ADC-ADCI, ADCH) using the K-Means clustering algorithm. An unpaired two-tailed Student’s t-test was performed for all metrics to determine statistical differences in the means between the benign and malignant pathologies. Results Statistically significant difference between the mean ADCL clusters in benign and malignant pathologies was seen in the 3 cluster models of both readers (p=0.03, 0.022 respectively) and the 2 cluster model of reader 2 (p=0.04) with the other metrics (ADCH, ADCI, whole lesion mean ADC) not revealing any significant differences. Receiver operating characteristics curves demonstrated the quantitative difference in mean ADCH and ADCL in both the 2 and 3 cluster models to be predictive of malignancy (2 clusters: p=0.008, area under curve=0.850, 3 clusters: p=0.01, area under curve=0.825). Conclusion The K-Means clustering algorithm that generates partitions of large datasets may provide a better characterization of neck pathologies and may be of additional benefit in distinguishing benign and malignant neck pathologies compared to whole lesion mean ADC alone. PMID:20007723
Factorial and reduced K-means reconsidered
Timmerman, Marieke E.; Ceulemans, Eva; Kiers, Henk A. L.; Vichi, Maurizio
2010-01-01
Factorial K-means analysis (FKM) and Reduced K-means analysis (RKM) are clustering methods that aim at simultaneously achieving a clustering of the objects and a dimension reduction of the variables. Because a comprehensive comparison between FKM and RKM is lacking in the literature so far, a
Yu, Miao; Li, Yan; Shu, Tong; Zhang, Yifan; Hong, Xiaobin; Qiu, Jifang; Zuo, Yong; Guo, Hongxiang; Li, Wei; Wu, Jian
2018-02-01
A method of recognizing 16QAM signal based on k-means clustering algorithm is proposed to mitigate the impact of transmitter finite extinction ratio. There are pilot symbols with 0.39% overhead assigned to be regarded as initial centroids of k-means clustering algorithm. Simulation result in 10 GBaud 16QAM system shows that the proposed method obtains higher precision of identification compared with traditional decision method for finite ER and IQ mismatch. Specially, the proposed method improves the required OSNR by 5.5 dB, 4.5 dB, 4 dB and 3 dB at FEC limit with ER= 12 dB, 16 dB, 20 dB and 24 dB, respectively, and the acceptable bias error and IQ mismatch range is widened by 767% and 360% with ER =16 dB, respectively.
A new method of spatio-temporal topographic mapping by correlation coefficient of K-means cluster.
Li, Ling; Yao, Dezhong
2007-01-01
It would be of the utmost interest to map correlated sources in the working human brain by Event-Related Potentials (ERPs). This work is to develop a new method to map correlated neural sources based on the time courses of the scalp ERPs waveforms. The ERP data are classified first by k-means cluster analysis, and then the Correlation Coefficients (CC) between the original data of each electrode channel and the time course of each cluster centroid are calculated and utilized as the mapping variable on the scalp surface. With a normalized 4-concentric-sphere head model with radius 1, the performance of the method is evaluated by simulated data. CC, between simulated four sources (s (1)-s (4)) and the estimated cluster centroids (c (1)-c (4)), and the distances (Ds), between the scalp projection points of the s (1)-s (4) and that of the c (1)-c (4), are utilized as the evaluation indexes. Applied to four sources with two of them partially correlated (with maximum mutual CC = 0.4892), CC (Ds) between s (1)-s (4) and c (1)-c (4) are larger (smaller) than 0.893 (0.108) for noise levels NSRclusters located at left, right occipital and frontal. The estimated vectors of the contra-occipital area demonstrate that attention to the stimulus location produces increased amplitude of the P1 and N1 components over the contra-occipital scalp. The estimated vector in the frontal area displays two large processing negativity waves around 100 ms and 250 ms when subjects are attentive, and there is a small negative wave around 140 ms and a P300 when subjects are unattentive. The results of simulations and real Visual Evoked Potentials (VEPs) data demonstrate the validity of the method in mapping correlated sources. This method may be an objective, heuristic and important tool to study the properties of cerebral, neural networks in cognitive and clinical neurosciences.
Classification of Two Class Motor Imagery Tasks Using Hybrid GA-PSO Based K-Means Clustering.
Suraj; Tiwari, Purnendu; Ghosh, Subhojit; Sinha, Rakesh Kumar
2015-01-01
Transferring the brain computer interface (BCI) from laboratory condition to meet the real world application needs BCI to be applied asynchronously without any time constraint. High level of dynamism in the electroencephalogram (EEG) signal reasons us to look toward evolutionary algorithm (EA). Motivated by these two facts, in this work a hybrid GA-PSO based K-means clustering technique has been used to distinguish two class motor imagery (MI) tasks. The proposed hybrid GA-PSO based K-means clustering is found to outperform genetic algorithm (GA) and particle swarm optimization (PSO) based K-means clustering techniques in terms of both accuracy and execution time. The lesser execution time of hybrid GA-PSO technique makes it suitable for real time BCI application. Time frequency representation (TFR) techniques have been used to extract the feature of the signal under investigation. TFRs based features are extracted and relying on the concept of event related synchronization (ERD) and desynchronization (ERD) feature vector is formed.
Gray, Calum; MacGillivray, Thomas J; Eeley, Clare; Stephens, Nathan A; Beggs, Ian; Fearon, Kenneth C; Greig, Carolyn A
2011-02-01
Sarcopenia and cachexia are characterized by infiltration of non-contractile tissue within muscle which influences area and volume measurements. We applied a statistical clustering (k-means) technique to magnetic resonance (MR) images of the quadriceps of young and elderly healthy women and women with cancer to objectively separate the contractile and non-contractile tissue compartments. MR scans of the thigh were obtained for 34 women (n = 16 young, (median) age 26 y; n = 9 older, age 80 y; n = 9 upper gastrointestinal cancer patients, age 65 y). Segmented regions of consecutive axial images were used to calculate cross-sectional area and (gross) volume. The k-means unsupervised algorithm was subsequently applied to the MR binary mask image array data with resultant volumes compared between groups. Older women and women with cancer had 37% and 48% less quadriceps muscle respectively than young women (p k-means subtracted a significant 9%, 14% and 20% non-contractile tissue from the quadriceps of young, older and patient groups respectively (p K-means objectively separates contractile and non-contractile tissue components. Women with upper GI cancer have significant fatty infiltration throughout whole muscle groups which is maintained when controlling for age. Copyright © 2010 Elsevier Ltd and European Society for Clinical Nutrition and Metabolism. All rights reserved.
Husein, A. M.; Harahap, M.; Aisyah, S.; Purba, W.; Muhazir, A.
2018-03-01
Medication planning aim to get types, amount of medicine according to needs, and avoid the emptiness medicine based on patterns of disease. In making the medicine planning is still rely on ability and leadership experience, this is due to take a long time, skill, difficult to obtain a definite disease data, need a good record keeping and reporting, and the dependence of the budget resulted in planning is not going well, and lead to frequent lack and excess of medicines. In this research, we propose Adaptive Neuro Fuzzy Inference System (ANFIS) method to predict medication needs in 2016 and 2017 based on medical data in 2015 and 2016 from two source of hospital. The framework of analysis using two approaches. The first phase is implementing ANFIS to a data source, while the second approach we keep using ANFIS, but after the process of clustering from K-Means algorithm, both approaches are calculated values of Root Mean Square Error (RMSE) for training and testing. From the testing result, the proposed method with better prediction rates based on the evaluation analysis of quantitative and qualitative compared with existing systems, however the implementation of K-Means Algorithm against ANFIS have an effect on the timing of the training process and provide a classification accuracy significantly better without clustering.
International Nuclear Information System (INIS)
Marzouk, Youssef M.; Ghoniem, Ahmed F.
2005-01-01
A number of complex physical problems can be approached through N-body simulation, from fluid flow at high Reynolds number to gravitational astrophysics and molecular dynamics. In all these applications, direct summation is prohibitively expensive for large N and thus hierarchical methods are employed for fast summation. This work introduces new algorithms, based on k-means clustering, for partitioning parallel hierarchical N-body interactions. We demonstrate that the number of particle-cluster interactions and the order at which they are performed are directly affected by partition geometry. Weighted k-means partitions minimize the sum of clusters' second moments and create well-localized domains, and thus reduce the computational cost of N-body approximations by enabling the use of lower-order approximations and fewer cells. We also introduce compatible techniques for dynamic load balancing, including adaptive scaling of cluster volumes and adaptive redistribution of cluster centroids. We demonstrate the performance of these algorithms by constructing a parallel treecode for vortex particle simulations, based on the serial variable-order Cartesian code developed by Lindsay and Krasny [Journal of Computational Physics 172 (2) (2001) 879-907]. The method is applied to vortex simulations of a transverse jet. Results show outstanding parallel efficiencies even at high concurrencies, with velocity evaluation errors maintained at or below their serial values; on a realistic distribution of 1.2 million vortex particles, we observe a parallel efficiency of 98% on 1024 processors. Excellent load balance is achieved even in the face of several obstacles, such as an irregular, time-evolving particle distribution containing a range of length scales and the continual introduction of new vortex particles throughout the domain. Moreover, results suggest that k-means yields a more efficient partition of the domain than a global oct-tree
Extension of K-Means Algorithm for clustering mixed data | Onuodu ...
African Journals Online (AJOL)
Also proposed is a new dissimilarity measure that uses relative cumulative frequency-based method in clustering objects with mixed values. The dissimilarity model developed could serve as a predictive tool for identifying attributes of objects in mixed datasets. It has been implemented using JAVA programming language ...
Yang, Yao Ming; Jia, Ruo; Xun, Hui; Yang, Jie; Chen, Qiang; Zeng, Xiang Guang; Yang, Ming
2018-02-21
Simulium quinquestriatum Shiraki (Diptera: Simuliidae), a human-biting fly that is distributed widely across Asia, is a vector for multiple pathogens. However, the larval development of this species is poorly understood. In this study, we determined the number of instars in this pest using three batches of field-collected larvae from Guiyang, Guizhou, China. The postgenal length, head capsule width, mandibular phragma length, and body length of 773 individuals were measured, and k-means clustering was used for instar grouping. Four distance measures-Manhattan, Euclidean, Chebyshev, and Canberra-were determined. The reported instar numbers, ranging from 4 to 11, were set as initial cluster centers for k-means clustering. The Canberra distance yielded reliable instar grouping, which was consistent with the first instar, as characterized by egg bursters and prepupae with dark histoblasts. Females and males of the last cluster of larvae were identified using Feulgen-stained gonads. Morphometric differences between the two sexes were not significant. Validation was performed using the Brooks-Dyar and Crosby rules, revealing that the larval stage of S. quinquestriatum is composed of eight instars.
Clustering for Different Scales of Measurement - the Gap-Ratio Weighted K-means Algorithm
Guérin, Joris; Gibaru, Olivier; Thiery, Stéphane; Nyiri, Eric
2017-01-01
This paper describes a method for clustering data that are spread out over large regions and which dimensions are on different scales of measurement. Such an algorithm was developed to implement a robotics application consisting in sorting and storing objects in an unsupervised way. The toy dataset used to validate such application consists of Lego bricks of different shapes and colors. The uncontrolled lighting conditions together with the use of RGB color features, respectively involve data...
Wang, Xueyi
2012-02-08
The k-nearest neighbors (k-NN) algorithm is a widely used machine learning method that finds nearest neighbors of a test object in a feature space. We present a new exact k-NN algorithm called kMkNN (k-Means for k-Nearest Neighbors) that uses the k-means clustering and the triangle inequality to accelerate the searching for nearest neighbors in a high dimensional space. The kMkNN algorithm has two stages. In the buildup stage, instead of using complex tree structures such as metric trees, kd-trees, or ball-tree, kMkNN uses a simple k-means clustering method to preprocess the training dataset. In the searching stage, given a query object, kMkNN finds nearest training objects starting from the nearest cluster to the query object and uses the triangle inequality to reduce the distance calculations. Experiments show that the performance of kMkNN is surprisingly good compared to the traditional k-NN algorithm and tree-based k-NN algorithms such as kd-trees and ball-trees. On a collection of 20 datasets with up to 10(6) records and 10(4) dimensions, kMkNN shows a 2-to 80-fold reduction of distance calculations and a 2- to 60-fold speedup over the traditional k-NN algorithm for 16 datasets. Furthermore, kMkNN performs significant better than a kd-tree based k-NN algorithm for all datasets and performs better than a ball-tree based k-NN algorithm for most datasets. The results show that kMkNN is effective for searching nearest neighbors in high dimensional spaces.
International Nuclear Information System (INIS)
Seo, Inyong; Ha, Bokam; Lee, Sungwoo; Shin, Changhoon; Lee, Jaeyong; Kim, Seongjun
2011-01-01
In a nuclear power plant (NPP), periodic sensor calibrations are required to assure sensors are operating correctly. However, only a few faulty sensors are found to be rectified. For the safe operation of an NPP and the reduction of unnecessary calibration, on-line calibration monitoring is needed. In this study, an on-line calibration monitoring called KPCSVR using k-means clustering and principal component based Auto-Associative support vector regression (PCSVR) is proposed for nuclear power plant. To reduce the training time of the model, k-means clustering method was used. Response surface methodology is employed to efficiently determine the optimal values of support vector regression hyperparameters. The proposed KPCSVR model was confirmed with actual plant data of Kori Nuclear Power Plant Unit 3 which were measured from the primary and secondary systems of the plant, and compared with the PCSVR model. By using data clustering, the average accuracy of PCSVR improved from 1.228×10 -4 to 0.472×10 -4 and the average sensitivity of PCSVR from 0.0930 to 0.0909, which results in good detection of sensor drift. Moreover, the training time is greatly reduced from 123.5 to 31.5 sec. (author)
Directory of Open Access Journals (Sweden)
Widodo
2017-12-01
Full Text Available Penelitian ini bertujuan untuk mengetahui bidang skripsi mahasiswa peminatan multimedia PTIK UNJ angkatan 2010 yang dapat digunakan sebagai saran bagi mahasiswa yang belum mengajukan skripsi. Sedangkan bagi mahasiswa yang telah mengajukan skripsi dapat dijadikan sebagai perbandingan antara hasil program bantu dengan bidang skripsi yang diteliti. Penelitian dilakukan dengan menggunakan implementasi dari algoritma K-Means clustering, yaitu setiap data dikelompokkan berdasarkan jarak minimum terdekat dengan centroid. Data yang diolah merupakan rata-rata nilai mata kuliah Proyek Video Digital, Desain Grafis, dan Animasi Komputer untuk cluster 1 yaitu bidang video dan animasi. Untuk cluster 2 yaitu bidang aplikasi pengembangan perangkat lunak menggunakan rata-rata nilai mata kuliah Algoritma dan Pemrograman, Struktur Data, serta Pemrograman Web. Proses perhitungan menggunakan software MATLAB. Input data nilai berjumlah 53 mahasiswa dengan lima kali uji centroid. Hasil saran bidang skripsi untuk 19 mahasiswa yang belum mengajukan skripsi adalah 2 mahasiswa di bidang video dan animasi dan 17 mahasiswa di bidang aplikasi pengembangan perangkat lunak. Untuk 34 mahasiswa yang telah mengajukan skripsi, dilakukan perbandingan hasil bidang skripsi dengan menggunakan sign test. Berdasarkan hasil uji diketahui X2hitung < X2 tabel yaitu terima H0 dengan kesimpulan tidak terdapat perbedaan antara bidang skripsi hasil perhitungan program bantu algoritma K-Means dengan bidang skripsi yang telah diajukan mahasiswa.
Application of k-means clustering algorithm in grouping the DNA sequences of hepatitis B virus (HBV)
Bustamam, A.; Tasman, H.; Yuniarti, N.; Frisca, Mursidah, I.
2017-07-01
Based on WHO data, an estimated of 15 millions people worldwide who are infected with hepatitis B (HBsAg+), which is caused by HBV virus, are also infected by hepatitis D, which is caused by HDV virus. Hepatitis D infection can occur simultaneously with hepatitis B (co infection) or after a person is exposed to chronic hepatitis B (super infection). Since HDV cannot live without HBV, HDV infection is closely related to HBV infection, hence it is very realistic that every effort of prevention against hepatitis B can indirectly prevent hepatitis D. This paper presents clustering of HBV DNA sequences by using k-means clustering algorithm and R programming. Clustering processes are started with collecting HBV DNA sequences from GenBank, then performing extraction HBV DNA sequences using n-mers frequency and furthermore the extraction results are collected as a matrix and normalized using the min-max normalization with interval [0, 1] which will later be used as an input data. The number of clusters is two and the initial centroid selected of the cluster is chosen randomly. In each iteration, the distance of every object to each centroid are calculated using the Euclidean distance and the minimum distance is selected to determine the membership in a cluster until two convergent clusters are created. As the result, the HBV viruses in the first cluster is more virulent than the HBV viruses in the second cluster, so the HBV viruses in the first cluster can potentially evolve with HDV viruses that cause hepatitis D.
Ge, Yongchao; Sealfon, Stuart C
2012-08-01
For flow cytometry data, there are two common approaches to the unsupervised clustering problem: one is based on the finite mixture model and the other on spatial exploration of the histograms. The former is computationally slow and has difficulty to identify clusters of irregular shapes. The latter approach cannot be applied directly to high-dimensional data as the computational time and memory become unmanageable and the estimated histogram is unreliable. An algorithm without these two problems would be very useful. In this article, we combine ideas from the finite mixture model and histogram spatial exploration. This new algorithm, which we call flowPeaks, can be applied directly to high-dimensional data and identify irregular shape clusters. The algorithm first uses K-means algorithm with a large K to partition the cell population into many small clusters. These partitioned data allow the generation of a smoothed density function using the finite mixture model. All local peaks are exhaustively searched by exploring the density function and the cells are clustered by the associated local peak. The algorithm flowPeaks is automatic, fast and reliable and robust to cluster shape and outliers. This algorithm has been applied to flow cytometry data and it has been compared with state of the art algorithms, including Misty Mountain, FLOCK, flowMeans, flowMerge and FLAME. The R package flowPeaks is available at https://github.com/yongchao/flowPeaks. yongchao.ge@mssm.edu Supplementary data are available at Bioinformatics online.
Ichikawa, Kazuki; Morishita, Shinichi
2014-01-01
K-means clustering has been widely used to gain insight into biological systems from large-scale life science data. To quantify the similarities among biological data sets, Pearson correlation distance and standardized Euclidean distance are used most frequently; however, optimization methods have been largely unexplored. These two distance measurements are equivalent in the sense that they yield the same k-means clustering result for identical sets of k initial centroids. Thus, an efficient algorithm used for one is applicable to the other. Several optimization methods are available for the Euclidean distance and can be used for processing the standardized Euclidean distance; however, they are not customized for this context. We instead approached the problem by studying the properties of the Pearson correlation distance, and we invented a simple but powerful heuristic method for markedly pruning unnecessary computation while retaining the final solution. Tests using real biological data sets with 50-60K vectors of dimensions 10-2001 (~400 MB in size) demonstrated marked reduction in computation time for k = 10-500 in comparison with other state-of-the-art pruning methods such as Elkan's and Hamerly's algorithms. The BoostKCP software is available at http://mlab.cb.k.u-tokyo.ac.jp/~ichikawa/boostKCP/.
Directory of Open Access Journals (Sweden)
Mhd Gading Sadewo
2017-09-01
Full Text Available Ayam bukanlah makanan yang asing bagi penduduk Indonesia. Makanan tersebut sangat mudah dijumpai dalam kehidupan masyarakat sehari-hari. Namun tingkat konsumsi daging ayam di Indonesia masih tergolong rendah dibandingkan dengan Negara tetangga. Penelitian ini membahas tentang Penerapan Datamining Pada Populasi Daging Ayam Ras Pedaging di Indonesia Berdasarkan Provinsi Menggunakan K-Means Clustering. Sumber data penelitian ini dikumpulkan berdasarkan dokumen-dokumen keterangan populasi daging ayam yang dihasilkan oleh Badan Pusat Statistik Nasional. Data yang digunakan dalam penelitian ini adalah data dari tahun 2009-2016 yang terdiri dari 34 provinsi. Variable yang digunakan (1 jumlah populasi dari tahun 2009-2016. Data akan diolah dengan melakukan clushtering dalam 3 clushter yaitu clusther tingkat populasi tinggi, clusther tingkat populasi sedang dan rendah. Centroid data untuk cluster tingkat populasi tinggi 4711403141, Centroid data untuk cluster tingkat populasi sedang 304240647, dan Centroid data untuk cluster tingkat populasi rendah 554200. Sehingga diperoleh penilaian berdasarkan indeks populasi daging ayam dengan 1 provinsi tingkat populasi tinggi yaitu Jawa Barat, 6 provinsi tingkat populasi sedang yaitu Sumatera Utara, Jawa Tengah, Jawa Timur, Banten, Kalimantan Selatan dan Kalimantan Timur, dan 27 provinsi lainnya termasuk tingkat populasi rendah. Hal ini dapat menjadi masukan kepada pemerintah, provinsi yang menjadi perhatian lebih pada populasi daging ayam berdasarkan cluster yang telah dilakukan
Unemployment and sovereign debt crisis in the Eurozone: A k-means- r analysis
Dias, João
2017-09-01
Some southern countries in Europe, together with Ireland, were particularly affected by the sovereign debt crises in the Eurozone and were obliged to implement tough corrective measures which proved to be very recessive in nature. As a result, not only GDP declined but unemployment jumped to very high levels as well. This paper uses a modified version of k-means (restricted k-means) to analyze the clustering of the Eurozone countries during the recent sovereign debt crisis, combining monthly data on unemployment and government bond yield rates. Our method shows that the separation of southern Europe from the other Eurozone is not necessarily a good characterization of this area before the crisis but the group of externally assisted countries plus Italy gains consistence as the crisis evolved, although there is no perfect homogeneity in this group, since the problems they faced, the type of response requested, the speed of reaction to the crisis and the lasting effects were not the same for all these countries.
International Nuclear Information System (INIS)
Romli
1997-01-01
Cluster analysis is the name of group of multivariate techniques whose principal purpose is to distinguish similar entities from the characteristics they process.To study this analysis, there are several algorithms that can be used. Therefore, this topic focuses to discuss the algorithms, such as, similarity measures, and hierarchical clustering which includes single linkage, complete linkage and average linkage method. also, non-hierarchical clustering method, which is popular name K -mean method ' will be discussed. Finally, this paper will be described the advantages and disadvantages of every methods
k-Means has polynomial smoothed complexity
Arthur, David; Manthey, Bodo; Röglin, Heiko; Spielman, D.A.
2009-01-01
The k-means method is one of the most widely used clustering algorithms, drawing its popularity from its speed in practice. Recently, however, it was shown to have exponential worst-case running time. In order to close the gap between practical performance and theoretical analysis, the k-means
Sirait, Kamson; Tulus; Budhiarti Nababan, Erna
2017-12-01
Clustering methods that have high accuracy and time efficiency are necessary for the filtering process. One method that has been known and applied in clustering is K-Means Clustering. In its application, the determination of the begining value of the cluster center greatly affects the results of the K-Means algorithm. This research discusses the results of K-Means Clustering with starting centroid determination with a random and KD-Tree method. The initial determination of random centroid on the data set of 1000 student academic data to classify the potentially dropout has a sse value of 952972 for the quality variable and 232.48 for the GPA, whereas the initial centroid determination by KD-Tree has a sse value of 504302 for the quality variable and 214,37 for the GPA variable. The smaller sse values indicate that the result of K-Means Clustering with initial KD-Tree centroid selection have better accuracy than K-Means Clustering method with random initial centorid selection.
Research on classified real-time flood forecasting framework based on K-means cluster and rough set.
Xu, Wei; Peng, Yong
2015-01-01
This research presents a new classified real-time flood forecasting framework. In this framework, historical floods are classified by a K-means cluster according to the spatial and temporal distribution of precipitation, the time variance of precipitation intensity and other hydrological factors. Based on the classified results, a rough set is used to extract the identification rules for real-time flood forecasting. Then, the parameters of different categories within the conceptual hydrological model are calibrated using a genetic algorithm. In real-time forecasting, the corresponding category of parameters is selected for flood forecasting according to the obtained flood information. This research tests the new classified framework on Guanyinge Reservoir and compares the framework with the traditional flood forecasting method. It finds that the performance of the new classified framework is significantly better in terms of accuracy. Furthermore, the framework can be considered in a catchment with fewer historical floods.
Chen, Zhaoxue; Yu, Haizhong; Chen, Hao
2013-12-01
To solve the problem of traditional K-means clustering in which initial clustering centers are selected randomly, we proposed a new K-means segmentation algorithm based on robustly selecting 'peaks' standing for White Matter, Gray Matter and Cerebrospinal Fluid in multi-peaks gray histogram of MRI brain image. The new algorithm takes gray value of selected histogram 'peaks' as the initial K-means clustering center and can segment the MRI brain image into three parts of tissue more effectively, accurately, steadily and successfully. Massive experiments have proved that the proposed algorithm can overcome many shortcomings caused by traditional K-means clustering method such as low efficiency, veracity, robustness and time consuming. The histogram 'peak' selecting idea of the proposed segmentootion method is of more universal availability.
Chen, Y.; Ho, C.; Chang, L.
2011-12-01
In previous decades, the climate change caused by global warming increases the occurrence frequency of extreme hydrological events. Water supply shortages caused by extreme events create great challenges for water resource management. To evaluate future climate variations, general circulation models (GCMs) are the most wildly known tools which shows possible weather conditions under pre-defined CO2 emission scenarios announced by IPCC. Because the study area of GCMs is the entire earth, the grid sizes of GCMs are much larger than the basin scale. To overcome the gap, a statistic downscaling technique can transform the regional scale weather factors into basin scale precipitations. The statistic downscaling technique can be divided into three categories include transfer function, weather generator and weather type. The first two categories describe the relationships between the weather factors and precipitations respectively based on deterministic algorithms, such as linear or nonlinear regression and ANN, and stochastic approaches, such as Markov chain theory and statistical distributions. In the weather type, the method has ability to cluster weather factors, which are high dimensional and continuous variables, into weather types, which are limited number of discrete states. In this study, the proposed downscaling model integrates the weather type, using the K-means clustering algorithm, and the weather generator, using the kernel density estimation. The study area is Shihmen basin in northern of Taiwan. In this study, the research process contains two steps, a calibration step and a synthesis step. Three sub-steps were used in the calibration step. First, weather factors, such as pressures, humidities and wind speeds, obtained from NCEP and the precipitations observed from rainfall stations were collected for downscaling. Second, the K-means clustering grouped the weather factors into four weather types. Third, the Markov chain transition matrixes and the
Directory of Open Access Journals (Sweden)
S. Oh
2012-09-01
Full Text Available Recent development of laser scanning device increased the capability of representing rock outcrop in a very high resolution. Accurate 3D point cloud model with rock joint information can help geologist to estimate stability of rock slope on-site or off-site. An automatic plane extraction method was developed by computing normal directions and grouping them in similar direction. Point normal was calculated by moving least squares (MLS method considering every point within a given distance to minimize error to the fitting plane. Normal directions were classified into a number of dominating clusters by fuzzy K-means clustering. Region growing approach was exploited to discriminate joints in a point cloud. Overall procedure was applied to point cloud with about 120,000 points, and successfully extracted joints with joint information. The extraction procedure was implemented to minimize number of input parameters and to construct plane information into the existing point cloud for less redundancy and high usability of the point cloud itself.
Shi, Weifang; Zeng, Weihua
2013-06-20
Reducing human vulnerability to chemical hazards in the industrialized city is a matter of great urgency. Vulnerability mapping is an alternative approach for providing vulnerability-reducing interventions in a region. This study presents a method for mapping human vulnerability to chemical hazards by using clustering analysis for effective vulnerability reduction. Taking the city of Shanghai as the study area, we measure human exposure to chemical hazards by using the proximity model with additionally considering the toxicity of hazardous substances, and capture the sensitivity and coping capacity with corresponding indicators. We perform an improved k-means clustering approach on the basis of genetic algorithm by using a 500 m × 500 m geographical grid as basic spatial unit. The sum of squared errors and silhouette coefficient are combined to measure the quality of clustering and to determine the optimal clustering number. Clustering result reveals a set of six typical human vulnerability patterns that show distinct vulnerability dimension combinations. The vulnerability mapping of the study area reflects cluster-specific vulnerability characteristics and their spatial distribution. Finally, we suggest specific points that can provide new insights in rationally allocating the limited funds for the vulnerability reduction of each cluster.
Directory of Open Access Journals (Sweden)
Weihua Zeng
2013-06-01
Full Text Available Reducing human vulnerability to chemical hazards in the industrialized city is a matter of great urgency. Vulnerability mapping is an alternative approach for providing vulnerability-reducing interventions in a region. This study presents a method for mapping human vulnerability to chemical hazards by using clustering analysis for effective vulnerability reduction. Taking the city of Shanghai as the study area, we measure human exposure to chemical hazards by using the proximity model with additionally considering the toxicity of hazardous substances, and capture the sensitivity and coping capacity with corresponding indicators. We perform an improved k-means clustering approach on the basis of genetic algorithm by using a 500 m × 500 m geographical grid as basic spatial unit. The sum of squared errors and silhouette coefficient are combined to measure the quality of clustering and to determine the optimal clustering number. Clustering result reveals a set of six typical human vulnerability patterns that show distinct vulnerability dimension combinations. The vulnerability mapping of the study area reflects cluster-specific vulnerability characteristics and their spatial distribution. Finally, we suggest specific points that can provide new insights in rationally allocating the limited funds for the vulnerability reduction of each cluster.
"K"-Means Clustering and Mixture Model Clustering: Reply to McLachlan (2011) and Vermunt (2011)
Steinley, Douglas; Brusco, Michael J.
2011-01-01
McLachlan (2011) and Vermunt (2011) each provided thoughtful replies to our original article (Steinley & Brusco, 2011). This response serves to incorporate some of their comments while simultaneously clarifying our position. We argue that greater caution against overparamaterization must be taken when assuming that clusters are highly elliptical…
Directory of Open Access Journals (Sweden)
Lazuardi Arsy
2016-04-01
Full Text Available Kualitas suatu daging sapi ditentukan oleh beberapa parameter, diantaranya adalah parameter ukuran, terkstur, ciri warna, bau dari daging dan lain – lain. Parameter terseburt merupakan salah satu faktor penting untuk menentukan kualitas daging. Umunya dalam menetukan kualitas baik buruknya daging dilakukan dengan cara manual yaitu menggunakan indera penglihatan dari segi warna maupun bentuk yang memiliki banyak kelemahan seperti penilaian oleh manusia yang bersifat subyektif dan tak konsisten. Tujuan dari penelitian ini adalah untuk membuat aplikasi untuk mendeteksi kualitas daging. Aplikasi dibangun dengan menggunakan bahasa pemrograman Java pada Android yang terintegrasi dengan Android SDK dan Eclipse menggunakan library OpenCV sehingga aplikasi ini berbasis mobile. Metode yang dipakai menggunakan segmentasi k-mean clustering selanjutnya dianalisis secara statistik. Pendeteksian kualitas dilakukan dengan menggunakan pencocokan tekstur dan warna daging berdasar data yang sudah ada. Aplikasi yang dibuat dapat digunakan untuk mencari nilai k yang signifikan serta mampu mendeteksi kualitas baik atau buruknya daging dengan melakukan pengujian terhadap beberapa jenis daging serta aplikasi ini dapat digunakan oleh masyarakat luas.
Sanchez-Morillo, Daniel; Fernandez-Granero, Miguel Angel; Jiménez, Antonio León
2015-05-01
COPD places an enormous burden on the healthcare systems and causes diminished health-related quality of life. The highest proportion of human and economic cost is associated with admissions for acute exacerbation of respiratory symptoms (AECOPD). Since prompt detection and treatment of exacerbations may improve outcomes, early detection of AECOPD is a critical issue. This pilot study was aimed to determine whether a mobile health system could enable early detection of AECOPD on a day-to-day basis. A novel electronic questionnaire for the early detection of COPD exacerbations was evaluated during a 6-months field trial in a group of 16 patients. Pattern recognition techniques were applied. A k-means clustering algorithm was trained and validated, and its accuracy in detecting AECOPD was assessed. Sensitivity and specificity were 74.6 and 89.7 %, respectively, and area under the receiver operating characteristic curve was 0.84. 31 out of 33 AECOPD were early identified with an average of 4.5 ± 2.1 days prior to the onset of the exacerbation that was considered the day of medical attendance. Based on the findings of this preliminary pilot study, the proposed electronic questionnaire and the applied methodology could help to early detect COPD exacerbations on a day-to-day basis and therefore could provide support to patients and physicians.
DEFF Research Database (Denmark)
Brix, Lau; Christoffersen, Christian P. V.; Kristiansen, Martin Søndergaard
was then categorized into groups by the k-means clustering method. Finally, the cluster containing the vessel under investigation was selected manually by a single mouse click. All calculations were performed on a Nvidia 8800 GTX graphics card using the Compute Unified Device Architecture (CUDA) extension to the C...
Directory of Open Access Journals (Sweden)
Aldi Nurzahputra
2017-07-01
Full Text Available In football, the selection of players line-up is based on their statistical performance. In this research, the line-up selection can implement the decision support system (DSS with FMADM SAW method. The criterias were used are goal, assists, saves, clean sheets, yellow cards, red cards, games, and an own goal. Then, the assessment players performance is using K-Means Clustering. There are two clusters: cluster_cukup and cluster_baik. The system used Manchester City player data in Forward, Mildfilder, Defender and Goal Keeper position. The purpose of this research is applying the FMADM and K-Means Clustering method to the system. Based on the results, the line-up selection can be processed by FMADM method and the performance assessed by K-Means Clustering method. By using the system, the selection and the assessment can be conducted and give the best decision for footbal coach objectively. Dalam sepak bola, pemilihan line-up pemain oleh pelatih dilakukan berdasarkan statistik yang dimiliki pemain. Penelitian ini menerapkan sistem pendukung keputusan (SPK dengan metode FMADM SAW untuk memilih pemain dari hasil pembobotan dari beberapa kriteria, yaitu goal, assist, saves, clean sheet, kartu kuning, kartu merah, main, dan gol bunuh diri. Penilaian performa pemain menggunakan metode K-Means clustering dengan dua cluster, yaitu cluster_cukup dan cluster_baik. Data yang digunakan dalam sistem ini menggunakan data pemain club Manchester City dengan posisi Forward, Mildfilder, Defender, dan Goal Keeper. Berdasarkan hasil yang diteliti, data statistik pemain dapat diolah dengan metode FMADM dan penilaian performa dengan metode K-Means clustering. Dengan adanya sistem ini, pemilihan dan penilaian dilakukan secara objektif dan memberikan pilihan untuk pelatih dalam mengambil keputusan.
La Rosa, Patricio S; Nehorai, Arye; Eswaran, Hari; Lowery, Curtis L; Preissl, Hubert
2008-02-01
We propose a single channel two-stage time-segment discriminator of uterine magnetomyogram (MMG) contractions during pregnancy. We assume that the preprocessed signals are piecewise stationary having distribution in a common family with a fixed number of parameters. Therefore, at the first stage, we propose a model-based segmentation procedure, which detects multiple change-points in the parameters of a piecewise constant time-varying autoregressive model using a robust formulation of the Schwarz information criterion (SIC) and a binary search approach. In particular, we propose a test statistic that depends on the SIC, derive its asymptotic distribution, and obtain closed-form optimal detection thresholds in the sense of the Neyman-Pearson criterion; therefore, we control the probability of false alarm and maximize the probability of change-point detection in each stage of the binary search algorithm. We compute and evaluate the relative energy variation [root mean squares (RMS)] and the dominant frequency component [first order zero crossing (FOZC)] in discriminating between time segments with and without contractions. The former consistently detects a time segment with contractions. Thus, at the second stage, we apply a nonsupervised K-means cluster algorithm to classify the detected time segments using the RMS values. We apply our detection algorithm to real MMG records obtained from ten patients admitted to the hospital for contractions with gestational ages between 31 and 40 weeks. We evaluate the performance of our detection algorithm in computing the detection and false alarm rate, respectively, using as a reference the patients' feedback. We also analyze the fusion of the decision signals from all the sensors as in the parallel distributed detection approach.
Agrawal, Ritu; Sharma, Manisha; Singh, Bikesh Kumar
2018-04-01
Manual segmentation and analysis of lesions in medical images is time consuming and subjected to human errors. Automated segmentation has thus gained significant attention in recent years. This article presents a hybrid approach for brain lesion segmentation in different imaging modalities by combining median filter, k means clustering, Sobel edge detection and morphological operations. Median filter is an essential pre-processing step and is used to remove impulsive noise from the acquired brain images followed by k-means segmentation, Sobel edge detection and morphological processing. The performance of proposed automated system is tested on standard datasets using performance measures such as segmentation accuracy and execution time. The proposed method achieves a high accuracy of 94% when compared with manual delineation performed by an expert radiologist. Furthermore, the statistical significance test between lesion segmented using automated approach and that by expert delineation using ANOVA and correlation coefficient achieved high significance values of 0.986 and 1 respectively. The experimental results obtained are discussed in lieu of some recently reported studies.
Yock, Adam D; Kim, Gwe-Ya
2017-09-01
To present the k-means clustering algorithm as a tool to address treatment planning considerations characteristic of stereotactic radiosurgery using a single isocenter for multiple targets. For 30 patients treated with stereotactic radiosurgery for multiple brain metastases, the geometric centroids and radii of each met were determined from the treatment planning system. In-house software used this as well as weighted and unweighted versions of the k-means clustering algorithm to group the targets to be treated with a single isocenter, and to position each isocenter. The algorithm results were evaluated using within-cluster sum of squares as well as a minimum target coverage metric that considered the effect of target size. Both versions of the algorithm were applied to an example patient to demonstrate the prospective determination of the appropriate number and location of isocenters. Both weighted and unweighted versions of the k-means algorithm were applied successfully to determine the number and position of isocenters. Comparing the two, both the within-cluster sum of squares metric and the minimum target coverage metric resulting from the unweighted version were less than those from the weighted version. The average magnitudes of the differences were small (-0.2 cm 2 and 0.1% for the within cluster sum of squares and minimum target coverage, respectively) but statistically significant (Wilcoxon signed-rank test, P k-means clustering algorithm represented an advantage of the unweighted version for the within-cluster sum of squares metric, and an advantage of the weighted version for the minimum target coverage metric. While additional treatment planning considerations have a large influence on the final treatment plan quality, both versions of the k-means algorithm provide automatic, consistent, quantitative, and objective solutions to the tasks associated with SRS treatment planning using a single isocenter for multiple targets. © 2017 The Authors. Journal
Towards explaining the speed of k-means
Manthey, Bodo; van de Pol, Jan Cornelis; Raamsdonk, F.; Stoelinga, Mariëlle Ida Antoinette
2011-01-01
The $k$-means method is a popular algorithm for clustering, known for its speed in practice. This stands in contrast to its exponential worst-case running-time. To explain the speed of the $k$-means method, a smoothed analysis has been conducted. We sketch this smoothed analysis and a generalization
Konicek, Andrew R; Lefman, Jonathan; Szakal, Christopher
2012-08-07
We present a novel method for correlating and classifying ion-specific time-of-flight secondary ion mass spectrometry (ToF-SIMS) images within a multispectral dataset by grouping images with similar pixel intensity distributions. Binary centroid images are created by employing a k-means-based custom algorithm. Centroid images are compared to grayscale SIMS images using a newly developed correlation method that assigns the SIMS images to classes that have similar spatial (rather than spectral) patterns. Image features of both large and small spatial extent are identified without the need for image pre-processing, such as normalization or fixed-range mass-binning. A subsequent classification step tracks the class assignment of SIMS images over multiple iterations of increasing n classes per iteration, providing information about groups of images that have similar chemistry. Details are discussed while presenting data acquired with ToF-SIMS on a model sample of laser-printed inks. This approach can lead to the identification of distinct ion-specific chemistries for mass spectral imaging by ToF-SIMS, as well as matrix-assisted laser desorption ionization (MALDI), and desorption electrospray ionization (DESI).
Amin, Morteza Moradi; Kermani, Saeed; Talebi, Ardeshir; Oghli, Mostafa Ghelich
2015-01-01
Acute lymphoblastic leukemia is the most common form of pediatric cancer which is categorized into three L1, L2, and L3 and could be detected through screening of blood and bone marrow smears by pathologists. Due to being time-consuming and tediousness of the procedure, a computer-based system is acquired for convenient detection of Acute lymphoblastic leukemia. Microscopic images are acquired from blood and bone marrow smears of patients with Acute lymphoblastic leukemia and normal cases. After applying image preprocessing, cells nuclei are segmented by k-means algorithm. Then geometric and statistical features are extracted from nuclei and finally these cells are classified to cancerous and noncancerous cells by means of support vector machine classifier with 10-fold cross validation. These cells are also classified into their sub-types by multi-Support vector machine classifier. Classifier is evaluated by these parameters: Sensitivity, specificity, and accuracy which values for cancerous and noncancerous cells 98%, 95%, and 97%, respectively. These parameters are also used for evaluation of cell sub-types which values in mean 84.3%, 97.3%, and 95.6%, respectively. The results show that proposed algorithm could achieve an acceptable performance for the diagnosis of Acute lymphoblastic leukemia and its sub-types and can be used as an assistant diagnostic tool for pathologists.
Lu, Jing; Chen, Lei; Yin, Jun; Huang, Tao; Bi, Yi; Kong, Xiangyin; Zheng, Mingyue; Cai, Yu-Dong
2016-01-01
Lung cancer, characterized by uncontrolled cell growth in the lung tissue, is the leading cause of global cancer deaths. Until now, effective treatment of this disease is limited. Many synthetic compounds have emerged with the advancement of combinatorial chemistry. Identification of effective lung cancer candidate drug compounds among them is a great challenge. Thus, it is necessary to build effective computational methods that can assist us in selecting for potential lung cancer drug compounds. In this study, a computational method was proposed to tackle this problem. The chemical-chemical interactions and chemical-protein interactions were utilized to select candidate drug compounds that have close associations with approved lung cancer drugs and lung cancer-related genes. A permutation test and K-means clustering algorithm were employed to exclude candidate drugs with low possibilities to treat lung cancer. The final analysis suggests that the remaining drug compounds have potential anti-lung cancer activities and most of them have structural dissimilarity with approved drugs for lung cancer.
Ghane, Narjes; Vard, Alireza; Talebi, Ardeshir; Nematollahy, Pardis
2017-01-01
Recognition of white blood cells (WBCs) is the first step to diagnose some particular diseases such as acquired immune deficiency syndrome, leukemia, and other blood-related diseases that are usually done by pathologists using an optical microscope. This process is time-consuming, extremely tedious, and expensive and needs experienced experts in this field. Thus, a computer-aided diagnosis system that assists pathologists in the diagnostic process can be so effective. Segmentation of WBCs is usually a first step in developing a computer-aided diagnosis system. The main purpose of this paper is to segment WBCs from microscopic images. For this purpose, we present a novel combination of thresholding, k-means clustering, and modified watershed algorithms in three stages including (1) segmentation of WBCs from a microscopic image, (2) extraction of nuclei from cell's image, and (3) separation of overlapping cells and nuclei. The evaluation results of the proposed method show that similarity measures, precision, and sensitivity respectively were 92.07, 96.07, and 94.30% for nucleus segmentation and 92.93, 97.41, and 93.78% for cell segmentation. In addition, statistical analysis presents high similarity between manual segmentation and the results obtained by the proposed method.
Directory of Open Access Journals (Sweden)
Adewale Oparinde
Full Text Available Analysis of market segments within a population remains critical to agricultural systems and policy processes for targeting new innovations. Patterns in attitudes and intentions toward cultivating Provitamin A GM cassava are examined through the use of a combination of behavioural theory and k-means cluster analysis method, investigating the interrelationship among various behavioural antecedents. Using a state-level sample of smallholder cassava farmers in Nigeria, this paper identifies three distinct classes of attitude and intention denoted as low opposition, medium opposition and high opposition farmers. It was estimated that only 25% of the surveyed population of farmers was highly opposed to cultivating Provitamin A GM cassava.
Oparinde, Adewale; Abdoulaye, Tahirou; Mignouna, Djana Babatima; Bamire, Adebayo Simeon
2017-01-01
Analysis of market segments within a population remains critical to agricultural systems and policy processes for targeting new innovations. Patterns in attitudes and intentions toward cultivating Provitamin A GM cassava are examined through the use of a combination of behavioural theory and k-means cluster analysis method, investigating the interrelationship among various behavioural antecedents. Using a state-level sample of smallholder cassava farmers in Nigeria, this paper identifies three distinct classes of attitude and intention denoted as low opposition, medium opposition and high opposition farmers. It was estimated that only 25% of the surveyed population of farmers was highly opposed to cultivating Provitamin A GM cassava.
Abdoulaye, Tahirou; Mignouna, Djana Babatima; Bamire, Adebayo Simeon
2017-01-01
Analysis of market segments within a population remains critical to agricultural systems and policy processes for targeting new innovations. Patterns in attitudes and intentions toward cultivating Provitamin A GM cassava are examined through the use of a combination of behavioural theory and k-means cluster analysis method, investigating the interrelationship among various behavioural antecedents. Using a state-level sample of smallholder cassava farmers in Nigeria, this paper identifies three distinct classes of attitude and intention denoted as low opposition, medium opposition and high opposition farmers. It was estimated that only 25% of the surveyed population of farmers was highly opposed to cultivating Provitamin A GM cassava. PMID:28700605
Directory of Open Access Journals (Sweden)
Nur Diyana Kamarudin
2017-01-01
Full Text Available In tongue diagnosis, colour information of tongue body has kept valuable information regarding the state of disease and its correlation with the internal organs. Qualitatively, practitioners may have difficulty in their judgement due to the instable lighting condition and naked eye’s ability to capture the exact colour distribution on the tongue especially the tongue with multicolour substance. To overcome this ambiguity, this paper presents a two-stage tongue’s multicolour classification based on a support vector machine (SVM whose support vectors are reduced by our proposed k-means clustering identifiers and red colour range for precise tongue colour diagnosis. In the first stage, k-means clustering is used to cluster a tongue image into four clusters of image background (black, deep red region, red/light red region, and transitional region. In the second-stage classification, red/light red tongue images are further classified into red tongue or light red tongue based on the red colour range derived in our work. Overall, true rate classification accuracy of the proposed two-stage classification to diagnose red, light red, and deep red tongue colours is 94%. The number of support vectors in SVM is improved by 41.2%, and the execution time for one image is recorded as 48 seconds.
Ooi, Chia Yee; Kawanabe, Tadaaki; Odaguchi, Hiroshi; Kobayashi, Fuminori
2017-01-01
In tongue diagnosis, colour information of tongue body has kept valuable information regarding the state of disease and its correlation with the internal organs. Qualitatively, practitioners may have difficulty in their judgement due to the instable lighting condition and naked eye's ability to capture the exact colour distribution on the tongue especially the tongue with multicolour substance. To overcome this ambiguity, this paper presents a two-stage tongue's multicolour classification based on a support vector machine (SVM) whose support vectors are reduced by our proposed k-means clustering identifiers and red colour range for precise tongue colour diagnosis. In the first stage, k-means clustering is used to cluster a tongue image into four clusters of image background (black), deep red region, red/light red region, and transitional region. In the second-stage classification, red/light red tongue images are further classified into red tongue or light red tongue based on the red colour range derived in our work. Overall, true rate classification accuracy of the proposed two-stage classification to diagnose red, light red, and deep red tongue colours is 94%. The number of support vectors in SVM is improved by 41.2%, and the execution time for one image is recorded as 48 seconds. PMID:29065640
Kamarudin, Nur Diyana; Ooi, Chia Yee; Kawanabe, Tadaaki; Odaguchi, Hiroshi; Kobayashi, Fuminori
2017-01-01
In tongue diagnosis, colour information of tongue body has kept valuable information regarding the state of disease and its correlation with the internal organs. Qualitatively, practitioners may have difficulty in their judgement due to the instable lighting condition and naked eye's ability to capture the exact colour distribution on the tongue especially the tongue with multicolour substance. To overcome this ambiguity, this paper presents a two-stage tongue's multicolour classification based on a support vector machine (SVM) whose support vectors are reduced by our proposed k -means clustering identifiers and red colour range for precise tongue colour diagnosis. In the first stage, k -means clustering is used to cluster a tongue image into four clusters of image background (black), deep red region, red/light red region, and transitional region. In the second-stage classification, red/light red tongue images are further classified into red tongue or light red tongue based on the red colour range derived in our work. Overall, true rate classification accuracy of the proposed two-stage classification to diagnose red, light red, and deep red tongue colours is 94%. The number of support vectors in SVM is improved by 41.2%, and the execution time for one image is recorded as 48 seconds.
The global Minmax k-means algorithm.
Wang, Xiaoyan; Bai, Yanping
2016-01-01
The global k -means algorithm is an incremental approach to clustering that dynamically adds one cluster center at a time through a deterministic global search procedure from suitable initial positions, and employs k -means to minimize the sum of the intra-cluster variances. However the global k -means algorithm sometimes results singleton clusters and the initial positions sometimes are bad, after a bad initialization, poor local optimal can be easily obtained by k -means algorithm. In this paper, we modified the global k -means algorithm to eliminate the singleton clusters at first, and then we apply MinMax k -means clustering error method to global k -means algorithm to overcome the effect of bad initialization, proposed the global Minmax k -means algorithm. The proposed clustering method is tested on some popular data sets and compared to the k -means algorithm, the global k -means algorithm and the MinMax k -means algorithm. The experiment results show our proposed algorithm outperforms other algorithms mentioned in the paper.
Directory of Open Access Journals (Sweden)
Shizhen Zhao
2018-06-01
Full Text Available Mobile activity recognition is significant to the development of human-centric pervasive applications including elderly care, personalized recommendations, etc. Nevertheless, the distribution of inertial sensor data can be influenced to a great extent by varying users. This means that the performance of an activity recognition classifier trained by one user’s dataset will degenerate when transferred to others. In this study, we focus on building a personalized classifier to detect four categories of human activities: light intensity activity, moderate intensity activity, vigorous intensity activity, and fall. In order to solve the problem caused by different distributions of inertial sensor signals, a user-adaptive algorithm based on K-Means clustering, local outlier factor (LOF, and multivariate Gaussian distribution (MGD is proposed. To automatically cluster and annotate a specific user’s activity data, an improved K-Means algorithm with a novel initialization method is designed. By quantifying the samples’ informative degree in a labeled individual dataset, the most profitable samples can be selected for activity recognition model adaption. Through experiments, we conclude that our proposed models can adapt to new users with good recognition performance.
Directory of Open Access Journals (Sweden)
Xiaoyu Li
2015-07-01
Full Text Available This paper presents a novel grouping method for lithium iron phosphate batteries. In this method, a simplified electrochemical impedance spectroscopy (EIS model is utilized to describe the battery characteristics. Dynamic stress test (DST and fractional joint Kalman filter (FJKF are used to extract battery model parameters. In order to realize equal-number grouping of batteries, a new modified K-means clustering algorithm is proposed. Two rules are designed to equalize the numbers of elements in each group and exchange samples among groups. In this paper, the principles of battery model selection, physical meaning and identification method of model parameters, data preprocessing and equal-number clustering method for battery grouping are comprehensively described. Additionally, experiments for battery grouping and method validation are designed. This method is meaningful to application involving the grouping of fresh batteries for electric vehicles (EVs and screening of aged batteries for recycling.
RoK: Roll-Up with the K-Means Clustering Method for Recommending OLAP Queries
Bentayeb, Fadila; Favre, Cécile
Dimension hierarchies represent a substantial part of the data warehouse model. Indeed they allow decision makers to examine data at different levels of detail with On-Line Analytical Processing (OLAP) operators such as drill-down and roll-up. The granularity levels which compose a dimension hierarchy are usually fixed during the design step of the data warehouse, according to the identified analysis needs of the users. However, in practice, the needs of users may evolve and grow in time. Hence, to take into account the users’ analysis evolution into the data warehouse, we propose to integrate personalization techniques within the OLAP process. We propose two kinds of OLAP personalization in the data warehouse: (1) adaptation and (2) recommendation.
[Cluster analysis in biomedical researches].
Akopov, A S; Moskovtsev, A A; Dolenko, S A; Savina, G D
2013-01-01
Cluster analysis is one of the most popular methods for the analysis of multi-parameter data. The cluster analysis reveals the internal structure of the data, group the separate observations on the degree of their similarity. The review provides a definition of the basic concepts of cluster analysis, and discusses the most popular clustering algorithms: k-means, hierarchical algorithms, Kohonen networks algorithms. Examples are the use of these algorithms in biomedical research.
Pisana, Francesco; Henzler, Thomas; Schönberg, Stefan; Klotz, Ernst; Schmidt, Bernhard; Kachelrieß, Marc
2017-07-01
Dynamic CT perfusion (CTP) consists in repeated acquisitions of the same volume in different time steps, slightly before, during and slightly afterwards the injection of contrast media. Important functional information can be derived for each voxel, which reflect the local hemodynamic properties and hence the metabolism of the tissue. Different approaches are being investigated to exploit data redundancy and prior knowledge for noise reduction of such datasets, ranging from iterative reconstruction schemes to high dimensional filters. We propose a new spatial bilateral filter which makes use of the k-means clustering algorithm and of an optimal calculated guiding image. We named the proposed filter as k-means clustering guided bilateral filter (KMGB). In this study, the KMGB filter is compared with the partial temporal non-local means filter (PATEN), with the time-intensity profile similarity (TIPS) filter, and with a new version derived from it, by introducing the guiding image (GB-TIPS). All the filters were tested on a digital in-house developed brain CTP phantom, were noise was added to simulate 80 kV and 200 mAs (default scanning parameters), 100 mAs and 30 mAs. Moreover, the filters performances were tested on 7 noisy clinical datasets with different pathologies in different body regions. The original contribution of our work is two-fold: first we propose an efficient algorithm to calculate a guiding image to improve the results of the TIPS filter, secondly we propose the introduction of the k-means clustering step and demonstrate how this can potentially replace the TIPS part of the filter obtaining better results at lower computational efforts. As expected, in the GB-TIPS, the introduction of the guiding image limits the over-smoothing of the TIPS filter, improving spatial resolution by more than 50%. Furthermore, replacing the time-intensity profile similarity calculation with a fuzzy k-means clustering strategy (KMGB) allows to control the edge preserving
Directory of Open Access Journals (Sweden)
Luiz Fernando Novack
2013-04-01
Full Text Available INTRODUÇÃO: A preparação física no futebol necessita estar sempre em constante atualização em virtude das exigências presentes no futebol contemporâneo. OBJETIVO: Verificar a sensibilidade da técnica estatística K Means Cluster na distribuição de grupos com base nas respostas fisiológicas pertinentes ao futebol. MÉTODOS: Os atletas foram submetidos a avaliações antropométricas para determinar o percentual de gordura (%G e de massa magra (MM, teste incremental em esteira para obter o VO2 máximo (VO2máx e a velocidade de limiar ventilatório (VLim, bem como testes de campo para a agilidade (AG e o salto vertical (SV. Os dados foram analisados pelo teste de Kruskal-Wallis e a distribuição dos grupos foi desenvolvida pela técnica de K Means Cluster conforme as semelhanças dos jogadores com essas variáveis fisiológicas, assumindo o nível de significância de p INTRODUCTION: Physical fitness in soccer needs to be constantly updated due to current demands in contemporary soccer. OBJECTIVE: To assess the sensitivity of the K Means Clustering in group distribution based on physiological responses relevant to soccer. METHODS: The athletes underwent anthropometric evaluations to determine fat percentage (%F lean mass (LM, treadmill incremental test to obtain the VO2 maximum (VO2max and ventilatory threshold velocity (VL, as well as a field test for agility (AG and vertical jump (VJ. Data were analyzed by Kruskal-Wallis and distribution of groups was determined by K Means Clustering according to their similarities with these physiological variables, assuming significance level of p < 0.05. RESULTS: Showed that both groups were significantly different only concerning VJ (p < 0.001; LM (p < 0.001; VL (p = 0.011 and VO2max (p = 0.029 indicating that the athletes need to be distributed in groups for these variables. Nevertheless, %F and AG (p = 0.317; p = 0.922 respectively, were not different, indicating that these variables can be
Alagha, Jawad S.; Seyam, Mohammed; Md Said, Md Azlin; Mogheir, Yunes
2017-12-01
Artificial intelligence (AI) techniques have increasingly become efficient alternative modeling tools in the water resources field, particularly when the modeled process is influenced by complex and interrelated variables. In this study, two AI techniques—artificial neural networks (ANNs) and support vector machine (SVM)—were employed to achieve deeper understanding of the salinization process (represented by chloride concentration) in complex coastal aquifers influenced by various salinity sources. Both models were trained using 11 years of groundwater quality data from 22 municipal wells in Khan Younis Governorate, Gaza, Palestine. Both techniques showed satisfactory prediction performance, where the mean absolute percentage error (MAPE) and correlation coefficient ( R) for the test data set were, respectively, about 4.5 and 99.8% for the ANNs model, and 4.6 and 99.7% for SVM model. The performances of the developed models were further noticeably improved through preprocessing the wells data set using a k-means clustering method, then conducting AI techniques separately for each cluster. The developed models with clustered data were associated with higher performance, easiness and simplicity. They can be employed as an analytical tool to investigate the influence of input variables on coastal aquifer salinity, which is of great importance for understanding salinization processes, leading to more effective water-resources-related planning and decision making.
Directory of Open Access Journals (Sweden)
Evanita Evanita
2016-04-01
Full Text Available Di Indonesia kepadatan arus lalu lintas terjadi pada jam berangkat dan pulang kantor, hari-hari libur panjang atau hari-hari besar nasional terutama saat hari raya Idul Fitri (lebaran. Mudik sudah menjadi tradisi bagi masyarakat Indonesia yang ditunggu-tunggu menjelang lebaran, berbondong-bondong untuk pulang ke kampung halaman untuk bertemu dan berkumpul dengan keluarga. Kegiatan rutin tahunan ini banyak di lakukan khususnya bagi masyarakat kota-kota besar seperti Jakarta, dimana diketahui bahwa Jakarta adalah Ibu kota negara Republik Indonesia dan menjadi tujuan merantau untuk mencari pekerjaan yang lebih layak yang merupakan harapan besar bagi masyarakat desa. Volume kendaraan bertambah sejak 7 hari menjelang lebaran sampai 7 hari setelah lebaran tiap tahunnya terutama pada arah keluar dan masuk wilayah Jawa Tengah yang banyak menjadi tujuan mudik. Volume kendaraan saat arus mudik yang selalu meningkat inilah yang akan diteliti lebih lanjut dengan metode ANFIS agar dapat menjadi alternatif solusi langkah apa yang akan dilakukan di tahun selanjutnya agar pelayanan lalu lintas, kemacetan panjang dan angka kecelakaan berkurang. Dengan input parameter ANFIS yang digunakan yaitu pengclusteran hingga 5 cluster, epoch 100, error goal 0 diperoleh performa terbaik ANFIS dengan K-Means clustering yang terbagi menjadi 3 cluster, epoch terbaik sebesar 20 dengan RMSE Training terbaik sebesar 0,1198, RMSE Testing terbaik sebesar 0,0282 dan waktu proses tersingkat sebesar 0,0695.Selanjutnya hasil prediksi diharapkan dapat bermanfaat menjadi alternatif solusi langkah apa yang akan dilakukan di tahun selanjutnya agar pelayanan lalu lintas lebih baik lagi. Kata kunci: angkutan lebaran, Jawa Tengah, ANFIS.
Mokdad, Fatiha; Haddad, Boualem
2017-06-01
In this paper, two new infrared precipitation estimation approaches based on the concept of k-means clustering are first proposed, named the NAW-Kmeans and the GPI-Kmeans methods. Then, they are adapted to the southern Mediterranean basin, where the subtropical climate prevails. The infrared data (10.8 μm channel) acquired by MSG-SEVIRI sensor in winter and spring 2012 are used. Tests are carried out in eight areas distributed over northern Algeria: Sebra, El Bordj, Chlef, Blida, Bordj Menael, Sidi Aich, Beni Ourthilane, and Beni Aziz. The validation is performed by a comparison of the estimated rainfalls to rain gauges observations collected by the National Office of Meteorology in Dar El Beida (Algeria). Despite the complexity of the subtropical climate, the obtained results indicate that the NAW-Kmeans and the GPI-Kmeans approaches gave satisfactory results for the considered rain rates. Also, the proposed schemes lead to improvement in precipitation estimation performance when compared to the original algorithms NAW (Nagri, Adler, and Wetzel) and GPI (GOES Precipitation Index).
Turan, Muhammed K.; Sehirli, Eftal; Elen, Abdullah; Karas, Ismail R.
2015-07-01
Gel electrophoresis (GE) is one of the most used method to separate DNA, RNA, protein molecules according to size, weight and quantity parameters in many areas such as genetics, molecular biology, biochemistry, microbiology. The main way to separate each molecule is to find borders of each molecule fragment. This paper presents a software application that show columns edges of DNA fragments in 3 steps. In the first step the application obtains lane histograms of agarose gel electrophoresis images by doing projection based on x-axis. In the second step, it utilizes k-means clustering algorithm to classify point values of lane histogram such as left side values, right side values and undesired values. In the third step, column edges of DNA fragments is shown by using mean algorithm and mathematical processes to separate DNA fragments from the background in a fully automated way. In addition to this, the application presents locations of DNA fragments and how many DNA fragments exist on images captured by a scientific camera.
A Parametric k-Means Algorithm
Tarpey, Thaddeus
2007-01-01
Summary The k points that optimally represent a distribution (usually in terms of a squared error loss) are called the k principal points. This paper presents a computationally intensive method that automatically determines the principal points of a parametric distribution. Cluster means from the k-means algorithm are nonparametric estimators of principal points. A parametric k-means approach is introduced for estimating principal points by running the k-means algorithm on a very large simulated data set from a distribution whose parameters are estimated using maximum likelihood. Theoretical and simulation results are presented comparing the parametric k-means algorithm to the usual k-means algorithm and an example on determining sizes of gas masks is used to illustrate the parametric k-means algorithm. PMID:17917692
Reducing the time requirement of k-means algorithm.
Osamor, Victor Chukwudi; Adebiyi, Ezekiel Femi; Oyelade, Jelilli Olarenwaju; Doumbia, Seydou
2012-01-01
Traditional k-means and most k-means variants are still computationally expensive for large datasets, such as microarray data, which have large datasets with large dimension size d. In k-means clustering, we are given a set of n data points in d-dimensional space R(d) and an integer k. The problem is to determine a set of k points in R(d), called centers, so as to minimize the mean squared distance from each data point to its nearest center. In this work, we develop a novel k-means algorithm, which is simple but more efficient than the traditional k-means and the recent enhanced k-means. Our new algorithm is based on the recently established relationship between principal component analysis and the k-means clustering. We provided the correctness proof for this algorithm. Results obtained from testing the algorithm on three biological data and six non-biological data (three of these data are real, while the other three are simulated) also indicate that our algorithm is empirically faster than other known k-means algorithms. We assessed the quality of our algorithm clusters against the clusters of a known structure using the Hubert-Arabie Adjusted Rand index (ARI(HA)). We found that when k is close to d, the quality is good (ARI(HA)>0.8) and when k is not close to d, the quality of our new k-means algorithm is excellent (ARI(HA)>0.9). In this paper, emphases are on the reduction of the time requirement of the k-means algorithm and its application to microarray data due to the desire to create a tool for clustering and malaria research. However, the new clustering algorithm can be used for other clustering needs as long as an appropriate measure of distance between the centroids and the members is used. This has been demonstrated in this work on six non-biological data.
Elastic K-means using posterior probability.
Zheng, Aihua; Jiang, Bo; Li, Yan; Zhang, Xuehan; Ding, Chris
2017-01-01
The widely used K-means clustering is a hard clustering algorithm. Here we propose a Elastic K-means clustering model (EKM) using posterior probability with soft capability where each data point can belong to multiple clusters fractionally and show the benefit of proposed Elastic K-means. Furthermore, in many applications, besides vector attributes information, pairwise relations (graph information) are also available. Thus we integrate EKM with Normalized Cut graph clustering into a single clustering formulation. Finally, we provide several useful matrix inequalities which are useful for matrix formulations of learning models. Based on these results, we prove the correctness and the convergence of EKM algorithms. Experimental results on six benchmark datasets demonstrate the effectiveness of proposed EKM and its integrated model.
An implementation of the relational k-means algorithm
Szalkai, Balázs
2013-01-01
A C# implementation of a generalized k-means variant called relational k-means is described here. Relational k-means is a generalization of the well-known k-means clustering method which works for non-Euclidean scenarios as well. The input is an arbitrary distance matrix, as opposed to the traditional k-means method, where the clustered objects need to be identified with vectors.
Kim, Chan Moon; Parnichkun, Manukid
2017-11-01
Coagulation is an important process in drinking water treatment to attain acceptable treated water quality. However, the determination of coagulant dosage is still a challenging task for operators, because coagulation is nonlinear and complicated process. Feedback control to achieve the desired treated water quality is difficult due to lengthy process time. In this research, a hybrid of k-means clustering and adaptive neuro-fuzzy inference system ( k-means-ANFIS) is proposed for the settled water turbidity prediction and the optimal coagulant dosage determination using full-scale historical data. To build a well-adaptive model to different process states from influent water, raw water quality data are classified into four clusters according to its properties by a k-means clustering technique. The sub-models are developed individually on the basis of each clustered data set. Results reveal that the sub-models constructed by a hybrid k-means-ANFIS perform better than not only a single ANFIS model, but also seasonal models by artificial neural network (ANN). The finally completed model consisting of sub-models shows more accurate and consistent prediction ability than a single model of ANFIS and a single model of ANN based on all five evaluation indices. Therefore, the hybrid model of k-means-ANFIS can be employed as a robust tool for managing both treated water quality and production costs simultaneously.
DEFF Research Database (Denmark)
Haack, Søren; Pedersen, Erik Morre; Vinding, Mads Sloth
in dose planning of radiotherapy. This study evaluates the use of k-means clustering for automatic user independent delineation of regions of reduced apparent diffusion coefficient (ADC) and the value of B0-correction of DW-MRI for reduction of geometrical distortions during dose planning of brachytherapy...
International Nuclear Information System (INIS)
Boersma, C.; Bregman, J.; Allamandola, L. J.
2014-01-01
Polycyclic aromatic hydrocarbon (PAH) emission in the Spitzer-IRS spectral map of the northwest photon dominated region (PDR) in NGC 7023 is analyzed using the 'traditional' approach in which the PAH bands and plateaus between 5.2-19.5 μm are isolated by subtracting the underlying continuum and removing H 2 emission lines. The spectra are organized into seven spectroscopic bins by using k-means clustering. Each cluster corresponds to, and reveals, a morphological zone within NGC 7023. The zones self-organize parallel to the well-defined PDR front that coincides with an increase in intensity of the H 2 emission lines. PAH band profiles and integrated strengths are measured, classified, and mapped. The morphological zones revealed by the k-means clustering provides deeper insight into the conditions that drive variations in band strength ratios and evolution of the PAH population that otherwise would be lost. For example, certain band-band relations are bifurcated, revealing two limiting cases; one associated with the PDR, the other with the diffuse medium. Traditionally, PAH band strength ratios are used to gain insight into the properties of the emitting PAH population, i.e., charge, size, structure, and composition. Insights inferred from this work are compared and contrasted to those from Boersma et al. (first paper in this series), where the PAH emission in NGC 7023 is decomposed exclusively using the PAH spectra and tools made available through the NASA Ames PAH IR Spectroscopic Database.
Everitt, Brian S; Leese, Morven; Stahl, Daniel
2011-01-01
Cluster analysis comprises a range of methods for classifying multivariate data into subgroups. By organizing multivariate data into such subgroups, clustering can help reveal the characteristics of any structure or patterns present. These techniques have proven useful in a wide range of areas such as medicine, psychology, market research and bioinformatics.This fifth edition of the highly successful Cluster Analysis includes coverage of the latest developments in the field and a new chapter dealing with finite mixture models for structured data.Real life examples are used throughout to demons
Vermunt, Jeroen K.
2011-01-01
Steinley and Brusco (2011) presented the results of a huge simulation study aimed at evaluating cluster recovery of mixture model clustering (MMC) both for the situation where the number of clusters is known and is unknown. They derived rather strong conclusions on the basis of this study, especially with regard to the good performance of…
Simultaneous Two-Way Clustering of Multiple Correspondence Analysis
Hwang, Heungsun; Dillon, William R.
2010-01-01
A 2-way clustering approach to multiple correspondence analysis is proposed to account for cluster-level heterogeneity of both respondents and variable categories in multivariate categorical data. Specifically, in the proposed method, multiple correspondence analysis is combined with k-means in a unified framework in which "k"-means is…
Improved Performance of Unsupervised Method by Renovated K-Means
Ashok, P.; Nawaz, G. M Kadhar; Elayaraja, E.; Vadivel, V.
2013-01-01
Clustering is a separation of data into groups of similar objects. Every group called cluster consists of objects that are similar to one another and dissimilar to objects of other groups. In this paper, the K-Means algorithm is implemented by three distance functions and to identify the optimal distance function for clustering methods. The proposed K-Means algorithm is compared with K-Means, Static Weighted K-Means (SWK-Means) and Dynamic Weighted K-Means (DWK-Means) algorithm by using Davis...
Energy Technology Data Exchange (ETDEWEB)
Boersma, C.; Bregman, J.; Allamandola, L. J., E-mail: Christiaan.Boersma@nasa.gov [NASA Ames Research Center, MS 245-6, Moffett Field, CA 94035-0001 (United States)
2014-11-10
Polycyclic aromatic hydrocarbon (PAH) emission in the Spitzer-IRS spectral map of the northwest photon dominated region (PDR) in NGC 7023 is analyzed using the 'traditional' approach in which the PAH bands and plateaus between 5.2-19.5 μm are isolated by subtracting the underlying continuum and removing H{sub 2} emission lines. The spectra are organized into seven spectroscopic bins by using k-means clustering. Each cluster corresponds to, and reveals, a morphological zone within NGC 7023. The zones self-organize parallel to the well-defined PDR front that coincides with an increase in intensity of the H{sub 2} emission lines. PAH band profiles and integrated strengths are measured, classified, and mapped. The morphological zones revealed by the k-means clustering provides deeper insight into the conditions that drive variations in band strength ratios and evolution of the PAH population that otherwise would be lost. For example, certain band-band relations are bifurcated, revealing two limiting cases; one associated with the PDR, the other with the diffuse medium. Traditionally, PAH band strength ratios are used to gain insight into the properties of the emitting PAH population, i.e., charge, size, structure, and composition. Insights inferred from this work are compared and contrasted to those from Boersma et al. (first paper in this series), where the PAH emission in NGC 7023 is decomposed exclusively using the PAH spectra and tools made available through the NASA Ames PAH IR Spectroscopic Database.
Dudik, Joshua M; Kurosu, Atsuko; Coyle, James L; Sejdić, Ervin
2015-04-01
Cervical auscultation with high resolution sensors is currently under consideration as a method of automatically screening for specific swallowing abnormalities. To be clinically useful without human involvement, any devices based on cervical auscultation should be able to detect specified swallowing events in an automatic manner. In this paper, we comparatively analyze the density-based spatial clustering of applications with noise algorithm (DBSCAN), a k-means based algorithm, and an algorithm based on quadratic variation as methods of differentiating periods of swallowing activity from periods of time without swallows. These algorithms utilized swallowing vibration data exclusively and compared the results to a gold standard measure of swallowing duration. Data was collected from 23 subjects that were actively suffering from swallowing difficulties. Comparing the performance of the DBSCAN algorithm with a proven segmentation algorithm that utilizes k-means clustering demonstrated that the DBSCAN algorithm had a higher sensitivity and correctly segmented more swallows. Comparing its performance with a threshold-based algorithm that utilized the quadratic variation of the signal showed that the DBSCAN algorithm offered no direct increase in performance. However, it offered several other benefits including a faster run time and more consistent performance between patients. All algorithms showed noticeable differentiation from the endpoints provided by a videofluoroscopy examination as well as reduced sensitivity. In summary, we showed that the DBSCAN algorithm is a viable method for detecting the occurrence of a swallowing event using cervical auscultation signals, but significant work must be done to improve its performance before it can be implemented in an unsupervised manner. Copyright © 2015 Elsevier Ltd. All rights reserved.
Mucha, Hans-Joachim; Sofyan, Hizir
2000-01-01
As an explorative technique, duster analysis provides a description or a reduction in the dimension of the data. It classifies a set of observations into two or more mutually exclusive unknown groups based on combinations of many variables. Its aim is to construct groups in such a way that the profiles of objects in the same groups are relatively homogenous whereas the profiles of objects in different groups are relatively heterogeneous. Clustering is distinct from classification techniques, ...
Semi-supervised consensus clustering for gene expression data analysis
Wang, Yunli; Pan, Youlian
2014-01-01
Background Simple clustering methods such as hierarchical clustering and k-means are widely used for gene expression data analysis; but they are unable to deal with noise and high dimensionality associated with the microarray gene expression data. Consensus clustering appears to improve the robustness and quality of clustering results. Incorporating prior knowledge in clustering process (semi-supervised clustering) has been shown to improve the consistency between the data partitioning and do...
Parallel k-means++ for Multiple Shared-Memory Architectures
Energy Technology Data Exchange (ETDEWEB)
Mackey, Patrick S.; Lewis, Robert R.
2016-09-22
In recent years k-means++ has become a popular initialization technique for improved k-means clustering. To date, most of the work done to improve its performance has involved parallelizing algorithms that are only approximations of k-means++. In this paper we present a parallelization of the exact k-means++ algorithm, with a proof of its correctness. We develop implementations for three distinct shared-memory architectures: multicore CPU, high performance GPU, and the massively multithreaded Cray XMT platform. We demonstrate the scalability of the algorithm on each platform. In addition we present a visual approach for showing which platform performed k-means++ the fastest for varying data sizes.
Improved Fuzzy Art Method for Initializing K-means
Directory of Open Access Journals (Sweden)
Sevinc Ilhan
2010-09-01
Full Text Available The K-means algorithm is quite sensitive to the cluster centers selected initially and can perform different clusterings depending on these initialization conditions. Within the scope of this study, a new method based on the Fuzzy ART algorithm which is called Improved Fuzzy ART (IFART is used in the determination of initial cluster centers. By using IFART, better quality clusters are achieved than Fuzzy ART do and also IFART is as good as Fuzzy ART about capable of fast clustering and capability on large scaled data clustering. Consequently, it is observed that, with the proposed method, the clustering operation is completed in fewer steps, that it is performed in a more stable manner by fixing the initialization points and that it is completed with a smaller error margin compared with the conventional K-means.
Research on hotspot discovery in internet public opinions based on improved K-means.
Wang, Gensheng
2013-01-01
How to discover hotspot in the Internet public opinions effectively is a hot research field for the researchers related which plays a key role for governments and corporations to find useful information from mass data in the Internet. An improved K-means algorithm for hotspot discovery in internet public opinions is presented based on the analysis of existing defects and calculation principle of original K-means algorithm. First, some new methods are designed to preprocess website texts, select and express the characteristics of website texts, and define the similarity between two website texts, respectively. Second, clustering principle and the method of initial classification centers selection are analyzed and improved in order to overcome the limitations of original K-means algorithm. Finally, the experimental results verify that the improved algorithm can improve the clustering stability and classification accuracy of hotspot discovery in internet public opinions when used in practice.
Research on Hotspot Discovery in Internet Public Opinions Based on Improved K-Means
2013-01-01
How to discover hotspot in the Internet public opinions effectively is a hot research field for the researchers related which plays a key role for governments and corporations to find useful information from mass data in the Internet. An improved K-means algorithm for hotspot discovery in internet public opinions is presented based on the analysis of existing defects and calculation principle of original K-means algorithm. First, some new methods are designed to preprocess website texts, select and express the characteristics of website texts, and define the similarity between two website texts, respectively. Second, clustering principle and the method of initial classification centers selection are analyzed and improved in order to overcome the limitations of original K-means algorithm. Finally, the experimental results verify that the improved algorithm can improve the clustering stability and classification accuracy of hotspot discovery in internet public opinions when used in practice. PMID:24106496
Cluster analysis for applications
Anderberg, Michael R
1973-01-01
Cluster Analysis for Applications deals with methods and various applications of cluster analysis. Topics covered range from variables and scales to measures of association among variables and among data units. Conceptual problems in cluster analysis are discussed, along with hierarchical and non-hierarchical clustering methods. The necessary elements of data analysis, statistics, cluster analysis, and computer implementation are integrated vertically to cover the complete path from raw data to a finished analysis.Comprised of 10 chapters, this book begins with an introduction to the subject o
Marketing research cluster analysis
Directory of Open Access Journals (Sweden)
Marić Nebojša
2002-01-01
Full Text Available One area of applications of cluster analysis in marketing is identification of groups of cities and towns with similar demographic profiles. This paper considers main aspects of cluster analysis by an example of clustering 12 cities with the use of Minitab software.
Marketing research cluster analysis
Marić Nebojša
2002-01-01
One area of applications of cluster analysis in marketing is identification of groups of cities and towns with similar demographic profiles. This paper considers main aspects of cluster analysis by an example of clustering 12 cities with the use of Minitab software.
An initialization method for the k-means using the concept of useful nearest centers
Ismkhan, Hassan
2017-01-01
The aim of the k-means is to minimize squared sum of Euclidean distance from the mean (SSEDM) of each cluster. The k-means can effectively optimize this function, but it is too sensitive for initial centers (seeds). This paper proposed a method for initialization of the k-means using the concept of useful nearest center for each data point.
A SURVEY ON DOCUMENT CLUSTERING APPROACH FOR COMPUTER FORENSIC ANALYSIS
Monika Raghuvanshi*, Rahul Patel
2016-01-01
In a forensic analysis, large numbers of files are examined. Much of the information comprises of in unstructured format, so it’s quite difficult task for computer forensic to perform such analysis. That’s why to do the forensic analysis of document within a limited period of time require a special approach such as document clustering. This paper review different document clustering algorithms methodologies for example K-mean, K-medoid, single link, complete link, average link in accorandance...
Sistem Multiagen untuk Pengklasteran Pendaki Menggunakan K-Means
Directory of Open Access Journals (Sweden)
Maya Cendana
2015-01-01
Abstract The beginner climbers should do mountain climbing as a group, however, manually grouping method that is currently running is not effective and efficient , especially for the solo climber who do not have the mountaineering community . Therefore, it is necessary to build an online media that is able to classify mountaineers automatically. The grouping is done by the algorithm K-Means clustering -based intelligent agents . The agents will collaborate in the negotiation process and determines the cluster members that have similar criteria . The main advantage of using multiagentsis multithreading proces, so the clustering process will run at once . The agentsconsists of the user agent , the database agent , clustering agents , and validation agent . The agents are implemented with JADE platform because JADE is using FIPA ACL communication language . Evaluation will calculate the value of cohesion / density in one cluster and inter - cluster separation distances with 10 , 100 and 200 data. Metric measurement used are WGAD and BGAD . Thequality of a cluster member is better than using an usual k-means . Keywords: agen, jade, fipa acl, wgad, bgad
Hierarchical Aligned Cluster Analysis for Temporal Clustering of Human Motion.
Zhou, Feng; De la Torre, Fernando; Hodgins, Jessica K
2013-03-01
Temporal segmentation of human motion into plausible motion primitives is central to understanding and building computational models of human motion. Several issues contribute to the challenge of discovering motion primitives: the exponential nature of all possible movement combinations, the variability in the temporal scale of human actions, and the complexity of representing articulated motion. We pose the problem of learning motion primitives as one of temporal clustering, and derive an unsupervised hierarchical bottom-up framework called hierarchical aligned cluster analysis (HACA). HACA finds a partition of a given multidimensional time series into m disjoint segments such that each segment belongs to one of k clusters. HACA combines kernel k-means with the generalized dynamic time alignment kernel to cluster time series data. Moreover, it provides a natural framework to find a low-dimensional embedding for time series. HACA is efficiently optimized with a coordinate descent strategy and dynamic programming. Experimental results on motion capture and video data demonstrate the effectiveness of HACA for segmenting complex motions and as a visualization tool. We also compare the performance of HACA to state-of-the-art algorithms for temporal clustering on data of a honey bee dance. The HACA code is available online.
Cluster analysis for validated climatology stations using precipitation in Mexico
Bravo Cabrera, J. L.; Azpra-Romero, E.; Zarraluqui-Such, V.; Gay-García, C.; Estrada Porrúa, F.
2012-01-01
Annual average of daily precipitation was used to group climatological stations into clusters using the k-means procedure and principal component analysis with varimax rotation. After a careful selection of the stations deployed in Mexico since 1950, we selected 349 characterized by having 35 to 40
k-Means: Random Sampling Procedure
Indian Academy of Sciences (India)
First page Back Continue Last page Overview Graphics. k-Means: Random Sampling Procedure. Optimal 1-Mean is. Approximation of Centroid (Inaba et al). S = random sample of size O(1/ ); Centroid of S is a (1+ )-approx centroid of P with constant probability.
Cluster analysis of rural, urban, and curbside atmospheric particle size data.
Beddows, David C S; Dall'Osto, Manuel; Harrison, Roy M
2009-07-01
Particle size is a key determinant of the hazard posed by airborne particles. Continuous multivariate particle size data have been collected using aerosol particle size spectrometers sited at four locations within the UK: Harwell (Oxfordshire); Regents Park (London); British Telecom Tower (London); and Marylebone Road (London). These data have been analyzed using k-means cluster analysis, deduced to be the preferred cluster analysis technique, selected from an option of four partitional cluster packages, namelythe following: Fuzzy; k-means; k-median; and Model-Based clustering. Using cluster validation indices k-means clustering was shown to produce clusters with the smallest size, furthest separation, and importantly the highest degree of similarity between the elements within each partition. Using k-means clustering, the complexity of the data set is reduced allowing characterization of the data according to the temporal and spatial trends of the clusters. At Harwell, the rural background measurement site, the cluster analysis showed that the spectra may be differentiated by their modal-diameters and average temporal trends showing either high counts during the day-time or night-time hours. Likewise for the urban sites, the cluster analysis differentiated the spectra into a small number of size distributions according their modal-diameter, the location of the measurement site, and time of day. The responsible aerosol emission, formation, and dynamic processes can be inferred according to the cluster characteristics and correlation to concurrently measured meteorological, gas phase, and particle phase measurements.
Yin, Jiandong; Sun, Hongzan; Yang, Jiawen; Guo, Qiyong
2014-01-01
The arterial input function (AIF) plays a crucial role in the quantification of cerebral perfusion parameters. The traditional method for AIF detection is based on manual operation, which is time-consuming and subjective. Two automatic methods have been reported that are based on two frequently used clustering algorithms: fuzzy c-means (FCM) and K-means. However, it is still not clear which is better for AIF detection. Hence, we compared the performance of these two clustering methods using both simulated and clinical data. The results demonstrate that K-means analysis can yield more accurate and robust AIF results, although it takes longer to execute than the FCM method. We consider that this longer execution time is trivial relative to the total time required for image manipulation in a PACS setting, and is acceptable if an ideal AIF is obtained. Therefore, the K-means method is preferable to FCM in AIF detection.
Walthouwer, Michel Jean Louis; Oenema, Anke; Soetens, Katja; Lechner, Lilian; de Vries, Hein
2014-11-01
Developing nutrition education interventions based on clusters of dietary patterns can only be done adequately when it is clear if distinctive clusters of dietary patterns can be derived and reproduced over time, if cluster membership is stable, and if it is predictable which type of people belong to a certain cluster. Hence, this study aimed to: (1) identify clusters of dietary patterns among Dutch adults, (2) test the reproducibility of these clusters and stability of cluster membership over time, and (3) identify sociodemographic predictors of cluster membership and cluster transition. This study had a longitudinal design with online measurements at baseline (N=483) and 6 months follow-up (N=379). Dietary intake was assessed with a validated food frequency questionnaire. A hierarchical cluster analysis was performed, followed by a K-means cluster analysis. Multinomial logistic regression analyses were conducted to identify the sociodemographic predictors of cluster membership and cluster transition. At baseline and follow-up, a comparable three-cluster solution was derived, distinguishing a healthy, moderately healthy, and unhealthy dietary pattern. Male and lower educated participants were significantly more likely to have a less healthy dietary pattern. Further, 251 (66.2%) participants remained in the same cluster, 45 (11.9%) participants changed to an unhealthier cluster, and 83 (21.9%) participants shifted to a healthier cluster. Men and people living alone were significantly more likely to shift toward a less healthy dietary pattern. Distinctive clusters of dietary patterns can be derived. Yet, cluster membership is unstable and only few sociodemographic factors were associated with cluster membership and cluster transition. These findings imply that clusters based on dietary intake may not be suitable as a basis for nutrition education interventions. Copyright © 2014 Elsevier Ltd. All rights reserved.
Clustering of users of digital libraries through log file analysis
Directory of Open Access Journals (Sweden)
Juan Antonio Martínez-Comeche
2017-09-01
Full Text Available This study analyzes how users perform information retrieval tasks when introducing queries to the Hispanic Digital Library. Clusters of users are differentiated based on their distinct information behavior. The study used the log files collected by the server over a year and different possible clustering algorithms are compared. The k-means algorithm is found to be a suitable clustering method for the analysis of large log files from digital libraries. In the case of the Hispanic Digital Library the results show three clusters of users and the characteristic information behavior of each group is described.
Two-Way Regularized Fuzzy Clustering of Multiple Correspondence Analysis.
Kim, Sunmee; Choi, Ji Yeh; Hwang, Heungsun
2017-01-01
Multiple correspondence analysis (MCA) is a useful tool for investigating the interrelationships among dummy-coded categorical variables. MCA has been combined with clustering methods to examine whether there exist heterogeneous subclusters of a population, which exhibit cluster-level heterogeneity. These combined approaches aim to classify either observations only (one-way clustering of MCA) or both observations and variable categories (two-way clustering of MCA). The latter approach is favored because its solutions are easier to interpret by providing explicitly which subgroup of observations is associated with which subset of variable categories. Nonetheless, the two-way approach has been built on hard classification that assumes observations and/or variable categories to belong to only one cluster. To relax this assumption, we propose two-way fuzzy clustering of MCA. Specifically, we combine MCA with fuzzy k-means simultaneously to classify a subgroup of observations and a subset of variable categories into a common cluster, while allowing both observations and variable categories to belong partially to multiple clusters. Importantly, we adopt regularized fuzzy k-means, thereby enabling us to decide the degree of fuzziness in cluster memberships automatically. We evaluate the performance of the proposed approach through the analysis of simulated and real data, in comparison with existing two-way clustering approaches.
Minku, Leandro L.; Hou, Siqing
2017-01-01
baseline WC model is also included in the analysis. Results: Clustering Dycom with K-Means can potentially help to split the CC projects, managing to achieve similar or better predictive performance than Dycom. However, K-Means still requires the number
A comparison of heuristic and model-based clustering methods for dietary pattern analysis.
Greve, Benjamin; Pigeot, Iris; Huybrechts, Inge; Pala, Valeria; Börnhorst, Claudia
2016-02-01
Cluster analysis is widely applied to identify dietary patterns. A new method based on Gaussian mixture models (GMM) seems to be more flexible compared with the commonly applied k-means and Ward's method. In the present paper, these clustering approaches are compared to find the most appropriate one for clustering dietary data. The clustering methods were applied to simulated data sets with different cluster structures to compare their performance knowing the true cluster membership of observations. Furthermore, the three methods were applied to FFQ data assessed in 1791 children participating in the IDEFICS (Identification and Prevention of Dietary- and Lifestyle-Induced Health Effects in Children and Infants) Study to explore their performance in practice. The GMM outperformed the other methods in the simulation study in 72 % up to 100 % of cases, depending on the simulated cluster structure. Comparing the computationally less complex k-means and Ward's methods, the performance of k-means was better in 64-100 % of cases. Applied to real data, all methods identified three similar dietary patterns which may be roughly characterized as a 'non-processed' cluster with a high consumption of fruits, vegetables and wholemeal bread, a 'balanced' cluster with only slight preferences of single foods and a 'junk food' cluster. The simulation study suggests that clustering via GMM should be preferred due to its higher flexibility regarding cluster volume, shape and orientation. The k-means seems to be a good alternative, being easier to use while giving similar results when applied to real data.
PREPAID TELECOM CUSTOMERS SEGMENTATION USING THE K-MEAN ALGORITHM
Directory of Open Access Journals (Sweden)
Marar Liviu Ioan
2012-07-01
Full Text Available The scope of relationship marketing is to retain customers and win their loyalty. This can be achieved if the companiesâ€™ products and services are developed and sold considering customersâ€™ demands. Fulfilling customersâ€™ demands, taken as the starting point of relationship marketing, can be obtained by acknowledging that the customersâ€™ needs and wishes are heterogeneous. The segmentation of the customersâ€™ base allows operators to overcome this because it illustrates the whole heterogeneous market as the sum of smaller homogeneous markets. The concept of segmentation relies on the high probability of persons grouped into segments based on common demands and behaviours to have a similar response to marketing strategies. This article focuses on the segmentation of a telecom customer base according to specific and noticeable criteria of a certain service. Although the segmentation concept is widely approached in professional literature, articles on the segmentation of a telecom customer base are very scarce, due to the strategic nature of this information. Market segmentation is carried out based on how customers spent their money on credit recharging, on making calls, on sending SMS and on Internet navigation. The method used for customer segmentation is the K-mean cluster analysis. To assess the internal cohesion of the clusters we employed the average sum of squares error indicator, and to determine the differences among the clusters we used the ANOVA and the post-hoc Tukey tests. The analyses revealed seven customer segments with different features and behaviours. The results enable the telecom company to conceive marketing strategies and planning which lead to better understanding of its customersâ€™ needs and ultimately to a more efficient relationship with the subscribers and enhanced customer satisfaction. At the same time, the results enable the description and characterization of expenditure patterns
Iris recognition using image moments and k-means algorithm.
Khan, Yaser Daanial; Khan, Sher Afzal; Ahmad, Farooq; Islam, Saeed
2014-01-01
This paper presents a biometric technique for identification of a person using the iris image. The iris is first segmented from the acquired image of an eye using an edge detection algorithm. The disk shaped area of the iris is transformed into a rectangular form. Described moments are extracted from the grayscale image which yields a feature vector containing scale, rotation, and translation invariant moments. Images are clustered using the k-means algorithm and centroids for each cluster are computed. An arbitrary image is assumed to belong to the cluster whose centroid is the nearest to the feature vector in terms of Euclidean distance computed. The described model exhibits an accuracy of 98.5%.
Comprehensive cluster analysis with Transitivity Clustering.
Wittkop, Tobias; Emig, Dorothea; Truss, Anke; Albrecht, Mario; Böcker, Sebastian; Baumbach, Jan
2011-03-01
Transitivity Clustering is a method for the partitioning of biological data into groups of similar objects, such as genes, for instance. It provides integrated access to various functions addressing each step of a typical cluster analysis. To facilitate this, Transitivity Clustering is accessible online and offers three user-friendly interfaces: a powerful stand-alone version, a web interface, and a collection of Cytoscape plug-ins. In this paper, we describe three major workflows: (i) protein (super)family detection with Cytoscape, (ii) protein homology detection with incomplete gold standards and (iii) clustering of gene expression data. This protocol guides the user through the most important features of Transitivity Clustering and takes ∼1 h to complete.
A Flocking Based algorithm for Document Clustering Analysis
Energy Technology Data Exchange (ETDEWEB)
Cui, Xiaohui [ORNL; Gao, Jinzhu [ORNL; Potok, Thomas E [ORNL
2006-01-01
Social animals or insects in nature often exhibit a form of emergent collective behavior known as flocking. In this paper, we present a novel Flocking based approach for document clustering analysis. Our Flocking clustering algorithm uses stochastic and heuristic principles discovered from observing bird flocks or fish schools. Unlike other partition clustering algorithm such as K-means, the Flocking based algorithm does not require initial partitional seeds. The algorithm generates a clustering of a given set of data through the embedding of the high-dimensional data items on a two-dimensional grid for easy clustering result retrieval and visualization. Inspired by the self-organized behavior of bird flocks, we represent each document object with a flock boid. The simple local rules followed by each flock boid result in the entire document flock generating complex global behaviors, which eventually result in a clustering of the documents. We evaluate the efficiency of our algorithm with both a synthetic dataset and a real document collection that includes 100 news articles collected from the Internet. Our results show that the Flocking clustering algorithm achieves better performance compared to the K- means and the Ant clustering algorithm for real document clustering.
Identify High-Quality Protein Structural Models by Enhanced K-Means.
Wu, Hongjie; Li, Haiou; Jiang, Min; Chen, Cheng; Lv, Qiang; Wu, Chuang
2017-01-01
Background. One critical issue in protein three-dimensional structure prediction using either ab initio or comparative modeling involves identification of high-quality protein structural models from generated decoys. Currently, clustering algorithms are widely used to identify near-native models; however, their performance is dependent upon different conformational decoys, and, for some algorithms, the accuracy declines when the decoy population increases. Results. Here, we proposed two enhanced K -means clustering algorithms capable of robustly identifying high-quality protein structural models. The first one employs the clustering algorithm SPICKER to determine the initial centroids for basic K -means clustering ( SK -means), whereas the other employs squared distance to optimize the initial centroids ( K -means++). Our results showed that SK -means and K -means++ were more robust as compared with SPICKER alone, detecting 33 (59%) and 42 (75%) of 56 targets, respectively, with template modeling scores better than or equal to those of SPICKER. Conclusions. We observed that the classic K -means algorithm showed a similar performance to that of SPICKER, which is a widely used algorithm for protein-structure identification. Both SK -means and K -means++ demonstrated substantial improvements relative to results from SPICKER and classical K -means.
The Classification of Diabetes Mellitus Using Kernel k-means
Alamsyah, M.; Nafisah, Z.; Prayitno, E.; Afida, A. M.; Imah, E. M.
2018-01-01
Diabetes Mellitus is a metabolic disorder which is characterized by chronicle hypertensive glucose. Automatics detection of diabetes mellitus is still challenging. This study detected diabetes mellitus by using kernel k-Means algorithm. Kernel k-means is an algorithm which was developed from k-means algorithm. Kernel k-means used kernel learning that is able to handle non linear separable data; where it differs with a common k-means. The performance of kernel k-means in detecting diabetes mellitus is also compared with SOM algorithms. The experiment result shows that kernel k-means has good performance and a way much better than SOM.
International Nuclear Information System (INIS)
Benmouiza, Khalil; Cheknane, Ali
2013-01-01
Highlights: • An unsupervised clustering algorithm with a neural network model was explored. • The forecasting results of solar radiation time series and the comparison of their performance was simulated. • A new method was proposed combining k-means algorithm and NAR network to provide better prediction results. - Abstract: In this paper, we review our work for forecasting hourly global horizontal solar radiation based on the combination of unsupervised k-means clustering algorithm and artificial neural networks (ANN). k-Means algorithm focused on extracting useful information from the data with the aim of modeling the time series behavior and find patterns of the input space by clustering the data. On the other hand, nonlinear autoregressive (NAR) neural networks are powerful computational models for modeling and forecasting nonlinear time series. Taking the advantage of both methods, a new method was proposed combining k-means algorithm and NAR network to provide better forecasting results
Single pass kernel k-means clustering method
Indian Academy of Sciences (India)
2016-08-26
Aug 26, 2016 ... Department of Computer Science and Engineering, Srinivasa Ramanujan Institute of Technology, Anantapur 515701, India; Department of Computer Science and Engineering, Rajeev Gandhi Memorial College of Engineering and Technology, Nandyal 518501, India; Department of Computer Science and ...
Performance Analysis of Unsupervised Clustering Methods for Brain Tumor Segmentation
Directory of Open Access Journals (Sweden)
Tushar H Jaware
2013-10-01
Full Text Available Medical image processing is the most challenging and emerging field of neuroscience. The ultimate goal of medical image analysis in brain MRI is to extract important clinical features that would improve methods of diagnosis & treatment of disease. This paper focuses on methods to detect & extract brain tumour from brain MR images. MATLAB is used to design, software tool for locating brain tumor, based on unsupervised clustering methods. K-Means clustering algorithm is implemented & tested on data base of 30 images. Performance evolution of unsupervised clusteringmethods is presented.
The composite sequential clustering technique for analysis of multispectral scanner data
Su, M. Y.
1972-01-01
The clustering technique consists of two parts: (1) a sequential statistical clustering which is essentially a sequential variance analysis, and (2) a generalized K-means clustering. In this composite clustering technique, the output of (1) is a set of initial clusters which are input to (2) for further improvement by an iterative scheme. This unsupervised composite technique was employed for automatic classification of two sets of remote multispectral earth resource observations. The classification accuracy by the unsupervised technique is found to be comparable to that by traditional supervised maximum likelihood classification techniques. The mathematical algorithms for the composite sequential clustering program and a detailed computer program description with job setup are given.
Directory of Open Access Journals (Sweden)
Sorana D. BOLBOACĂ
2011-06-01
Full Text Available Aim: The properness of random assignment of compounds in training and validation sets was assessed using the generalized cluster technique. Material and Method: A quantitative Structure-Activity Relationship model using Molecular Descriptors Family on Vertices was evaluated in terms of assignment of carboquinone derivatives in training and test sets during the leave-many-out analysis. Assignment of compounds was investigated using five variables: observed anticancer activity and four structure descriptors. Generalized cluster analysis with K-means algorithm was applied in order to investigate if the assignment of compounds was or not proper. The Euclidian distance and maximization of the initial distance using a cross-validation with a v-fold of 10 was applied. Results: All five variables included in analysis proved to have statistically significant contribution in identification of clusters. Three clusters were identified, each of them containing both carboquinone derivatives belonging to training as well as to test sets. The observed activity of carboquinone derivatives proved to be normal distributed on every. The presence of training and test sets in all clusters identified using generalized cluster analysis with K-means algorithm and the distribution of observed activity within clusters sustain a proper assignment of compounds in training and test set. Conclusion: Generalized cluster analysis using the K-means algorithm proved to be a valid method in assessment of random assignment of carboquinone derivatives in training and test sets.
Cluster Analysis of Flow Cytometric List Mode Data on a Personal Computer
Bakker Schut, Tom C.; Bakker schut, T.C.; de Grooth, B.G.; Greve, Jan
1993-01-01
A cluster analysis algorithm, dedicated to analysis of flow cytometric data is described. The algorithm is written in Pascal and implemented on an MS-DOS personal computer. It uses k-means, initialized with a large number of seed points, followed by a modified nearest neighbor technique to reduce
Adaptive phase k-means algorithm for waveform classification
Song, Chengyun; Liu, Zhining; Wang, Yaojun; Xu, Feng; Li, Xingming; Hu, Guangmin
2018-01-01
Waveform classification is a powerful technique for seismic facies analysis that describes the heterogeneity and compartments within a reservoir. Horizon interpretation is a critical step in waveform classification. However, the horizon often produces inconsistent waveform phase, and thus results in an unsatisfied classification. To alleviate this problem, an adaptive phase waveform classification method called the adaptive phase k-means is introduced in this paper. Our method improves the traditional k-means algorithm using an adaptive phase distance for waveform similarity measure. The proposed distance is a measure with variable phases as it moves from sample to sample along the traces. Model traces are also updated with the best phase interference in the iterative process. Therefore, our method is robust to phase variations caused by the interpretation horizon. We tested the effectiveness of our algorithm by applying it to synthetic and real data. The satisfactory results reveal that the proposed method tolerates certain waveform phase variation and is a good tool for seismic facies analysis.
A Modified MinMax k-Means Algorithm Based on PSO.
Wang, Xiaoyan; Bai, Yanping
The MinMax k -means algorithm is widely used to tackle the effect of bad initialization by minimizing the maximum intraclustering errors. Two parameters, including the exponent parameter and memory parameter, are involved in the executive process. Since different parameters have different clustering errors, it is crucial to choose appropriate parameters. In the original algorithm, a practical framework is given. Such framework extends the MinMax k -means to automatically adapt the exponent parameter to the data set. It has been believed that if the maximum exponent parameter has been set, then the programme can reach the lowest intraclustering errors. However, our experiments show that this is not always correct. In this paper, we modified the MinMax k -means algorithm by PSO to determine the proper values of parameters which can subject the algorithm to attain the lowest clustering errors. The proposed clustering method is tested on some favorite data sets in several different initial situations and is compared to the k -means algorithm and the original MinMax k -means algorithm. The experimental results indicate that our proposed algorithm can reach the lowest clustering errors automatically.
From virtual clustering analysis to self-consistent clustering analysis: a mathematical study
Tang, Shaoqiang; Zhang, Lei; Liu, Wing Kam
2018-03-01
In this paper, we propose a new homogenization algorithm, virtual clustering analysis (VCA), as well as provide a mathematical framework for the recently proposed self-consistent clustering analysis (SCA) (Liu et al. in Comput Methods Appl Mech Eng 306:319-341, 2016). In the mathematical theory, we clarify the key assumptions and ideas of VCA and SCA, and derive the continuous and discrete Lippmann-Schwinger equations. Based on a key postulation of "once response similarly, always response similarly", clustering is performed in an offline stage by machine learning techniques (k-means and SOM), and facilitates substantial reduction of computational complexity in an online predictive stage. The clear mathematical setup allows for the first time a convergence study of clustering refinement in one space dimension. Convergence is proved rigorously, and found to be of second order from numerical investigations. Furthermore, we propose to suitably enlarge the domain in VCA, such that the boundary terms may be neglected in the Lippmann-Schwinger equation, by virtue of the Saint-Venant's principle. In contrast, they were not obtained in the original SCA paper, and we discover these terms may well be responsible for the numerical dependency on the choice of reference material property. Since VCA enhances the accuracy by overcoming the modeling error, and reduce the numerical cost by avoiding an outer loop iteration for attaining the material property consistency in SCA, its efficiency is expected even higher than the recently proposed SCA algorithm.
Further heuristics for $k$-means: The merge-and-split heuristic and the $(k,l)$-means
Nielsen, Frank; Nock, Richard
2014-01-01
Finding the optimal $k$-means clustering is NP-hard in general and many heuristics have been designed for minimizing monotonically the $k$-means objective. We first show how to extend Lloyd's batched relocation heuristic and Hartigan's single-point relocation heuristic to take into account empty-cluster and single-point cluster events, respectively. Those events tend to increasingly occur when $k$ or $d$ increases, or when performing several restarts. First, we show that those special events ...
Integrative cluster analysis in bioinformatics
Abu-Jamous, Basel; Nandi, Asoke K
2015-01-01
Clustering techniques are increasingly being put to use in the analysis of high-throughput biological datasets. Novel computational techniques to analyse high throughput data in the form of sequences, gene and protein expressions, pathways, and images are becoming vital for understanding diseases and future drug discovery. This book details the complete pathway of cluster analysis, from the basics of molecular biology to the generation of biological knowledge. The book also presents the latest clustering methods and clustering validation, thereby offering the reader a comprehensive review o
Cluster analysis of HZE particle tracks as applied to space radiobiology problems
International Nuclear Information System (INIS)
Batmunkh, M.; Bayarchimeg, L.; Lkhagva, O.; Belov, O.
2013-01-01
A cluster analysis is performed of ionizations in tracks produced by the most abundant nuclei in the charge and energy spectra of the galactic cosmic rays. The frequency distribution of clusters is estimated for cluster sizes comparable to the DNA molecule at different packaging levels. For this purpose, an improved K-mean-based algorithm is suggested. This technique allows processing particle tracks containing a large number of ionization events without setting the number of clusters as an input parameter. Using this method, the ionization distribution pattern is analyzed depending on the cluster size and particle's linear energy transfer
International Nuclear Information System (INIS)
Pirkle, F.L.; Stablein, N.K.; Howell, J.A.; Wecksung, G.W.; Duran, B.S.
1982-11-01
One objective of the aerial radiometric surveys flown as part of the US Department of Energy's National Uranium Resource Evaluation (NURE) program was to ascertain the regional distribution of near-surface radioelement abundances. Some method for identifying groups of observations with similar radioelement values was therefore required. It is shown in this report that cluster analysis can identify such groups even when no a priori knowledge of the geology of an area exists. A method of convergent k-means cluster analysis coupled with a hierarchical cluster analysis is used to classify 6991 observations (three radiometric variables at each observation location) from the Precambrian rocks of the Copper Mountain, Wyoming, area. Another method, one that combines a principal components analysis with a convergent k-means analysis, is applied to the same data. These two methods are compared with a convergent k-means analysis that utilizes available geologic knowledge. All three methods identify four clusters. Three of the clusters represent background values for the Precambrian rocks of the area, and one represents outliers (anomalously high 214 Bi). A segmentation of the data corresponding to geologic reality as discovered by other methods has been achieved based solely on analysis of aerial radiometric data. The techniques employed are composites of classical clustering methods designed to handle the special problems presented by large data sets. 20 figures, 7 tables
Enhanced bag of words using multilevel k-means for human activity recognition
Directory of Open Access Journals (Sweden)
Motasem Elshourbagy
2016-07-01
Full Text Available This paper aims to enhance the bag of features in order to improve the accuracy of human activity recognition. In this paper, human activity recognition process consists of four stages: local space time features detection, feature description, bag of features representation, and SVMs classification. The k-means step in the bag of features is enhanced by applying three levels of clustering: clustering per video, clustering per action class, and clustering for the final code book. The experimental results show that the proposed method of enhancement reduces the time and memory requirements, and enables the use of all training data in the k-means clustering algorithm. The evaluation of accuracy of action classification on two popular datasets (KTH and Weizmann has been performed. In addition, the proposed method improves the human activity recognition accuracy by 5.57% on the KTH dataset using the same detector, descriptor, and classifier.
2-Way k-Means as a Model for Microbiome Samples.
Jackson, Weston J; Agarwal, Ipsita; Pe'er, Itsik
2017-01-01
Motivation . Microbiome sequencing allows defining clusters of samples with shared composition. However, this paradigm poorly accounts for samples whose composition is a mixture of cluster-characterizing ones and which therefore lie in between them in the cluster space. This paper addresses unsupervised learning of 2-way clusters. It defines a mixture model that allows 2-way cluster assignment and describes a variant of generalized k -means for learning such a model. We demonstrate applicability to microbial 16S rDNA sequencing data from the Human Vaginal Microbiome Project.
Directory of Open Access Journals (Sweden)
Issa Arwani
2015-07-01
Abstract Generally, clustering implemented with taking data from database to be stored temporarily in a program variable (eg, in an array then continue with clustering process.Directclustering where the data is storedby integrating the clustering algorithm using the SQL language on the DBMS is proposed.In this study focused on the design and implementation of K-means clustering algorithm on a Relational DBMS using the SQL language. The clustering process carried out with a case study of GPA student in the Faculty of Computer Science University of Brawijaya.Based on results with a variety of dimensions, the number of clusters and different distance calculation methods, has obtained clustering data correctly. Based on time complexity to review each stage of the implementation K - means using SQL and without SQL, showing the same results of asymptotic time complexity where phase euclidean distance still requires the highest time complexity. Keywords: Clustering, K-means, SQL, GPA (Grade Point Average
Zhou, Shuguang; Zhou, Kefa; Wang, Jinlin; Yang, Genfang; Wang, Shanshan
2017-12-01
Cluster analysis is a well-known technique that is used to analyze various types of data. In this study, cluster analysis is applied to geochemical data that describe 1444 stream sediment samples collected in northwestern Xinjiang with a sample spacing of approximately 2 km. Three algorithms (the hierarchical, k-means, and fuzzy c-means algorithms) and six data transformation methods (the z-score standardization, ZST; the logarithmic transformation, LT; the additive log-ratio transformation, ALT; the centered log-ratio transformation, CLT; the isometric log-ratio transformation, ILT; and no transformation, NT) are compared in terms of their effects on the cluster analysis of the geochemical compositional data. The study shows that, on the one hand, the ZST does not affect the results of column- or variable-based (R-type) cluster analysis, whereas the other methods, including the LT, the ALT, and the CLT, have substantial effects on the results. On the other hand, the results of the row- or observation-based (Q-type) cluster analysis obtained from the geochemical data after applying NT and the ZST are relatively poor. However, we derive some improved results from the geochemical data after applying the CLT, the ILT, the LT, and the ALT. Moreover, the k-means and fuzzy c-means clustering algorithms are more reliable than the hierarchical algorithm when they are used to cluster the geochemical data. We apply cluster analysis to the geochemical data to explore for Au deposits within the study area, and we obtain a good correlation between the results retrieved by combining the CLT or the ILT with the k-means or fuzzy c-means algorithms and the potential zones of Au mineralization. Therefore, we suggest that the combination of the CLT or the ILT with the k-means or fuzzy c-means algorithms is an effective tool to identify potential zones of mineralization from geochemical data.
Cluster analysis of track structure
International Nuclear Information System (INIS)
Michalik, V.
1991-01-01
One of the possibilities of classifying track structures is application of conventional partition techniques of analysis of multidimensional data to the track structure. Using these cluster algorithms this paper attempts to find characteristics of radiation reflecting the spatial distribution of ionizations in the primary particle track. An absolute frequency distribution of clusters of ionizations giving the mean number of clusters produced by radiation per unit of deposited energy can serve as this characteristic. General computation techniques used as well as methods of calculations of distributions of clusters for different radiations are discussed. 8 refs.; 5 figs
Comparative analysis of clustering methods for gene expression time course data
Directory of Open Access Journals (Sweden)
Ivan G. Costa
2004-01-01
Full Text Available This work performs a data driven comparative study of clustering methods used in the analysis of gene expression time courses (or time series. Five clustering methods found in the literature of gene expression analysis are compared: agglomerative hierarchical clustering, CLICK, dynamical clustering, k-means and self-organizing maps. In order to evaluate the methods, a k-fold cross-validation procedure adapted to unsupervised methods is applied. The accuracy of the results is assessed by the comparison of the partitions obtained in these experiments with gene annotation, such as protein function and series classification.
Cluster analysis for DNA methylation profiles having a detection threshold
Directory of Open Access Journals (Sweden)
Siegmund Kimberly D
2006-07-01
Full Text Available Abstract Background DNA methylation, a molecular feature used to investigate tumor heterogeneity, can be measured on many genomic regions using the MethyLight technology. Due to the combination of the underlying biology of DNA methylation and the MethyLight technology, the measurements, while being generated on a continuous scale, have a large number of 0 values. This suggests that conventional clustering methodology may not perform well on this data. Results We compare performance of existing methodology (such as k-means with two novel methods that explicitly allow for the preponderance of values at 0. We also consider how the ability to successfully cluster such data depends upon the number of informative genes for which methylation is measured and the correlation structure of the methylation values for those genes. We show that when data is collected for a sufficient number of genes, our models do improve clustering performance compared to methods, such as k-means, that do not explicitly respect the supposed biological realities of the situation. Conclusion The performance of analysis methods depends upon how well the assumptions of those methods reflect the properties of the data being analyzed. Differing technologies will lead to data with differing properties, and should therefore be analyzed differently. Consequently, it is prudent to give thought to what the properties of the data are likely to be, and which analysis method might therefore be likely to best capture those properties.
Classifying epileptic EEG signals with delay permutation entropy and Multi-Scale K-means.
Zhu, Guohun; Li, Yan; Wen, Peng Paul; Wang, Shuaifang
2015-01-01
Most epileptic EEG classification algorithms are supervised and require large training datasets, that hinder their use in real time applications. This chapter proposes an unsupervised Multi-Scale K-means (MSK-means) MSK-means algorithm to distinguish epileptic EEG signals and identify epileptic zones. The random initialization of the K-means algorithm can lead to wrong clusters. Based on the characteristics of EEGs, the MSK-means MSK-means algorithm initializes the coarse-scale centroid of a cluster with a suitable scale factor. In this chapter, the MSK-means algorithm is proved theoretically superior to the K-means algorithm on efficiency. In addition, three classifiers: the K-means, MSK-means MSK-means and support vector machine (SVM), are used to identify seizure and localize epileptogenic zone using delay permutation entropy features. The experimental results demonstrate that identifying seizure with the MSK-means algorithm and delay permutation entropy achieves 4. 7 % higher accuracy than that of K-means, and 0. 7 % higher accuracy than that of the SVM.
ARK: Aggregation of Reads by K-Means for Estimation of Bacterial Community Composition.
Koslicki, David; Chatterjee, Saikat; Shahrivar, Damon; Walker, Alan W; Francis, Suzanna C; Fraser, Louise J; Vehkaperä, Mikko; Lan, Yueheng; Corander, Jukka
2015-01-01
Estimation of bacterial community composition from high-throughput sequenced 16S rRNA gene amplicons is a key task in microbial ecology. Since the sequence data from each sample typically consist of a large number of reads and are adversely impacted by different levels of biological and technical noise, accurate analysis of such large datasets is challenging. There has been a recent surge of interest in using compressed sensing inspired and convex-optimization based methods to solve the estimation problem for bacterial community composition. These methods typically rely on summarizing the sequence data by frequencies of low-order k-mers and matching this information statistically with a taxonomically structured database. Here we show that the accuracy of the resulting community composition estimates can be substantially improved by aggregating the reads from a sample with an unsupervised machine learning approach prior to the estimation phase. The aggregation of reads is a pre-processing approach where we use a standard K-means clustering algorithm that partitions a large set of reads into subsets with reasonable computational cost to provide several vectors of first order statistics instead of only single statistical summarization in terms of k-mer frequencies. The output of the clustering is then processed further to obtain the final estimate for each sample. The resulting method is called Aggregation of Reads by K-means (ARK), and it is based on a statistical argument via mixture density formulation. ARK is found to improve the fidelity and robustness of several recently introduced methods, with only a modest increase in computational complexity. An open source, platform-independent implementation of the method in the Julia programming language is freely available at https://github.com/dkoslicki/ARK. A Matlab implementation is available at http://www.ee.kth.se/ctsoftware.
A Simple Density with Distance Based Initial Seed Selection Technique for K Means Algorithm
Directory of Open Access Journals (Sweden)
Sajidha Syed Azimuddin
2017-01-01
Full Text Available Open issues with respect to K means algorithm are identifying the number of clusters, initial seed concept selection, clustering tendency, handling empty clusters, identifying outliers etc. In this paper we propose a novel and a simple technique considering both density and distance of the concepts in a dataset to identify initial seed concepts for clustering. Many authors have proposed different techniques to identify initial seed concepts; but our method ensures that the initial seed concepts are chosen from different clusters that are to be generated by the clustering solution. The hallmark of our algorithm is that it is a single pass algorithm that does not require any extra parameters to be estimated. Further, our seed concepts are one among the actual concepts and not the mean of representative concepts as is the case in many other algorithms. We have implemented our proposed algorithm and compared the results with the interval based technique of Fouad Khan. We see that our method outperforms the interval based method. We have also compared our method with the original random K means and K Means++ algorithms.
Machine learning in APOGEE. Unsupervised spectral classification with K-means
Garcia-Dias, Rafael; Allende Prieto, Carlos; Sánchez Almeida, Jorge; Ordovás-Pascual, Ignacio
2018-05-01
Context. The volume of data generated by astronomical surveys is growing rapidly. Traditional analysis techniques in spectroscopy either demand intensive human interaction or are computationally expensive. In this scenario, machine learning, and unsupervised clustering algorithms in particular, offer interesting alternatives. The Apache Point Observatory Galactic Evolution Experiment (APOGEE) offers a vast data set of near-infrared stellar spectra, which is perfect for testing such alternatives. Aims: Our research applies an unsupervised classification scheme based on K-means to the massive APOGEE data set. We explore whether the data are amenable to classification into discrete classes. Methods: We apply the K-means algorithm to 153 847 high resolution spectra (R ≈ 22 500). We discuss the main virtues and weaknesses of the algorithm, as well as our choice of parameters. Results: We show that a classification based on normalised spectra captures the variations in stellar atmospheric parameters, chemical abundances, and rotational velocity, among other factors. The algorithm is able to separate the bulge and halo populations, and distinguish dwarfs, sub-giants, RC, and RGB stars. However, a discrete classification in flux space does not result in a neat organisation in the parameters' space. Furthermore, the lack of obvious groups in flux space causes the results to be fairly sensitive to the initialisation, and disrupts the efficiency of commonly-used methods to select the optimal number of clusters. Our classification is publicly available, including extensive online material associated with the APOGEE Data Release 12 (DR12). Conclusions: Our description of the APOGEE database can help greatly with the identification of specific types of targets for various applications. We find a lack of obvious groups in flux space, and identify limitations of the K-means algorithm in dealing with this kind of data. Full Tables B.1-B.4 are only available at the CDS via
A REVIEW WAVELET TRANSFORM AND FUZZY K-MEANS BASED IMAGE DE-NOISING METHOD
Nidhi Patel*, Asst. Prof. Pratik Kumar Soni
2017-01-01
The research area of image processing technique using fuzzy k-means and wavelet transform. The enormous amount of data necessary for images is a main reason for the growth of many areas within the research field of computer imaging such as image processing and compression. In order to get this in requisites of the concerned research work, wavelet transforms and k-means clustering is applied. This can be done in order to discover more possible combinations that may lead to the finest de-noisin...
Performance analysis of clustering techniques over microarray data: A case study
Dash, Rasmita; Misra, Bijan Bihari
2018-03-01
Handling big data is one of the major issues in the field of statistical data analysis. In such investigation cluster analysis plays a vital role to deal with the large scale data. There are many clustering techniques with different cluster analysis approach. But which approach suits a particular dataset is difficult to predict. To deal with this problem a grading approach is introduced over many clustering techniques to identify a stable technique. But the grading approach depends on the characteristic of dataset as well as on the validity indices. So a two stage grading approach is implemented. In this study the grading approach is implemented over five clustering techniques like hybrid swarm based clustering (HSC), k-means, partitioning around medoids (PAM), vector quantization (VQ) and agglomerative nesting (AGNES). The experimentation is conducted over five microarray datasets with seven validity indices. The finding of grading approach that a cluster technique is significant is also established by Nemenyi post-hoc hypothetical test.
A cluster analysis on road traffic accidents using genetic algorithms
Saharan, Sabariah; Baragona, Roberto
2017-04-01
The analysis of traffic road accidents is increasingly important because of the accidents cost and public road safety. The availability or large data sets makes the study of factors that affect the frequency and severity accidents are viable. However, the data are often highly unbalanced and overlapped. We deal with the data set of the road traffic accidents recorded in Christchurch, New Zealand, from 2000-2009 with a total of 26440 accidents. The data is in a binary set and there are 50 factors road traffic accidents with four level of severity. We used genetic algorithm for the analysis because we are in the presence of a large unbalanced data set and standard clustering like k-means algorithm may not be suitable for the task. The genetic algorithm based on clustering for unknown K, (GCUK) has been used to identify the factors associated with accidents of different levels of severity. The results provided us with an interesting insight into the relationship between factors and accidents severity level and suggest that the two main factors that contributes to fatal accidents are "Speed greater than 60 km h" and "Did not see other people until it was too late". A comparison with the k-means algorithm and the independent component analysis is performed to validate the results.
Huo, Zhiguang; Tseng, George
2017-06-01
Cancer subtypes discovery is the first step to deliver personalized medicine to cancer patients. With the accumulation of massive multi-level omics datasets and established biological knowledge databases, omics data integration with incorporation of rich existing biological knowledge is essential for deciphering a biological mechanism behind the complex diseases. In this manuscript, we propose an integrative sparse K -means (is- K means) approach to discover disease subtypes with the guidance of prior biological knowledge via sparse overlapping group lasso. An algorithm using an alternating direction method of multiplier (ADMM) will be applied for fast optimization. Simulation and three real applications in breast cancer and leukemia will be used to compare is- K means with existing methods and demonstrate its superior clustering accuracy, feature selection, functional annotation of detected molecular features and computing efficiency.
FINGER KNUCKLE PRINT RECOGNITION WITH SIFT AND K-MEANS ALGORITHM
Directory of Open Access Journals (Sweden)
A. Muthukumar
2013-02-01
Full Text Available In general, the identification and verification are done by passwords, pin number, etc., which is easily cracked by others. Biometrics is a powerful and unique tool based on the anatomical and behavioral characteristics of the human beings in order to prove their authentication. This paper proposes a novel recognition methodology of biometrics named as Finger Knuckle print (FKP. Hence this paper has focused on the extraction of features of Finger knuckle print using Scale Invariant Feature Transform (SIFT, and the key points are derived from FKP are clustered using K-Means Algorithm. The centroid of K-Means is stored in the database which is compared with the query FKP K-Means centroid value to prove the recognition and authentication. The comparison is based on the XOR operation. Hence this paper provides a novel recognition method to provide authentication. Results are performed on the PolyU FKP database to check the proposed FKP recognition method.
Directory of Open Access Journals (Sweden)
Jocelyn H Bolin
2014-04-01
Full Text Available Although traditional clustering methods (e.g., K-means have been shown to be useful in the social sciences it is often difficult for such methods to handle situations where clusters in the population overlap or are ambiguous. Fuzzy clustering, a method already recognized in many disciplines, provides a more flexible alternative to these traditional clustering methods. Fuzzy clustering differs from other traditional clustering methods in that it allows for a case to belong to multiple clusters simultaneously. Unfortunately, fuzzy clustering techniques remain relatively unused in the social and behavioral sciences. The purpose of this paper is to introduce fuzzy clustering to these audiences who are currently relatively unfamiliar with the technique. In order to demonstrate the advantages associated with this method, cluster solutions of a common perfectionism measure were created using both fuzzy clustering and K-means clustering, and the results compared. Results of these analyses reveal that different cluster solutions are found by the two methods, and the similarity between the different clustering solutions depends on the amount of cluster overlap allowed for in fuzzy clustering.
Bolin, Jocelyn H; Edwards, Julianne M; Finch, W Holmes; Cassady, Jerrell C
2014-01-01
Although traditional clustering methods (e.g., K-means) have been shown to be useful in the social sciences it is often difficult for such methods to handle situations where clusters in the population overlap or are ambiguous. Fuzzy clustering, a method already recognized in many disciplines, provides a more flexible alternative to these traditional clustering methods. Fuzzy clustering differs from other traditional clustering methods in that it allows for a case to belong to multiple clusters simultaneously. Unfortunately, fuzzy clustering techniques remain relatively unused in the social and behavioral sciences. The purpose of this paper is to introduce fuzzy clustering to these audiences who are currently relatively unfamiliar with the technique. In order to demonstrate the advantages associated with this method, cluster solutions of a common perfectionism measure were created using both fuzzy clustering and K-means clustering, and the results compared. Results of these analyses reveal that different cluster solutions are found by the two methods, and the similarity between the different clustering solutions depends on the amount of cluster overlap allowed for in fuzzy clustering.
A Framework To Support Management Of HIVAIDS Using K-Means And Random Forest Algorithm
Directory of Open Access Journals (Sweden)
Gladys Iseu
2017-06-01
Full Text Available Healthcare industry generates large amounts of complex data about patients hospital resources disease management electronic patient records and medical devices among others. The availability of these huge amounts of medical data creates a need for powerful mining tools to support health care professionals in diagnosis treatment and management of HIVAIDS. Several data mining techniques have been used in management of different data sets. Data mining techniques have been categorized into regression algorithms segmentation algorithms association algorithms sequence analysis algorithms and classification algorithms. In the medical field there has not been a specific study that has incorporated two or more data mining algorithms hence limiting decision making levels by medical practitioners. This study identified the extent to which K-means algorithm cluster patient characteristics it has also evaluated the extent to which random forest algorithm can classify the data for informed decision making as well as design a framework to support medical decision making in the treatment of HIVAIDS related diseases in Kenya. The paper further used random forest classification algorithm to compute proximities between pairs of cases that can be used in clustering locating outliers or by scaling to give interesting views of the data.
Accident patterns for construction-related workers: a cluster analysis
Liao, Chia-Wen; Tyan, Yaw-Yauan
2012-01-01
The construction industry has been identified as one of the most hazardous industries. The risk of constructionrelated workers is far greater than that in a manufacturing based industry. However, some steps can be taken to reduce worker risk through effective injury prevention strategies. In this article, k-means clustering methodology is employed in specifying the factors related to different worker types and in identifying the patterns of industrial occupational accidents. Accident reports during the period 1998 to 2008 are extracted from case reports of the Northern Region Inspection Office of the Council of Labor Affairs of Taiwan. The results show that the cluster analysis can indicate some patterns of occupational injuries in the construction industry. Inspection plans should be proposed according to the type of construction-related workers. The findings provide a direction for more effective inspection strategies and injury prevention programs.
Image Registration Algorithm Based on Parallax Constraint and Clustering Analysis
Wang, Zhe; Dong, Min; Mu, Xiaomin; Wang, Song
2018-01-01
To resolve the problem of slow computation speed and low matching accuracy in image registration, a new image registration algorithm based on parallax constraint and clustering analysis is proposed. Firstly, Harris corner detection algorithm is used to extract the feature points of two images. Secondly, use Normalized Cross Correlation (NCC) function to perform the approximate matching of feature points, and the initial feature pair is obtained. Then, according to the parallax constraint condition, the initial feature pair is preprocessed by K-means clustering algorithm, which is used to remove the feature point pairs with obvious errors in the approximate matching process. Finally, adopt Random Sample Consensus (RANSAC) algorithm to optimize the feature points to obtain the final feature point matching result, and the fast and accurate image registration is realized. The experimental results show that the image registration algorithm proposed in this paper can improve the accuracy of the image matching while ensuring the real-time performance of the algorithm.
Phenotypes Determined by Cluster Analysis in Moderate to Severe Bronchial Asthma.
Youroukova, Vania M; Dimitrova, Denitsa G; Valerieva, Anna D; Lesichkova, Spaska S; Velikova, Tsvetelina V; Ivanova-Todorova, Ekaterina I; Tumangelova-Yuzeir, Kalina D
2017-06-01
Bronchial asthma is a heterogeneous disease that includes various subtypes. They may share similar clinical characteristics, but probably have different pathological mechanisms. To identify phenotypes using cluster analysis in moderate to severe bronchial asthma and to compare differences in clinical, physiological, immunological and inflammatory data between the clusters. Forty adult patients with moderate to severe bronchial asthma out of exacerbation were included. All underwent clinical assessment, anthropometric measurements, skin prick testing, standard spirometry and measurement fraction of exhaled nitric oxide. Blood eosinophilic count, serum total IgE and periostin levels were determined. Two-step cluster approach, hierarchical clustering method and k-mean analysis were used for identification of the clusters. We have identified four clusters. Cluster 1 (n=14) - late-onset, non-atopic asthma with impaired lung function, Cluster 2 (n=13) - late-onset, atopic asthma, Cluster 3 (n=6) - late-onset, aspirin sensitivity, eosinophilic asthma, and Cluster 4 (n=7) - early-onset, atopic asthma. Our study is the first in Bulgaria in which cluster analysis is applied to asthmatic patients. We identified four clusters. The variables with greatest force for differentiation in our study were: age of asthma onset, duration of diseases, atopy, smoking, blood eosinophils, nonsteroidal anti-inflammatory drugs hypersensitivity, baseline FEV1/FVC and symptoms severity. Our results support the concept of heterogeneity of bronchial asthma and demonstrate that cluster analysis can be an useful tool for phenotyping of disease and personalized approach to the treatment of patients.
Analisis Perbandingan Algoritma Fuzzy C-Means dan K-Means
Yohannes, Yohannes
2016-01-01
Klasterisasi merupakan teknik pengelompokkan data berdasarkan kemiripan data. Teknik klasterisasi ini banyak digunakan pada bidang ilmu komputer khususnya pengolahan citra, pengenalan pola, dan data mining. Banyak sekali algoritma yang digunakan untuk klasterisasi data. Algoritma yang sering digunakan untuk klasterisasi data pada umumnya adalah Fuzzy C-Means dan K-Means. Algoritma Fuzzy C-Means merupakan algoritma klasterisasi dimana data dikelompokkan ke dalam suatu pusat cluster data denga...
A diabetic retinopathy detection method using an improved pillar K-means algorithm.
Gogula, Susmitha Valli; Divakar, Ch; Satyanarayana, Ch; Rao, Allam Appa
2014-01-01
The paper presents a new approach for medical image segmentation. Exudates are a visible sign of diabetic retinopathy that is the major reason of vision loss in patients with diabetes. If the exudates extend into the macular area, blindness may occur. Automated detection of exudates will assist ophthalmologists in early diagnosis. This segmentation process includes a new mechanism for clustering the elements of high-resolution images in order to improve precision and reduce computation time. The system applies K-means clustering to the image segmentation after getting optimized by Pillar algorithm; pillars are constructed in such a way that they can withstand the pressure. Improved pillar algorithm can optimize the K-means clustering for image segmentation in aspects of precision and computation time. This evaluates the proposed approach for image segmentation by comparing with Kmeans and Fuzzy C-means in a medical image. Using this method, identification of dark spot in the retina becomes easier and the proposed algorithm is applied on diabetic retinal images of all stages to identify hard and soft exudates, where the existing pillar K-means is more appropriate for brain MRI images. This proposed system help the doctors to identify the problem in the early stage and can suggest a better drug for preventing further retinal damage.
Determining the k in k-means with MapReduce
Debatty , Thibault; Michiardi , Pietro; Mees , Wim; Thonnard , Olivier
2014-01-01
International audience; In this paper we propose a MapReduce implementation of G-means, a variant of k-means that is able to automatically determine k, the number of clusters. We show that our implementation scales to very large datasets and very large values of k, as the computation cost is proportional to nk. Other techniques that run a clustering algorithm with different values of k and choose the value of k that provides the " best " results have a computation cost that is proportional to...
Cluster analysis for portfolio optimization
Vincenzo Tola; Fabrizio Lillo; Mauro Gallegati; Rosario N. Mantegna
2005-01-01
We consider the problem of the statistical uncertainty of the correlation matrix in the optimization of a financial portfolio. We show that the use of clustering algorithms can improve the reliability of the portfolio in terms of the ratio between predicted and realized risk. Bootstrap analysis indicates that this improvement is obtained in a wide range of the parameters N (number of assets) and T (investment horizon). The predicted and realized risk level and the relative portfolio compositi...
Full text clustering and relationship network analysis of biomedical publications.
Directory of Open Access Journals (Sweden)
Renchu Guan
Full Text Available Rapid developments in the biomedical sciences have increased the demand for automatic clustering of biomedical publications. In contrast to current approaches to text clustering, which focus exclusively on the contents of abstracts, a novel method is proposed for clustering and analysis of complete biomedical article texts. To reduce dimensionality, Cosine Coefficient is used on a sub-space of only two vectors, instead of computing the Euclidean distance within the space of all vectors. Then a strategy and algorithm is introduced for Semi-supervised Affinity Propagation (SSAP to improve analysis efficiency, using biomedical journal names as an evaluation background. Experimental results show that by avoiding high-dimensional sparse matrix computations, SSAP outperforms conventional k-means methods and improves upon the standard Affinity Propagation algorithm. In constructing a directed relationship network and distribution matrix for the clustering results, it can be noted that overlaps in scope and interests among BioMed publications can be easily identified, providing a valuable analytical tool for editors, authors and readers.
Full text clustering and relationship network analysis of biomedical publications.
Guan, Renchu; Yang, Chen; Marchese, Maurizio; Liang, Yanchun; Shi, Xiaohu
2014-01-01
Rapid developments in the biomedical sciences have increased the demand for automatic clustering of biomedical publications. In contrast to current approaches to text clustering, which focus exclusively on the contents of abstracts, a novel method is proposed for clustering and analysis of complete biomedical article texts. To reduce dimensionality, Cosine Coefficient is used on a sub-space of only two vectors, instead of computing the Euclidean distance within the space of all vectors. Then a strategy and algorithm is introduced for Semi-supervised Affinity Propagation (SSAP) to improve analysis efficiency, using biomedical journal names as an evaluation background. Experimental results show that by avoiding high-dimensional sparse matrix computations, SSAP outperforms conventional k-means methods and improves upon the standard Affinity Propagation algorithm. In constructing a directed relationship network and distribution matrix for the clustering results, it can be noted that overlaps in scope and interests among BioMed publications can be easily identified, providing a valuable analytical tool for editors, authors and readers.
Clustering Binary Data in the Presence of Masking Variables
Brusco, Michael J.
2004-01-01
A number of important applications require the clustering of binary data sets. Traditional nonhierarchical cluster analysis techniques, such as the popular K-means algorithm, can often be successfully applied to these data sets. However, the presence of masking variables in a data set can impede the ability of the K-means algorithm to recover the…
A spectral k-means approach to bright-field cell image segmentation.
Bradbury, Laura; Wan, Justin W L
2010-01-01
Automatic segmentation of bright-field cell images is important to cell biologists, but difficult to complete due to the complex nature of the cells in bright-field images (poor contrast, broken halo, missing boundaries). Standard approaches such as level set segmentation and active contours work well for fluorescent images where cells appear as round shape, but become less effective when optical artifacts such as halo exist in bright-field images. In this paper, we present a robust segmentation method which combines the spectral and k-means clustering techniques to locate cells in bright-field images. This approach models an image as a matrix graph and segment different regions of the image by computing the appropriate eigenvectors of the matrix graph and using the k-means algorithm. We illustrate the effectiveness of the method by segmentation results of C2C12 (muscle) cells in bright-field images.
Extending the input–output energy balance methodology in agriculture through cluster analysis
International Nuclear Information System (INIS)
Bojacá, Carlos Ricardo; Casilimas, Héctor Albeiro; Gil, Rodrigo; Schrevens, Eddie
2012-01-01
The input–output balance methodology has been applied to characterize the energy balance of agricultural systems. This study proposes to extend this methodology with the inclusion of multivariate analysis to reveal particular patterns in the energy use of a system. The objective was to demonstrate the usefulness of multivariate exploratory techniques to analyze the variability found in a farming system and, establish efficiency categories that can be used to improve the energy balance of the system. To this purpose an input–output analysis was applied to the major greenhouse tomato production area in Colombia. Individual energy profiles were built and the k-means clustering method was applied to the production factors. On average, the production system in the study zone consumes 141.8 GJ ha −1 to produce 96.4 GJ ha −1 , resulting in an energy efficiency of 0.68. With the k-means clustering analysis, three clusters of farmers were identified with energy efficiencies of 0.54, 0.67 and 0.78. The most energy efficient cluster grouped 56.3% of the farmers. It is possible to optimize the production system by improving the management practices of those with the lowest energy use efficiencies. Multivariate analysis techniques demonstrated to be a complementary pathway to improve the energy efficiency of a system. -- Highlights: ► An input–output energy balance was estimated for greenhouse tomatoes in Colombia. ► We used the k-means clustering method to classify growers based on their energy use. ► Three clusters of growers were found with energy efficiencies of 0.54, 0.67 and 0.78. ► Overall system optimization is possible by improving the energy use of the less efficient.
Analysis of Learning Development With Sugeno Fuzzy Logic And Clustering
Directory of Open Access Journals (Sweden)
Maulana Erwin Saputra
2017-06-01
Full Text Available In the first journal, I made this attempt to analyze things that affect the achievement of students in each school of course vary. Because students are one of the goals of achieving the goals of successful educational organizations. The mental influence of students’ emotions and behaviors themselves in relation to learning performance. Fuzzy logic can be used in various fields as well as Clustering for grouping, as in Learning Development analyzes. The process will be performed on students based on the symptoms that exist. In this research will use fuzzy logic and clustering. Fuzzy is an uncertain logic but its excess is capable in the process of language reasoning so that in its design is not required complicated mathematical equations. However Clustering method is K-Means method is method where data analysis is broken down by group k (k = 1,2,3, .. k. To know the optimal number of Performance group. The results of the research is with a questionnaire entered into matlab will produce a value that means in generating the graph. And simplify the school in seeing Student performance in the learning process by using certain criteria. So from the system that obtained the results for a decision-making required by the school.
Identification and validation of asthma phenotypes in Chinese population using cluster analysis.
Wang, Lei; Liang, Rui; Zhou, Ting; Zheng, Jing; Liang, Bing Miao; Zhang, Hong Ping; Luo, Feng Ming; Gibson, Peter G; Wang, Gang
2017-10-01
Asthma is a heterogeneous airway disease, so it is crucial to clearly identify clinical phenotypes to achieve better asthma management. To identify and prospectively validate asthma clusters in a Chinese population. Two hundred eighty-four patients were consecutively recruited and 18 sociodemographic and clinical variables were collected. Hierarchical cluster analysis was performed by the Ward method followed by k-means cluster analysis. Then, a prospective 12-month cohort study was used to validate the identified clusters. Five clusters were successfully identified. Clusters 1 (n = 71) and 3 (n = 81) were mild asthma phenotypes with slight airway obstruction and low exacerbation risk, but with a sex differential. Cluster 2 (n = 65) described an "allergic" phenotype, cluster 4 (n = 33) featured a "fixed airflow limitation" phenotype with smoking, and cluster 5 (n = 34) was a "low socioeconomic status" phenotype. Patients in clusters 2, 4, and 5 had distinctly lower socioeconomic status and more psychological symptoms. Cluster 2 had a significantly increased risk of exacerbations (risk ratio [RR] 1.13, 95% confidence interval [CI] 1.03-1.25), unplanned visits for asthma (RR 1.98, 95% CI 1.07-3.66), and emergency visits for asthma (RR 7.17, 95% CI 1.26-40.80). Cluster 4 had an increased risk of unplanned visits (RR 2.22, 95% CI 1.02-4.81), and cluster 5 had increased emergency visits (RR 12.72, 95% CI 1.95-69.78). Kaplan-Meier analysis confirmed that cluster grouping was predictive of time to the first asthma exacerbation, unplanned visit, emergency visit, and hospital admission (P clusters as "allergic asthma," "fixed airflow limitation," and "low socioeconomic status" phenotypes that are at high risk of severe asthma exacerbations and that have management implications for clinical practice in developing countries. Copyright © 2017 American College of Allergy, Asthma & Immunology. Published by Elsevier Inc. All rights reserved.
Cluster analysis in phenotyping a Portuguese population.
Loureiro, C C; Sa-Couto, P; Todo-Bom, A; Bousquet, J
2015-09-03
Unbiased cluster analysis using clinical parameters has identified asthma phenotypes. Adding inflammatory biomarkers to this analysis provided a better insight into the disease mechanisms. This approach has not yet been applied to asthmatic Portuguese patients. To identify phenotypes of asthma using cluster analysis in a Portuguese asthmatic population treated in secondary medical care. Consecutive patients with asthma were recruited from the outpatient clinic. Patients were optimally treated according to GINA guidelines and enrolled in the study. Procedures were performed according to a standard evaluation of asthma. Phenotypes were identified by cluster analysis using Ward's clustering method. Of the 72 patients enrolled, 57 had full data and were included for cluster analysis. Distribution was set in 5 clusters described as follows: cluster (C) 1, early onset mild allergic asthma; C2, moderate allergic asthma, with long evolution, female prevalence and mixed inflammation; C3, allergic brittle asthma in young females with early disease onset and no evidence of inflammation; C4, severe asthma in obese females with late disease onset, highly symptomatic despite low Th2 inflammation; C5, severe asthma with chronic airflow obstruction, late disease onset and eosinophilic inflammation. In our study population, the identified clusters were mainly coincident with other larger-scale cluster analysis. Variables such as age at disease onset, obesity, lung function, FeNO (Th2 biomarker) and disease severity were important for cluster distinction. Copyright © 2015. Published by Elsevier España, S.L.U.
Directory of Open Access Journals (Sweden)
Martinez Fernando J
2010-03-01
Full Text Available Abstract Background Numerous studies have demonstrated associations between genetic markers and COPD, but results have been inconsistent. One reason may be heterogeneity in disease definition. Unsupervised learning approaches may assist in understanding disease heterogeneity. Methods We selected 31 phenotypic variables and 12 SNPs from five candidate genes in 308 subjects in the National Emphysema Treatment Trial (NETT Genetics Ancillary Study cohort. We used factor analysis to select a subset of phenotypic variables, and then used cluster analysis to identify subtypes of severe emphysema. We examined the phenotypic and genotypic characteristics of each cluster. Results We identified six factors accounting for 75% of the shared variability among our initial phenotypic variables. We selected four phenotypic variables from these factors for cluster analysis: 1 post-bronchodilator FEV1 percent predicted, 2 percent bronchodilator responsiveness, and quantitative CT measurements of 3 apical emphysema and 4 airway wall thickness. K-means cluster analysis revealed four clusters, though separation between clusters was modest: 1 emphysema predominant, 2 bronchodilator responsive, with higher FEV1; 3 discordant, with a lower FEV1 despite less severe emphysema and lower airway wall thickness, and 4 airway predominant. Of the genotypes examined, membership in cluster 1 (emphysema-predominant was associated with TGFB1 SNP rs1800470. Conclusions Cluster analysis may identify meaningful disease subtypes and/or groups of related phenotypic variables even in a highly selected group of severe emphysema subjects, and may be useful for genetic association studies.
Directory of Open Access Journals (Sweden)
Stefano Bernardinetti
2017-06-01
Full Text Available The need to obtain a detailed hydrogeological characterization of the subsurface and its interpretation for the groundwater resources management, often requires to apply several and complementary geophysical methods. The goal of the approach in this paper is to provide a unique model of the aquifer by synthesizing and optimizing the information provided by several geophysical methods. This approach greatly reduces the degree of uncertainty and subjectivity of the interpretation by exploiting the different physical and mechanic characteristics of the aquifer. The studied area, into the municipality of Laterina (Arezzo, Italy, is a shallow basin filled by lacustrine and alluvial deposits (Pleistocene and Olocene epochs, Quaternary period, with alternated silt, sand with variable content of gravel and clay where the bottom is represented by arenaceous-pelitic rocks (Mt. Cervarola Unit, Tuscan Domain, Miocene epoch. This shallow basin constitutes the unconfined superficial aquifer to be exploited in the nearly future. To improve the geological model obtained from a detailed geological survey we performed electrical resistivity and P wave refraction tomographies along the same line in order to obtain different, independent and integrable data sets. For the seismic data also the reflected events have been processed, a remarkable contribution to draw the geologic setting. Through the k-means algorithm, we perform a cluster analysis for the bivariate data set to individuate relationships between the two sets of variables. This algorithm allows to individuate clusters with the aim of minimizing the dissimilarity within each cluster and maximizing it among different clusters of the bivariate data set. The optimal number of clusters “K”, corresponding to the individuated geophysical facies, depends to the multivariate data set distribution and in this work is estimated with the Silhouettes. The result is an integrated tomography that shows a finite
Parkinson's Disease Subtypes Identified from Cluster Analysis of Motor and Non-motor Symptoms.
Mu, Jesse; Chaudhuri, Kallol R; Bielza, Concha; de Pedro-Cuesta, Jesus; Larrañaga, Pedro; Martinez-Martin, Pablo
2017-01-01
Parkinson's disease is now considered a complex, multi-peptide, central, and peripheral nervous system disorder with considerable clinical heterogeneity. Non-motor symptoms play a key role in the trajectory of Parkinson's disease, from prodromal premotor to end stages. To understand the clinical heterogeneity of Parkinson's disease, this study used cluster analysis to search for subtypes from a large, multi-center, international, and well-characterized cohort of Parkinson's disease patients across all motor stages, using a combination of cardinal motor features (bradykinesia, rigidity, tremor, axial signs) and, for the first time, specific validated rater-based non-motor symptom scales. Two independent international cohort studies were used: (a) the validation study of the Non-Motor Symptoms Scale ( n = 411) and (b) baseline data from the global Non-Motor International Longitudinal Study ( n = 540). k -means cluster analyses were performed on the non-motor and motor domains (domains clustering) and the 30 individual non-motor symptoms alone (symptoms clustering), and hierarchical agglomerative clustering was performed to group symptoms together. Four clusters are identified from the domains clustering supporting previous studies: mild, non-motor dominant, motor-dominant, and severe. In addition, six new smaller clusters are identified from the symptoms clustering, each characterized by clinically-relevant non-motor symptoms. The clusters identified in this study present statistical confirmation of the increasingly important role of non-motor symptoms (NMS) in Parkinson's disease heterogeneity and take steps toward subtype-specific treatment packages.
Weighted K-means support vector machine for cancer prediction.
Kim, SungHwan
2016-01-01
To date, the support vector machine (SVM) has been widely applied to diverse bio-medical fields to address disease subtype identification and pathogenicity of genetic variants. In this paper, I propose the weighted K-means support vector machine (wKM-SVM) and weighted support vector machine (wSVM), for which I allow the SVM to impose weights to the loss term. Besides, I demonstrate the numerical relations between the objective function of the SVM and weights. Motivated by general ensemble techniques, which are known to improve accuracy, I directly adopt the boosting algorithm to the newly proposed weighted KM-SVM (and wSVM). For predictive performance, a range of simulation studies demonstrate that the weighted KM-SVM (and wSVM) with boosting outperforms the standard KM-SVM (and SVM) including but not limited to many popular classification rules. I applied the proposed methods to simulated data and two large-scale real applications in the TCGA pan-cancer methylation data of breast and kidney cancer. In conclusion, the weighted KM-SVM (and wSVM) increases accuracy of the classification model, and will facilitate disease diagnosis and clinical treatment decisions to benefit patients. A software package (wSVM) is publicly available at the R-project webpage (https://www.r-project.org).
Clustering Analysis for Credit Default Probabilities in a Retail Bank Portfolio
Directory of Open Access Journals (Sweden)
Elena ANDREI (DRAGOMIR
2012-08-01
Full Text Available Methods underlying cluster analysis are very useful in data analysis, especially when the processed volume of data is very large, so that it becomes impossible to extract essential information, unless specific instruments are used to summarize and structure the gross information. In this context, cluster analysis techniques are used particularly, for systematic information analysis. The aim of this article is to build an useful model for banking field, based on data mining techniques, by dividing the groups of borrowers into clusters, in order to obtain a profile of the customers (debtors and good payers. We assume that a class is appropriate if it contains members that have a high degree of similarity and the standard method for measuring the similarity within a group shows the lowest variance. After clustering, data mining techniques are implemented on the cluster with bad debtors, reaching a very high accuracy after implementation. The paper is structured as follows: Section 2 describes the model for data analysis based on a specific scoring model that we proposed. In section 3, we present a cluster analysis using K-means algorithm and the DM models are applied on a specific cluster. Section 4 shows the conclusions.
Improving estimation of kinetic parameters in dynamic force spectroscopy using cluster analysis
Yen, Chi-Fu; Sivasankar, Sanjeevi
2018-03-01
Dynamic Force Spectroscopy (DFS) is a widely used technique to characterize the dissociation kinetics and interaction energy landscape of receptor-ligand complexes with single-molecule resolution. In an Atomic Force Microscope (AFM)-based DFS experiment, receptor-ligand complexes, sandwiched between an AFM tip and substrate, are ruptured at different stress rates by varying the speed at which the AFM-tip and substrate are pulled away from each other. The rupture events are grouped according to their pulling speeds, and the mean force and loading rate of each group are calculated. These data are subsequently fit to established models, and energy landscape parameters such as the intrinsic off-rate (koff) and the width of the potential energy barrier (xβ) are extracted. However, due to large uncertainties in determining mean forces and loading rates of the groups, errors in the estimated koff and xβ can be substantial. Here, we demonstrate that the accuracy of fitted parameters in a DFS experiment can be dramatically improved by sorting rupture events into groups using cluster analysis instead of sorting them according to their pulling speeds. We test different clustering algorithms including Gaussian mixture, logistic regression, and K-means clustering, under conditions that closely mimic DFS experiments. Using Monte Carlo simulations, we benchmark the performance of these clustering algorithms over a wide range of koff and xβ, under different levels of thermal noise, and as a function of both the number of unbinding events and the number of pulling speeds. Our results demonstrate that cluster analysis, particularly K-means clustering, is very effective in improving the accuracy of parameter estimation, particularly when the number of unbinding events are limited and not well separated into distinct groups. Cluster analysis is easy to implement, and our performance benchmarks serve as a guide in choosing an appropriate method for DFS data analysis.
Prediction of Tibial Rotation Pathologies Using Particle Swarm Optimization and K-Means Algorithms.
Sari, Murat; Tuna, Can; Akogul, Serkan
2018-03-28
The aim of this article is to investigate pathological subjects from a population through different physical factors. To achieve this, particle swarm optimization (PSO) and K-means (KM) clustering algorithms have been combined (PSO-KM). Datasets provided by the literature were divided into three clusters based on age and weight parameters and each one of right tibial external rotation (RTER), right tibial internal rotation (RTIR), left tibial external rotation (LTER), and left tibial internal rotation (LTIR) values were divided into three types as Type 1, Type 2 and Type 3 (Type 2 is non-pathological (normal) and the other two types are pathological (abnormal)), respectively. The rotation values of every subject in any cluster were noted. Then the algorithm was run and the produced values were also considered. The values of the produced algorithm, the PSO-KM, have been compared with the real values. The hybrid PSO-KM algorithm has been very successful on the optimal clustering of the tibial rotation types through the physical criteria. In this investigation, Type 2 (pathological subjects) is of especially high predictability and the PSO-KM algorithm has been very successful as an operation system for clustering and optimizing the tibial motion data assessments. These research findings are expected to be very useful for health providers, such as physiotherapists, orthopedists, and so on, in which this consequence may help clinicians to appropriately designing proper treatment schedules for patients.
International Nuclear Information System (INIS)
Harmon, S; Wendelberger, B; Jeraj, R
2014-01-01
Purpose: Radiogenomics aims to establish relationships between patient genotypes and imaging phenotypes. An open question remains on how best to integrate information from these distinct datasets. This work investigates if similarities in genetic features across patients correspond to similarities in PET-imaging features, assessed with various clustering algorithms. Methods: [ 18 F]FDG PET data was obtained for 26 NSCLC patients from a public database (TCIA). Tumors were contoured using an in-house segmentation algorithm combining gradient and region-growing techniques; resulting ROIs were used to extract 54 PET-based features. Corresponding genetic microarray data containing 48,778 elements were also obtained for each tumor. Given mismatch in feature sizes, two dimension reduction techniques were also applied to the genetic data: principle component analysis (PCA) and selective filtering of 25 NSCLC-associated genes-ofinterest (GOI). Gene datasets (full, PCA, and GOI) and PET feature datasets were independently clustered using K-means and hierarchical clustering using variable number of clusters (K). Jaccard Index (JI) was used to score similarity of cluster assignments across different datasets. Results: Patient clusters from imaging data showed poor similarity to clusters from gene datasets, regardless of clustering algorithms or number of clusters (JI mean = 0.3429±0.1623). Notably, we found clustering algorithms had different sensitivities to data reduction techniques. Using hierarchical clustering, the PCA dataset showed perfect cluster agreement to the full-gene set (JI =1) for all values of K, and the agreement between the GOI set and the full-gene set decreased as number of clusters increased (JI=0.9231 and 0.5769 for K=2 and 5, respectively). K-means clustering assignments were highly sensitive to data reduction and showed poor stability for different values of K (JI range : 0.2301–1). Conclusion: Using commonly-used clustering algorithms, we found
Energy Technology Data Exchange (ETDEWEB)
Harmon, S; Wendelberger, B [University of Wisconsin-Madison, Madison, WI (United States); Jeraj, R [University of Wisconsin-Madison, Madison, WI (United States); University of Ljubljana (Slovenia)
2014-06-01
Purpose: Radiogenomics aims to establish relationships between patient genotypes and imaging phenotypes. An open question remains on how best to integrate information from these distinct datasets. This work investigates if similarities in genetic features across patients correspond to similarities in PET-imaging features, assessed with various clustering algorithms. Methods: [{sup 18}F]FDG PET data was obtained for 26 NSCLC patients from a public database (TCIA). Tumors were contoured using an in-house segmentation algorithm combining gradient and region-growing techniques; resulting ROIs were used to extract 54 PET-based features. Corresponding genetic microarray data containing 48,778 elements were also obtained for each tumor. Given mismatch in feature sizes, two dimension reduction techniques were also applied to the genetic data: principle component analysis (PCA) and selective filtering of 25 NSCLC-associated genes-ofinterest (GOI). Gene datasets (full, PCA, and GOI) and PET feature datasets were independently clustered using K-means and hierarchical clustering using variable number of clusters (K). Jaccard Index (JI) was used to score similarity of cluster assignments across different datasets. Results: Patient clusters from imaging data showed poor similarity to clusters from gene datasets, regardless of clustering algorithms or number of clusters (JI{sub mean}= 0.3429±0.1623). Notably, we found clustering algorithms had different sensitivities to data reduction techniques. Using hierarchical clustering, the PCA dataset showed perfect cluster agreement to the full-gene set (JI =1) for all values of K, and the agreement between the GOI set and the full-gene set decreased as number of clusters increased (JI=0.9231 and 0.5769 for K=2 and 5, respectively). K-means clustering assignments were highly sensitive to data reduction and showed poor stability for different values of K (JI{sub range}: 0.2301–1). Conclusion: Using commonly-used clustering algorithms
Methodology сomparative statistical analysis of Russian industry based on cluster analysis
Directory of Open Access Journals (Sweden)
Sergey S. Shishulin
2017-01-01
Full Text Available The article is devoted to researching of the possibilities of applying multidimensional statistical analysis in the study of industrial production on the basis of comparing its growth rates and structure with other developed and developing countries of the world. The purpose of this article is to determine the optimal set of statistical methods and the results of their application to industrial production data, which would give the best access to the analysis of the result.Data includes such indicators as output, output, gross value added, the number of employed and other indicators of the system of national accounts and operational business statistics. The objects of observation are the industry of the countrys of the Customs Union, the United States, Japan and Erope in 2005-2015. As the research tool used as the simplest methods of transformation, graphical and tabular visualization of data, and methods of statistical analysis. In particular, based on a specialized software package (SPSS, the main components method, discriminant analysis, hierarchical methods of cluster analysis, Ward’s method and k-means were applied.The application of the method of principal components to the initial data makes it possible to substantially and effectively reduce the initial space of industrial production data. Thus, for example, in analyzing the structure of industrial production, the reduction was from fifteen industries to three basic, well-interpreted factors: the relatively extractive industries (with a low degree of processing, high-tech industries and consumer goods (medium-technology sectors. At the same time, as a result of comparison of the results of application of cluster analysis to the initial data and data obtained on the basis of the principal components method, it was established that clustering industrial production data on the basis of new factors significantly improves the results of clustering.As a result of analyzing the parameters of
Minku, Leandro L.
2017-10-06
Background: Software Effort Estimation (SEE) can be formulated as an online learning problem, where new projects are completed over time and may become available for training. In this scenario, a Cross-Company (CC) SEE approach called Dycom can drastically reduce the number of Within-Company (WC) projects needed for training, saving the high cost of collecting such training projects. However, Dycom relies on splitting CC projects into different subsets in order to create its CC models. Such splitting can have a significant impact on Dycom\\'s predictive performance. Aims: This paper investigates whether clustering methods can be used to help finding good CC splits for Dycom. Method: Dycom is extended to use clustering methods for creating the CC subsets. Three different clustering methods are investigated, namely Hierarchical Clustering, K-Means, and Expectation-Maximisation. Clustering Dycom is compared against the original Dycom with CC subsets of different sizes, based on four SEE databases. A baseline WC model is also included in the analysis. Results: Clustering Dycom with K-Means can potentially help to split the CC projects, managing to achieve similar or better predictive performance than Dycom. However, K-Means still requires the number of CC subsets to be pre-defined, and a poor choice can negatively affect predictive performance. EM enables Dycom to automatically set the number of CC subsets while still maintaining or improving predictive performance with respect to the baseline WC model. Clustering Dycom with Hierarchical Clustering did not offer significant advantage in terms of predictive performance. Conclusion: Clustering methods can be an effective way to automatically generate Dycom\\'s CC subsets.
Robust cluster analysis and variable selection
Ritter, Gunter
2014-01-01
Clustering remains a vibrant area of research in statistics. Although there are many books on this topic, there are relatively few that are well founded in the theoretical aspects. In Robust Cluster Analysis and Variable Selection, Gunter Ritter presents an overview of the theory and applications of probabilistic clustering and variable selection, synthesizing the key research results of the last 50 years. The author focuses on the robust clustering methods he found to be the most useful on simulated data and real-time applications. The book provides clear guidance for the varying needs of bot
Optimization of a truck-drone in tandem delivery network using k-means and genetic algorithm
Energy Technology Data Exchange (ETDEWEB)
Ferrandez, S. M.; Harbison, T.; Weber, T.; Sturges, R.; Rich, R.
2016-07-01
The purpose of this paper is to investigate the effectiveness of implementing unmanned aerial delivery vehicles in delivery networks. We investigate the notion of the reduced overall delivery time, energy, and costs for a truck-drone network by comparing the in-tandem system with a stand-alone delivery effort. The objectives are (1) to investigate the time, energy, and costs associated to a truck-drone delivery network compared to standalone truck or drone, (2) to propose an optimization algorithm that determines the optimal number of launch sites and locations given delivery requirements, and drones per truck, (3) to develop mathematical formulations for closed form estimations for the optimal number of launch locations, optimal total time, as well as the associated cost for the system. The design of the algorithm herein computes the minimal time of delivery utilizing K-means clustering to find launch locations, as well as a genetic algorithm to solve the truck route as a traveling salesmen problem (TSP). The optimal solution is determined by finding the minimum cost associated to the parabolic convex cost function. The optimal min-cost is determined by finding the most efficient launch locations using K-means algorithms to determine launch locations and a genetic algorithm to determine truck route between those launch locations. Results show improvements with in-tandem delivery efforts as opposed to standalone systems. Further, multiple drones per truck are more optimal and contribute to savings in both energy and time. For this, we sampled various initialization variables to derive closed form mathematical solutions for the problem. Ultimately, this provides the necessary analysis of an integrated truck-drone delivery system which could be implemented by a company in order to maximize deliveries while minimizing time and energy. Closed-form mathematical solutions can be used as close estimators for final costs and time. (Author)
Optimization of a truck-drone in tandem delivery network using k-means and genetic algorithm
Directory of Open Access Journals (Sweden)
Sergio Mourelo Ferrandez
2016-04-01
Full Text Available Purpose: The purpose of this paper is to investigate the effectiveness of implementing unmanned aerial delivery vehicles in delivery networks. We investigate the notion of the reduced overall delivery time, energy, and costs for a truck-drone network by comparing the in-tandem system with a stand-alone delivery effort. The objectives are (1 to investigate the time, energy, and costs associated to a truck-drone delivery network compared to standalone truck or drone, (2 to propose an optimization algorithm that determines the optimal number of launch sites and locations given delivery requirements, and drones per truck, (3 to develop mathematical formulations for closed form estimations for the optimal number of launch locations, optimal total time, as well as the associated cost for the system. Design/methodology/approach: The design of the algorithm herein computes the minimal time of delivery utilizing K-means clustering to find launch locations, as well as a genetic algorithm to solve the truck route as a traveling salesmen problem (TSP. The optimal solution is determined by finding the minimum cost associated to the parabolic convex cost function. The optimal min-cost is determined by finding the most efficient launch locations using K-means algorithms to determine launch locations and a genetic algorithm to determine truck route between those launch locations. Findings: Results show improvements with in-tandem delivery efforts as opposed to standalone systems. Further, multiple drones per truck are more optimal and contribute to savings in both energy and time. For this, we sampled various initialization variables to derive closed form mathematical solutions for the problem. Originality/value: Ultimately, this provides the necessary analysis of an integrated truck-drone delivery system which could be implemented by a company in order to maximize deliveries while minimizing time and energy. Closed-form mathematical solutions can be used as
Research on Abnormal Detection Based on Improved Combination of K - means and SVDD
Hao, Xiaohong; Zhang, Xiaofeng
2018-01-01
In order to improve the efficiency of network intrusion detection and reduce the false alarm rate, this paper proposes an anomaly detection algorithm based on improved K-means and SVDD. The algorithm first uses the improved K-means algorithm to cluster the training samples of each class, so that each class is independent and compact in class; Then, according to the training samples, the SVDD algorithm is used to construct the minimum superspheres. The subordinate relationship of the samples is determined by calculating the distance of the minimum superspheres constructed by SVDD. If the test sample is less than the center of the hypersphere, the test sample belongs to this class, otherwise it does not belong to this class, after several comparisons, the final test of the effective detection of the test sample.In this paper, we use KDD CUP99 data set to simulate the proposed anomaly detection algorithm. The results show that the algorithm has high detection rate and low false alarm rate, which is an effective network security protection method.
Envelopment filter and K-means for the detection of QRS waveforms in electrocardiogram.
Merino, Manuel; Gómez, Isabel María; Molina, Alberto J
2015-06-01
The electrocardiogram (ECG) is a well-established technique for determining the electrical activity of the heart and studying its diseases. One of the most common pieces of information that can be read from the ECG is the heart rate (HR) through the detection of its most prominent feature: the QRS complex. This paper describes an offline version and a real-time implementation of a new algorithm to determine QRS localization in the ECG signal based on its envelopment and K-means clustering algorithm. The envelopment is used to obtain a signal with only QRS complexes, deleting P, T, and U waves and baseline wander. Two moving average filters are applied to smooth data. The K-means algorithm classifies data into QRS and non-QRS. The technique is validated using 22 h of ECG data from five Physionet databases. These databases were arbitrarily selected to analyze different morphologies of QRS complexes: three stored data with cardiac pathologies, and two had data with normal heartbeats. The algorithm has a low computational load, with no decision thresholds. Furthermore, it does not require any additional parameter. Sensitivity, positive prediction and accuracy from results are over 99.7%. Copyright © 2015 IPEM. Published by Elsevier Ltd. All rights reserved.
Exact WKB analysis and cluster algebras
International Nuclear Information System (INIS)
Iwaki, Kohei; Nakanishi, Tomoki
2014-01-01
We develop the mutation theory in the exact WKB analysis using the framework of cluster algebras. Under a continuous deformation of the potential of the Schrödinger equation on a compact Riemann surface, the Stokes graph may change the topology. We call this phenomenon the mutation of Stokes graphs. Along the mutation of Stokes graphs, the Voros symbols, which are monodromy data of the equation, also mutate due to the Stokes phenomenon. We show that the Voros symbols mutate as variables of a cluster algebra with surface realization. As an application, we obtain the identities of Stokes automorphisms associated with periods of cluster algebras. The paper also includes an extensive introduction of the exact WKB analysis and the surface realization of cluster algebras for nonexperts. This article is part of a special issue of Journal of Physics A: Mathematical and Theoretical devoted to ‘Cluster algebras in mathematical physics’. (paper)
Orbit Clustering Based on Transfer Cost
Gustafson, Eric D.; Arrieta-Camacho, Juan J.; Petropoulos, Anastassios E.
2013-01-01
We propose using cluster analysis to perform quick screening for combinatorial global optimization problems. The key missing component currently preventing cluster analysis from use in this context is the lack of a useable metric function that defines the cost to transfer between two orbits. We study several proposed metrics and clustering algorithms, including k-means and the expectation maximization algorithm. We also show that proven heuristic methods such as the Q-law can be modified to work with cluster analysis.
Lee, Junghee; Rizzo, Shemra; Altshuler, Lori; Glahn, David C; Miklowitz, David J; Sugar, Catherine A; Wynn, Jonathan K; Green, Michael F
2017-02-01
Bipolar disorder (BD) and schizophrenia (SZ) show substantial overlap. It has been suggested that a subgroup of patients might contribute to these overlapping features. This study employed a cross-diagnostic cluster analysis to identify subgroups of individuals with shared cognitive phenotypes. 143 participants (68 BD patients, 39 SZ patients and 36 healthy controls) completed a battery of EEG and performance assessments on perception, nonsocial cognition and social cognition. A K-means cluster analysis was conducted with all participants across diagnostic groups. Clinical symptoms, functional capacity, and functional outcome were assessed in patients. A two-cluster solution across 3 groups was the most stable. One cluster including 44 BD patients, 31 controls and 5 SZ patients showed better cognition (High cluster) than the other cluster with 24 BD patients, 35 SZ patients and 5 controls (Low cluster). BD patients in the High cluster performed better than BD patients in the Low cluster across cognitive domains. Within each cluster, participants with different clinical diagnoses showed different profiles across cognitive domains. All patients are in the chronic phase and out of mood episode at the time of assessment and most of the assessment were behavioral measures. This study identified two clusters with shared cognitive phenotype profiles that were not proxies for clinical diagnoses. The finding of better social cognitive performance of BD patients than SZ patients in the Lowe cluster suggest that relatively preserved social cognition may be important to identify disease process distinct to each disorder. Copyright © 2016 Elsevier B.V. All rights reserved.
Hybrid Radar Emitter Recognition Based on Rough k-Means Classifier and Relevance Vector Machine
Yang, Zhutian; Wu, Zhilu; Yin, Zhendong; Quan, Taifan; Sun, Hongjian
2013-01-01
Due to the increasing complexity of electromagnetic signals, there exists a significant challenge for recognizing radar emitter signals. In this paper, a hybrid recognition approach is presented that classifies radar emitter signals by exploiting the different separability of samples. The proposed approach comprises two steps, namely the primary signal recognition and the advanced signal recognition. In the former step, a novel rough k-means classifier, which comprises three regions, i.e., certain area, rough area and uncertain area, is proposed to cluster the samples of radar emitter signals. In the latter step, the samples within the rough boundary are used to train the relevance vector machine (RVM). Then RVM is used to recognize the samples in the uncertain area; therefore, the classification accuracy is improved. Simulation results show that, for recognizing radar emitter signals, the proposed hybrid recognition approach is more accurate, and presents lower computational complexity than traditional approaches. PMID:23344380
Bai, Mei; Dixon, Jane; Williams, Anna-Leila; Jeon, Sangchoon; Lazenby, Mark; McCorkle, Ruth
2016-11-01
Research shows that spiritual well-being correlates positively with quality of life (QOL) for people with cancer, whereas contradictory findings are frequently reported with respect to the differentiated associations between dimensions of spiritual well-being, namely peace, meaning and faith, and QOL. This study aimed to examine individual patterns of spiritual well-being among patients newly diagnosed with advanced cancer. Cluster analysis was based on the twelve items of the 12-item Functional Assessment of Chronic Illness Therapy-Spiritual Well-Being Scale at Time 1. A combination of hierarchical and k-means (non-hierarchical) clustering methods was employed to jointly determine the number of clusters. Self-rated health, depressive symptoms, peace, meaning and faith, and overall QOL were compared at Time 1 and Time 2. Hierarchical and k-means clustering methods both suggested four clusters. Comparison of the four clusters supported statistically significant and clinically meaningful differences in QOL outcomes among clusters while revealing contrasting relations of faith with QOL. Cluster 1, Cluster 3, and Cluster 4 represented high, medium, and low levels of overall QOL, respectively, with correspondingly high, medium, and low levels of peace, meaning, and faith. Cluster 2 was distinguished from other clusters by its medium levels of overall QOL, peace, and meaning and low level of faith. This study provides empirical support for individual difference in response to a newly diagnosed cancer and brings into focus conceptual and methodological challenges associated with the measure of spiritual well-being, which may partly contribute to the attenuated relation between faith and QOL.
Russell, Louise B; Bhanot, Gyan; Kim, Sun-Young; Sinha, Anushua
2018-02-01
To explore the use of cluster analysis to define groups of similar countries for the purpose of evaluating the cost-effectiveness of a public health intervention-maternal immunization-within the constraints of a project budget originally meant for an overall regional analysis. We used the most common cluster analysis algorithm, K-means, and the most common measure of distance, Euclidean distance, to group 37 low-income, sub-Saharan African countries on the basis of 24 measures of economic development, general health resources, and past success in public health programs. The groups were tested for robustness and reviewed by regional disease experts. We explored 2-, 3- and 4-group clustering. Public health performance was consistently important in determining the groups. For the 2-group clustering, for example, infant mortality in Group 1 was 81 per 1,000 live births compared with 51 per 1,000 in Group 2, and 67% of children in Group 1 received DPT immunization compared with 87% in Group 2. The experts preferred four groups to fewer, on the ground that national decision makers would more readily recognize their country among four groups. Clusters defined by K-means clustering made sense to subject experts and allowed a more detailed evaluation of the cost-effectiveness of maternal immunization within the constraint of the project budget. The method may be useful for other evaluations that, without having the resources to conduct separate analyses for each unit, seek to inform decision makers in numerous countries or subdivisions within countries, such as states or counties.
Raouafi, Sana; Achiche, Sofiane; Begon, Mickael; Sarcher, Aurélie; Raison, Maxime
2018-01-01
Treatment for cerebral palsy depends upon the severity of the child's condition and requires knowledge about upper limb disability. The aim of this study was to develop a systematic quantitative classification method of the upper limb disability levels for children with spastic unilateral cerebral palsy based on upper limb movements and muscle activation. Thirteen children with spastic unilateral cerebral palsy and six typically developing children participated in this study. Patients were matched on age and manual ability classification system levels I to III. Twenty-three kinematic and electromyographic variables were collected from two tasks. Discriminative analysis and K-means clustering algorithm were applied using 23 kinematic and EMG variables of each participant. Among the 23 kinematic and electromyographic variables, only two variables containing the most relevant information for the prediction of the four levels of severity of spastic unilateral cerebral palsy, which are fixed by manual ability classification system, were identified by discriminant analysis: (1) the Falconer index (CAI E ) which represents the ratio of biceps to triceps brachii activity during extension and (2) the maximal angle extension (θ Extension,max ). A good correlation (Kendall Rank correlation coefficient = -0.53, p = 0.01) was found between levels fixed by manual ability classification system and the obtained classes. These findings suggest that the cost and effort needed to assess and characterize the disability level of a child can be further reduced.
Cluster Analysis of Customer Reviews Extracted from Web Pages
Directory of Open Access Journals (Sweden)
S. Shivashankar
2010-01-01
Full Text Available As e-commerce is gaining popularity day by day, the web has become an excellent source for gathering customer reviews / opinions by the market researchers. The number of customer reviews that a product receives is growing at very fast rate (It could be in hundreds or thousands. Customer reviews posted on the websites vary greatly in quality. The potential customer has to read necessarily all the reviews irrespective of their quality to make a decision on whether to purchase the product or not. In this paper, we make an attempt to assess are view based on its quality, to help the customer make a proper buying decision. The quality of customer review is assessed as most significant, more significant, significant and insignificant.A novel and effective web mining technique is proposed for assessing a customer review of a particular product based on the feature clustering techniques, namely, k-means method and fuzzy c-means method. This is performed in three steps : (1Identify review regions and extract reviews from it, (2 Extract and cluster the features of reviews by a clustering technique and then assign weights to the features belonging to each of the clusters (groups and (3 Assess the review by considering the feature weights and group belongingness. The k-means and fuzzy c-means clustering techniques are implemented and tested on customer reviews extracted from web pages. Performance of these techniques are analyzed.
Qin, Jiahu; Fu, Weiming; Gao, Huijun; Zheng, Wei Xing
2016-03-03
This paper is concerned with developing a distributed k-means algorithm and a distributed fuzzy c-means algorithm for wireless sensor networks (WSNs) where each node is equipped with sensors. The underlying topology of the WSN is supposed to be strongly connected. The consensus algorithm in multiagent consensus theory is utilized to exchange the measurement information of the sensors in WSN. To obtain a faster convergence speed as well as a higher possibility of having the global optimum, a distributed k-means++ algorithm is first proposed to find the initial centroids before executing the distributed k-means algorithm and the distributed fuzzy c-means algorithm. The proposed distributed k-means algorithm is capable of partitioning the data observed by the nodes into measure-dependent groups which have small in-group and large out-group distances, while the proposed distributed fuzzy c-means algorithm is capable of partitioning the data observed by the nodes into different measure-dependent groups with degrees of membership values ranging from 0 to 1. Simulation results show that the proposed distributed algorithms can achieve almost the same results as that given by the centralized clustering algorithms.
Energy Technology Data Exchange (ETDEWEB)
Lalonde, Michel, E-mail: mlalonde15@rogers.com; Wassenaar, Richard [Department of Physics, Carleton University, Ottawa, Ontario K1S 5B6 (Canada); Wells, R. Glenn; Birnie, David; Ruddy, Terrence D. [Division of Cardiology, University of Ottawa Heart Institute, Ottawa, Ontario K1Y 4W7 (Canada)
2014-07-15
Purpose: Phase analysis of single photon emission computed tomography (SPECT) radionuclide angiography (RNA) has been investigated for its potential to predict the outcome of cardiac resynchronization therapy (CRT). However, phase analysis may be limited in its potential at predicting CRT outcome as valuable information may be lost by assuming that time-activity curves (TAC) follow a simple sinusoidal shape. A new method, cluster analysis, is proposed which directly evaluates the TACs and may lead to a better understanding of dyssynchrony patterns and CRT outcome. Cluster analysis algorithms were developed and optimized to maximize their ability to predict CRT response. Methods: About 49 patients (N = 27 ischemic etiology) received a SPECT RNA scan as well as positron emission tomography (PET) perfusion and viability scans prior to undergoing CRT. A semiautomated algorithm sampled the left ventricle wall to produce 568 TACs from SPECT RNA data. The TACs were then subjected to two different cluster analysis techniques, K-means, and normal average, where several input metrics were also varied to determine the optimal settings for the prediction of CRT outcome. Each TAC was assigned to a cluster group based on the comparison criteria and global and segmental cluster size and scores were used as measures of dyssynchrony and used to predict response to CRT. A repeated random twofold cross-validation technique was used to train and validate the cluster algorithm. Receiver operating characteristic (ROC) analysis was used to calculate the area under the curve (AUC) and compare results to those obtained for SPECT RNA phase analysis and PET scar size analysis methods. Results: Using the normal average cluster analysis approach, the septal wall produced statistically significant results for predicting CRT results in the ischemic population (ROC AUC = 0.73;p < 0.05 vs. equal chance ROC AUC = 0.50) with an optimal operating point of 71% sensitivity and 60% specificity. Cluster
International Nuclear Information System (INIS)
Lalonde, Michel; Wassenaar, Richard; Wells, R. Glenn; Birnie, David; Ruddy, Terrence D.
2014-01-01
Purpose: Phase analysis of single photon emission computed tomography (SPECT) radionuclide angiography (RNA) has been investigated for its potential to predict the outcome of cardiac resynchronization therapy (CRT). However, phase analysis may be limited in its potential at predicting CRT outcome as valuable information may be lost by assuming that time-activity curves (TAC) follow a simple sinusoidal shape. A new method, cluster analysis, is proposed which directly evaluates the TACs and may lead to a better understanding of dyssynchrony patterns and CRT outcome. Cluster analysis algorithms were developed and optimized to maximize their ability to predict CRT response. Methods: About 49 patients (N = 27 ischemic etiology) received a SPECT RNA scan as well as positron emission tomography (PET) perfusion and viability scans prior to undergoing CRT. A semiautomated algorithm sampled the left ventricle wall to produce 568 TACs from SPECT RNA data. The TACs were then subjected to two different cluster analysis techniques, K-means, and normal average, where several input metrics were also varied to determine the optimal settings for the prediction of CRT outcome. Each TAC was assigned to a cluster group based on the comparison criteria and global and segmental cluster size and scores were used as measures of dyssynchrony and used to predict response to CRT. A repeated random twofold cross-validation technique was used to train and validate the cluster algorithm. Receiver operating characteristic (ROC) analysis was used to calculate the area under the curve (AUC) and compare results to those obtained for SPECT RNA phase analysis and PET scar size analysis methods. Results: Using the normal average cluster analysis approach, the septal wall produced statistically significant results for predicting CRT results in the ischemic population (ROC AUC = 0.73;p < 0.05 vs. equal chance ROC AUC = 0.50) with an optimal operating point of 71% sensitivity and 60% specificity. Cluster
Directory of Open Access Journals (Sweden)
Gede Aditra Pradnyana
2018-01-01
Full Text Available Permasalahan yang terjadi saat pembentukan atau pembagian kelas mahasiswa adalah perbedaan kemampuan yang dimiliki oleh mahasiswa di setiap kelasnya yang dapat berdampak pada tidak efektifnya proses pembelajaran yang berlangsung. Pengelompokkan mahasiswa dengan kemampuan yang sama merupakan hal yang sangat penting dalam rangka meningkatkan kualitas proses belajar mengajar yang dilakukan. Dengan pengelompokkan mahasiswa yang tepat, mereka akan dapat saling membantu dalam proses pembelajaran. Selain itu, membagi kelas mahasiswa sesuai dengan kemampuannya dapat mempermudah tenaga pendidik dalam menentukan metode atau strategi pembelajaran yang sesuai. Penggunaan metode dan strategi pembelajaran yang tepat akan meningkatkan efektifitas proses belajar mengajar. Pada penelitian ini dirancang sebuah metode baru untuk pembagian kelas kuliah mahasiswa dengan mengkombinasikan metode K-Means dan K-Nearest Neighbors (KNN. Metode K-means digunakan untuk pembagian kelas kuliah mahasiswa berdasarkan komponen penilaian dari mata kuliah prasyaratnya. Adapun fitur yang digunakan dalam pengelompokkan adalah nilai tugas, nilai ujian tengah semester, nilai ujian akhir semester, dan indeks prestasi kumulatif (IPK. Metode KNN digunakan untuk memprediksi kelulusan seoarang mahasiswa di sebuah matakuliah berdasarkan data sebelumnya. Hasil prediksi ini akan digunakan sebagai fitur tambahan yang digunakan dalam pembentukan kelas mahasiswa menggunakan metode K-means. Pendekatan yang digunakan dalam penelitian ini adalah Software Development Live Cycle (SDLC dengan model waterfall. Berdasarkan hasil pengujian yang dilakukan diperoleh kesimpulan bahwa jumlah cluster atau kelas dan jumlah data yang digunakan mempengaruhi dari kualitas cluster yang dibentuk oleh metode K-Means dan KNN yang digunakan. Nilai Silhouette Indeks tertinggi diperolah saat menggunakan 100 data dengan jumlah cluster 10 sebesar 0,534 yang tergolong kelas dengan kualitas medium structure.
Fault detection of flywheel system based on clustering and principal component analysis
Directory of Open Access Journals (Sweden)
Wang Rixin
2015-12-01
Full Text Available Considering the nonlinear, multifunctional properties of double-flywheel with closed-loop control, a two-step method including clustering and principal component analysis is proposed to detect the two faults in the multifunctional flywheels. At the first step of the proposed algorithm, clustering is taken as feature recognition to check the instructions of “integrated power and attitude control” system, such as attitude control, energy storage or energy discharge. These commands will ask the flywheel system to work in different operation modes. Therefore, the relationship of parameters in different operations can define the cluster structure of training data. Ordering points to identify the clustering structure (OPTICS can automatically identify these clusters by the reachability-plot. K-means algorithm can divide the training data into the corresponding operations according to the reachability-plot. Finally, the last step of proposed model is used to define the relationship of parameters in each operation through the principal component analysis (PCA method. Compared with the PCA model, the proposed approach is capable of identifying the new clusters and learning the new behavior of incoming data. The simulation results show that it can effectively detect the faults in the multifunctional flywheels system.
Cluster analysis of obesity and asthma phenotypes.
Directory of Open Access Journals (Sweden)
E Rand Sutherland
Full Text Available Asthma is a heterogeneous disease with variability among patients in characteristics such as lung function, symptoms and control, body weight, markers of inflammation, and responsiveness to glucocorticoids (GC. Cluster analysis of well-characterized cohorts can advance understanding of disease subgroups in asthma and point to unsuspected disease mechanisms. We utilized an hypothesis-free cluster analytical approach to define the contribution of obesity and related variables to asthma phenotype.In a cohort of clinical trial participants (n = 250, minimum-variance hierarchical clustering was used to identify clinical and inflammatory biomarkers important in determining disease cluster membership in mild and moderate persistent asthmatics. In a subset of participants, GC sensitivity was assessed via expression of GC receptor alpha (GCRα and induction of MAP kinase phosphatase-1 (MKP-1 expression by dexamethasone. Four asthma clusters were identified, with body mass index (BMI, kg/m(2 and severity of asthma symptoms (AEQ score the most significant determinants of cluster membership (F = 57.1, p<0.0001 and F = 44.8, p<0.0001, respectively. Two clusters were composed of predominantly obese individuals; these two obese asthma clusters differed from one another with regard to age of asthma onset, measures of asthma symptoms (AEQ and control (ACQ, exhaled nitric oxide concentration (F(ENO and airway hyperresponsiveness (methacholine PC(20 but were similar with regard to measures of lung function (FEV(1 (% and FEV(1/FVC, airway eosinophilia, IgE, leptin, adiponectin and C-reactive protein (hsCRP. Members of obese clusters demonstrated evidence of reduced expression of GCRα, a finding which was correlated with a reduced induction of MKP-1 expression by dexamethasoneObesity is an important determinant of asthma phenotype in adults. There is heterogeneity in expression of clinical and inflammatory biomarkers of asthma across obese individuals
Liao, Minlei; Li, Yunfeng; Kianifard, Farid; Obi, Engels; Arcona, Stephen
2016-03-02
Cluster analysis (CA) is a frequently used applied statistical technique that helps to reveal hidden structures and "clusters" found in large data sets. However, this method has not been widely used in large healthcare claims databases where the distribution of expenditure data is commonly severely skewed. The purpose of this study was to identify cost change patterns of patients with end-stage renal disease (ESRD) who initiated hemodialysis (HD) by applying different clustering methods. A retrospective, cross-sectional, observational study was conducted using the Truven Health MarketScan® Research Databases. Patients aged ≥18 years with ≥2 ESRD diagnoses who initiated HD between 2008 and 2010 were included. The K-means CA method and hierarchical CA with various linkage methods were applied to all-cause costs within baseline (12-months pre-HD) and follow-up periods (12-months post-HD) to identify clusters. Demographic, clinical, and cost information was extracted from both periods, and then examined by cluster. A total of 18,380 patients were identified. Meaningful all-cause cost clusters were generated using K-means CA and hierarchical CA with either flexible beta or Ward's methods. Based on cluster sample sizes and change of cost patterns, the K-means CA method and 4 clusters were selected: Cluster 1: Average to High (n = 113); Cluster 2: Very High to High (n = 89); Cluster 3: Average to Average (n = 16,624); or Cluster 4: Increasing Costs, High at Both Points (n = 1554). Median cost changes in the 12-month pre-HD and post-HD periods increased from $185,070 to $884,605 for Cluster 1 (Average to High), decreased from $910,930 to $157,997 for Cluster 2 (Very High to High), were relatively stable and remained low from $15,168 to $13,026 for Cluster 3 (Average to Average), and increased from $57,909 to $193,140 for Cluster 4 (Increasing Costs, High at Both Points). Relatively stable costs after starting HD were associated with more stable scores
A Location-Aware Service Deployment Algorithm Based on K-Means for Cloudlets
Directory of Open Access Journals (Sweden)
Tyng-Yeu Liang
2017-01-01
Full Text Available Cloudlet recently was proposed to push data centers towards network edges for reducing the network latency of delivering cloud services to mobile devices. For the sake of user mobility, it is necessary to deploy and hand off services anytime anywhere for achieving the minimal network latency for users’ service requests. However, the cost of this solution usually is too high for service providers and is not effective for resource exploitation. To resolve this problem, we propose a location-aware service deployment algorithm based on K-means for cloudlets in this paper. Simply speaking, the proposed algorithm divides mobile devices into a number of device clusters according to the geographical location of mobile devices and then deploys service instances onto the edge cloud servers nearest to the centers of device clusters. Our performance evaluation has shown that the proposed algorithm can effectively reduce not only the network latency of edge cloud services but also the number of service instances used for satisfying the condition of tolerable network latency.
Sistem Informasi Geografis Berbasis Web untuk Pemetaan Sebaran Alumni Menggunakan Metode K-Means
Directory of Open Access Journals (Sweden)
Slamet Handoko Handoko
2014-01-01
Full Text Available The graduates of State Polytechnic of Semarang are not only the member of social community but also part of State Polytechnic of Semarang community who have academic knowledge and special skills. Based on the researcher observation the graduates of State Polytechnic of Semarang are not recorded, the management of State Polytechnic of Semarang has not provided a system that can facilitate the interaction between State Polytechnic of Semarang and graduates. In this thesis, the system for mapping the graduates distribution is aimed to measure the level of the graduates compliance skill with the competence area of their job. The method of KMeans Clustering is used for grouping the distribution of State Polytechnic of Semarang graduates. Grouping or clustering mechanism in this system is based on four variables. They are type of company, job classification, working area, and competency of study program. While the geographical position of graduates is used to filter the data when the users are searching the graduates location in a ce rtain province. In this research the cluster is divided into three, they are, cluster one: graduates have matching competence, cluster two: graduates have matching enough competence, and cluster three: graduates have no matching competence.Keywords: Clustering; GIS ; K-Means
Directory of Open Access Journals (Sweden)
Yasser Khouj
2018-02-01
Full Text Available Hyperspectral imaging (HSI is a non-invasive optical imaging modality that shows the potential to aid pathologists in breast cancer diagnoses cases. In this study, breast cancer tissues from different patients were imaged by a hyperspectral system to detect spectral differences between normal and breast cancer tissues. Tissue samples mounted on slides were identified from 10 different patients. Samples from each patient included both normal and ductal carcinoma tissue, both stained with hematoxylin and eosin stain and unstained. Slides were imaged using a snapshot HSI system, and the spectral reflectance differences were evaluated. Analysis of the spectral reflectance values indicated that wavelengths near 550 nm showed the best differentiation between tissue types. This information was used to train image processing algorithms using supervised and unsupervised data. The K-means method was applied to the hyperspectral data cubes, and successfully detected spectral tissue differences with sensitivity of 85.45%, and specificity of 94.64% with true negative rate of 95.8%, and false positive rate of 4.2%. These results were verified by ground-truth marking of the tissue samples by a pathologist. In the hyperspectral image analysis, the image processing algorithm, K-means, shows the greatest potential for building a semi-automated system that could identify and sort between normal and ductal carcinoma in situ tissues.
Khouj, Yasser; Dawson, Jeremy; Coad, James; Vona-Davis, Linda
2018-01-01
Hyperspectral imaging (HSI) is a non-invasive optical imaging modality that shows the potential to aid pathologists in breast cancer diagnoses cases. In this study, breast cancer tissues from different patients were imaged by a hyperspectral system to detect spectral differences between normal and breast cancer tissues. Tissue samples mounted on slides were identified from 10 different patients. Samples from each patient included both normal and ductal carcinoma tissue, both stained with hematoxylin and eosin stain and unstained. Slides were imaged using a snapshot HSI system, and the spectral reflectance differences were evaluated. Analysis of the spectral reflectance values indicated that wavelengths near 550 nm showed the best differentiation between tissue types. This information was used to train image processing algorithms using supervised and unsupervised data. The K-means method was applied to the hyperspectral data cubes, and successfully detected spectral tissue differences with sensitivity of 85.45%, and specificity of 94.64% with true negative rate of 95.8%, and false positive rate of 4.2%. These results were verified by ground-truth marking of the tissue samples by a pathologist. In the hyperspectral image analysis, the image processing algorithm, K-means, shows the greatest potential for building a semi-automated system that could identify and sort between normal and ductal carcinoma in situ tissues.
Genome-scale cluster analysis of replicated microarrays using shrinkage correlation coefficient.
Yao, Jianchao; Chang, Chunqi; Salmi, Mari L; Hung, Yeung Sam; Loraine, Ann; Roux, Stanley J
2008-06-18
Currently, clustering with some form of correlation coefficient as the gene similarity metric has become a popular method for profiling genomic data. The Pearson correlation coefficient and the standard deviation (SD)-weighted correlation coefficient are the two most widely-used correlations as the similarity metrics in clustering microarray data. However, these two correlations are not optimal for analyzing replicated microarray data generated by most laboratories. An effective correlation coefficient is needed to provide statistically sufficient analysis of replicated microarray data. In this study, we describe a novel correlation coefficient, shrinkage correlation coefficient (SCC), that fully exploits the similarity between the replicated microarray experimental samples. The methodology considers both the number of replicates and the variance within each experimental group in clustering expression data, and provides a robust statistical estimation of the error of replicated microarray data. The value of SCC is revealed by its comparison with two other correlation coefficients that are currently the most widely-used (Pearson correlation coefficient and SD-weighted correlation coefficient) using statistical measures on both synthetic expression data as well as real gene expression data from Saccharomyces cerevisiae. Two leading clustering methods, hierarchical and k-means clustering were applied for the comparison. The comparison indicated that using SCC achieves better clustering performance. Applying SCC-based hierarchical clustering to the replicated microarray data obtained from germinating spores of the fern Ceratopteris richardii, we discovered two clusters of genes with shared expression patterns during spore germination. Functional analysis suggested that some of the genetic mechanisms that control germination in such diverse plant lineages as mosses and angiosperms are also conserved among ferns. This study shows that SCC is an alternative to the Pearson
Factor Analysis for Clustered Observations.
Longford, N. T.; Muthen, B. O.
1992-01-01
A two-level model for factor analysis is defined, and formulas for a scoring algorithm for this model are derived. A simple noniterative method based on decomposition of total sums of the squares and cross-products is discussed and illustrated with simulated data and data from the Second International Mathematics Study. (SLD)
An evaluation of centrality measures used in cluster analysis
Engström, Christopher; Silvestrov, Sergei
2014-12-01
Clustering of data into groups of similar objects plays an important part when analysing many types of data, especially when the datasets are large as they often are in for example bioinformatics, social networks and computational linguistics. Many clustering algorithms such as K-means and some types of hierarchical clustering need a number of centroids representing the 'center' of the clusters. The choice of centroids for the initial clusters often plays an important role in the quality of the clusters. Since a data point with a high centrality supposedly lies close to the 'center' of some cluster, this can be used to assign centroids rather than through some other method such as picking them at random. Some work have been done to evaluate the use of centrality measures such as degree, betweenness and eigenvector centrality in clustering algorithms. The aim of this article is to compare and evaluate the usefulness of a number of common centrality measures such as the above mentioned and others such as PageRank and related measures.
Particle Control in Phase Space by Global K-Means Clustering
DEFF Research Database (Denmark)
Frederiksen, Jacob Trier; Lapenta, G.; Pessah, M. E.
2015-01-01
We devise and explore an iterative optimization procedure for controlling particle populations in particle-in-cell (PIC) codes via merging and splitting of computational macro-particles. Our approach, is to compute an optimal representation of the global particle phase space structure while decre...
Parallel k-Means Clustering for Quantitative Ecoregion Delineation Using Large Data Sets
Jitendra Kumar; Richard T. Mills; Forrest M Hoffman; William W Hargrove
2011-01-01
Identification of geographic ecoregions has long been of interest to environmental scientists and ecologists for identifying regions of similar ecological and environmental conditions. Such classifications are important for predicting suitable species ranges, for stratification of ecological samples, and to help prioritize habitat preservation and remediation efforts....
Implementasi KD-Tree K-Means Clustering Untuk Klasterisasi Dokumen
Gosno, Eric Budiman; Arieshanti, Isye; Soelaiman, Rully
2013-01-01
Klasterisasi dokumen adalah suatu proses pengelompokan dokumen secara otomatis dan unsupervised. Klasterisasi dokumen merupakan permasalahan yang sering ditemui dalam berbagai bidang seperti text mining dan sistem temu kembali informasi. Metode klasterisasi dokumen yang memiliki akurasi dan efisiensi waktu yang tinggi sangat diperlukan untuk meningkatkan hasil pada mesin pencari web, dan untuk proses filtering. Salah satu metode klasterisasi yang telah dikenal dan diaplikasikan dalam klaster...
Comparison of k-means related clustering methods for nuclear medicine images segmentation
Borys, Damian; Bzowski, Pawel; Danch-Wierzchowska, Marta; Psiuk-Maksymowicz, Krzysztof
2017-03-01
In this paper, we evaluate the performance of SURF descriptor for high resolution satellite imagery (HRSI) retrieval through a BoVW model on a land-use/land-cover (LULC) dataset. Local feature approaches such as SIFT and SURF descriptors can deal with a large variation of scale, rotation and illumination of the images, providing, therefore, a better discriminative power and retrieval efficiency than global features, especially for HRSI which contain a great range of objects and spatial patterns. Moreover, we combine SURF and color features to improve the retrieval accuracy, and we propose to learn a category-specific dictionary for each image category which results in a more discriminative image representation and boosts the image retrieval performance.
Cluster analysis for determining distribution center location
Lestari Widaningrum, Dyah; Andika, Aditya; Murphiyanto, Richard Dimas Julian
2017-12-01
Determination of distribution facilities is highly important to survive in the high level of competition in today’s business world. Companies can operate multiple distribution centers to mitigate supply chain risk. Thus, new problems arise, namely how many and where the facilities should be provided. This study examines a fast-food restaurant brand, which located in the Greater Jakarta. This brand is included in the category of top 5 fast food restaurant chain based on retail sales. There were three stages in this study, compiling spatial data, cluster analysis, and network analysis. Cluster analysis results are used to consider the location of the additional distribution center. Network analysis results show a more efficient process referring to a shorter distance to the distribution process.
Wang, Liansheng; Li, Shusheng; Chen, Rongzhen; Liu, Sze-Yu; Chen, Jyh-Cheng
2017-04-01
Accurate classification of different anatomical structures of teeth from medical images provides crucial information for the stress analysis in dentistry. Usually, the anatomical structures of teeth are manually labeled by experienced clinical doctors, which is time consuming. However, automatic segmentation and classification is a challenging task because the anatomical structures and surroundings of the tooth in medical images are rather complex. Therefore, in this paper, we propose an effective framework which is designed to segment the tooth with a Selective Binary and Gaussian Filtering Regularized Level Set (GFRLS) method improved by fully utilizing 3 dimensional (3D) information, and classify the tooth by employing unsupervised learning i.e., k-means++ method. In order to evaluate the proposed method, the experiments are conducted on the sufficient and extensive datasets of mandibular molars. The experimental results show that our method can achieve higher accuracy and robustness compared to other three clustering methods. Copyright © 2016 Elsevier Ltd. All rights reserved.
Electricity Consumption Clustering Using Smart Meter Data
Directory of Open Access Journals (Sweden)
Alexander Tureczek
2018-04-01
Full Text Available Electricity smart meter consumption data is enabling utilities to analyze consumption information at unprecedented granularity. Much focus has been directed towards consumption clustering for diversifying tariffs; through modern clustering methods, cluster analyses have been performed. However, the clusters developed exhibit a large variation with resulting shadow clusters, making it impossible to truly identify the individual clusters. Using clearly defined dwelling types, this paper will present methods to improve clustering by harvesting inherent structure from the smart meter data. This paper clusters domestic electricity consumption using smart meter data from the Danish city of Esbjerg. Methods from time series analysis and wavelets are applied to enable the K-Means clustering method to account for autocorrelation in data and thereby improve the clustering performance. The results show the importance of data knowledge and we identify sub-clusters of consumption within the dwelling types and enable K-Means to produce satisfactory clustering by accounting for a temporal component. Furthermore our study shows that careful preprocessing of the data to account for intrinsic structure enables better clustering performance by the K-Means method.
2014-01-01
Background There are many methodological challenges in the conduct and analysis of cluster randomised controlled trials, but one that has received little attention is that of post-randomisation changes to cluster composition. To illustrate this, we focus on the issue of cluster merging, considering the impact on the design, analysis and interpretation of trial outcomes. Methods We explored the effects of merging clusters on study power using standard methods of power calculation. We assessed the potential impacts on study findings of both homogeneous cluster merges (involving clusters randomised to the same arm of a trial) and heterogeneous merges (involving clusters randomised to different arms of a trial) by simulation. To determine the impact on bias and precision of treatment effect estimates, we applied standard methods of analysis to different populations under analysis. Results Cluster merging produced a systematic reduction in study power. This effect depended on the number of merges and was most pronounced when variability in cluster size was at its greatest. Simulations demonstrate that the impact on analysis was minimal when cluster merges were homogeneous, with impact on study power being balanced by a change in observed intracluster correlation coefficient (ICC). We found a decrease in study power when cluster merges were heterogeneous, and the estimate of treatment effect was attenuated. Conclusions Examples of cluster merges found in previously published reports of cluster randomised trials were typically homogeneous rather than heterogeneous. Simulations demonstrated that trial findings in such cases would be unbiased. However, simulations also showed that any heterogeneous cluster merges would introduce bias that would be hard to quantify, as well as having negative impacts on the precision of estimates obtained. Further methodological development is warranted to better determine how to analyse such trials appropriately. Interim recommendations
Text Mining Untuk Analisis Sentimen Review Film Menggunakan Algoritma K-Means
Directory of Open Access Journals (Sweden)
Setyo Budi
2017-02-01
Full Text Available Kemudahan manusia didalam menggunakan website mengakibatkan bertambahnya dokumen teks yang berupa pendapat dan informasi. Dalam waktu yang lama dokumen teks akan bertambah besar. Text mining merupakan salah satu teknik yang digunakan untuk menggali kumpulan dokumen text sehingga dapat diambil intisarinya. Ada beberapa algoritma yang di gunakan untuk penggalian dokumen untuk analisis sentimen, salah satunya adalah K-Means. Didalam penelitian ini algoritma yang digunakan adalah K-Means. Hasil penelitian menunjukkan bahwa akurasi K-Means dengan dataset digunakan 300 positif dan 300 negatif akurasinya 57.83%, 700 dokumen positif dan 700 negatif akurasinya 56.71%%, 1000 dokumen positif dan 1000 negatif akurasinya 50.40%%. Dari hasil pengujian disimpulkan bahwa semakin besar dataset yang digunakan semakin rendah akurasi K-Means. Kata Kunci : Text Mining, Analisis Sentimen, K-Means, Review Film
Cluster Analysis on Longitudinal Data of Patients with Adult-Onset Asthma.
Ilmarinen, Pinja; Tuomisto, Leena E; Niemelä, Onni; Tommola, Minna; Haanpää, Jussi; Kankaanranta, Hannu
Previous cluster analyses on asthma are based on cross-sectional data. To identify phenotypes of adult-onset asthma by using data from baseline (diagnostic) and 12-year follow-up visits. The Seinäjoki Adult Asthma Study is a 12-year follow-up study of patients with new-onset adult asthma. K-means cluster analysis was performed by using variables from baseline and follow-up visits on 171 patients to identify phenotypes. Five clusters were identified. Patients in cluster 1 (n = 38) were predominantly nonatopic males with moderate smoking history at baseline. At follow-up, 40% of these patients had developed persistent obstruction but the number of patients with uncontrolled asthma (5%) and rhinitis (10%) was the lowest. Cluster 2 (n = 19) was characterized by older men with heavy smoking history, poor lung function, and persistent obstruction at baseline. At follow-up, these patients were mostly uncontrolled (84%) despite daily use of inhaled corticosteroid (ICS) with add-on therapy. Cluster 3 (n = 50) consisted mostly of nonsmoking females with good lung function at diagnosis/follow-up and well-controlled/partially controlled asthma at follow-up. Cluster 4 (n = 25) had obese and symptomatic patients at baseline/follow-up. At follow-up, these patients had several comorbidities (40% psychiatric disease) and were treated daily with ICS and add-on therapy. Patients in cluster 5 (n = 39) were mostly atopic and had the earliest onset of asthma, the highest blood eosinophils, and FEV 1 reversibility at diagnosis. At follow-up, these patients used the lowest ICS dose but 56% were well controlled. Results can be used to predict outcomes of patients with adult-onset asthma and to aid in development of personalized therapy (NCT02733016 at ClinicalTrials.gov). Copyright © 2017 The Authors. Published by Elsevier Inc. All rights reserved.
MANNER OF STOCKS SORTING USING CLUSTER ANALYSIS METHODS
Directory of Open Access Journals (Sweden)
Jana Halčinová
2014-06-01
Full Text Available The aim of the present article is to show the possibility of using the methods of cluster analysis in classification of stocks of finished products. Cluster analysis creates groups (clusters of finished products according to similarity in demand i.e. customer requirements for each product. Manner stocks sorting of finished products by clusters is described a practical example. The resultants clusters are incorporated into the draft layout of the distribution warehouse.
Advanced analysis of forest fire clustering
Kanevski, Mikhail; Pereira, Mario; Golay, Jean
2017-04-01
Analysis of point pattern clustering is an important topic in spatial statistics and for many applications: biodiversity, epidemiology, natural hazards, geomarketing, etc. There are several fundamental approaches used to quantify spatial data clustering using topological, statistical and fractal measures. In the present research, the recently introduced multi-point Morisita index (mMI) is applied to study the spatial clustering of forest fires in Portugal. The data set consists of more than 30000 fire events covering the time period from 1975 to 2013. The distribution of forest fires is very complex and highly variable in space. mMI is a multi-point extension of the classical two-point Morisita index. In essence, mMI is estimated by covering the region under study by a grid and by computing how many times more likely it is that m points selected at random will be from the same grid cell than it would be in the case of a complete random Poisson process. By changing the number of grid cells (size of the grid cells), mMI characterizes the scaling properties of spatial clustering. From mMI, the data intrinsic dimension (fractal dimension) of the point distribution can be estimated as well. In this study, the mMI of forest fires is compared with the mMI of random patterns (RPs) generated within the validity domain defined as the forest area of Portugal. It turns out that the forest fires are highly clustered inside the validity domain in comparison with the RPs. Moreover, they demonstrate different scaling properties at different spatial scales. The results obtained from the mMI analysis are also compared with those of fractal measures of clustering - box counting and sand box counting approaches. REFERENCES Golay J., Kanevski M., Vega Orozco C., Leuenberger M., 2014: The multipoint Morisita index for the analysis of spatial patterns. Physica A, 406, 191-202. Golay J., Kanevski M. 2015: A new estimator of intrinsic dimension based on the multipoint Morisita index
Cluster Analysis in Rapeseed (Brassica Napus L.)
International Nuclear Information System (INIS)
Mahasi, J.M
2002-01-01
With widening edible deficit, Kenya has become increasingly dependent on imported edible oils. Many oilseed crops (e.g. sunflower, soya beans, rapeseed/mustard, sesame, groundnuts etc) can be grown in Kenya. But oilseed rape is preferred because it very high yielding (1.5 tons-4.0 tons/ha) with oil content of 42-46%. Other uses include fitting in various cropping systems as; relay/inter crops, rotational crops, trap crops and fodder. It is soft seeded hence oil extraction is relatively easy. The meal is high in protein and very useful in livestock supplementation. Rapeseed can be straight combined using adjusted wheat combines. The priority is to expand domestic oilseed production, hence the need to introduce improved rapeseed germplasm from other countries. The success of any crop improvement programme depends on the extent of genetic diversity in the material. Hence, it is essential to understand the adaptation of introduced genotypes and the similarities if any among them. Evaluation trials were carried out on 17 rapeseed genotypes (nine Canadian origin and eight of European origin) grown at 4 locations namely Endebess, Njoro, Timau and Mau Narok in three years (1992, 1993 and 1994). Results for 1993 were discarded due to severe drought. An analysis of variance was carried out only on seed yields and the treatments were found to be significantly different. Cluster analysis was then carried out on mean seed yields and based on this analysis; only one major group exists within the material. In 1992, varieties 2,3,8 and 9 didn't fall in the same cluster as the rest. Variety 8 was the only one not classified with the rest of the Canadian varieties. Three European varieties (2,3 and 9) were however not classified with the others. In 1994, varieties 10 and 6 didn't fall in the major cluster. Of these two, variety 10 is of Canadian origin. Varieties were more similar in 1994 than 1992 due to favorable weather. It is evident that, genotypes from different geographical
Robust multi-scale clustering of large DNA microarray datasets with the consensus algorithm
DEFF Research Database (Denmark)
Grotkjær, Thomas; Winther, Ole; Regenberg, Birgitte
2006-01-01
Motivation: Hierarchical and relocation clustering (e.g. K-means and self-organizing maps) have been successful tools in the display and analysis of whole genome DNA microarray expression data. However, the results of hierarchical clustering are sensitive to outliers, and most relocation methods...... analysis by collecting re-occurring clustering patterns in a co-occurrence matrix. The results show that consensus clustering obtained from clustering multiple times with Variational Bayes Mixtures of Gaussians or K-means significantly reduces the classification error rate for a simulated dataset...
Wagstaff, Kiri L.
2012-03-01
particular application involves considerations of the kind of data being analyzed, algorithm runtime efficiency, and how much prior knowledge is available about the problem domain, which can dictate the nature of clusters sought. Fundamentally, the clustering method and its representations of clusters carries with it a definition of what a cluster is, and it is important that this be aligned with the analysis goals for the problem at hand. In this chapter, I emphasize this point by identifying for each algorithm the cluster representation as a model, m_j , even for algorithms that are not typically thought of as creating a “model.” This chapter surveys a basic collection of clustering methods useful to any practitioner who is interested in applying clustering to a new data set. The algorithms include k-means (Section 25.2), EM (Section 25.3), agglomerative (Section 25.4), and spectral (Section 25.5) clustering, with side mentions of variants such as kernel k-means and divisive clustering. The chapter also discusses each algorithm’s strengths and limitations and provides pointers to additional in-depth reading for each subject. Section 25.6 discusses methods for incorporating domain knowledge into the clustering process. This chapter concludes with a brief survey of interesting applications of clustering methods to astronomy data (Section 25.7). The chapter begins with k-means because it is both generally accessible and so widely used that understanding it can be considered a necessary prerequisite for further work in the field. EM can be viewed as a more sophisticated version of k-means that uses a generative model for each cluster and probabilistic item assignments. Agglomerative clustering is the most basic form of hierarchical clustering and provides a basis for further exploration of algorithms in that vein. Spectral clustering permits a departure from feature-vector-based clustering and can operate on data sets instead represented as affinity, or similarity
Tweets clustering using latent semantic analysis
Rasidi, Norsuhaili Mahamed; Bakar, Sakhinah Abu; Razak, Fatimah Abdul
2017-04-01
Social media are becoming overloaded with information due to the increasing number of information feeds. Unlike other social media, Twitter users are allowed to broadcast a short message called as `tweet". In this study, we extract tweets related to MH370 for certain of time. In this paper, we present overview of our approach for tweets clustering to analyze the users' responses toward tragedy of MH370. The tweets were clustered based on the frequency of terms obtained from the classification process. The method we used for the text classification is Latent Semantic Analysis. As a result, there are two types of tweets that response to MH370 tragedy which is emotional and non-emotional. We show some of our initial results to demonstrate the effectiveness of our approach.
Dynamic Trajectory Extraction from Stereo Vision Using Fuzzy Clustering
Onishi, Masaki; Yoda, Ikushi
In recent years, many human tracking researches have been proposed in order to analyze human dynamic trajectory. These researches are general technology applicable to various fields, such as customer purchase analysis in a shopping environment and safety control in a (railroad) crossing. In this paper, we present a new approach for tracking human positions by stereo image. We use the framework of two-stepped clustering with k-means method and fuzzy clustering to detect human regions. In the initial clustering, k-means method makes middle clusters from objective features extracted by stereo vision at high speed. In the last clustering, c-means fuzzy method cluster middle clusters based on attributes into human regions. Our proposed method can be correctly clustered by expressing ambiguity using fuzzy clustering, even when many people are close to each other. The validity of our technique was evaluated with the experiment of trajectories extraction of doctors and nurses in an emergency room of a hospital.
CytoCluster: A Cytoscape Plugin for Cluster Analysis and Visualization of Biological Networks.
Li, Min; Li, Dongyan; Tang, Yu; Wu, Fangxiang; Wang, Jianxin
2017-08-31
Nowadays, cluster analysis of biological networks has become one of the most important approaches to identifying functional modules as well as predicting protein complexes and network biomarkers. Furthermore, the visualization of clustering results is crucial to display the structure of biological networks. Here we present CytoCluster, a cytoscape plugin integrating six clustering algorithms, HC-PIN (Hierarchical Clustering algorithm in Protein Interaction Networks), OH-PIN (identifying Overlapping and Hierarchical modules in Protein Interaction Networks), IPCA (Identifying Protein Complex Algorithm), ClusterONE (Clustering with Overlapping Neighborhood Expansion), DCU (Detecting Complexes based on Uncertain graph model), IPC-MCE (Identifying Protein Complexes based on Maximal Complex Extension), and BinGO (the Biological networks Gene Ontology) function. Users can select different clustering algorithms according to their requirements. The main function of these six clustering algorithms is to detect protein complexes or functional modules. In addition, BinGO is used to determine which Gene Ontology (GO) categories are statistically overrepresented in a set of genes or a subgraph of a biological network. CytoCluster can be easily expanded, so that more clustering algorithms and functions can be added to this plugin. Since it was created in July 2013, CytoCluster has been downloaded more than 9700 times in the Cytoscape App store and has already been applied to the analysis of different biological networks. CytoCluster is available from http://apps.cytoscape.org/apps/cytocluster.
Developing a Clustering-Based Empirical Bayes Analysis Method for Hotspot Identification
Directory of Open Access Journals (Sweden)
Yajie Zou
2017-01-01
Full Text Available Hotspot identification (HSID is a critical part of network-wide safety evaluations. Typical methods for ranking sites are often rooted in using the Empirical Bayes (EB method to estimate safety from both observed crash records and predicted crash frequency based on similar sites. The performance of the EB method is highly related to the selection of a reference group of sites (i.e., roadway segments or intersections similar to the target site from which safety performance functions (SPF used to predict crash frequency will be developed. As crash data often contain underlying heterogeneity that, in essence, can make them appear to be generated from distinct subpopulations, methods are needed to select similar sites in a principled manner. To overcome this possible heterogeneity problem, EB-based HSID methods that use common clustering methodologies (e.g., mixture models, K-means, and hierarchical clustering to select “similar” sites for building SPFs are developed. Performance of the clustering-based EB methods is then compared using real crash data. Here, HSID results, when computed on Texas undivided rural highway cash data, suggest that all three clustering-based EB analysis methods are preferred over the conventional statistical methods. Thus, properly classifying the road segments for heterogeneous crash data can further improve HSID accuracy.
Clustering analysis of line indices for LAMOST spectra with AstroStat
Chen, Shu-Xin; Sun, Wei-Min; Yan, Qi
2018-06-01
The application of data mining in astronomical surveys, such as the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST) survey, provides an effective approach to automatically analyze a large amount of complex survey data. Unsupervised clustering could help astronomers find the associations and outliers in a big data set. In this paper, we employ the k-means method to perform clustering for the line index of LAMOST spectra with the powerful software AstroStat. Implementing the line index approach for analyzing astronomical spectra is an effective way to extract spectral features for low resolution spectra, which can represent the main spectral characteristics of stars. A total of 144 340 line indices for A type stars is analyzed through calculating their intra and inter distances between pairs of stars. For intra distance, we use the definition of Mahalanobis distance to explore the degree of clustering for each class, while for outlier detection, we define a local outlier factor for each spectrum. AstroStat furnishes a set of visualization tools for illustrating the analysis results. Checking the spectra detected as outliers, we find that most of them are problematic data and only a few correspond to rare astronomical objects. We show two examples of these outliers, a spectrum with abnormal continuumand a spectrum with emission lines. Our work demonstrates that line index clustering is a good method for examining data quality and identifying rare objects.
Multisource Images Analysis Using Collaborative Clustering
Directory of Open Access Journals (Sweden)
Pierre Gançarski
2008-04-01
Full Text Available The development of very high-resolution (VHR satellite imagery has produced a huge amount of data. The multiplication of satellites which embed different types of sensors provides a lot of heterogeneous images. Consequently, the image analyst has often many different images available, representing the same area of the Earth surface. These images can be from different dates, produced by different sensors, or even at different resolutions. The lack of machine learning tools using all these representations in an overall process constraints to a sequential analysis of these various images. In order to use all the information available simultaneously, we propose a framework where different algorithms can use different views of the scene. Each one works on a different remotely sensed image and, thus, produces different and useful information. These algorithms work together in a collaborative way through an automatic and mutual refinement of their results, so that all the results have almost the same number of clusters, which are statistically similar. Finally, a unique result is produced, representing a consensus among the information obtained by each clustering method on its own image. The unified result and the complementarity of the single results (i.e., the agreement between the clustering methods as well as the disagreement lead to a better understanding of the scene. The experiments carried out on multispectral remote sensing images have shown that this method is efficient to extract relevant information and to improve the scene understanding.
Clustering User Behavior in Scientific Collections
Blixhavn, Øystein Hoel
2014-01-01
This master thesis looks at how clustering techniques can be appliedto a collection of scientific documents. Approximately one year of serverlogs from the CERN Document Server (CDS) are analyzed and preprocessed.Based on the findings of this analysis, and a review of thecurrent state of the art, three different clustering methods are selectedfor further work: Simple k-Means, Hierarchical Agglomerative Clustering(HAC) and Graph Partitioning. In addition, a custom, agglomerativeclustering algor...
Text Mining Untuk Analisis Sentimen Review Film Menggunakan Algoritma K-Means
Setyo Budi
2017-01-01
Kemudahan manusia didalam menggunakan website mengakibatkan bertambahnya dokumen teks yang berupa pendapat dan informasi. Dalam waktu yang lama dokumen teks akan bertambah besar. Text mining merupakan salah satu teknik yang digunakan untuk menggali kumpulan dokumen text sehingga dapat diambil intisarinya. Ada beberapa algoritma yang di gunakan untuk penggalian dokumen untuk analisis sentimen, salah satunya adalah K-Means. Didalam penelitian ini algoritma yang digunakan adalah K-Means. Hasil p...
Constructing storyboards based on hierarchical clustering analysis
Hasebe, Satoshi; Sami, Mustafa M.; Muramatsu, Shogo; Kikuchi, Hisakazu
2005-07-01
There are growing needs for quick preview of video contents for the purpose of improving accessibility of video archives as well as reducing network traffics. In this paper, a storyboard that contains a user-specified number of keyframes is produced from a given video sequence. It is based on hierarchical cluster analysis of feature vectors that are derived from wavelet coefficients of video frames. Consistent use of extracted feature vectors is the key to avoid a repetition of computationally-intensive parsing of the same video sequence. Experimental results suggest that a significant reduction in computational time is gained by this strategy.
A new methodology to study customer electrocardiogram using RFM analysis and clustering
Directory of Open Access Journals (Sweden)
Mohammad Reza Gholamian
2011-04-01
Full Text Available One of the primary issues on marketing planning is to know the customer's behavioral trends. A customer's purchasing interest may fluctuate for different reasons and it is important to find the declining or increasing trends whenever they happen. It is important to study these fluctuations to improve customer relationships. There are different methods to increase the customer's willingness such as planning good promotions, an increase on advertisement, etc. This paper proposes a new methodology to measure customer's behavioral trends called customer electrocardiogram. The proposed model of this paper uses K-means clustering method with RFM analysis to study customer's fluctuations over different time frames. We also apply the proposed electrocardiogram methodology for a real-world case study of food industry and the results are discussed in details.
EU Travel and Tourism Industry - A Cluster Analysis of Impact and Competitiveness
Directory of Open Access Journals (Sweden)
DANIEL BULIN
2014-05-01
Full Text Available The tourism industry has known a sustained growth in recent decades, this sector taking advantage of the capacity to generate added value regardless of the type of capital input. The impact of tourism on the economy is indisputable, but the efficiency and the competitiveness provide a sustainable development of this industry. The EU enlargement, geographical and numerical, provides both-a diversity of tourism destinations and an opportunity for growth, considering widening of single market. This paper aims to assess tourism in the European Union, considering the impact and value of the tourism multiplier effect in economy, respectively efficiency and competitiveness of tourism. This paper proposes a classification of EU countries based on cluster analysis, using K-means algorithm.
Using Cluster Analysis and ICP-MS to Identify Groups of Ecstasy Tablets in Sao Paulo State, Brazil.
Maione, Camila; de Oliveira Souza, Vanessa Cristina; Togni, Loraine Rezende; da Costa, José Luiz; Campiglia, Andres Dobal; Barbosa, Fernando; Barbosa, Rommel Melgaço
2017-11-01
The variations found in the elemental composition in ecstasy samples result in spectral profiles with useful information for data analysis, and cluster analysis of these profiles can help uncover different categories of the drug. We provide a cluster analysis of ecstasy tablets based on their elemental composition. Twenty-five elements were determined by ICP-MS in tablets apprehended by Sao Paulo's State Police, Brazil. We employ the K-means clustering algorithm along with C4.5 decision tree to help us interpret the clustering results. We found a better number of two clusters within the data, which can refer to the approximated number of sources of the drug which supply the cities of seizures. The C4.5 model was capable of differentiating the ecstasy samples from the two clusters with high prediction accuracy using the leave-one-out cross-validation. The model used only Nd, Ni, and Pb concentration values in the classification of the samples. © 2017 American Academy of Forensic Sciences.
Cluster Analysis of Maize Inbred Lines
Directory of Open Access Journals (Sweden)
Jiban Shrestha
2016-12-01
Full Text Available The determination of diversity among inbred lines is important for heterosis breeding. Sixty maize inbred lines were evaluated for their eight agro morphological traits during winter season of 2011 to analyze their genetic diversity. Clustering was done by average linkage method. The inbred lines were grouped into six clusters. Inbred lines grouped into Clusters II had taller plants with maximum number of leaves. The cluster III was characterized with shorter plants with minimum number of leaves. The inbred lines categorized into cluster V had early flowering whereas the group into cluster VI had late flowering time. The inbred lines grouped into the cluster III were characterized by higher value of anthesis silking interval (ASI and those of cluster VI had lower value of ASI. These results showed that the inbred lines having widely divergent clusters can be utilized in hybrid breeding programme.
Directory of Open Access Journals (Sweden)
Byungwan Jo
2017-03-01
Full Text Available In the present case study, the use of an advanced, efficient and low-cost technique for monitoring an urban stream was reported. Physicochemical parameters (PcPs of Jungnangcheon stream (Seoul, South Korea were assessed using an Internet of Things (IoT platform. Temperature, dissolved oxygen (DO, and pH parameters were monitored for the three summer months and the first fall month at a fixed location. Analysis was performed using clustering techniques (CTs, such as K-means clustering, agglomerative hierarchical clustering (AHC, and density-based spatial clustering of applications with noise (DBSCAN. An IoT-based Arduino sensor module (ASM network with a 99.99% efficient communication platform was developed to allow collection of stream data with user-friendly software and hardware and facilitated data analysis by interested individuals using their smartphones. Clustering was used to formulate relationships among physicochemical parameters. K-means clustering was used to identify natural clusters using the silhouette coefficient based on cluster compactness and looseness. AHC grouped all data into two clusters as well as temperature, DO and pH into four, eight, and four clusters, respectively. DBSCAN analysis was also performed to evaluate yearly variations in physicochemical parameters. Noise points (NOISE of temperature in 2016 were border points (ƥ, whereas in 2014 and 2015 they remained core points (ɋ, indicating a trend toward increasing stream temperature. We found the stream parameters were within the permissible limits set by the Water Quality Standards for River Water, South Korea.
Wu, Hsin-Hung; Lin, Shih-Yen; Liu, Chih-Wei
2014-01-01
This study combines cluster analysis and LRFM (length, recency, frequency, and monetary) model in a pediatric dental clinic in Taiwan to analyze patients' values. A two-stage approach by self-organizing maps and K-means method is applied to segment 1,462 patients into twelve clusters. The average values of L, R, and F excluding monetary covered by national health insurance program are computed for each cluster. In addition, customer value matrix is used to analyze customer values of twelve clusters in terms of frequency and monetary. Customer relationship matrix considering length and recency is also applied to classify different types of customers from these twelve clusters. The results show that three clusters can be classified into loyal patients with L, R, and F values greater than the respective average L, R, and F values, while three clusters can be viewed as lost patients without any variable above the average values of L, R, and F. When different types of patients are identified, marketing strategies can be designed to meet different patients' needs.
Lin, Shih-Yen; Liu, Chih-Wei
2014-01-01
This study combines cluster analysis and LRFM (length, recency, frequency, and monetary) model in a pediatric dental clinic in Taiwan to analyze patients' values. A two-stage approach by self-organizing maps and K-means method is applied to segment 1,462 patients into twelve clusters. The average values of L, R, and F excluding monetary covered by national health insurance program are computed for each cluster. In addition, customer value matrix is used to analyze customer values of twelve clusters in terms of frequency and monetary. Customer relationship matrix considering length and recency is also applied to classify different types of customers from these twelve clusters. The results show that three clusters can be classified into loyal patients with L, R, and F values greater than the respective average L, R, and F values, while three clusters can be viewed as lost patients without any variable above the average values of L, R, and F. When different types of patients are identified, marketing strategies can be designed to meet different patients' needs. PMID:25045741
Directory of Open Access Journals (Sweden)
Hsin-Hung Wu
2014-01-01
Full Text Available This study combines cluster analysis and LRFM (length, recency, frequency, and monetary model in a pediatric dental clinic in Taiwan to analyze patients’ values. A two-stage approach by self-organizing maps and K-means method is applied to segment 1,462 patients into twelve clusters. The average values of L, R, and F excluding monetary covered by national health insurance program are computed for each cluster. In addition, customer value matrix is used to analyze customer values of twelve clusters in terms of frequency and monetary. Customer relationship matrix considering length and recency is also applied to classify different types of customers from these twelve clusters. The results show that three clusters can be classified into loyal patients with L, R, and F values greater than the respective average L, R, and F values, while three clusters can be viewed as lost patients without any variable above the average values of L, R, and F. When different types of patients are identified, marketing strategies can be designed to meet different patients’ needs.
Shan, Jiajia; Wang, Xue; Zhou, Hao; Han, Shuqing; Riza, Dimas Firmanda Al; Kondo, Naoshi
2018-04-01
Synchronous fluorescence spectra, combined with multivariate analysis were used to predict flavonoids content in green tea rapidly and nondestructively. This paper presented a new and efficient spectral intervals selection method called clustering based partial least square (CL-PLS), which selected informative wavelengths by combining clustering concept and partial least square (PLS) methods to improve models’ performance by synchronous fluorescence spectra. The fluorescence spectra of tea samples were obtained and k-means and kohonen-self organizing map clustering algorithms were carried out to cluster full spectra into several clusters, and sub-PLS regression model was developed on each cluster. Finally, CL-PLS models consisting of gradually selected clusters were built. Correlation coefficient (R) was used to evaluate the effect on prediction performance of PLS models. In addition, variable influence on projection partial least square (VIP-PLS), selectivity ratio partial least square (SR-PLS), interval partial least square (iPLS) models and full spectra PLS model were investigated and the results were compared. The results showed that CL-PLS presented the best result for flavonoids prediction using synchronous fluorescence spectra.
Hearty, Aine P; Gibney, Michael J
2009-02-01
The aims of the present study were to examine and compare dietary patterns in adults using cluster and factor analyses and to examine the format of the dietary variables on the pattern solutions (i.e. expressed as grams/day (g/d) of each food group or as the percentage contribution to total energy intake). Food intake data were derived from the North/South Ireland Food Consumption Survey 1997-9, which was a randomised cross-sectional study of 7 d recorded food and nutrient intakes of a representative sample of 1379 Irish adults aged 18-64 years. Cluster analysis was performed using the k-means algorithm and principal component analysis (PCA) was used to extract dietary factors. Food data were reduced to thirty-three food groups. For cluster analysis, the most suitable format of the food-group variable was found to be the percentage contribution to energy intake, which produced six clusters: 'Traditional Irish'; 'Continental'; 'Unhealthy foods'; 'Light-meal foods & low-fat milk'; 'Healthy foods'; 'Wholemeal bread & desserts'. For PCA, food groups in the format of g/d were found to be the most suitable format, and this revealed four dietary patterns: 'Unhealthy foods & high alcohol'; 'Traditional Irish'; 'Healthy foods'; 'Sweet convenience foods & low alcohol'. In summary, cluster and PCA identified similar dietary patterns when presented with the same dataset. However, the two dietary pattern methods required a different format of the food-group variable, and the most appropriate format of the input variable should be considered in future studies.
Mapping of medicine data with k-means and apriori combinations based on patient diagnosis
Dharshinni, N. P.; Mawengkang, H.; Nasution, M. K. M.
2018-03-01
Medicine is one of the items needed by sick society, the high influence of medicine on service and the economy in hospitals, requires mapping and planning the optimal need for medicines according to the conditions, because 50% -60% of hospital income is sourced from medicine sales. The purpose of this study was to find patterns of doctor’s prescription medicine association with sales data using an apriori algorithm based on data grouping using a k-means algorithm. The results of the experiments show that medicine prescription data with medicine sales have significant differences so that the data can not be used as materials for medicine planning, this is due to some indication of one of the unavailability of medicine caused by mapping inaccuracy so that the planning of medicine requirements is not optimal. The results of this analysis can be used as input materials in decision making, so the planning needs of medicines can be in accordance with the development of patient disease patterns.
Energy Technology Data Exchange (ETDEWEB)
Mills, Richard T [ORNL; Hoffman, Forrest M [ORNL; Kumar, Jitendra [ORNL; HargroveJr., William Walter [USDA Forest Service
2011-01-01
We investigate methods for geospatiotemporal data mining of multi-year land surface phenology data (250 m2 Normalized Difference Vegetation Index (NDVI) values derived from the Moderate Resolution Imaging Spectrometer (MODIS) in this study) for the conterminous United States (CONUS) as part of an early warning system for detecting threats to forest ecosystems. The approaches explored here are based on k-means cluster analysis of this massive data set, which provides a basis for defining the bounds of the expected or normal phenological patterns that indicate healthy vegetation at a given geographic location. We briefly describe the computational approaches we have used to make cluster analysis of such massive data sets feasible, describe approaches we have explored for distinguishing between normal and abnormal phenology, and present some examples in which we have applied these approaches to identify various forest disturbances in the CONUS.
Mathematical classification and clustering
Mirkin, Boris
1996-01-01
I am very happy to have this opportunity to present the work of Boris Mirkin, a distinguished Russian scholar in the areas of data analysis and decision making methodologies. The monograph is devoted entirely to clustering, a discipline dispersed through many theoretical and application areas, from mathematical statistics and combina torial optimization to biology, sociology and organizational structures. It compiles an immense amount of research done to date, including many original Russian de velopments never presented to the international community before (for instance, cluster-by-cluster versions of the K-Means method in Chapter 4 or uniform par titioning in Chapter 5). The author's approach, approximation clustering, allows him both to systematize a great part of the discipline and to develop many in novative methods in the framework of optimization problems. The optimization methods considered are proved to be meaningful in the contexts of data analysis and clustering. The material presented in ...
Cluster analysis of word frequency dynamics
Maslennikova, Yu S.; Bochkarev, V. V.; Belashova, I. A.
2015-01-01
This paper describes the analysis and modelling of word usage frequency time series. During one of previous studies, an assumption was put forward that all word usage frequencies have uniform dynamics approaching the shape of a Gaussian function. This assumption can be checked using the frequency dictionaries of the Google Books Ngram database. This database includes 5.2 million books published between 1500 and 2008. The corpus contains over 500 billion words in American English, British English, French, German, Spanish, Russian, Hebrew, and Chinese. We clustered time series of word usage frequencies using a Kohonen neural network. The similarity between input vectors was estimated using several algorithms. As a result of the neural network training procedure, more than ten different forms of time series were found. They describe the dynamics of word usage frequencies from birth to death of individual words. Different groups of word forms were found to have different dynamics of word usage frequency variations.
Cluster analysis of word frequency dynamics
International Nuclear Information System (INIS)
Maslennikova, Yu S; Bochkarev, V V; Belashova, I A
2015-01-01
This paper describes the analysis and modelling of word usage frequency time series. During one of previous studies, an assumption was put forward that all word usage frequencies have uniform dynamics approaching the shape of a Gaussian function. This assumption can be checked using the frequency dictionaries of the Google Books Ngram database. This database includes 5.2 million books published between 1500 and 2008. The corpus contains over 500 billion words in American English, British English, French, German, Spanish, Russian, Hebrew, and Chinese. We clustered time series of word usage frequencies using a Kohonen neural network. The similarity between input vectors was estimated using several algorithms. As a result of the neural network training procedure, more than ten different forms of time series were found. They describe the dynamics of word usage frequencies from birth to death of individual words. Different groups of word forms were found to have different dynamics of word usage frequency variations
A Preliminary Study Application Clustering System in Acoustic Emission Monitoring
Directory of Open Access Journals (Sweden)
Saiful Bahari Nur Amira Afiza
2017-01-01
Full Text Available Acoustic Emission (AE is a non-destructive testing known as assessment on damage detection in structural engineering. It also can be used to discriminate the different types of damage occurring in a composite materials. The main problem associated with the data analysis is the discrimination between the different AE sources and analysis of the AE signal in order to identify the most critical damage mechanism. Clustering analysis is a technique in which the set of object are assigned to a group called cluster. The objective of the cluster analysis is to separate a set of data into several classes that reflect the internal structure of data. In this paper was used k-means algorithm for partitioned clustering method, numerous effort have been made to improve the performance of application k-means clustering algorithm. This paper presents a current review on application clustering system in Acoustic Emission.
OPTIMALISASI SUPPORT VEKTOR MACHINE (SVM UNTUK KLASIFIKASI TEMA TUGAS AKHIR BERBASIS K-MEANS
Directory of Open Access Journals (Sweden)
Oman Somantri
2017-01-01
Full Text Available The difficulty in determining the classification of students final project theme often experienced by each college. The purpose of this study is to provide a decision support for policy makers in the study program so that each student can be achieved in accordance with their own competence. From the research that has been done text mining algorithms using Support Vector Machine ( SVM and K -Means as the technology used was produced a better accuracy rate with an accuracy rate of 86.21 % when compared to the SVM without K -Means is 85 , 38 %
Coping profiles, perceived stress and health-related behaviors: a cluster analysis approach.
Doron, Julie; Trouillet, Raphael; Maneveau, Anaïs; Ninot, Grégory; Neveu, Dorine
2015-03-01
Using cluster analytical procedure, this study aimed (i) to determine whether people could be differentiated on the basis of coping profiles (or unique combinations of coping strategies); and (ii) to examine the relationships between these profiles and perceived stress and health-related behaviors. A sample of 578 French students (345 females, 233 males; M(age)= 21.78, SD(age)= 2.21) completed the Perceived Stress Scale-14 ( Bruchon-Schweitzer, 2002), the Brief COPE ( Muller and Spitz, 2003) and a series of items measuring health-related behaviors. A two-phased cluster analytic procedure (i.e. hierarchical and non-hierarchical-k-means) was employed to derive clusters of coping strategy profiles. The results yielded four distinctive coping profiles: High Copers, Adaptive Copers, Avoidant Copers and Low Copers. The results showed that clusters differed significantly in perceived stress and health-related behaviors. High Copers and Avoidant Copers displayed higher levels of perceived stress and engaged more in unhealthy behavior, compared with Adaptive Copers and Low Copers who reported lower levels of stress and engaged more in healthy behaviors. These findings suggested that individuals' relative reliance on some strategies and de-emphasis on others may be a more advantageous way of understanding the manner in which individuals cope with stress. Therefore, cluster analysis approach may provide an advantage over more traditional statistical techniques by identifying distinct coping profiles that might best benefit from interventions. Future research should consider coping profiles to provide a deeper understanding of the relationships between coping strategies and health outcomes and to identify risk groups. © The Author 2014. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.
International Nuclear Information System (INIS)
Azimi, R.; Ghayekhloo, M.; Ghofrani, M.
2016-01-01
Highlights: • A novel clustering approach is proposed based on the data transformation approach. • A novel cluster selection method based on correlation analysis is presented. • The proposed hybrid clustering approach leads to deep learning for MLPNN. • A hybrid forecasting method is developed to predict solar radiations. • The evaluation results show superior performance of the proposed forecasting model. - Abstract: Accurate forecasting of renewable energy sources plays a key role in their integration into the grid. This paper proposes a hybrid solar irradiance forecasting framework using a Transformation based K-means algorithm, named TB K-means, to increase the forecast accuracy. The proposed clustering method is a combination of a new initialization technique, K-means algorithm and a new gradual data transformation approach. Unlike the other K-means based clustering methods which are not capable of providing a fixed and definitive answer due to the selection of different cluster centroids for each run, the proposed clustering provides constant results for different runs of the algorithm. The proposed clustering is combined with a time-series analysis, a novel cluster selection algorithm and a multilayer perceptron neural network (MLPNN) to develop the hybrid solar radiation forecasting method for different time horizons (1 h ahead, 2 h ahead, …, 48 h ahead). The performance of the proposed TB K-means clustering is evaluated using several different datasets and compared with different variants of K-means algorithm. Solar datasets with different solar radiation characteristics are also used to determine the accuracy and processing speed of the developed forecasting method with the proposed TB K-means and other clustering techniques. The results of direct comparison with other well-established forecasting models demonstrate the superior performance of the proposed hybrid forecasting method. Furthermore, a comparative analysis with the benchmark solar
An analysis of hospital brand mark clusters.
Vollmers, Stacy M; Miller, Darryl W; Kilic, Ozcan
2010-07-01
This study analyzed brand mark clusters (i.e., various types of brand marks displayed in combination) used by hospitals in the United States. The brand marks were assessed against several normative criteria for creating brand marks that are memorable and that elicit positive affect. Overall, results show a reasonably high level of adherence to many of these normative criteria. Many of the clusters exhibited pictorial elements that reflected benefits and that were conceptually consistent with the verbal content of the cluster. Also, many clusters featured icons that were balanced and moderately complex. However, only a few contained interactive imagery or taglines communicating benefits.
Directory of Open Access Journals (Sweden)
mohammad reza karimi alavijeh
2016-07-01
Full Text Available The utilization of 3G and 4G is rapidly increasing and also cellphone users are briskly changing their consumption behavior, using preferences and shopping manner. Accordingly, cellphone manufacturers should create an accurate insight of their target market and provide a “special offer” to their target consumers. In order to reach a correct understanding of the target market, consumption behavior and lifestyle of the submarkets we found the appropriate number of community clusters after criticizing the traditional methods and introducing market segmentation techniques which were based on neural networks. By utilizing the fuzzy Delphi technique, variables of target market segmentation were found. Finally, the obtained clusters and segmentations of the market were refined by using the techniques of K-means and aggregation (Agglomerative. The population of this research included the consumers of mobile in Tehran with a sample of 130 specimens after collecting data through questionnaires, results demonstrated that the Tehran cellphone market was comprised of 5 Clusters, each one are capable of implementing marketing strategy and marketing mix separately with taking into account the competitive advantages of ICT companies to maximize their demand and margin.
Cluster analysis of midlatitude oceanic cloud regimes: mean properties and temperature sensitivity
Directory of Open Access Journals (Sweden)
N. D. Gordon
2010-07-01
Full Text Available Clouds play an important role in the climate system by reducing the amount of shortwave radiation reaching the surface and the amount of longwave radiation escaping to space. Accurate simulation of clouds in computer models remains elusive, however, pointing to a lack of understanding of the connection between large-scale dynamics and cloud properties. This study uses a k-means clustering algorithm to group 21 years of satellite cloud data over midlatitude oceans into seven clusters, and demonstrates that the cloud clusters are associated with distinct large-scale dynamical conditions. Three clusters correspond to low-level cloud regimes with different cloud fraction and cumuliform or stratiform characteristics, but all occur under large-scale descent and a relatively dry free troposphere. Three clusters correspond to vertically extensive cloud regimes with tops in the middle or upper troposphere, and they differ according to the strength of large-scale ascent and enhancement of tropospheric temperature and humidity. The final cluster is associated with a lower troposphere that is dry and an upper troposphere that is moist and experiencing weak ascent and horizontal moist advection.
Since the present balance of reflection of shortwave and absorption of longwave radiation by clouds could change as the atmosphere warms from increasing anthropogenic greenhouse gases, we must also better understand how increasing temperature modifies cloud and radiative properties. We therefore undertake an observational analysis of how midlatitude oceanic clouds change with temperature when dynamical processes are held constant (i.e., partial derivative with respect to temperature. For each of the seven cloud regimes, we examine the difference in cloud and radiative properties between warm and cold subsets. To avoid misinterpreting a cloud response to large-scale dynamical forcing as a cloud response to temperature, we require horizontal and vertical
Smartness and Italian Cities. A Cluster Analysis
Directory of Open Access Journals (Sweden)
Flavio Boscacci
2014-05-01
Full Text Available Smart cities have been recently recognized as the most pleasing and attractive places to live in; due to this, both scholars and policy-makers pay close attention to this topic. Specifically, urban “smartness” has been identified by plenty of characteristics that can be grouped into six dimensions (Giffinger et al. 2007: smart Economy (competitiveness, smart People (social and human capital, smart Governance (participation, smart Mobility (both ICTs and transport, smart Environment (natural resources, and smart Living (quality of life. According to this analytical framework, in the present paper the relation between urban attractiveness and the “smart” characteristics has been investigated in the 103 Italian NUTS3 province capitals in the year 2011. To this aim, a descriptive statistics has been followed by a regression analysis (OLS, where the dependent variable measuring the urban attractiveness has been proxied by housing market prices. Besides, a Cluster Analysis (CA has been developed in order to find differences and commonalities among the province capitals.The OLS results indicate that living, people and economy are the key drivers for achieving a better urban attractiveness. Environment, instead, keeps on playing a minor role. Besides, the CA groups the province capitals a
Kim, Jihye; Yu, Areum; Choi, Bo Youl; Nam, Jung Hyun; Kim, Mi Kyung; Oh, Dong Hoon; Yang, Yoon Jung
2015-05-29
The objective of this study was to investigate major dietary patterns among older Korean adults through cluster analysis and to determine an association between dietary patterns and cognitive function. This is a cross-sectional study. The data from the Korean Multi-Rural Communities Cohort Study was used. Participants included 765 participants aged 60 years and over. A quantitative food frequency questionnaire with 106 items was used to investigate dietary intake. The Korean version of the MMSE-KC (Mini-Mental Status Examination-Korean version) was used to assess cognitive function. Two major dietary patterns were identified using K-means cluster analysis. The "MFDF" dietary pattern indicated high consumption of Multigrain rice, Fish, Dairy products, Fruits and fruit juices, while the "WNC" dietary pattern referred to higher intakes of White rice, Noodles, and Coffee. Means of the total MMSE-KC and orientation score of the participants in the MFDF dietary pattern were higher than those of the WNC dietary pattern. Compared with the WNC dietary pattern, the MFDF dietary pattern showed a lower risk of cognitive impairment after adjusting for covariates (OR 0.64, 95% CI 0.44-0.94). The MFDF dietary pattern, with high consumption of multigrain rice, fish, dairy products, and fruits may be related to better cognition among Korean older adults.
Directory of Open Access Journals (Sweden)
Jihye Kim
2015-05-01
Full Text Available The objective of this study was to investigate major dietary patterns among older Korean adults through cluster analysis and to determine an association between dietary patterns and cognitive function. This is a cross-sectional study. The data from the Korean Multi-Rural Communities Cohort Study was used. Participants included 765 participants aged 60 years and over. A quantitative food frequency questionnaire with 106 items was used to investigate dietary intake. The Korean version of the MMSE-KC (Mini-Mental Status Examination–Korean version was used to assess cognitive function. Two major dietary patterns were identified using K-means cluster analysis. The “MFDF” dietary pattern indicated high consumption of Multigrain rice, Fish, Dairy products, Fruits and fruit juices, while the “WNC” dietary pattern referred to higher intakes of White rice, Noodles, and Coffee. Means of the total MMSE-KC and orientation score of the participants in the MFDF dietary pattern were higher than those of the WNC dietary pattern. Compared with the WNC dietary pattern, the MFDF dietary pattern showed a lower risk of cognitive impairment after adjusting for covariates (OR 0.64, 95% CI 0.44–0.94. The MFDF dietary pattern, with high consumption of multigrain rice, fish, dairy products, and fruits may be related to better cognition among Korean older adults.
Taxonomical analysis of the Cancer cluster of galaxies
International Nuclear Information System (INIS)
Perea, J.; Olmo, A. del; Moles, M.
1986-01-01
A description is presented of the Cancer cluster of galaxies, based on a taxonomical analysis in (α,delta, Vsub(r)) space. Earlier results by previous authors on the lack of dynamical entity of the cluster are confirmed. The present analysis points out the existence of a binary structure in the most populated region of the complex. (author)
Using Cluster Analysis for Data Mining in Educational Technology Research
Antonenko, Pavlo D.; Toy, Serkan; Niederhauser, Dale S.
2012-01-01
Cluster analysis is a group of statistical methods that has great potential for analyzing the vast amounts of web server-log data to understand student learning from hyperlinked information resources. In this methodological paper we provide an introduction to cluster analysis for educational technology researchers and illustrate its use through…
DEFF Research Database (Denmark)
Löwe, Roland; Madsen, Henrik; McSharry, Patrick
2016-01-01
operators to change modes of control of their facilities. A k-means clustering technique was applied to group events retrospectively and was able to distinguish events with clearly different temporal and spatial correlation properties. For online applications, techniques based on k-means clustering...... and quadratic discriminant analysis both provided a fast and reliable identification of rain events of "high" variability, while the k-means provided the smallest number of rain events falsely identified as being of "high" variability (false hits). A simple classification method based on a threshold...
Clustering-based analysis for residential district heating data
DEFF Research Database (Denmark)
Gianniou, Panagiota; Liu, Xiufeng; Heller, Alfred
2018-01-01
The wide use of smart meters enables collection of a large amount of fine-granular time series, which can be used to improve the understanding of consumption behavior and used for consumption optimization. This paper presents a clustering-based knowledge discovery in databases method to analyze r....... These findings will be valuable for district heating utilities and energy planners to optimize their operations, design demand-side management strategies, and develop targeting energy-efficiency programs or policies.......The wide use of smart meters enables collection of a large amount of fine-granular time series, which can be used to improve the understanding of consumption behavior and used for consumption optimization. This paper presents a clustering-based knowledge discovery in databases method to analyze...... residential heating consumption data and evaluate information included in national building databases. The proposed method uses the K-means algorithm to segment consumption groups based on consumption intensity and representative patterns and ranks the groups according to daily consumption. This paper also...
Cluster analysis of activity-time series in motor learning
DEFF Research Database (Denmark)
Balslev, Daniela; Nielsen, Finn Å; Futiger, Sally A
2002-01-01
Neuroimaging studies of learning focus on brain areas where the activity changes as a function of time. To circumvent the difficult problem of model selection, we used a data-driven analytic tool, cluster analysis, which extracts representative temporal and spatial patterns from the voxel......-time series. The optimal number of clusters was chosen using a cross-validated likelihood method, which highlights the clustering pattern that generalizes best over the subjects. Data were acquired with PET at different time points during practice of a visuomotor task. The results from cluster analysis show...
Lei, Dang; Holder, Roger L; Smith, Francis W; Wardlaw, Douglas; Hukins, David W L
2006-12-01
Statistical analysis of clinical radiologic data. To develop an objective method for finding the number of sizes for a lumbar disc replacement. Cluster analysis is a well-established technique for sorting observations into clusters so that the "similarity level" is maximal if they belong to the same cluster and minimal otherwise. Magnetic resonance scans from 69 patients, with no abnormal discs, yielded 206 sagittal and transverse images of 206 discs (levels L3-L4-L5-S1). Anteroposterior and lateral dimensions were measured from vertebral margins on transverse images; disc heights were measured from sagittal images. Hierarchical cluster analysis was performed to determine the number of clusters followed by nonhierarchical (K-means) cluster analysis. Discriminant analysis was used to determine how well the clusters could be used to classify an observation. The most successful method of clustering the data involved the following parameters: anteroposterior dimension; lateral dimension (both were the mean of results from the superior and inferior margins of a vertebral body, measured on transverse images); and maximum disc height (from a midsagittal image). These were grouped into 7 clusters so that a discriminant analysis was capable of correctly classifying 97.1% of the observations. The mean and standard deviations for the parameter values in each cluster were determined. Cluster analysis has been successfully used to find the dimensions of the minimum number of prosthesis sizes required to replace L3-L4 to L5-S1 discs; the range of sizes would enable them to be used at higher lumbar levels in some patients.
Schaefer, Andreas M.; Daniell, James E.; Wenzel, Friedemann
2017-07-01
Earthquake clustering is an essential part of almost any statistical analysis of spatial and temporal properties of seismic activity. The nature of earthquake clusters and subsequent declustering of earthquake catalogues plays a crucial role in determining the magnitude-dependent earthquake return period and its respective spatial variation for probabilistic seismic hazard assessment. This study introduces the Smart Cluster Method (SCM), a new methodology to identify earthquake clusters, which uses an adaptive point process for spatio-temporal cluster identification. It utilises the magnitude-dependent spatio-temporal earthquake density to adjust the search properties, subsequently analyses the identified clusters to determine directional variation and adjusts its search space with respect to directional properties. In the case of rapid subsequent ruptures like the 1992 Landers sequence or the 2010-2011 Darfield-Christchurch sequence, a reclassification procedure is applied to disassemble subsequent ruptures using near-field searches, nearest neighbour classification and temporal splitting. The method is capable of identifying and classifying earthquake clusters in space and time. It has been tested and validated using earthquake data from California and New Zealand. A total of more than 1500 clusters have been found in both regions since 1980 with M m i n = 2.0. Utilising the knowledge of cluster classification, the method has been adjusted to provide an earthquake declustering algorithm, which has been compared to existing methods. Its performance is comparable to established methodologies. The analysis of earthquake clustering statistics lead to various new and updated correlation functions, e.g. for ratios between mainshock and strongest aftershock and general aftershock activity metrics.
Rezaee, Kh; Haddadnia, J
2013-09-01
Breast cancer is currently one of the leading causes of death among women worldwide. The diagnosis and separation of cancerous tumors in mammographic images require accuracy, experience and time, and it has always posed itself as a major challenge to the radiologists and physicians. This paper proposes a new algorithm which draws on discrete wavelet transform and adaptive K-means techniques to transmute the medical images implement the tumor estimation and detect breast cancer tumors in mammograms in early stages. It also allows the rapid processing of the input data. In the first step, after designing a filter, the discrete wavelet transform is applied to the input images and the approximate coefficients of scaling components are constructed. Then, the different parts of image are classified in continuous spectrum. In the next step, by using adaptive K-means algorithm for initializing and smart choice of clusters' number, the appropriate threshold is selected. Finally, the suspicious cancerous mass is separated by implementing the image processing techniques. We Received 120 mammographic images in LJPEG format, which had been scanned in Gray-Scale with 50 microns size, 3% noise and 20% INU from clinical data taken from two medical databases (mini-MIAS and DDSM). The proposed algorithm detected tumors at an acceptable level with an average accuracy of 92.32% and sensitivity of 90.24%. Also, the Kappa coefficient was approximately 0.85, which proved the suitable reliability of the system performance. The exact positioning of the cancerous tumors allows the radiologist to determine the stage of disease progression and suggest an appropriate treatment in accordance with the tumor growth. The low PPV and high NPV of the system is a warranty of the system and both clinical specialists and patients can trust its output.
Directory of Open Access Journals (Sweden)
David Camarena-Martinez
2016-01-01
Full Text Available For industry, the induction motors are essential elements in production chains. Despite the robustness of induction motors, they are susceptible to failures. The broken rotor bar (BRB fault in induction motors has received special attention since one of its characteristics is that the motor can continue operating with apparent normality; however, at certain point the fault may cause severe damage to the motor. In this work, a methodology to detect BRBs using vibration signals is proposed. The methodology uses the Shannon entropy to quantify the amount of information provided by the vibration signals, which changes due to the presence of new frequency components associated with the fault. For automatic diagnosis, the K-means cluster algorithm and a decision-making unit that looks for the nearest cluster through the Euclidian distance are applied. Unlike other reported works, the proposal can diagnose the BRB condition during startup transient and steady state regimes of operation. Additionally, the proposal is also implemented into a field programmable gate array in order to offer a low-cost and low-complex online monitoring system. The obtained results demonstrate the proposal effectiveness to diagnose half, one, and two BRBs.
DEFF Research Database (Denmark)
Walton, David M; Kwok, Timothy S H; Mehta, Swati
2017-01-01
OBJECTIVE: To determine pressure pain detection threshold (PPDT) related phenotypes of individuals with mechanical neck pain that may be identifiable in clinical practice. METHODS: This report describes a secondary analysis of 5 independent, international mechanical neck pain databases of PPDT...... values taken at both a local and distal region (total N=1176). Minor systematic differences in mean PPDT values across cohorts necessitated z-transformation before analysis, and each cohort was split into male and female sexes. Latent profile analysis (LPA) using the k-means approach was undertaken...... to identify the most parsimonious set of PPDT-based phenotypes that were both statistically and clinically meaningful. RESULTS: LPA revealed 4 distinct clusters named according to PPDT levels at the local and distal zones: low-low PPDT (67%), mod-mod (25%), mod-high (4%), and high-high (4%). Secondary...
Allergen Sensitization Pattern by Sex: A Cluster Analysis in Korea.
Ohn, Jungyoon; Paik, Seung Hwan; Doh, Eun Jin; Park, Hyun-Sun; Yoon, Hyun-Sun; Cho, Soyun
2017-12-01
Allergens tend to sensitize simultaneously. Etiology of this phenomenon has been suggested to be allergen cross-reactivity or concurrent exposure. However, little is known about specific allergen sensitization patterns. To investigate the allergen sensitization characteristics according to gender. Multiple allergen simultaneous test (MAST) is widely used as a screening tool for detecting allergen sensitization in dermatologic clinics. We retrospectively reviewed the medical records of patients with MAST results between 2008 and 2014 in our Department of Dermatology. A cluster analysis was performed to elucidate the allergen-specific immunoglobulin (Ig)E cluster pattern. The results of MAST (39 allergen-specific IgEs) from 4,360 cases were analyzed. By cluster analysis, 39items were grouped into 8 clusters. Each cluster had characteristic features. When compared with female, the male group tended to be sensitized more frequently to all tested allergens, except for fungus allergens cluster. The cluster and comparative analysis results demonstrate that the allergen sensitization is clustered, manifesting allergen similarity or co-exposure. Only the fungus cluster allergens tend to sensitize female group more frequently than male group.
Yun, Younghee; Jung, Wonmo; Kim, Hyunho; Jang, Bo-Hyoung; Kim, Min-Hee; Noh, Jiseong; Ko, Seong-Gyu; Choi, Inhwa
2017-08-01
Syndrome differentiation (SD) results in a diagnostic conclusion based on a cluster of concurrent symptoms and signs, including pulse form and tongue color. In Korea, there is a strong interest in the standardization of Traditional Medicine (TM). In order to standardize TM treatment, standardization of SD should be given priority. The aim of this study was to explore the SD, or symptom clusters, of patients with atopic dermatitis (AD) using non-negative factorization methods and k-means clustering analysis. We screened 80 patients and enrolled 73 eligible patients. One TM dermatologist evaluated the symptoms/signs using an existing clinical dataset from patients with AD. This dataset was designed to collect 15 dermatologic and 18 systemic symptoms/signs associated with AD. Non-negative matrix factorization was used to decompose the original data into a matrix with three features and a weight matrix. The point of intersection of the three coordinates from each patient was placed in three-dimensional space. With five clusters, the silhouette score reached 0.484, and this was the best silhouette score obtained from two to nine clusters. Patients were clustered according to the varying severity of concurrent symptoms/signs. Through the distribution of the null hypothesis generated by 10,000 permutation tests, we found significant cluster-specific symptoms/signs from the confidence intervals in the upper and lower 2.5% of the distribution. Patients in each cluster showed differences in symptoms/signs and severity. In a clinical situation, SD and treatment are based on the practitioners' observations and clinical experience. SD, identified through informatics, can contribute to development of standardized, objective, and consistent SD for each disease. Copyright © 2017. Published by Elsevier Ltd.
Analysis of Network Clustering Algorithms and Cluster Quality Metrics at Scale.
Emmons, Scott; Kobourov, Stephen; Gallant, Mike; Börner, Katy
2016-01-01
Notions of community quality underlie the clustering of networks. While studies surrounding network clustering are increasingly common, a precise understanding of the realtionship between different cluster quality metrics is unknown. In this paper, we examine the relationship between stand-alone cluster quality metrics and information recovery metrics through a rigorous analysis of four widely-used network clustering algorithms-Louvain, Infomap, label propagation, and smart local moving. We consider the stand-alone quality metrics of modularity, conductance, and coverage, and we consider the information recovery metrics of adjusted Rand score, normalized mutual information, and a variant of normalized mutual information used in previous work. Our study includes both synthetic graphs and empirical data sets of sizes varying from 1,000 to 1,000,000 nodes. We find significant differences among the results of the different cluster quality metrics. For example, clustering algorithms can return a value of 0.4 out of 1 on modularity but score 0 out of 1 on information recovery. We find conductance, though imperfect, to be the stand-alone quality metric that best indicates performance on the information recovery metrics. Additionally, our study shows that the variant of normalized mutual information used in previous work cannot be assumed to differ only slightly from traditional normalized mutual information. Smart local moving is the overall best performing algorithm in our study, but discrepancies between cluster evaluation metrics prevent us from declaring it an absolutely superior algorithm. Interestingly, Louvain performed better than Infomap in nearly all the tests in our study, contradicting the results of previous work in which Infomap was superior to Louvain. We find that although label propagation performs poorly when clusters are less clearly defined, it scales efficiently and accurately to large graphs with well-defined clusters.
Huo, Zhiguang; Ding, Ying; Liu, Silvia; Oesterreich, Steffi; Tseng, George
Disease phenotyping by omics data has become a popular approach that potentially can lead to better personalized treatment. Identifying disease subtypes via unsupervised machine learning is the first step towards this goal. In this paper, we extend a sparse K -means method towards a meta-analytic framework to identify novel disease subtypes when expression profiles of multiple cohorts are available. The lasso regularization and meta-analysis identify a unique set of gene features for subtype characterization. An additional pattern matching reward function guarantees consistent subtype signatures across studies. The method was evaluated by simulations and leukemia and breast cancer data sets. The identified disease subtypes from meta-analysis were characterized with improved accuracy and stability compared to single study analysis. The breast cancer model was applied to an independent METABRIC dataset and generated improved survival difference between subtypes. These results provide a basis for diagnosis and development of targeted treatments for disease subgroups.
Hybrid Modified K-Means with C4.5 for Intrusion Detection Systems in Multiagent Systems.
Laftah Al-Yaseen, Wathiq; Ali Othman, Zulaiha; Ahmad Nazri, Mohd Zakree
2015-01-01
Presently, the processing time and performance of intrusion detection systems are of great importance due to the increased speed of traffic data networks and a growing number of attacks on networks and computers. Several approaches have been proposed to address this issue, including hybridizing with several algorithms. However, this paper aims at proposing a hybrid of modified K-means with C4.5 intrusion detection system in a multiagent system (MAS-IDS). The MAS-IDS consists of three agents, namely, coordinator, analysis, and communication agent. The basic concept underpinning the utilized MAS is dividing the large captured network dataset into a number of subsets and distributing these to a number of agents depending on the data network size and core CPU availability. KDD Cup 1999 dataset is used for evaluation. The proposed hybrid modified K-means with C4.5 classification in MAS is developed in JADE platform. The results show that compared to the current methods, the MAS-IDS reduces the IDS processing time by up to 70%, while improving the detection accuracy.
Merging Galaxy Clusters: Analysis of Simulated Analogs
Nguyen, Jayke; Wittman, David; Cornell, Hunter
2018-01-01
The nature of dark matter can be better constrained by observing merging galaxy clusters. However, uncertainty in the viewing angle leads to uncertainty in dynamical quantities such as 3-d velocities, 3-d separations, and time since pericenter. The classic timing argument links these quantities via equations of motion, but neglects effects of nonzero impact parameter (i.e. it assumes velocities are parallel to the separation vector), dynamical friction, substructure, and larger-scale environment. We present a new approach using n-body cosmological simulations that naturally incorporate these effects. By uniformly sampling viewing angles about simulated cluster analogs, we see projected merger parameters in the many possible configurations of a given cluster. We select comparable simulated analogs and evaluate the likelihood of particular merger parameters as a function of viewing angle. We present viewing angle constraints for a sample of observed mergers including the Bullet cluster and El Gordo, and show that the separation vectors are closer to the plane of the sky than previously reported.
Application of clustering for customer segmentation in private banking
Yang, Xuan; Chen, Jin; Hao, Pengpeng; Wang, Yanbo J.
2015-07-01
With fierce competition in banking industry, more and more banks have realised that accurate customer segmentation is of fundamental importance, especially for the identification of those high-value customers. In order to solve this problem, we collected real data about private banking customers of a commercial bank in China, conducted empirical analysis by applying K-means clustering technique. When determine the K value, we propose a mechanism that meet both academic requirements and practical needs. Through K-means clustering, we successfully segmented the customers into three categories, and features of each group have been illustrated in details.
Analysis of Aspects of Innovation in a Brazilian Cluster
Directory of Open Access Journals (Sweden)
Adriana Valélia Saraceni
2012-09-01
Full Text Available Innovation through clustering has become very important on the increased significance that interaction represents on innovation and learning process concept. This study aims to identify whereas a case analysis on innovation process in a cluster represents on the learning process. Therefore, this study is developed in two stages. First, we used a preliminary case study verifying a cluster innovation analysis and it Innovation Index, for further, exploring a combined body of theory and practice. Further, the second stage is developed by exploring the learning process concept. Both stages allowed us building a theory model for the learning process development in clusters. The main results of the model development come up with a mechanism of improvement implementation on clusters when case studies are applied.
Reproducibility of Cognitive Profiles in Psychosis Using Cluster Analysis.
Lewandowski, Kathryn E; Baker, Justin T; McCarthy, Julie M; Norris, Lesley A; Öngür, Dost
2018-04-01
Cognitive dysfunction is a core symptom dimension that cuts across the psychoses. Recent findings support classification of patients along the cognitive dimension using cluster analysis; however, data-derived groupings may be highly determined by sampling characteristics and the measures used to derive the clusters, and so their interpretability must be established. We examined cognitive clusters in a cross-diagnostic sample of patients with psychosis and associations with clinical and functional outcomes. We then compared our findings to a previous report of cognitive clusters in a separate sample using a different cognitive battery. Participants with affective or non-affective psychosis (n=120) and healthy controls (n=31) were administered the MATRICS Consensus Cognitive Battery, and clinical and community functioning assessments. Cluster analyses were performed on cognitive variables, and clusters were compared on demographic, cognitive, and clinical measures. Results were compared to findings from our previous report. A four-cluster solution provided a good fit to the data; profiles included a neuropsychologically normal cluster, a globally impaired cluster, and two clusters of mixed profiles. Cognitive burden was associated with symptom severity and poorer community functioning. The patterns of cognitive performance by cluster were highly consistent with our previous findings. We found evidence of four cognitive subgroups of patients with psychosis, with cognitive profiles that map closely to those produced in our previous work. Clusters were associated with clinical and community variables and a measure of premorbid functioning, suggesting that they reflect meaningful groupings: replicable, and related to clinical presentation and functional outcomes. (JINS, 2018, 24, 382-390).
Network Analysis Tools: from biological networks to clusters and pathways.
Brohée, Sylvain; Faust, Karoline; Lima-Mendez, Gipsi; Vanderstocken, Gilles; van Helden, Jacques
2008-01-01
Network Analysis Tools (NeAT) is a suite of computer tools that integrate various algorithms for the analysis of biological networks: comparison between graphs, between clusters, or between graphs and clusters; network randomization; analysis of degree distribution; network-based clustering and path finding. The tools are interconnected to enable a stepwise analysis of the network through a complete analytical workflow. In this protocol, we present a typical case of utilization, where the tasks above are combined to decipher a protein-protein interaction network retrieved from the STRING database. The results returned by NeAT are typically subnetworks, networks enriched with additional information (i.e., clusters or paths) or tables displaying statistics. Typical networks comprising several thousands of nodes and arcs can be analyzed within a few minutes. The complete protocol can be read and executed in approximately 1 h.
Cluster analysis of typhoid cases in Kota Bharu, Kelantan, Malaysia
Directory of Open Access Journals (Sweden)
Nazarudin Safian
2008-09-01
Full Text Available Typhoid fever is still a major public health problem globally as well as in Malaysia. This study was done to identify the spatial epidemiology of typhoid fever in the Kota Bharu District of Malaysia as a first step to developing more advanced analysis of the whole country. The main characteristic of the epidemiological pattern that interested us was whether typhoid cases occurred in clusters or whether they were evenly distributed throughout the area. We also wanted to know at what spatial distances they were clustered. All confirmed typhoid cases that were reported to the Kota Bharu District Health Department from the year 2001 to June of 2005 were taken as the samples. From the home address of the cases, the location of the house was traced and a coordinate was taken using handheld GPS devices. Spatial statistical analysis was done to determine the distribution of typhoid cases, whether clustered, random or dispersed. The spatial statistical analysis was done using CrimeStat III software to determine whether typhoid cases occur in clusters, and later on to determine at what distances it clustered. From 736 cases involved in the study there was significant clustering for cases occurring in the years 2001, 2002, 2003 and 2005. There was no significant clustering in year 2004. Typhoid clustering also occurred strongly for distances up to 6 km. This study shows that typhoid cases occur in clusters, and this method could be applicable to describe spatial epidemiology for a specific area. (Med J Indones 2008; 17: 175-82Keywords: typhoid, clustering, spatial epidemiology, GIS
Using cluster analysis to organize and explore regional GPS velocities
Simpson, Robert W.; Thatcher, Wayne; Savage, James C.
2012-01-01
Cluster analysis offers a simple visual exploratory tool for the initial investigation of regional Global Positioning System (GPS) velocity observations, which are providing increasingly precise mappings of actively deforming continental lithosphere. The deformation fields from dense regional GPS networks can often be concisely described in terms of relatively coherent blocks bounded by active faults, although the choice of blocks, their number and size, can be subjective and is often guided by the distribution of known faults. To illustrate our method, we apply cluster analysis to GPS velocities from the San Francisco Bay Region, California, to search for spatially coherent patterns of deformation, including evidence of block-like behavior. The clustering process identifies four robust groupings of velocities that we identify with four crustal blocks. Although the analysis uses no prior geologic information other than the GPS velocities, the cluster/block boundaries track three major faults, both locked and creeping.
Wang, Guanglei; Wang, Pengyu; Han, Yechen; Liu, Xiuling; Li, Yan; Lu, Qian
2017-06-01
In recent years, optical coherence tomography (OCT) has developed into a popular coronary imaging technology at home and abroad. The segmentation of plaque regions in coronary OCT images has great significance for vulnerable plaque recognition and research. In this paper, a new algorithm based on K -means clustering and improved random walk is proposed and Semi-automated segmentation of calcified plaque, fibrotic plaque and lipid pool was achieved. And the weight function of random walk is improved. The distance between the edges of pixels in the image and the seed points is added to the definition of the weight function. It increases the weak edge weights and prevent over-segmentation. Based on the above methods, the OCT images of 9 coronary atherosclerotic patients were selected for plaque segmentation. By contrasting the doctor's manual segmentation results with this method, it was proved that this method had good robustness and accuracy. It is hoped that this method can be helpful for the clinical diagnosis of coronary heart disease.
A Novel Divisive Hierarchical Clustering Algorithm for Geospatial Analysis
Directory of Open Access Journals (Sweden)
Shaoning Li
2017-01-01
Full Text Available In the fields of geographic information systems (GIS and remote sensing (RS, the clustering algorithm has been widely used for image segmentation, pattern recognition, and cartographic generalization. Although clustering analysis plays a key role in geospatial modelling, traditional clustering methods are limited due to computational complexity, noise resistant ability and robustness. Furthermore, traditional methods are more focused on the adjacent spatial context, which makes it hard for the clustering methods to be applied to multi-density discrete objects. In this paper, a new method, cell-dividing hierarchical clustering (CDHC, is proposed based on convex hull retraction. The main steps are as follows. First, a convex hull structure is constructed to describe the global spatial context of geospatial objects. Then, the retracting structure of each borderline is established in sequence by setting the initial parameter. The objects are split into two clusters (i.e., “sub-clusters” if the retracting structure intersects with the borderlines. Finally, clusters are repeatedly split and the initial parameter is updated until the terminate condition is satisfied. The experimental results show that CDHC separates the multi-density objects from noise sufficiently and also reduces complexity compared to the traditional agglomerative hierarchical clustering algorithm.
A Distributed Flocking Approach for Information Stream Clustering Analysis
Energy Technology Data Exchange (ETDEWEB)
Cui, Xiaohui [ORNL; Potok, Thomas E [ORNL
2006-01-01
Intelligence analysts are currently overwhelmed with the amount of information streams generated everyday. There is a lack of comprehensive tool that can real-time analyze the information streams. Document clustering analysis plays an important role in improving the accuracy of information retrieval. However, most clustering technologies can only be applied for analyzing the static document collection because they normally require a large amount of computation resource and long time to get accurate result. It is very difficult to cluster a dynamic changed text information streams on an individual computer. Our early research has resulted in a dynamic reactive flock clustering algorithm which can continually refine the clustering result and quickly react to the change of document contents. This character makes the algorithm suitable for cluster analyzing dynamic changed document information, such as text information stream. Because of the decentralized character of this algorithm, a distributed approach is a very natural way to increase the clustering speed of the algorithm. In this paper, we present a distributed multi-agent flocking approach for the text information stream clustering and discuss the decentralized architectures and communication schemes for load balance and status information synchronization in this approach.
Cluster analysis of clinical data identifies fibromyalgia subgroups.
Directory of Open Access Journals (Sweden)
Elisa Docampo
Full Text Available INTRODUCTION: Fibromyalgia (FM is mainly characterized by widespread pain and multiple accompanying symptoms, which hinder FM assessment and management. In order to reduce FM heterogeneity we classified clinical data into simplified dimensions that were used to define FM subgroups. MATERIAL AND METHODS: 48 variables were evaluated in 1,446 Spanish FM cases fulfilling 1990 ACR FM criteria. A partitioning analysis was performed to find groups of variables similar to each other. Similarities between variables were identified and the variables were grouped into dimensions. This was performed in a subset of 559 patients, and cross-validated in the remaining 887 patients. For each sample and dimension, a composite index was obtained based on the weights of the variables included in the dimension. Finally, a clustering procedure was applied to the indexes, resulting in FM subgroups. RESULTS: VARIABLES CLUSTERED INTO THREE INDEPENDENT DIMENSIONS: "symptomatology", "comorbidities" and "clinical scales". Only the two first dimensions were considered for the construction of FM subgroups. Resulting scores classified FM samples into three subgroups: low symptomatology and comorbidities (Cluster 1, high symptomatology and comorbidities (Cluster 2, and high symptomatology but low comorbidities (Cluster 3, showing differences in measures of disease severity. CONCLUSIONS: We have identified three subgroups of FM samples in a large cohort of FM by clustering clinical data. Our analysis stresses the importance of family and personal history of FM comorbidities. Also, the resulting patient clusters could indicate different forms of the disease, relevant to future research, and might have an impact on clinical assessment.
Clustering Trajectories by Relevant Parts for Air Traffic Analysis.
Andrienko, Gennady; Andrienko, Natalia; Fuchs, Georg; Garcia, Jose Manuel Cordero
2018-01-01
Clustering of trajectories of moving objects by similarity is an important technique in movement analysis. Existing distance functions assess the similarity between trajectories based on properties of the trajectory points or segments. The properties may include the spatial positions, times, and thematic attributes. There may be a need to focus the analysis on certain parts of trajectories, i.e., points and segments that have particular properties. According to the analysis focus, the analyst may need to cluster trajectories by similarity of their relevant parts only. Throughout the analysis process, the focus may change, and different parts of trajectories may become relevant. We propose an analytical workflow in which interactive filtering tools are used to attach relevance flags to elements of trajectories, clustering is done using a distance function that ignores irrelevant elements, and the resulting clusters are summarized for further analysis. We demonstrate how this workflow can be useful for different analysis tasks in three case studies with real data from the domain of air traffic. We propose a suite of generic techniques and visualization guidelines to support movement data analysis by means of relevance-aware trajectory clustering.
Cluster analysis of Southeastern U.S. climate stations
Stooksbury, D. E.; Michaels, P. J.
1991-09-01
A two-step cluster analysis of 449 Southeastern climate stations is used to objectively determine general climate clusters (groups of climate stations) for eight southeastern states. The purpose is objectively to define regions of climatic homogeneity that should perform more robustly in subsequent climatic impact models. This type of analysis has been successfully used in many related climate research problems including the determination of corn/climate districts in Iowa (Ortiz-Valdez, 1985) and the classification of synoptic climate types (Davis, 1988). These general climate clusters may be more appropriate for climate research than the standard climate divisions (CD) groupings of climate stations, which are modifications of the agro-economic United States Department of Agriculture crop reporting districts. Unlike the CD's, these objectively determined climate clusters are not restricted by state borders and thus have reduced multicollinearity which makes them more appropriate for the study of the impact of climate and climatic change.
Energy Technology Data Exchange (ETDEWEB)
Heikkilae, U. [Bjerknes Centre for Climate Research, Uni Bjerknes Centre, Bergen (Norway); Australian Nuclear Science and Technology Organisation (ANSTO), Lucas Heights, NSW (Australia); Sorteberg, A. [University of Bergen, Geophysical Institute, Bergen (Norway); University of Bergen, Bjerknes Centre for Climate Research, Bergen (Norway)
2012-08-15
Extremely high autumn and winter precipitation events on the European west coast are often driven by low-pressure systems in the North Atlantic. Climate projections suggest the number and intensity of these events is likely to increase far more than the mean precipitation. In this study we investigate the autumn-winter extreme precipitation on the Norwegian west coast and the connection between its spatial distribution and sea level pressure (SLP) patterns using the k-means cluster analysis. We use three relatively high resolved downscalings of one global coupled model: the Arpege global atmospheric model (stretched grid with 35-km horizontal resolution over Norway) and the WRF-downscaled Arpege model (30 and 10-km) for the 30-year periods of 1961-1990 and 2021-2050. The cluster analysis finds three main SLP patterns responsible for extreme precipitation in different parts of the country. The SLP patterns found are similar to the NAO positive pattern known to strengthen the westerly flow towards European coast. We then apply the method to investigate future change in extreme precipitation. We find an increase in the number of days with extreme precipitation of 15, 39 and 35% in the two simulations (Arpege 35-km and WRF 30 and 10-km, respectively). We do not find evidence of a significant change in the frequency of weather patterns between the present and the future periods. Rather, it is the probability of a given weather pattern to cause extreme precipitation which is increased in the future, probably due to higher temperatures and an increased moisture content of the air. The WRF model predicts the increase in this probability caused by the most important SLP patterns to be >50%. The Arpege model does not predict such a significant change because the general increase in extreme precipitation predicted is smaller, probably due to its coarser resolution over ocean which leads to smoother representation of the low pressure systems. (orig.)
Push Recovery for Humanoid Robot in Dynamic Environment and Classifying the Data Using K-Mean
Directory of Open Access Journals (Sweden)
Anubha Parashar
2016-12-01
Full Text Available Push recovery is prime ability that is essential to be incorporated in the process of developing a robust humanoid robot to support bipedalism. In real environment it is very essential for humanoid robot to maintain balance. In this paper we are generating a control system and push recovery controller for humanoid robot walking. We apply different kind of pushes to humanoid robot and the algorithm that can bring a change in the walking stage to sustain walking. The simulation is done in 3D environment using Webots. This paper describes techniques for feature selection to foreshow push recovery for hip, ankle and knee joint. We train the system by K-Mean algorithm and testing is done on crouch data and tested results are reported. Random push data of humanoid robot is collected and classified to see whether push lie in safer region and then tested on given proposed system.
Accelerating Families of Fuzzy K-Means Algorithms for Vector Quantization Codebook Design.
Mata, Edson; Bandeira, Silvio; de Mattos Neto, Paulo; Lopes, Waslon; Madeiro, Francisco
2016-11-23
The performance of signal processing systems based on vector quantization depends on codebook design. In the image compression scenario, the quality of the reconstructed images depends on the codebooks used. In this paper, alternatives are proposed for accelerating families of fuzzy K-means algorithms for codebook design. The acceleration is obtained by reducing the number of iterations of the algorithms and applying efficient nearest neighbor search techniques. Simulation results concerning image vector quantization have shown that the acceleration obtained so far does not decrease the quality of the reconstructed images. Codebook design time savings up to about 40% are obtained by the accelerated versions with respect to the original versions of the algorithms.
A self-adaptive k-means classifier for business incentive in a fashion design environment
Directory of Open Access Journals (Sweden)
O.R. Vincent
2018-01-01
Full Text Available An incentive mechanism to target market for fashion designers is proposed. Recent researches have been focused on the art, style or the design; while a few were based on traditional practice. In this study, economy is considered as a major liberation in the fashion world by analyzing six attributes, namely, style, color, fabric, brand, price and size that could bring about commercial success. Dataset of 1000 customers’ records were used and categorized as original, combined and new designs using self-adaptive k-means algorithm, which extract common attributes that would foster better business from the dataset. The results would be useful to designers in knowing the type of designs usually ordered by customers with the design code, and which combinations of the attributes have high patronage. In addition, customers would have easy access to the best and current designs invoke from a combination of highest patronized designs.
A Link-Based Cluster Ensemble Approach For Improved Gene Expression Data Analysis
Directory of Open Access Journals (Sweden)
P.Balaji
2015-01-01
Full Text Available Abstract It is difficult from possibilities to select a most suitable effective way of clustering algorithm and its dataset for a defined set of gene expression data because we have a huge number of ways and huge number of gene expressions. At present many researchers are preferring to use hierarchical clustering in different forms this is no more totally optimal. Cluster ensemble research can solve this type of problem by automatically merging multiple data partitions from a wide range of different clusterings of any dimensions to improve both the quality and robustness of the clustering result. But we have many existing ensemble approaches using an association matrix to condense sample-cluster and co-occurrence statistics and relations within the ensemble are encapsulated only at raw level while the existing among clusters are totally discriminated. Finding these missing associations can greatly expand the capability of those ensemble methodologies for microarray data clustering. We propose general K-means cluster ensemble approach for the clustering of general categorical data into required number of partitions.
Development of small scale cluster computer for numerical analysis
Zulkifli, N. H. N.; Sapit, A.; Mohammed, A. N.
2017-09-01
In this study, two units of personal computer were successfully networked together to form a small scale cluster. Each of the processor involved are multicore processor which has four cores in it, thus made this cluster to have eight processors. Here, the cluster incorporate Ubuntu 14.04 LINUX environment with MPI implementation (MPICH2). Two main tests were conducted in order to test the cluster, which is communication test and performance test. The communication test was done to make sure that the computers are able to pass the required information without any problem and were done by using simple MPI Hello Program where the program written in C language. Additional, performance test was also done to prove that this cluster calculation performance is much better than single CPU computer. In this performance test, four tests were done by running the same code by using single node, 2 processors, 4 processors, and 8 processors. The result shows that with additional processors, the time required to solve the problem decrease. Time required for the calculation shorten to half when we double the processors. To conclude, we successfully develop a small scale cluster computer using common hardware which capable of higher computing power when compare to single CPU processor, and this can be beneficial for research that require high computing power especially numerical analysis such as finite element analysis, computational fluid dynamics, and computational physics analysis.
A Cluster-Analytical Approach towards Physical Activity and Eating Habits among 10-Year-Old Children
Sabbe, Dieter; De Bourdeaudhuij, I.; Legiest, E.; Maes, L.
2008-01-01
The purpose was to investigate whether clusters--based on physical activity (PA) and eating habits--can be found among children, and to explore subgroups' characteristics. A total of 1725 10-year olds completed a self-administered questionnaire. K-means cluster analysis was based on the weekly quantity of vigorous and moderate PA, the excess index…
Predicting healthcare outcomes in prematurely born infants using cluster analysis.
MacBean, Victoria; Lunt, Alan; Drysdale, Simon B; Yarzi, Muska N; Rafferty, Gerrard F; Greenough, Anne
2018-05-23
Prematurely born infants are at high risk of respiratory morbidity following neonatal unit discharge, though prediction of outcomes is challenging. We have tested the hypothesis that cluster analysis would identify discrete groups of prematurely born infants with differing respiratory outcomes during infancy. A total of 168 infants (median (IQR) gestational age 33 (31-34) weeks) were recruited in the neonatal period from consecutive births in a tertiary neonatal unit. The baseline characteristics of the infants were used to classify them into hierarchical agglomerative clusters. Rates of viral lower respiratory tract infections (LRTIs) were recorded for 151 infants in the first year after birth. Infants could be classified according to birth weight and duration of neonatal invasive mechanical ventilation (MV) into three clusters. Cluster one (MV ≤5 days) had few LRTIs. Clusters two and three (both MV ≥6 days, but BW ≥or <882 g respectively), had significantly higher LRTI rates. Cluster two had a higher proportion of infants experiencing respiratory syncytial virus LRTIs (P = 0.01) and cluster three a higher proportion of rhinovirus LRTIs (P < 0.001) CONCLUSIONS: Readily available clinical data allowed classification of prematurely born infants into one of three distinct groups with differing subsequent respiratory morbidity in infancy. © 2018 Wiley Periodicals, Inc.
An Initialization Method Based on Hybrid Distance for k-Means Algorithm.
Yang, Jie; Ma, Yan; Zhang, Xiangfen; Li, Shunbao; Zhang, Yuping
2017-11-01
The traditional [Formula: see text]-means algorithm has been widely used as a simple and efficient clustering method. However, the performance of this algorithm is highly dependent on the selection of initial cluster centers. Therefore, the method adopted for choosing initial cluster centers is extremely important. In this letter, we redefine the density of points according to the number of its neighbors, as well as the distance between points and their neighbors. In addition, we define a new distance measure that considers both Euclidean distance and density. Based on that, we propose an algorithm for selecting initial cluster centers that can dynamically adjust the weighting parameter. Furthermore, we propose a new internal clustering validation measure, the clustering validation index based on the neighbors (CVN), which can be exploited to select the optimal result among multiple clustering results. Experimental results show that the proposed algorithm outperforms existing initialization methods on real-world data sets and demonstrates the adaptability of the proposed algorithm to data sets with various characteristics.
Cluster analysis of radionuclide concentrations in beach sand
de Meijer, R.J.; James, I.; Jennings, P.J.; Keoyers, J.E.
This paper presents a method in which natural radionuclide concentrations of beach sand minerals are traced along a stretch of coast by cluster analysis. This analysis yields two groups of mineral deposit with different origins. The method deviates from standard methods of following dispersal of
Principal Component Clustering Approach to Teaching Quality Discriminant Analysis
Xian, Sidong; Xia, Haibo; Yin, Yubo; Zhai, Zhansheng; Shang, Yan
2016-01-01
Teaching quality is the lifeline of the higher education. Many universities have made some effective achievement about evaluating the teaching quality. In this paper, we establish the Students' evaluation of teaching (SET) discriminant analysis model and algorithm based on principal component clustering analysis. Additionally, we classify the SET…
Characterizing Suicide in Toronto: An Observational Study and Cluster Analysis
Sinyor, Mark; Schaffer, Ayal; Streiner, David L
2014-01-01
Objective: To determine whether people who have died from suicide in a large epidemiologic sample form clusters based on demographic, clinical, and psychosocial factors. Method: We conducted a coroner’s chart review for 2886 people who died in Toronto, Ontario, from 1998 to 2010, and whose death was ruled as suicide by the Office of the Chief Coroner of Ontario. A cluster analysis using known suicide risk factors was performed to determine whether suicide deaths separate into distinct groups. Clusters were compared according to person- and suicide-specific factors. Results: Five clusters emerged. Cluster 1 had the highest proportion of females and nonviolent methods, and all had depression and a past suicide attempt. Cluster 2 had the highest proportion of people with a recent stressor and violent suicide methods, and all were married. Cluster 3 had mostly males between the ages of 20 and 64, and all had either experienced recent stressors, suffered from mental illness, or had a history of substance abuse. Cluster 4 had the youngest people and the highest proportion of deaths by jumping from height, few were married, and nearly one-half had bipolar disorder or schizophrenia. Cluster 5 had all unmarried people with no prior suicide attempts, and were the least likely to have an identified mental illness and most likely to leave a suicide note. Conclusions: People who die from suicide assort into different patterns of demographic, clinical, and death-specific characteristics. Identifying and studying subgroups of suicides may advance our understanding of the heterogeneous nature of suicide and help to inform development of more targeted suicide prevention strategies. PMID:24444321
Pattern recognition in menstrual bleeding diaries by statistical cluster analysis
Directory of Open Access Journals (Sweden)
Wessel Jens
2009-07-01
Full Text Available Abstract Background The aim of this paper is to empirically identify a treatment-independent statistical method to describe clinically relevant bleeding patterns by using bleeding diaries of clinical studies on various sex hormone containing drugs. Methods We used the four cluster analysis methods single, average and complete linkage as well as the method of Ward for the pattern recognition in menstrual bleeding diaries. The optimal number of clusters was determined using the semi-partial R2, the cubic cluster criterion, the pseudo-F- and the pseudo-t2-statistic. Finally, the interpretability of the results from a gynecological point of view was assessed. Results The method of Ward yielded distinct clusters of the bleeding diaries. The other methods successively chained the observations into one cluster. The optimal number of distinctive bleeding patterns was six. We found two desirable and four undesirable bleeding patterns. Cyclic and non cyclic bleeding patterns were well separated. Conclusion Using this cluster analysis with the method of Ward medications and devices having an impact on bleeding can be easily compared and categorized.
Technology Clusters Exploration for Patent Portfolio through Patent Abstract Analysis
Directory of Open Access Journals (Sweden)
Gabjo Kim
2016-12-01
Full Text Available This study explores technology clusters through patent analysis. The aim of exploring technology clusters is to grasp competitors’ levels of sustainable research and development (R&D and establish a sustainable strategy for entering an industry. To achieve this, we first grouped the patent documents with similar technologies by applying affinity propagation (AP clustering, which is effective while grouping large amounts of data. Next, in order to define the technology clusters, we adopted the term frequency-inverse document frequency (TF-IDF weight, which lists the terms in order of importance. We collected the patent data of Korean electric car companies from the United States Patent and Trademark Office (USPTO to verify our proposed methodology. As a result, our proposed methodology presents more detailed information on the Korean electric car industry than previous studies.
Kazemi, Fatemeh; Najafabadi, Tooraj Abbasian; Araabi, Babak Nadjar
2016-01-01
Acute myelogenous leukemia (AML) is a subtype of acute leukemia, which is characterized by the accumulation of myeloid blasts in the bone marrow. Careful microscopic examination of stained blood smear or bone marrow aspirate is still the most significant diagnostic methodology for initial AML screening and considered as the first step toward diagnosis. It is time-consuming and due to the elusive nature of the signs and symptoms of AML; wrong diagnosis may occur by pathologists. Therefore, the need for automation of leukemia detection has arisen. In this paper, an automatic technique for identification and detection of AML and its prevalent subtypes, i.e., M2-M5 is presented. At first, microscopic images are acquired from blood smears of patients with AML and normal cases. After applying image preprocessing, color segmentation strategy is applied for segmenting white blood cells from other blood components and then discriminative features, i.e., irregularity, nucleus-cytoplasm ratio, Hausdorff dimension, shape, color, and texture features are extracted from the entire nucleus in the whole images containing multiple nuclei. Images are classified to cancerous and noncancerous images by binary support vector machine (SVM) classifier with 10-fold cross validation technique. Classifier performance is evaluated by three parameters, i.e., sensitivity, specificity, and accuracy. Cancerous images are also classified into their prevalent subtypes by multi-SVM classifier. The results show that the proposed algorithm has achieved an acceptable performance for diagnosis of AML and its common subtypes. Therefore, it can be used as an assistant diagnostic tool for pathologists.
CLUSTER ANALYSIS UKRAINIAN REGIONAL DISTRIBUTION BY LEVEL OF INNOVATION
Directory of Open Access Journals (Sweden)
Roman Shchur
2016-07-01
Full Text Available SWOT-analysis of the threats and benefits of innovation development strategy of Ivano-Frankivsk region in the context of financial support was сonducted. Methodical approach to determine of public-private partnerships potential that is tool of innovative economic development financing was identified. Cluster analysis of possibilities of forming public-private partnership in a particular region was carried out. Optimal set of problem areas that require urgent solutions and financial security is defined on the basis of cluster approach. It will help to form practical recommendations for the formation of an effective financial mechanism in the regions of Ukraine. Key words: the mechanism of innovation development financial provision, innovation development, public-private partnerships, cluster analysis, innovative development strategy.
A semi-supervised segmentation algorithm as applied to k-means ...
African Journals Online (AJOL)
Density based clustering makes use of probability density estimates to define ...... [2] Anderson R, 2007, The credit scoring toolkit: theory and practice for retail credit .... [46] Shifa N & Rashid M, 2003, Monte Carlo Evaluation of Consistency and ...
Cluster-based analysis of multi-model climate ensembles
Hyde, Richard; Hossaini, Ryan; Leeson, Amber A.
2018-06-01
Clustering - the automated grouping of similar data - can provide powerful and unique insight into large and complex data sets, in a fast and computationally efficient manner. While clustering has been used in a variety of fields (from medical image processing to economics), its application within atmospheric science has been fairly limited to date, and the potential benefits of the application of advanced clustering techniques to climate data (both model output and observations) has yet to be fully realised. In this paper, we explore the specific application of clustering to a multi-model climate ensemble. We hypothesise that clustering techniques can provide (a) a flexible, data-driven method of testing model-observation agreement and (b) a mechanism with which to identify model development priorities. We focus our analysis on chemistry-climate model (CCM) output of tropospheric ozone - an important greenhouse gas - from the recent Atmospheric Chemistry and Climate Model Intercomparison Project (ACCMIP). Tropospheric column ozone from the ACCMIP ensemble was clustered using the Data Density based Clustering (DDC) algorithm. We find that a multi-model mean (MMM) calculated using members of the most-populous cluster identified at each location offers a reduction of up to ˜ 20 % in the global absolute mean bias between the MMM and an observed satellite-based tropospheric ozone climatology, with respect to a simple, all-model MMM. On a spatial basis, the bias is reduced at ˜ 62 % of all locations, with the largest bias reductions occurring in the Northern Hemisphere - where ozone concentrations are relatively large. However, the bias is unchanged at 9 % of all locations and increases at 29 %, particularly in the Southern Hemisphere. The latter demonstrates that although cluster-based subsampling acts to remove outlier model data, such data may in fact be closer to observed values in some locations. We further demonstrate that clustering can provide a viable and
Application of microarray analysis on computer cluster and cloud platforms.
Bernau, C; Boulesteix, A-L; Knaus, J
2013-01-01
Analysis of recent high-dimensional biological data tends to be computationally intensive as many common approaches such as resampling or permutation tests require the basic statistical analysis to be repeated many times. A crucial advantage of these methods is that they can be easily parallelized due to the computational independence of the resampling or permutation iterations, which has induced many statistics departments to establish their own computer clusters. An alternative is to rent computing resources in the cloud, e.g. at Amazon Web Services. In this article we analyze whether a selection of statistical projects, recently implemented at our department, can be efficiently realized on these cloud resources. Moreover, we illustrate an opportunity to combine computer cluster and cloud resources. In order to compare the efficiency of computer cluster and cloud implementations and their respective parallelizations we use microarray analysis procedures and compare their runtimes on the different platforms. Amazon Web Services provide various instance types which meet the particular needs of the different statistical projects we analyzed in this paper. Moreover, the network capacity is sufficient and the parallelization is comparable in efficiency to standard computer cluster implementations. Our results suggest that many statistical projects can be efficiently realized on cloud resources. It is important to mention, however, that workflows can change substantially as a result of a shift from computer cluster to cloud computing.
Cluster Analysis as an Analytical Tool of Population Policy
Directory of Open Access Journals (Sweden)
Oksana Mikhaylovna Shubat
2017-12-01
Full Text Available The predicted negative trends in Russian demography (falling birth rates, population decline actualize the need to strengthen measures of family and population policy. Our research purpose is to identify groups of Russian regions with similar characteristics in the family sphere using cluster analysis. The findings should make an important contribution to the field of family policy. We used hierarchical cluster analysis based on the Ward method and the Euclidean distance for segmentation of Russian regions. Clustering is based on four variables, which allowed assessing the family institution in the region. The authors used the data of Federal State Statistics Service from 2010 to 2015. Clustering and profiling of each segment has allowed forming a model of Russian regions depending on the features of the family institution in these regions. The authors revealed four clusters grouping regions with similar problems in the family sphere. This segmentation makes it possible to develop the most relevant family policy measures in each group of regions. Thus, the analysis has shown a high degree of differentiation of the family institution in the regions. This suggests that a unified approach to population problems’ solving is far from being effective. To achieve greater results in the implementation of family policy, a differentiated approach is needed. Methods of multidimensional data classification can be successfully applied as a relevant analytical toolkit. Further research could develop the adaptation of multidimensional classification methods to the analysis of the population problems in Russian regions. In particular, the algorithms of nonparametric cluster analysis may be of relevance in future studies.
Cluster Oriented Spatio Temporal Multidimensional Data Visualization of Earthquakes in Indonesia
Directory of Open Access Journals (Sweden)
Mohammad Nur Shodiq
2016-03-01
Full Text Available Spatio temporal data clustering is challenge task. The result of clustering data are utilized to investigate the seismic parameters. Seismic parameters are used to describe the characteristics of earthquake behavior. One of the effective technique to study multidimensional spatio temporal data is visualization. But, visualization of multidimensional data is complicated problem. Because, this analysis consists of observed data cluster and seismic parameters. In this paper, we propose a visualization system, called as IES (Indonesia Earthquake System, for cluster analysis, spatio temporal analysis, and visualize the multidimensional data of seismic parameters. We analyze the cluster analysis by using automatic clustering, that consists of get optimal number of cluster and Hierarchical K-means clustering. We explore the visual cluster and multidimensional data in low dimensional space visualization. We made experiment with observed data, that consists of seismic data around Indonesian archipelago during 2004 to 2014. Keywords: Clustering, visualization, multidimensional data, seismic parameters.
Cascaded K-means convolutional feature learner and its application to face recognition
Zhou, Daoxiang; Yang, Dan; Zhang, Xiaohong; Huang, Sheng; Feng, Shu
2017-09-01
Currently, considerable efforts have been devoted to devise image representation. However, handcrafted methods need strong domain knowledge and show low generalization ability, and conventional feature learning methods require enormous training data and rich parameters tuning experience. A lightened feature learner is presented to solve these problems with application to face recognition, which shares similar topology architecture as a convolutional neural network. Our model is divided into three components: cascaded convolution filters bank learning layer, nonlinear processing layer, and feature pooling layer. Specifically, in the filters learning layer, we use K-means to learn convolution filters. Features are extracted via convoluting images with the learned filters. Afterward, in the nonlinear processing layer, hyperbolic tangent is employed to capture the nonlinear feature. In the feature pooling layer, to remove the redundancy information and incorporate the spatial layout, we exploit multilevel spatial pyramid second-order pooling technique to pool the features in subregions and concatenate them together as the final representation. Extensive experiments on four representative datasets demonstrate the effectiveness and robustness of our model to various variations, yielding competitive recognition results on extended Yale B and FERET. In addition, our method achieves the best identification performance on AR and labeled faces in the wild datasets among the comparative methods.
The Segmentation of Point Clouds with K-Means and ANN (artifical Neural Network)
Kuçak, R. A.; Özdemir, E.; Erol, S.
2017-05-01
Segmentation of point clouds is recently used in many Geomatics Engineering applications such as the building extraction in urban areas, Digital Terrain Model (DTM) generation and the road or urban furniture extraction. Segmentation is a process of dividing point clouds according to their special characteristic layers. The present paper discusses K-means and self-organizing map (SOM) which is a type of ANN (Artificial Neural Network) segmentation algorithm which treats the segmentation of point cloud. The point clouds which generate with photogrammetric method and Terrestrial Lidar System (TLS) were segmented according to surface normal, intensity and curvature. Thus, the results were evaluated. LIDAR (Light Detection and Ranging) and Photogrammetry are commonly used to obtain point clouds in many remote sensing and geodesy applications. By photogrammetric method or LIDAR method, it is possible to obtain point cloud from terrestrial or airborne systems. In this study, the measurements were made with a Leica C10 laser scanner in LIDAR method. In photogrammetric method, the point cloud was obtained from photographs taken from the ground with a 13 MP non-metric camera.
THE SEGMENTATION OF POINT CLOUDS WITH K-MEANS AND ANN (ARTIFICAL NEURAL NETWORK
Directory of Open Access Journals (Sweden)
R. A. Kuçak
2017-05-01
Full Text Available Segmentation of point clouds is recently used in many Geomatics Engineering applications such as the building extraction in urban areas, Digital Terrain Model (DTM generation and the road or urban furniture extraction. Segmentation is a process of dividing point clouds according to their special characteristic layers. The present paper discusses K-means and self-organizing map (SOM which is a type of ANN (Artificial Neural Network segmentation algorithm which treats the segmentation of point cloud. The point clouds which generate with photogrammetric method and Terrestrial Lidar System (TLS were segmented according to surface normal, intensity and curvature. Thus, the results were evaluated. LIDAR (Light Detection and Ranging and Photogrammetry are commonly used to obtain point clouds in many remote sensing and geodesy applications. By photogrammetric method or LIDAR method, it is possible to obtain point cloud from terrestrial or airborne systems. In this study, the measurements were made with a Leica C10 laser scanner in LIDAR method. In photogrammetric method, the point cloud was obtained from photographs taken from the ground with a 13 MP non-metric camera.
Big Data Management with Incremental K-Means Trees–GPU-Accelerated Construction and Visualization
Directory of Open Access Journals (Sweden)
Jun Wang
2017-07-01
Full Text Available While big data is revolutionizing scientific research, the tasks of data management and analytics are becoming more challenging than ever. One way to remit the difficulty is to obtain the multilevel hierarchy embedded in the data. Knowing the hierarchy enables not only the revelation of the nature of the data, it is also often the first step in big data analytics. However, current algorithms for learning the hierarchy are typically not scalable to large volumes of data with high dimensionality. To tackle this challenge, in this paper, we propose a new scalable approach for constructing the tree structure from data. Our method builds the tree in a bottom-up manner, with adapted incremental k-means. By referencing the distribution of point distances, one can flexibly control the height of the tree and the branching of each node. Dimension reduction is also conducted as a pre-process, to further boost the computing efficiency. The algorithm takes a parallel design and is implemented with CUDA (Compute Unified Device Architecture, so that it can be efficiently applied to big data. We test the algorithm with two real-world datasets, and the results are visualized with extended circular dendrograms and other visualization techniques.
Discriminative Hierarchical K-Means Tree for Large-Scale Image Classification.
Chen, Shizhi; Yang, Xiaodong; Tian, Yingli
2015-09-01
A key challenge in large-scale image classification is how to achieve efficiency in terms of both computation and memory without compromising classification accuracy. The learning-based classifiers achieve the state-of-the-art accuracies, but have been criticized for the computational complexity that grows linearly with the number of classes. The nonparametric nearest neighbor (NN)-based classifiers naturally handle large numbers of categories, but incur prohibitively expensive computation and memory costs. In this brief, we present a novel classification scheme, i.e., discriminative hierarchical K-means tree (D-HKTree), which combines the advantages of both learning-based and NN-based classifiers. The complexity of the D-HKTree only grows sublinearly with the number of categories, which is much better than the recent hierarchical support vector machines-based methods. The memory requirement is the order of magnitude less than the recent Naïve Bayesian NN-based approaches. The proposed D-HKTree classification scheme is evaluated on several challenging benchmark databases and achieves the state-of-the-art accuracies, while with significantly lower computation cost and memory requirement.
Automated analysis of organic particles using cluster SIMS
Energy Technology Data Exchange (ETDEWEB)
Gillen, Greg; Zeissler, Cindy; Mahoney, Christine; Lindstrom, Abigail; Fletcher, Robert; Chi, Peter; Verkouteren, Jennifer; Bright, David; Lareau, Richard T.; Boldman, Mike
2004-06-15
Cluster primary ion bombardment combined with secondary ion imaging is used on an ion microscope secondary ion mass spectrometer for the spatially resolved analysis of organic particles on various surfaces. Compared to the use of monoatomic primary ion beam bombardment, the use of a cluster primary ion beam (SF{sub 5}{sup +} or C{sub 8}{sup -}) provides significant improvement in molecular ion yields and a reduction in beam-induced degradation of the analyte molecules. These characteristics of cluster bombardment, along with automated sample stage control and custom image analysis software are utilized to rapidly characterize the spatial distribution of trace explosive particles, narcotics and inkjet-printed microarrays on a variety of surfaces.
Fukuoka, Yoshimi; Zhou, Mo; Vittinghoff, Eric; Haskell, William; Goldberg, Ken; Aswani, Anil
2018-02-01
Determining patterns of physical activity throughout the day could assist in developing more personalized interventions or physical activity guidelines in general and, in particular, for women who are less likely to be physically active than men. The aims of this report are to identify clusters of women based on accelerometer-measured baseline raw metabolic equivalent of task (MET) values and a normalized version of the METs ≥3 data, and to compare sociodemographic and cardiometabolic risks among these identified clusters. A total of 215 women who were enrolled in the Mobile Phone Based Physical Activity Education (mPED) trial and wore an accelerometer for at least 8 hours per day for the 7 days prior to the randomization visit were analyzed. The k-means clustering method and the Lloyd algorithm were used on the data. We used the elbow method to choose the number of clusters, looking at the percentage of variance explained as a function of the number of clusters. The results of the k-means cluster analyses of raw METs revealed three different clusters. The unengaged group (n=102) had the highest depressive symptoms score compared with the afternoon engaged (n=65) and morning engaged (n=48) groups (overall Pcluster groups using a large national dataset. ClinicalTrials.gov NCT01280812; https://clinicaltrials.gov/ct2/show/NCT01280812 (Archived by WebCite at http://www.webcitation.org/6vVyLzwft). ©Yoshimi Fukuoka, Mo Zhou, Eric Vittinghoff, William Haskell, Ken Goldberg, Anil Aswani. Originally published in JMIR Public Health and Surveillance (http://publichealth.jmir.org), 01.02.2018.
Assessment of surface water quality using hierarchical cluster analysis
Directory of Open Access Journals (Sweden)
Dheeraj Kumar Dabgerwal
2016-02-01
Full Text Available This study was carried out to assess the physicochemical quality river Varuna inVaranasi,India. Water samples were collected from 10 sites during January-June 2015. Pearson correlation analysis was used to assess the direction and strength of relationship between physicochemical parameters. Hierarchical Cluster analysis was also performed to determine the sources of pollution in the river Varuna. The result showed quite high value of DO, Nitrate, BOD, COD and Total Alkalinity, above the BIS permissible limit. The results of correlation analysis identified key water parameters as pH, electrical conductivity, total alkalinity and nitrate, which influence the concentration of other water parameters. Cluster analysis identified three major clusters of sampling sites out of total 10 sites, according to the similarity in water quality. This study illustrated the usefulness of correlation and cluster analysis for getting better information about the river water quality.International Journal of Environment Vol. 5 (1 2016, pp: 32-44
application of single-linkage clustering method in the analysis of ...
African Journals Online (AJOL)
Admin
ANALYSIS OF GROWTH RATE OF GROSS DOMESTIC PRODUCT. (GDP) AT ... The end result of the algorithm is a tree of clusters called a dendrogram, which shows how the clusters are ..... Number of cluster sum from from observations of ...
Cluster Analysis of Clinical Data Identifies Fibromyalgia Subgroups
Docampo, Elisa; Collado, Antonio; Escaramís, Geòrgia; Carbonell, Jordi; Rivera, Javier; Vidal, Javier; Alegre, José
2013-01-01
Introduction Fibromyalgia (FM) is mainly characterized by widespread pain and multiple accompanying symptoms, which hinder FM assessment and management. In order to reduce FM heterogeneity we classified clinical data into simplified dimensions that were used to define FM subgroups. Material and Methods 48 variables were evaluated in 1,446 Spanish FM cases fulfilling 1990 ACR FM criteria. A partitioning analysis was performed to find groups of variables similar to each other. Similarities between variables were identified and the variables were grouped into dimensions. This was performed in a subset of 559 patients, and cross-validated in the remaining 887 patients. For each sample and dimension, a composite index was obtained based on the weights of the variables included in the dimension. Finally, a clustering procedure was applied to the indexes, resulting in FM subgroups. Results Variables clustered into three independent dimensions: “symptomatology”, “comorbidities” and “clinical scales”. Only the two first dimensions were considered for the construction of FM subgroups. Resulting scores classified FM samples into three subgroups: low symptomatology and comorbidities (Cluster 1), high symptomatology and comorbidities (Cluster 2), and high symptomatology but low comorbidities (Cluster 3), showing differences in measures of disease severity. Conclusions We have identified three subgroups of FM samples in a large cohort of FM by clustering clinical data. Our analysis stresses the importance of family and personal history of FM comorbidities. Also, the resulting patient clusters could indicate different forms of the disease, relevant to future research, and might have an impact on clinical assessment. PMID:24098674
Transcriptional analysis of ESAT-6 cluster 3 in Mycobacterium smegmatis
Directory of Open Access Journals (Sweden)
Riccardi Giovanna
2009-03-01
Full Text Available Abstract Background The ESAT-6 (early secreted antigenic target, 6 kDa family collects small mycobacterial proteins secreted by Mycobacterium tuberculosis, particularly in the early phase of growth. There are 23 ESAT-6 family members in M. tuberculosis H37Rv. In a previous work, we identified the Zur- dependent regulation of five proteins of the ESAT-6/CFP-10 family (esxG, esxH, esxQ, esxR, and esxS. esxG and esxH are part of ESAT-6 cluster 3, whose expression was already known to be induced by iron starvation. Results In this research, we performed EMSA experiments and transcriptional analysis of ESAT-6 cluster 3 in Mycobacterium smegmatis (msmeg0615-msmeg0625 and M. tuberculosis. In contrast to what we had observed in M. tuberculosis, we found that in M. smegmatis ESAT-6 cluster 3 responds only to iron and not to zinc. In both organisms we identified an internal promoter, a finding which suggests the presence of two transcriptional units and, by consequence, a differential expression of cluster 3 genes. We compared the expression of msmeg0615 and msmeg0620 in different growth and stress conditions by means of relative quantitative PCR. The expression of msmeg0615 and msmeg0620 genes was essentially similar; they appeared to be repressed in most of the tested conditions, with the exception of acid stress (pH 4.2 where msmeg0615 was about 4-fold induced, while msmeg0620 was repressed. Analysis revealed that in acid stress conditions M. tuberculosis rv0282 gene was 3-fold induced too, while rv0287 induction was almost insignificant. Conclusion In contrast with what has been reported for M. tuberculosis, our results suggest that in M. smegmatis only IdeR-dependent regulation is retained, while zinc has no effect on gene expression. The role of cluster 3 in M. tuberculosis virulence is still to be defined; however, iron- and zinc-dependent expression strongly suggests that cluster 3 is highly expressed in the infective process, and that the cluster
Graph analysis of cell clusters forming vascular networks
Alves, A. P.; Mesquita, O. N.; Gómez-Gardeñes, J.; Agero, U.
2018-03-01
This manuscript describes the experimental observation of vasculogenesis in chick embryos by means of network analysis. The formation of the vascular network was observed in the area opaca of embryos from 40 to 55 h of development. In the area opaca endothelial cell clusters self-organize as a primitive and approximately regular network of capillaries. The process was observed by bright-field microscopy in control embryos and in embryos treated with Bevacizumab (Avastin), an antibody that inhibits the signalling of the vascular endothelial growth factor (VEGF). The sequence of images of the vascular growth were thresholded, and used to quantify the forming network in control and Avastin-treated embryos. This characterization is made by measuring vessels density, number of cell clusters and the largest cluster density. From the original images, the topology of the vascular network was extracted and characterized by means of the usual network metrics such as: the degree distribution, average clustering coefficient, average short path length and assortativity, among others. This analysis allows to monitor how the largest connected cluster of the vascular network evolves in time and provides with quantitative evidence of the disruptive effects that Avastin has on the tree structure of vascular networks.
Indian Academy of Sciences (India)
2017-09-27
Sep 27, 2017 ... Author for correspondence (zh4403701@126.com). MS received 15 ... lic clusters using density functional theory (DFT)-GGA of the DMOL3 package. ... In the process of geometric optimization, con- vergence thresholds ..... and Postgraduate Research & Practice Innovation Program of. Jiangsu Province ...
Indian Academy of Sciences (India)
environmental as well as technical problems during fuel gas utilization. ... adsorption on some alloys of Pd, namely PdAu, PdAg ... ried out on small neutral and charged Au24,26,27, Cu,28 ... study of Zanti et al.29 on Pdn (n = 1–9) clusters.
Cluster Analysis of International Information and Social Development.
Lau, Jesus
1990-01-01
Analyzes information activities in relation to socioeconomic characteristics in low, middle, and highly developed economies for the years 1960 and 1977 through the use of cluster analysis. Results of data from 31 countries suggest that information development is achieved mainly by countries that have also achieved social development. (26…
Making Sense of Cluster Analysis: Revelations from Pakistani Science Classes
Pell, Tony; Hargreaves, Linda
2011-01-01
Cluster analysis has been applied to quantitative data in educational research over several decades and has been a feature of the Maurice Galton's research in primary and secondary classrooms. It has offered potentially useful insights for teaching yet its implications for practice are rarely implemented. It has been subject also to negative…
A Cluster Analysis of Personality Style in Adults with ADHD
Robin, Arthur L.; Tzelepis, Angela; Bedway, Marquita
2008-01-01
Objective: The purpose of this study was to use hierarchical linear cluster analysis to examine the normative personality styles of adults with ADHD. Method: A total of 311 adults with ADHD completed the Millon Index of Personality Styles, which consists of 24 scales assessing motivating aims, cognitive modes, and interpersonal behaviors. Results:…
Characterization of population exposure to organochlorines: A cluster analysis application
R.M. Guimarães (Raphael Mendonça); S. Asmus (Sven); A. Burdorf (Alex)
2013-01-01
textabstractThis study aimed to show the results from a cluster analysis application in the characterization of population exposure to organochlorines through variables related to time and exposure dose. Characteristics of 354 subjects in a population exposed to organochlorine pesticides residues
Robustness in cluster analysis in the presence of anomalous observations
Zhuk, EE
Cluster analysis of multivariate observations in the presence of "outliers" (anomalous observations) in a sample is studied. The expected (mean) fraction of erroneous decisions for the decision rule is computed analytically by minimizing the intraclass scatter. A robust decision rule (stable to
Language Learner Motivational Types: A Cluster Analysis Study
Papi, Mostafa; Teimouri, Yasser
2014-01-01
The study aimed to identify different second language (L2) learner motivational types drawing on the framework of the L2 motivational self system. A total of 1,278 secondary school students learning English in Iran completed a questionnaire survey. Cluster analysis yielded five different groups based on the strength of different variables within…
Cluster analysis as a prediction tool for pregnancy outcomes.
Banjari, Ines; Kenjerić, Daniela; Šolić, Krešimir; Mandić, Milena L
2015-03-01
Considering specific physiology changes during gestation and thinking of pregnancy as a "critical window", classification of pregnant women at early pregnancy can be considered as crucial. The paper demonstrates the use of a method based on an approach from intelligent data mining, cluster analysis. Cluster analysis method is a statistical method which makes possible to group individuals based on sets of identifying variables. The method was chosen in order to determine possibility for classification of pregnant women at early pregnancy to analyze unknown correlations between different variables so that the certain outcomes could be predicted. 222 pregnant women from two general obstetric offices' were recruited. The main orient was set on characteristics of these pregnant women: their age, pre-pregnancy body mass index (BMI) and haemoglobin value. Cluster analysis gained a 94.1% classification accuracy rate with three branch- es or groups of pregnant women showing statistically significant correlations with pregnancy outcomes. The results are showing that pregnant women both of older age and higher pre-pregnancy BMI have a significantly higher incidence of delivering baby of higher birth weight but they gain significantly less weight during pregnancy. Their babies are also longer, and these women have significantly higher probability for complications during pregnancy (gestosis) and higher probability of induced or caesarean delivery. We can conclude that the cluster analysis method can appropriately classify pregnant women at early pregnancy to predict certain outcomes.
Identifying clinical course patterns in SMS data using cluster analysis
DEFF Research Database (Denmark)
Kent, Peter; Kongsted, Alice
2012-01-01
ABSTRACT: BACKGROUND: Recently, there has been interest in using the short message service (SMS or text messaging), to gather frequent information on the clinical course of individual patients. One possible role for identifying clinical course patterns is to assist in exploring clinically important...... showed that clinical course patterns can be identified by cluster analysis using all SMS time points as cluster variables. This method is simple, intuitive and does not require a high level of statistical skill. However, there are alternative ways of managing SMS data and many different methods...
Color segmentation in the HSI color space using the K-means algorithm
Weeks, Arthur R.; Hague, G. Eric
1997-04-01
Segmentation of images is an important aspect of image recognition. While grayscale image segmentation has become quite a mature field, much less work has been done with regard to color image segmentation. Until recently, this was predominantly due to the lack of available computing power and color display hardware that is required to manipulate true color images (24-bit). TOday, it is not uncommon to find a standard desktop computer system with a true-color 24-bit display, at least 8 million bytes of memory, and 2 gigabytes of hard disk storage. Segmentation of color images is not as simple as segmenting each of the three RGB color components separately. The difficulty of using the RGB color space is that it doesn't closely model the psychological understanding of color. A better color model, which closely follows that of human visual perception is the hue, saturation, intensity model. This color model separates the color components in terms of chromatic and achromatic information. Strickland et al. was able to show the importance of color in the extraction of edge features form an image. His method enhances the edges that are detectable in the luminance image with information from the saturation image. Segmentation of both the saturation and intensity components is easily accomplished with any gray scale segmentation algorithm, since these spaces are linear. The modulus 2(pi) nature of the hue color component makes its segmentation difficult. For example, a hue of 0 and 2(pi) yields the same color tint. Instead of applying separate image segmentation to each of the hue, saturation, and intensity components, a better method is to segment the chromatic component separately from the intensity component because of the importance that the chromatic information plays in the segmentation of color images. This paper presents a method of using the gray scale K-means algorithm to segment 24-bit color images. Additionally, this paper will show the importance the hue
Chang, Bingguo; Chen, Xiaofei
2018-05-01
Ultrasonography is an important examination for the diagnosis of chronic liver disease. The doctor gives the liver indicators and suggests the patient's condition according to the description of ultrasound report. With the rapid increase in the amount of data of ultrasound report, the workload of professional physician to manually distinguish ultrasound results significantly increases. In this paper, we use the spectral clustering method to cluster analysis of the description of the ultrasound report, and automatically generate the ultrasonic diagnostic diagnosis by machine learning. 110 groups ultrasound examination report of chronic liver disease were selected as test samples in this experiment, and the results were validated by spectral clustering and compared with k-means clustering algorithm. The results show that the accuracy of spectral clustering is 92.73%, which is higher than that of k-means clustering algorithm, which provides a powerful ultrasound-assisted diagnosis for patients with chronic liver disease.
Outcome-Driven Cluster Analysis with Application to Microarray Data.
Directory of Open Access Journals (Sweden)
Jessie J Hsu
Full Text Available One goal of cluster analysis is to sort characteristics into groups (clusters so that those in the same group are more highly correlated to each other than they are to those in other groups. An example is the search for groups of genes whose expression of RNA is correlated in a population of patients. These genes would be of greater interest if their common level of RNA expression were additionally predictive of the clinical outcome. This issue arose in the context of a study of trauma patients on whom RNA samples were available. The question of interest was whether there were groups of genes that were behaving similarly, and whether each gene in the cluster would have a similar effect on who would recover. For this, we develop an algorithm to simultaneously assign characteristics (genes into groups of highly correlated genes that have the same effect on the outcome (recovery. We propose a random effects model where the genes within each group (cluster equal the sum of a random effect, specific to the observation and cluster, and an independent error term. The outcome variable is a linear combination of the random effects of each cluster. To fit the model, we implement a Markov chain Monte Carlo algorithm based on the likelihood of the observed data. We evaluate the effect of including outcome in the model through simulation studies and describe a strategy for prediction. These methods are applied to trauma data from the Inflammation and Host Response to Injury research program, revealing a clustering of the genes that are informed by the recovery outcome.
Semi-supervised clustering methods.
Bair, Eric
2013-01-01
Cluster analysis methods seek to partition a data set into homogeneous subgroups. It is useful in a wide variety of applications, including document processing and modern genetics. Conventional clustering methods are unsupervised, meaning that there is no outcome variable nor is anything known about the relationship between the observations in the data set. In many situations, however, information about the clusters is available in addition to the values of the features. For example, the cluster labels of some observations may be known, or certain observations may be known to belong to the same cluster. In other cases, one may wish to identify clusters that are associated with a particular outcome variable. This review describes several clustering algorithms (known as "semi-supervised clustering" methods) that can be applied in these situations. The majority of these methods are modifications of the popular k-means clustering method, and several of them will be described in detail. A brief description of some other semi-supervised clustering algorithms is also provided.
High-dimensional cluster analysis with the Masked EM Algorithm
Kadir, Shabnam N.; Goodman, Dan F. M.; Harris, Kenneth D.
2014-01-01
Cluster analysis faces two problems in high dimensions: first, the “curse of dimensionality” that can lead to overfitting and poor generalization performance; and second, the sheer time taken for conventional algorithms to process large amounts of high-dimensional data. We describe a solution to these problems, designed for the application of “spike sorting” for next-generation high channel-count neural probes. In this problem, only a small subset of features provide information about the cluster member-ship of any one data vector, but this informative feature subset is not the same for all data points, rendering classical feature selection ineffective. We introduce a “Masked EM” algorithm that allows accurate and time-efficient clustering of up to millions of points in thousands of dimensions. We demonstrate its applicability to synthetic data, and to real-world high-channel-count spike sorting data. PMID:25149694
A cluster analysis investigation of workaholism as a syndrome.
Aziz, Shahnaz; Zickar, Michael J
2006-01-01
Workaholism has been conceptualized as a syndrome although there have been few tests that explicitly consider its syndrome status. The authors analyzed a three-dimensional scale of workaholism developed by Spence and Robbins (1992) using cluster analysis. The authors identified three clusters of individuals, one of which corresponded to Spence and Robbins's profile of the workaholic (high work involvement, high drive to work, low work enjoyment). Consistent with previously conjectured relations with workaholism, individuals in the workaholic cluster were more likely to label themselves as workaholics, more likely to have acquaintances label them as workaholics, and more likely to have lower life satisfaction and higher work-life imbalance. The importance of considering workaholism as a syndrome and the implications for effective interventions are discussed. Copyright 2006 APA.
Cosmological analysis of galaxy clusters surveys in X-rays
International Nuclear Information System (INIS)
Clerc, N.
2012-01-01
Clusters of galaxies are the most massive objects in equilibrium in our Universe. Their study allows to test cosmological scenarios of structure formation with precision, bringing constraints complementary to those stemming from the cosmological background radiation, supernovae or galaxies. They are identified through the X-ray emission of their heated gas, thus facilitating their mapping at different epochs of the Universe. This report presents two surveys of galaxy clusters detected in X-rays and puts forward a method for their cosmological interpretation. Thanks to its multi-wavelength coverage extending over 10 sq. deg. and after one decade of expertise, the XMM-LSS allows a systematic census of clusters in a large volume of the Universe. In the framework of this survey, the first part of this report describes the techniques developed to the purpose of characterizing the detected objects. A particular emphasis is placed on the most distant ones (z ≥ 1) through the complementarity of observations in X-ray, optical and infrared bands. Then the X-CLASS survey is fully described. Based on XMM archival data, it provides a new catalogue of 800 clusters detected in X-rays. A cosmological analysis of this survey is performed thanks to 'CR-HR' diagrams. This new method self-consistently includes selection effects and scaling relations and provides a means to bypass the computation of individual cluster masses. Propositions are made for applying this method to future surveys as XMM-XXL and eRosita. (author) [fr
Cluster analysis by optimal decomposition of induced fuzzy sets
Energy Technology Data Exchange (ETDEWEB)
Backer, E
1978-01-01
Nonsupervised pattern recognition is addressed and the concept of fuzzy sets is explored in order to provide the investigator (data analyst) additional information supplied by the pattern class membership values apart from the classical pattern class assignments. The basic ideas behind the pattern recognition problem, the clustering problem, and the concept of fuzzy sets in cluster analysis are discussed, and a brief review of the literature of the fuzzy cluster analysis is given. Some mathematical aspects of fuzzy set theory are briefly discussed; in particular, a measure of fuzziness is suggested. The optimization-clustering problem is characterized. Then the fundamental idea behind affinity decomposition is considered. Next, further analysis takes place with respect to the partitioning-characterization functions. The iterative optimization procedure is then addressed. The reclassification function is investigated and convergence properties are examined. Finally, several experiments in support of the method suggested are described. Four object data sets serve as appropriate test cases. 120 references, 70 figures, 11 tables. (RWR)
Clustering Professional Basketball Players by Performance
Patel, Riki
2017-01-01
Basketball players are traditionally grouped into five distinct positions, but these designationsare quickly becoming outdated. We attempt to reclassify players into new groupsbased on personal performance in the 2016-2017 NBA regular season. Two dimensionalityreduction techniques, t-Distributed Stochastic Neighbor Embedding (t-SNE) and principalcomponent analysis (PCA), were employed to reduce 18 classic metrics down to two dimensionsfor visualization. k-means clustering discovered four grou...
DGA Clustering and Analysis: Mastering Modern, Evolving Threats, DGALab
Directory of Open Access Journals (Sweden)
Alexander Chailytko
2016-05-01
Full Text Available Domain Generation Algorithms (DGA is a basic building block used in almost all modern malware. Malware researchers have attempted to tackle the DGA problem with various tools and techniques, with varying degrees of success. We present a complex solution to populate DGA feed using reversed DGAs, third-party feeds, and a smart DGA extraction and clustering based on emulation of a large number of samples. Smart DGA extraction requires no reverse engineering and works regardless of the DGA type or initialization vector, while enabling a cluster-based analysis. Our method also automatically allows analysis of the whole malware family, specific campaign, etc. We present our system and demonstrate its abilities on more than 20 malware families. This includes showing connections between different campaigns, as well as comparing results. Most importantly, we discuss how to utilize the outcome of the analysis to create smarter protections against similar malware.
Analysis of RXTE data on Clusters of Galaxies
Petrosian, Vahe
2004-01-01
This grant provided support for the reduction, analysis and interpretation of of hard X-ray (HXR, for short) observations of the cluster of galaxies RXJO658--5557 scheduled for the week of August 23, 2002 under the RXTE Cycle 7 program (PI Vahe Petrosian, Obs. ID 70165). The goal of the observation was to search for and characterize the shape of the HXR component beyond the well established thermal soft X-ray (SXR) component. Such hard components have been detected in several nearby clusters. distant cluster would provide information on the characteristics of this radiation at a different epoch in the evolution of the imiverse and shed light on its origin. We (Petrosian, 2001) have argued that thermal bremsstrahlung, as proposed earlier, cannot be the mechanism for the production of the HXRs and that the most likely mechanism is Compton upscattering of the cosmic microwave radiation by relativistic electrons which are known to be present in the clusters and be responsible for the observed radio emission. Based on this picture we estimated that this cluster, in spite of its relatively large distance, will have HXR signal comparable to the other nearby ones. The planned observation of a relatively The proposed RXTE observations were carried out and the data have been analyzed. We detect a hard X-ray tail in the spectrum of this cluster with a flux very nearly equal to our predicted value. This has strengthen the case for the Compton scattering model. We intend the data obtained via this observation to be a part of a larger data set. We have identified other clusters of galaxies (in archival RXTE and other instrument data sets) with sufficiently high quality data where we can search for and measure (or at least put meaningful limits) on the strength of the hard component. With these studies we expect to clarify the mechanism for acceleration of particles in the intercluster medium and provide guidance for future observations of this intriguing phenomenon by instrument
Mobility in Europe: Recent Trends from a Cluster Analysis
Directory of Open Access Journals (Sweden)
Ioana Manafi
2017-08-01
Full Text Available During the past decade, Europe was confronted with major changes and events offering large opportunities for mobility. The EU enlargement process, the EU policies regarding youth, the economic crisis affecting national economies on different levels, political instabilities in some European countries, high rates of unemployment or the increasing number of refugees are only a few of the factors influencing net migration in Europe. Based on a set of socio-economic indicators for EU/EFTA countries and cluster analysis, the paper provides an overview of regional differences across European countries, related to migration magnitude in the identified clusters. The obtained clusters are in accordance with previous studies in migration, and appear stable during the period of 2005-2013, with only some exceptions. The analysis revealed three country clusters: EU/EFTA center-receiving countries, EU/EFTA periphery-sending countries and EU/EFTA outlier countries, the names suggesting not only the geographical position within Europe, but the trends in net migration flows during the years. Therewith, the results provide evidence for the persistence of a movement from periphery to center countries, which is correlated with recent flows of mobility in Europe.
The Productivity Analysis of Chennai Automotive Industry Cluster
Bhaskaran, E.
2014-07-01
Chennai, also called the Detroit of India, is India's second fastest growing auto market and exports auto components and vehicles to US, Germany, Japan and Brazil. For inclusive growth and sustainable development, 250 auto component industries in Ambattur, Thirumalisai and Thirumudivakkam Industrial Estates located in Chennai have adopted the Cluster Development Approach called Automotive Component Cluster. The objective is to study the Value Chain, Correlation and Data Envelopment Analysis by determining technical efficiency, peer weights, input and output slacks of 100 auto component industries in three estates. The methodology adopted is using Data Envelopment Analysis of Output Oriented Banker Charnes Cooper model by taking net worth, fixed assets, employment as inputs and gross output as outputs. The non-zero represents the weights for efficient clusters. The higher slack obtained reveals the excess net worth, fixed assets, employment and shortage in gross output. To conclude, the variables are highly correlated and the inefficient industries should increase their gross output or decrease the fixed assets or employment. Moreover for sustainable development, the cluster should strengthen infrastructure, technology, procurement, production and marketing interrelationships to decrease costs and to increase productivity and efficiency to compete in the indigenous and export market.
Sirenomelia in Argentina: Prevalence, geographic clusters and temporal trends analysis.
Groisman, Boris; Liascovich, Rosa; Gili, Juan Antonio; Barbero, Pablo; Bidondo, María Paz
2016-07-01
Sirenomelia is a severe malformation of the lower body characterized by a single medial lower limb and a variable combination of visceral abnormalities. Given that Sirenomelia is a very rare birth defect, epidemiological studies are scarce. The aim of this study is to evaluate prevalence, geographic clusters and time trends of sirenomelia in Argentina, using data from the National Network of Congenital Anomalies of Argentina (RENAC) from November 2009 until December 2014. This is a descriptive study using data from the RENAC, a hospital-based surveillance system for newborns affected with major morphological congenital anomalies. We calculated sirenomelia prevalence throughout the period, searched for geographical clusters, and evaluated time trends. The prevalence of confirmed cases of sirenomelia throughout the period was 2.35 per 100,000 births. Cluster analysis showed no statistically significant geographical aggregates. Time-trends analysis showed that the prevalence was higher in years 2009 to 2010. The observed prevalence was higher than the observed in previous epidemiological studies in other geographic regions. We observed a likely real increase in the initial period of our study. We used strict diagnostic criteria, excluding cases that only had clinical diagnosis of sirenomelia. Therefore, real prevalence could be even higher. This study did not show any geographic clusters. Because etiology of sirenomelia has not yet been established, studies of epidemiological features of this defect may contribute to define its causes. Birth Defects Research (Part A) 106:604-611, 2016. © 2016 Wiley Periodicals, Inc. © 2016 Wiley Periodicals, Inc.
Vastano, Valeria; Perrone, Filomena; Marasco, Rosangela; Sacco, Margherita; Muscariello, Lidia
2016-04-01
Exopolysaccharides (EPS) from lactic acid bacteria contribute to specific rheology and texture of fermented milk products and find applications also in non-dairy foods and in therapeutics. Recently, four clusters of genes (cps) associated with surface polysaccharide production have been identified in Lactobacillus plantarum WCFS1, a probiotic and food-associated lactobacillus. These clusters are involved in cell surface architecture and probably in release and/or exposure of immunomodulating bacterial molecules. Here we show a transcriptional analysis of these clusters. Indeed, RT-PCR experiments revealed that the cps loci are organized in five operons. Moreover, by reverse transcription-qPCR analysis performed on L. plantarum WCFS1 (wild type) and WCFS1-2 (ΔccpA), we demonstrated that expression of three cps clusters is under the control of the global regulator CcpA. These results, together with the identification of putative CcpA target sequences (catabolite responsive element CRE) in the regulatory region of four out of five transcriptional units, strongly suggest for the first time a role of the master regulator CcpA in EPS gene transcription among lactobacilli.
Latent cluster analysis of ALS phenotypes identifies prognostically differing groups.
Directory of Open Access Journals (Sweden)
Jeban Ganesalingam
2009-09-01
Full Text Available Amyotrophic lateral sclerosis (ALS is a degenerative disease predominantly affecting motor neurons and manifesting as several different phenotypes. Whether these phenotypes correspond to different underlying disease processes is unknown. We used latent cluster analysis to identify groupings of clinical variables in an objective and unbiased way to improve phenotyping for clinical and research purposes.Latent class cluster analysis was applied to a large database consisting of 1467 records of people with ALS, using discrete variables which can be readily determined at the first clinic appointment. The model was tested for clinical relevance by survival analysis of the phenotypic groupings using the Kaplan-Meier method.The best model generated five distinct phenotypic classes that strongly predicted survival (p<0.0001. Eight variables were used for the latent class analysis, but a good estimate of the classification could be obtained using just two variables: site of first symptoms (bulbar or limb and time from symptom onset to diagnosis (p<0.00001.The five phenotypic classes identified using latent cluster analysis can predict prognosis. They could be used to stratify patients recruited into clinical trials and generating more homogeneous disease groups for genetic, proteomic and risk factor research.
The Quantitative Analysis of Chennai Automotive Industry Cluster
Bhaskaran, Ethirajan
2016-07-01
Chennai, also called as Detroit of India due to presence of Automotive Industry producing over 40 % of the India's vehicle and components. During 2001-2002, the Automotive Component Industries (ACI) in Ambattur, Thirumalizai and Thirumudivakkam Industrial Estate, Chennai has faced problems on infrastructure, technology, procurement, production and marketing. The objective is to study the Quantitative Performance of Chennai Automotive Industry Cluster before (2001-2002) and after the CDA (2008-2009). The methodology adopted is collection of primary data from 100 ACI using quantitative questionnaire and analyzing using Correlation Analysis (CA), Regression Analysis (RA), Friedman Test (FMT), and Kruskall Wallis Test (KWT).The CA computed for the different set of variables reveals that there is high degree of relationship between the variables studied. The RA models constructed establish the strong relationship between the dependent variable and a host of independent variables. The models proposed here reveal the approximate relationship in a closer form. KWT proves, there is no significant difference between three locations clusters with respect to: Net Profit, Production Cost, Marketing Costs, Procurement Costs and Gross Output. This supports that each location has contributed for development of automobile component cluster uniformly. The FMT proves, there is no significant difference between industrial units in respect of cost like Production, Infrastructure, Technology, Marketing and Net Profit. To conclude, the Automotive Industries have fully utilized the Physical Infrastructure and Centralised Facilities by adopting CDA and now exporting their products to North America, South America, Europe, Australia, Africa and Asia. The value chain analysis models have been implemented in all the cluster units. This Cluster Development Approach (CDA) model can be implemented in industries of under developed and developing countries for cost reduction and productivity
Statistical analysis of the spatial distribution of galaxies and clusters
International Nuclear Information System (INIS)
Cappi, Alberto
1993-01-01
This thesis deals with the analysis of the distribution of galaxies and clusters, describing some observational problems and statistical results. First chapter gives a theoretical introduction, aiming to describe the framework of the formation of structures, tracing the history of the Universe from the Planck time, t_p = 10"-"4"3 sec and temperature corresponding to 10"1"9 GeV, to the present epoch. The most usual statistical tools and models of the galaxy distribution, with their advantages and limitations, are described in chapter two. A study of the main observed properties of galaxy clustering, together with a detailed statistical analysis of the effects of selecting galaxies according to apparent magnitude or diameter, is reported in chapter three. Chapter four delineates some properties of groups of galaxies, explaining the reasons of discrepant results on group distributions. Chapter five is a study of the distribution of galaxy clusters, with different statistical tools, like correlations, percolation, void probability function and counts in cells; it is found the same scaling-invariant behaviour of galaxies. Chapter six describes our finding that rich galaxy clusters too belong to the fundamental plane of elliptical galaxies, and gives a discussion of its possible implications. Finally chapter seven reviews the possibilities offered by multi-slit and multi-fibre spectrographs, and I present some observational work on nearby and distant galaxy clusters. In particular, I show the opportunities offered by ongoing surveys of galaxies coupled with multi-object fibre spectrographs, focusing on the ESO Key Programme A galaxy redshift survey in the south galactic pole region to which I collaborate and on MEFOS, a multi-fibre instrument with automatic positioning. Published papers related to the work described in this thesis are reported in the last appendix. (author) [fr
Efficient Active Contour and K-Means Algorithms in Image Segmentation
Directory of Open Access Journals (Sweden)
J.R. Rommelse
2004-01-01
Full Text Available In this paper we discuss a classic clustering algorithm that can be used to segment images and a recently developed active contour image segmentation model. We propose integrating aspects of the classic algorithm to improve the active contour model. For the resulting CVK and B-means segmentation algorithms we examine methods to decrease the size of the image domain. The CVK method has been implemented to run on parallel and distributed computers. By changing the order of updating the pixels, it was possible to replace synchronous communication with asynchronous communication and subsequently the parallel efficiency is improved.
Directory of Open Access Journals (Sweden)
Utro Filippo
2008-10-01
Full Text Available Abstract Background Inferring cluster structure in microarray datasets is a fundamental task for the so-called -omic sciences. It is also a fundamental question in Statistics, Data Analysis and Classification, in particular with regard to the prediction of the number of clusters in a dataset, usually established via internal validation measures. Despite the wealth of internal measures available in the literature, new ones have been recently proposed, some of them specifically for microarray data. Results We consider five such measures: Clest, Consensus (Consensus Clustering, FOM (Figure of Merit, Gap (Gap Statistics and ME (Model Explorer, in addition to the classic WCSS (Within Cluster Sum-of-Squares and KL (Krzanowski and Lai index. We perform extensive experiments on six benchmark microarray datasets, using both Hierarchical and K-means clustering algorithms, and we provide an analysis assessing both the intrinsic ability of a measure to predict the correct number of clusters in a dataset and its merit relative to the other measures. We pay particular attention both to precision and speed. Moreover, we also provide various fast approximation algorithms for the computation of Gap, FOM and WCSS. The main result is a hierarchy of those measures in terms of precision and speed, highlighting some of their merits and limitations not reported before in the literature. Conclusion Based on our analysis, we draw several conclusions for the use of those internal measures on microarray data. We report the main ones. Consensus is by far the best performer in terms of predictive power and remarkably algorithm-independent. Unfortunately, on large datasets, it may be of no use because of its non-trivial computer time demand (weeks on a state of the art PC. FOM is the second best performer although, quite surprisingly, it may not be competitive in this scenario: it has essentially the same predictive power of WCSS but it is from 6 to 100 times slower in time
Semi-supervised clustering methods
Bair, Eric
2013-01-01
Cluster analysis methods seek to partition a data set into homogeneous subgroups. It is useful in a wide variety of applications, including document processing and modern genetics. Conventional clustering methods are unsupervised, meaning that there is no outcome variable nor is anything known about the relationship between the observations in the data set. In many situations, however, information about the clusters is available in addition to the values of the features. For example, the cluster labels of some observations may be known, or certain observations may be known to belong to the same cluster. In other cases, one may wish to identify clusters that are associated with a particular outcome variable. This review describes several clustering algorithms (known as “semi-supervised clustering” methods) that can be applied in these situations. The majority of these methods are modifications of the popular k-means clustering method, and several of them will be described in detail. A brief description of some other semi-supervised clustering algorithms is also provided. PMID:24729830
Sensory over responsivity and obsessive compulsive symptoms: A cluster analysis.
Ben-Sasson, Ayelet; Podoly, Tamar Yonit
2017-02-01
Several studies have examined the sensory component in Obsesseive Compulsive Disorder (OCD) and described an OCD subtype which has a unique profile, and that Sensory Phenomena (SP) is a significant component of this subtype. SP has some commonalities with Sensory Over Responsivity (SOR) and might be in part a characteristic of this subtype. Although there are some studies that have examined SOR and its relation to Obsessive Compulsive Symptoms (OCS), literature lacks sufficient data on this interplay. First to further examine the correlations between OCS and SOR, and to explore the correlations between SOR modalities (i.e. smell, touch, etc.) and OCS subscales (i.e. washing, ordering, etc.). Second, to investigate the cluster analysis of SOR and OCS dimensions in adults, that is, to classify the sample using the sensory scores to find whether a sensory OCD subtype can be specified. Our third goal was to explore the psychometric features of a new sensory questionnaire: the Sensory Perception Quotient (SPQ). A sample of non clinical adults (n=350) was recruited via e-mail, social media and social networks. Participants completed questionnaires for measuring SOR, OCS, and anxiety. SOR and OCI-F scores were moderately significantly correlated (n=274), significant correlations between all SOR modalities and OCS subscales were found with no specific higher correlation between one modality to one OCS subscale. Cluster analysis revealed four distinct clusters: (1) No OC and SOR symptoms (NONE; n=100), (2) High OC and SOR symptoms (BOTH; n=28), (3) Moderate OC symptoms (OCS; n=63), (4) Moderate SOR symptoms (SOR; n=83). The BOTH cluster had significantly higher anxiety levels than the other clusters, and shared OC subscales scores with the OCS cluster. The BOTH cluster also reported higher SOR scores across tactile, vision, taste and olfactory modalities. The SPQ was found reliable and suitable to detect SOR, the sample SPQ scores was normally distributed (n=350). SOR is a
Analysis of plasmaspheric plumes: CLUSTER and IMAGE observations
Directory of Open Access Journals (Sweden)
F. Darrouzet
2006-07-01
Full Text Available Plasmaspheric plumes have been routinely observed by CLUSTER and IMAGE. The CLUSTER mission provides high time resolution four-point measurements of the plasmasphere near perigee. Total electron density profiles have been derived from the electron plasma frequency identified by the WHISPER sounder supplemented, in-between soundings, by relative variations of the spacecraft potential measured by the electric field instrument EFW; ion velocity is also measured onboard these satellites. The EUV imager onboard the IMAGE spacecraft provides global images of the plasmasphere with a spatial resolution of 0.1 RE every 10 min; such images acquired near apogee from high above the pole show the geometry of plasmaspheric plumes, their evolution and motion. We present coordinated observations of three plume events and compare CLUSTER in-situ data with global images of the plasmasphere obtained by IMAGE. In particular, we study the geometry and the orientation of plasmaspheric plumes by using four-point analysis methods. We compare several aspects of plume motion as determined by different methods: (i inner and outer plume boundary velocity calculated from time delays of this boundary as observed by the wave experiment WHISPER on the four spacecraft, (ii drift velocity measured by the electron drift instrument EDI onboard CLUSTER and (iii global velocity determined from successive EUV images. These different techniques consistently indicate that plasmaspheric plumes rotate around the Earth, with their foot fully co-rotating, but with their tip rotating slower and moving farther out.
Convex Clustering: An Attractive Alternative to Hierarchical Clustering
Chen, Gary K.; Chi, Eric C.; Ranola, John Michael O.; Lange, Kenneth
2015-01-01
The primary goal in cluster analysis is to discover natural groupings of objects. The field of cluster analysis is crowded with diverse methods that make special assumptions about data and address different scientific aims. Despite its shortcomings in accuracy, hierarchical clustering is the dominant clustering method in bioinformatics. Biologists find the trees constructed by hierarchical clustering visually appealing and in tune with their evolutionary perspective. Hierarchical clustering operates on multiple scales simultaneously. This is essential, for instance, in transcriptome data, where one may be interested in making qualitative inferences about how lower-order relationships like gene modules lead to higher-order relationships like pathways or biological processes. The recently developed method of convex clustering preserves the visual appeal of hierarchical clustering while ameliorating its propensity to make false inferences in the presence of outliers and noise. The solution paths generated by convex clustering reveal relationships between clusters that are hidden by static methods such as k-means clustering. The current paper derives and tests a novel proximal distance algorithm for minimizing the objective function of convex clustering. The algorithm separates parameters, accommodates missing data, and supports prior information on relationships. Our program CONVEXCLUSTER incorporating the algorithm is implemented on ATI and nVidia graphics processing units (GPUs) for maximal speed. Several biological examples illustrate the strengths of convex clustering and the ability of the proximal distance algorithm to handle high-dimensional problems. CONVEXCLUSTER can be freely downloaded from the UCLA Human Genetics web site at http://www.genetics.ucla.edu/software/ PMID:25965340
HORIZONTAL BRANCH MORPHOLOGY OF GLOBULAR CLUSTERS: A MULTIVARIATE STATISTICAL ANALYSIS
International Nuclear Information System (INIS)
Jogesh Babu, G.; Chattopadhyay, Tanuka; Chattopadhyay, Asis Kumar; Mondal, Saptarshi
2009-01-01
The proper interpretation of horizontal branch (HB) morphology is crucial to the understanding of the formation history of stellar populations. In the present study a multivariate analysis is used (principal component analysis) for the selection of appropriate HB morphology parameter, which, in our case, is the logarithm of effective temperature extent of the HB (log T effHB ). Then this parameter is expressed in terms of the most significant observed independent parameters of Galactic globular clusters (GGCs) separately for coherent groups, obtained in a previous work, through a stepwise multiple regression technique. It is found that, metallicity ([Fe/H]), central surface brightness (μ v ), and core radius (r c ) are the significant parameters to explain most of the variations in HB morphology (multiple R 2 ∼ 0.86) for GGC elonging to the bulge/disk while metallicity ([Fe/H]) and absolute magnitude (M v ) are responsible for GGC belonging to the inner halo (multiple R 2 ∼ 0.52). The robustness is tested by taking 1000 bootstrap samples. A cluster analysis is performed for the red giant branch (RGB) stars of the GGC belonging to Galactic inner halo (Cluster 2). A multi-episodic star formation is preferred for RGB stars of GGC belonging to this group. It supports the asymptotic giant branch (AGB) model in three episodes instead of two as suggested by Carretta et al. for halo GGC while AGB model is suggested to be revisited for bulge/disk GGC.
Examining Subtypes of Behavioral/Emotional Risk Using Cluster Analysis
Dever, Bridget V.; Gallagher, Emily K.; Hochbein, Craig D.; Loukas, Austin; Dai, Chenchen
2017-01-01
Behavioral and emotional problems among children and adolescents can lead to numerous negative outcomes without intervention. From a prevention standpoint, screening for behavioral and emotional risk is an important step toward identifying such problems before the point of diagnosis or referral. The present study conducted a k-means cluster…
Poisson cluster analysis of cardiac arrest incidence in Columbus, Ohio.
Warden, Craig; Cudnik, Michael T; Sasson, Comilla; Schwartz, Greg; Semple, Hugh
2012-01-01
Scarce resources in disease prevention and emergency medical services (EMS) need to be focused on high-risk areas of out-of-hospital cardiac arrest (OHCA). Cluster analysis using geographic information systems (GISs) was used to find these high-risk areas and test potential predictive variables. This was a retrospective cohort analysis of EMS-treated adults with OHCAs occurring in Columbus, Ohio, from April 1, 2004, through March 31, 2009. The OHCAs were aggregated to census tracts and incidence rates were calculated based on their adult populations. Poisson cluster analysis determined significant clusters of high-risk census tracts. Both census tract-level and case-level characteristics were tested for association with high-risk areas by multivariate logistic regression. A total of 2,037 eligible OHCAs occurred within the city limits during the study period. The mean incidence rate was 0.85 OHCAs/1,000 population/year. There were five significant geographic clusters with 76 high-risk census tracts out of the total of 245 census tracts. In the case-level analysis, being in a high-risk cluster was associated with a slightly younger age (-3 years, adjusted odds ratio [OR] 0.99, 95% confidence interval [CI] 0.99-1.00), not being white, non-Hispanic (OR 0.54, 95% CI 0.45-0.64), cardiac arrest occurring at home (OR 1.53, 95% CI 1.23-1.71), and not receiving bystander cardiopulmonary resuscitation (CPR) (OR 0.77, 95% CI 0.62-0.96), but with higher survival to hospital discharge (OR 1.78, 95% CI 1.30-2.46). In the census tract-level analysis, high-risk census tracts were also associated with a slightly lower average age (-0.1 years, OR 1.14, 95% CI 1.06-1.22) and a lower proportion of white, non-Hispanic patients (-0.298, OR 0.04, 95% CI 0.01-0.19), but also a lower proportion of high-school graduates (-0.184, OR 0.00, 95% CI 0.00-0.00). This analysis identified high-risk census tracts and associated census tract-level and case-level characteristics that can be used to