Neural Network Models for Time Series Forecasts
Tim Hill; Marcus O'Connor; William Remus
1996-01-01
Neural networks have been advocated as an alternative to traditional statistical forecasting methods. In the present experiment, time series forecasts produced by neural networks are compared with forecasts from six statistical time series methods generated in a major forecasting competition (Makridakis et al. [Makridakis, S., A. Anderson, R. Carbone, R. Fildes, M. Hibon, R. Lewandowski, J. Newton, E. Parzen, R. Winkler. 1982. The accuracy of extrapolation (time series) methods: Results of a ...
Time series prediction: statistical and neural techniques
Zahirniak, Daniel R.; DeSimio, Martin P.
1996-03-01
In this paper we compare the performance of nonlinear neural network techniques to those of linear filtering techniques in the prediction of time series. Specifically, we compare the results of using the nonlinear systems, known as multilayer perceptron and radial basis function neural networks, with the results obtained using the conventional linear Wiener filter, Kalman filter and Widrow-Hoff adaptive filter in predicting future values of stationary and non- stationary time series. Our results indicate the performance of each type of system is heavily dependent upon the form of the time series being predicted and the size of the system used. In particular, the linear filters perform adequately for linear or near linear processes while the nonlinear systems perform better for nonlinear processes. Since the linear systems take much less time to be developed, they should be tried prior to using the nonlinear systems when the linearity properties of the time series process are unknown.
Nonlinear Time Series Analysis via Neural Networks
Volná, Eva; Janošek, Michal; Kocian, Václav; Kotyrba, Martin
This article deals with a time series analysis based on neural networks in order to make an effective forex market [Moore and Roche, J. Int. Econ. 58, 387-411 (2002)] pattern recognition. Our goal is to find and recognize important patterns which repeatedly appear in the market history to adapt our trading system behaviour based on them.
Effectiveness of firefly algorithm based neural network in time series ...
African Journals Online (AJOL)
Effectiveness of firefly algorithm based neural network in time series forecasting. ... In the experiments, three well known time series were used to evaluate the performance. Results obtained were compared with ... Keywords: Time series, Artificial Neural Network, Firefly Algorithm, Particle Swarm Optimization, Overfitting ...
Time series prediction with simple recurrent neural networks ...
African Journals Online (AJOL)
A hybrid of the two called Elman-Jordan (or Multi-recurrent) neural network is also being used. In this study, we evaluated the performance of these neural networks on three established bench mark time series prediction problems. Results from the experiments showed that Jordan neural network performed significantly ...
Stacked Heterogeneous Neural Networks for Time Series Forecasting
Directory of Open Access Journals (Sweden)
Florin Leon
2010-01-01
Full Text Available A hybrid model for time series forecasting is proposed. It is a stacked neural network, containing one normal multilayer perceptron with bipolar sigmoid activation functions, and the other with an exponential activation function in the output layer. As shown by the case studies, the proposed stacked hybrid neural model performs well on a variety of benchmark time series. The combination of weights of the two stack components that leads to optimal performance is also studied.
Trend time-series modeling and forecasting with neural networks.
Qi, Min; Zhang, G Peter
2008-05-01
Despite its great importance, there has been no general consensus on how to model the trends in time-series data. Compared to traditional approaches, neural networks (NNs) have shown some promise in time-series forecasting. This paper investigates how to best model trend time series using NNs. Four different strategies (raw data, raw data with time index, detrending, and differencing) are used to model various trend patterns (linear, nonlinear, deterministic, stochastic, and breaking trend). We find that with NNs differencing often gives meritorious results regardless of the underlying data generating processes (DGPs). This finding is also confirmed by the real gross national product (GNP) series.
Neural network versus classical time series forecasting models
Nor, Maria Elena; Safuan, Hamizah Mohd; Shab, Noorzehan Fazahiyah Md; Asrul, Mohd; Abdullah, Affendi; Mohamad, Nurul Asmaa Izzati; Lee, Muhammad Hisyam
2017-05-01
Artificial neural network (ANN) has advantage in time series forecasting as it has potential to solve complex forecasting problems. This is because ANN is data driven approach which able to be trained to map past values of a time series. In this study the forecast performance between neural network and classical time series forecasting method namely seasonal autoregressive integrated moving average models was being compared by utilizing gold price data. Moreover, the effect of different data preprocessing on the forecast performance of neural network being examined. The forecast accuracy was evaluated using mean absolute deviation, root mean square error and mean absolute percentage error. It was found that ANN produced the most accurate forecast when Box-Cox transformation was used as data preprocessing.
Financial Time Series Prediction Using Elman Recurrent Random Neural Networks
Directory of Open Access Journals (Sweden)
Jie Wang
2016-01-01
(ERNN, the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices.
Toward automatic time-series forecasting using neural networks.
Yan, Weizhong
2012-07-01
Over the past few decades, application of artificial neural networks (ANN) to time-series forecasting (TSF) has been growing rapidly due to several unique features of ANN models. However, to date, a consistent ANN performance over different studies has not been achieved. Many factors contribute to the inconsistency in the performance of neural network models. One such factor is that ANN modeling involves determining a large number of design parameters, and the current design practice is essentially heuristic and ad hoc, this does not exploit the full potential of neural networks. Systematic ANN modeling processes and strategies for TSF are, therefore, greatly needed. Motivated by this need, this paper attempts to develop an automatic ANN modeling scheme. It is based on the generalized regression neural network (GRNN), a special type of neural network. By taking advantage of several GRNN properties (i.e., a single design parameter and fast learning) and by incorporating several design strategies (e.g., fusing multiple GRNNs), we have been able to make the proposed modeling scheme to be effective for modeling large-scale business time series. The initial model was entered into the NN3 time-series competition. It was awarded the best prediction on the reduced dataset among approximately 60 different models submitted by scholars worldwide.
Financial time series prediction using spiking neural networks.
Reid, David; Hussain, Abir Jaafar; Tawfik, Hissam
2014-01-01
In this paper a novel application of a particular type of spiking neural network, a Polychronous Spiking Network, was used for financial time series prediction. It is argued that the inherent temporal capabilities of this type of network are suited to non-stationary data such as this. The performance of the spiking neural network was benchmarked against three systems: two "traditional", rate-encoded, neural networks; a Multi-Layer Perceptron neural network and a Dynamic Ridge Polynomial neural network, and a standard Linear Predictor Coefficients model. For this comparison three non-stationary and noisy time series were used: IBM stock data; US/Euro exchange rate data, and the price of Brent crude oil. The experiments demonstrated favourable prediction results for the Spiking Neural Network in terms of Annualised Return and prediction error for 5-Step ahead predictions. These results were also supported by other relevant metrics such as Maximum Drawdown and Signal-To-Noise ratio. This work demonstrated the applicability of the Polychronous Spiking Network to financial data forecasting and this in turn indicates the potential of using such networks over traditional systems in difficult to manage non-stationary environments.
Artificial neural networks applied to forecasting time series.
Montaño Moreno, Juan J; Palmer Pol, Alfonso; Muñoz Gracia, Pilar
2011-04-01
This study offers a description and comparison of the main models of Artificial Neural Networks (ANN) which have proved to be useful in time series forecasting, and also a standard procedure for the practical application of ANN in this type of task. The Multilayer Perceptron (MLP), Radial Base Function (RBF), Generalized Regression Neural Network (GRNN), and Recurrent Neural Network (RNN) models are analyzed. With this aim in mind, we use a time series made up of 244 time points. A comparative study establishes that the error made by the four neural network models analyzed is less than 10%. In accordance with the interpretation criteria of this performance, it can be concluded that the neural network models show a close fit regarding their forecasting capacity. The model with the best performance is the RBF, followed by the RNN and MLP. The GRNN model is the one with the worst performance. Finally, we analyze the advantages and limitations of ANN, the possible solutions to these limitations, and provide an orientation towards future research.
Recursive Bayesian recurrent neural networks for time-series modeling.
Mirikitani, Derrick T; Nikolaev, Nikolay
2010-02-01
This paper develops a probabilistic approach to recursive second-order training of recurrent neural networks (RNNs) for improved time-series modeling. A general recursive Bayesian Levenberg-Marquardt algorithm is derived to sequentially update the weights and the covariance (Hessian) matrix. The main strengths of the approach are a principled handling of the regularization hyperparameters that leads to better generalization, and stable numerical performance. The framework involves the adaptation of a noise hyperparameter and local weight prior hyperparameters, which represent the noise in the data and the uncertainties in the model parameters. Experimental investigations using artificial and real-world data sets show that RNNs equipped with the proposed approach outperform standard real-time recurrent learning and extended Kalman training algorithms for recurrent networks, as well as other contemporary nonlinear neural models, on time-series modeling.
Recurrent Neural Network Applications for Astronomical Time Series
Protopapas, Pavlos
2017-06-01
The benefits of good predictive models in astronomy lie in early event prediction systems and effective resource allocation. Current time series methods applicable to regular time series have not evolved to generalize for irregular time series. In this talk, I will describe two Recurrent Neural Network methods, Long Short-Term Memory (LSTM) and Echo State Networks (ESNs) for predicting irregular time series. Feature engineering along with a non-linear modeling proved to be an effective predictor. For noisy time series, the prediction is improved by training the network on error realizations using the error estimates from astronomical light curves. In addition to this, we propose a new neural network architecture to remove correlation from the residuals in order to improve prediction and compensate for the noisy data. Finally, I show how to set hyperparameters for a stable and performant solution correctly. In this work, we circumvent this obstacle by optimizing ESN hyperparameters using Bayesian optimization with Gaussian Process priors. This automates the tuning procedure, enabling users to employ the power of RNN without needing an in-depth understanding of the tuning procedure.
Time series prediction by feedforward neural networks - is it difficult?
International Nuclear Information System (INIS)
Rosen-Zvi, Michal; Kanter, Ido; Kinzel, Wolfgang
2003-01-01
The difficulties that a neural network faces when trying to learn from a quasi-periodic time series are studied analytically using a teacher-student scenario where the random input is divided into two macroscopic regions with different variances, 1 and 1/γ 2 (γ >> 1). The generalization error is found to decrease as ε g ∝ exp(-α/γ 2 ), where α is the number of examples per input dimension. In contradiction to this very slow vanishing generalization error, the next output prediction is found to be almost free of mistakes. This picture is consistent with learning quasi-periodic time series produced by feedforward neural networks, which is dominated by enhanced components of the Fourier spectrum of the input. Simulation results are in good agreement with the analytical results
Predicting physical time series using dynamic ridge polynomial neural networks.
Directory of Open Access Journals (Sweden)
Dhiya Al-Jumeily
Full Text Available Forecasting naturally occurring phenomena is a common problem in many domains of science, and this has been addressed and investigated by many scientists. The importance of time series prediction stems from the fact that it has wide range of applications, including control systems, engineering processes, environmental systems and economics. From the knowledge of some aspects of the previous behaviour of the system, the aim of the prediction process is to determine or predict its future behaviour. In this paper, we consider a novel application of a higher order polynomial neural network architecture called Dynamic Ridge Polynomial Neural Network that combines the properties of higher order and recurrent neural networks for the prediction of physical time series. In this study, four types of signals have been used, which are; The Lorenz attractor, mean value of the AE index, sunspot number, and heat wave temperature. The simulation results showed good improvements in terms of the signal to noise ratio in comparison to a number of higher order and feedforward neural networks in comparison to the benchmarked techniques.
Recurrent Neural Networks for Multivariate Time Series with Missing Values.
Che, Zhengping; Purushotham, Sanjay; Cho, Kyunghyun; Sontag, David; Liu, Yan
2018-04-17
Multivariate time series data in practical applications, such as health care, geoscience, and biology, are characterized by a variety of missing values. In time series prediction and other related tasks, it has been noted that missing values and their missing patterns are often correlated with the target labels, a.k.a., informative missingness. There is very limited work on exploiting the missing patterns for effective imputation and improving prediction performance. In this paper, we develop novel deep learning models, namely GRU-D, as one of the early attempts. GRU-D is based on Gated Recurrent Unit (GRU), a state-of-the-art recurrent neural network. It takes two representations of missing patterns, i.e., masking and time interval, and effectively incorporates them into a deep model architecture so that it not only captures the long-term temporal dependencies in time series, but also utilizes the missing patterns to achieve better prediction results. Experiments of time series classification tasks on real-world clinical datasets (MIMIC-III, PhysioNet) and synthetic datasets demonstrate that our models achieve state-of-the-art performance and provide useful insights for better understanding and utilization of missing values in time series analysis.
Optimization of recurrent neural networks for time series modeling
DEFF Research Database (Denmark)
Pedersen, Morten With
1997-01-01
The present thesis is about optimization of recurrent neural networks applied to time series modeling. In particular is considered fully recurrent networks working from only a single external input, one layer of nonlinear hidden units and a li near output unit applied to prediction of discrete time...... series. The overall objective s are to improve training by application of second-order methods and to improve generalization ability by architecture optimization accomplished by pruning. The major topics covered in the thesis are: 1. The problem of training recurrent networks is analyzed from a numerical...... of solution obtained as well as computation time required. 3. A theoretical definition of the generalization error for recurrent networks is provided. This definition justifies a commonly adopted approach for estimating generalization ability. 4. The viability of pruning recurrent networks by the Optimal...
Nonlinear Time Series Prediction Using Chaotic Neural Networks
Li, Ke-Ping; Chen, Tian-Lun
2001-06-01
A nonlinear feedback term is introduced into the evaluation equation of weights of the backpropagation algorithm for neural network, the network becomes a chaotic one. For the purpose of that we can investigate how the different feedback terms affect the process of learning and forecasting, we use the model to forecast the nonlinear time series which is produced by Makey-Glass equation. By selecting the suitable feedback term, the system can escape from the local minima and converge to the global minimum or its approximate solutions, and the forecasting results are better than those of backpropagation algorithm. The project supported by National Basic Research Project "Nonlinear Science" and National Natural Science Foundation of China under Grant No. 60074020
Conditional time series forecasting with convolutional neural networks
A. Borovykh (Anastasia); S.M. Bohte (Sander); C.W. Oosterlee (Cornelis)
2017-01-01
textabstractForecasting financial time series using past observations has been a significant topic of interest. While temporal relationships in the data exist, they are difficult to analyze and predict accurately due to the non-linear trends and noise present in the series. We propose to learn these
Generation and prediction of time series by a neural network
International Nuclear Information System (INIS)
Eisenstein, E.; Kanter, I.; Kessler, D.A.; Kinzel, W.
1995-01-01
Generation and prediction of time series are analyzed for the case of a bit generator: a perceptron where in each time step the input units are shifted one bit to the right with the state of the leftmost input unit set equal to the output unit in the previous time step. The long-time dynamical behavior of the bit generator consists of cycles whose typical period scales polynomially with the size of the network and whose spatial structure is periodic with a typical finite wavelength. The generalization error on a cycle is zero for a finite training set, and global dynamical behaviors can also be learned in a finite time. Hence, a projection of a rule can be learned in a finite time
Multi-step-prediction of chaotic time series based on co-evolutionary recurrent neural network
International Nuclear Information System (INIS)
Ma Qianli; Zheng Qilun; Peng Hong; Qin Jiangwei; Zhong Tanwei
2008-01-01
This paper proposes a co-evolutionary recurrent neural network (CERNN) for the multi-step-prediction of chaotic time series, it estimates the proper parameters of phase space reconstruction and optimizes the structure of recurrent neural networks by co-evolutionary strategy. The searching space was separated into two subspaces and the individuals are trained in a parallel computational procedure. It can dynamically combine the embedding method with the capability of recurrent neural network to incorporate past experience due to internal recurrence. The effectiveness of CERNN is evaluated by using three benchmark chaotic time series data sets: the Lorenz series, Mackey-Glass series and real-world sun spot series. The simulation results show that CERNN improves the performances of multi-step-prediction of chaotic time series
Time Series Neural Network Model for Part-of-Speech Tagging Indonesian Language
Tanadi, Theo
2018-03-01
Part-of-speech tagging (POS tagging) is an important part in natural language processing. Many methods have been used to do this task, including neural network. This paper models a neural network that attempts to do POS tagging. A time series neural network is modelled to solve the problems that a basic neural network faces when attempting to do POS tagging. In order to enable the neural network to have text data input, the text data will get clustered first using Brown Clustering, resulting a binary dictionary that the neural network can use. To further the accuracy of the neural network, other features such as the POS tag, suffix, and affix of previous words would also be fed to the neural network.
New Models for Forecasting Enrollments: Fuzzy Time Series and Neural Network Approaches.
Song, Qiang; Chissom, Brad S.
Since university enrollment forecasting is very important, many different methods and models have been proposed by researchers. Two new methods for enrollment forecasting are introduced: (1) the fuzzy time series model; and (2) the artificial neural networks model. Fuzzy time series has been proposed to deal with forecasting problems within a…
Hansen, J V; Nelson, R D
1997-01-01
Ever since the initial planning for the 1997 Utah legislative session, neural-network forecasting techniques have provided valuable insights for analysts forecasting tax revenues. These revenue estimates are critically important since agency budgets, support for education, and improvements to infrastructure all depend on their accuracy. Underforecasting generates windfalls that concern taxpayers, whereas overforecasting produces budget shortfalls that cause inadequately funded commitments. The pattern finding ability of neural networks gives insightful and alternative views of the seasonal and cyclical components commonly found in economic time series data. Two applications of neural networks to revenue forecasting clearly demonstrate how these models complement traditional time series techniques. In the first, preoccupation with a potential downturn in the economy distracts analysis based on traditional time series methods so that it overlooks an emerging new phenomenon in the data. In this case, neural networks identify the new pattern that then allows modification of the time series models and finally gives more accurate forecasts. In the second application, data structure found by traditional statistical tools allows analysts to provide neural networks with important information that the networks then use to create more accurate models. In summary, for the Utah revenue outlook, the insights that result from a portfolio of forecasts that includes neural networks exceeds the understanding generated from strictly statistical forecasting techniques. In this case, the synergy clearly results in the whole of the portfolio of forecasts being more accurate than the sum of the individual parts.
Optimasi parameter neural network pada data time series
Directory of Open Access Journals (Sweden)
Muzakir Hi Sultan
2014-05-01
Full Text Available Gempa bumi merupakan suatu pergerakan tanah yang terjadi secara tiba-tiba hingga menimbulkan getaran, besarnya kekuatan gempa dapat mengakibatkan bencana baik kerusakan maupun korban jiwa. Untuk mengantisipasi bencana yang akan datang maka diperlukan suatu model khususnya untuk meramalkan besarnya kekuatan gempa. Pada penelitian ini, digunakan model ARIMA dan model kombinasi dari Neural Network-Algoritma Genetik (NN-GA untuk memprediksi rata-rata kekuatan gempa bumi setiap bulan khususnya yang terjadi di wilayah Maluku Utara. Data yang digunakan adalah data kekuatan gempa berdasarkan skala richter yang diperoleh dari Badan Meteorologi, Klimatologi dan Geofisika (BMKG kota Ternate. Sebagai input pada model ARIMA dan NN-GA digunakan rata-rata kekuatan gempa bumi 36 bulan dan rata-rata kekuatan gempa 36 bulan berikutnya digunakan sebagai target untuk prediksi. Untuk meng-update parameter (bobot dari Neural Network digunakan metode Gradient Descent dan untuk mendapatkan parameter yang lebih optimal pada layer Output, maka di diterapkan Algoritma Genetik. Hasil peramalan dari kedua model kemudian dibandingkan dan model terbaik ditentukan dari nilai Mean square Error (MSE yang terkecil. dari hasil peramalan dengan model ARIMA diperoleh MSE sebesar 1.0125, sedangkan pada model NN-GA diperoleh MSE sebesar 0.9196. Nilai tersebut, menunjukkan bahwa model NN-GA lebih baik dari model ARIMA untuk peramalan rata-rata kekuatan gempa bumi beberapa bulan ke depan
Hayashi, Hideaki; Shima, Keisuke; Shibanoki, Taro; Kurita, Yuichi; Tsuji, Toshio
2013-01-01
This paper outlines a probabilistic neural network developed on the basis of time-series discriminant component analysis (TSDCA) that can be used to classify high-dimensional time-series patterns. TSDCA involves the compression of high-dimensional time series into a lower-dimensional space using a set of orthogonal transformations and the calculation of posterior probabilities based on a continuous-density hidden Markov model that incorporates a Gaussian mixture model expressed in the reduced-dimensional space. The analysis can be incorporated into a neural network so that parameters can be obtained appropriately as network coefficients according to backpropagation-through-time-based training algorithm. The network is considered to enable high-accuracy classification of high-dimensional time-series patterns and to reduce the computation time taken for network training. In the experiments conducted during the study, the validity of the proposed network was demonstrated for EEG signals.
Ridge Polynomial Neural Network with Error Feedback for Time Series Forecasting.
Waheeb, Waddah; Ghazali, Rozaida; Herawan, Tutut
2016-01-01
Time series forecasting has gained much attention due to its many practical applications. Higher-order neural network with recurrent feedback is a powerful technique that has been used successfully for time series forecasting. It maintains fast learning and the ability to learn the dynamics of the time series over time. Network output feedback is the most common recurrent feedback for many recurrent neural network models. However, not much attention has been paid to the use of network error feedback instead of network output feedback. In this study, we propose a novel model, called Ridge Polynomial Neural Network with Error Feedback (RPNN-EF) that incorporates higher order terms, recurrence and error feedback. To evaluate the performance of RPNN-EF, we used four univariate time series with different forecasting horizons, namely star brightness, monthly smoothed sunspot numbers, daily Euro/Dollar exchange rate, and Mackey-Glass time-delay differential equation. We compared the forecasting performance of RPNN-EF with the ordinary Ridge Polynomial Neural Network (RPNN) and the Dynamic Ridge Polynomial Neural Network (DRPNN). Simulation results showed an average 23.34% improvement in Root Mean Square Error (RMSE) with respect to RPNN and an average 10.74% improvement with respect to DRPNN. That means that using network errors during training helps enhance the overall forecasting performance for the network.
Ridge Polynomial Neural Network with Error Feedback for Time Series Forecasting.
Directory of Open Access Journals (Sweden)
Waddah Waheeb
Full Text Available Time series forecasting has gained much attention due to its many practical applications. Higher-order neural network with recurrent feedback is a powerful technique that has been used successfully for time series forecasting. It maintains fast learning and the ability to learn the dynamics of the time series over time. Network output feedback is the most common recurrent feedback for many recurrent neural network models. However, not much attention has been paid to the use of network error feedback instead of network output feedback. In this study, we propose a novel model, called Ridge Polynomial Neural Network with Error Feedback (RPNN-EF that incorporates higher order terms, recurrence and error feedback. To evaluate the performance of RPNN-EF, we used four univariate time series with different forecasting horizons, namely star brightness, monthly smoothed sunspot numbers, daily Euro/Dollar exchange rate, and Mackey-Glass time-delay differential equation. We compared the forecasting performance of RPNN-EF with the ordinary Ridge Polynomial Neural Network (RPNN and the Dynamic Ridge Polynomial Neural Network (DRPNN. Simulation results showed an average 23.34% improvement in Root Mean Square Error (RMSE with respect to RPNN and an average 10.74% improvement with respect to DRPNN. That means that using network errors during training helps enhance the overall forecasting performance for the network.
Multiple Time Series Forecasting Using Quasi-Randomized Functional Link Neural Networks
Directory of Open Access Journals (Sweden)
Thierry Moudiki
2018-03-01
Full Text Available We are interested in obtaining forecasts for multiple time series, by taking into account the potential nonlinear relationships between their observations. For this purpose, we use a specific type of regression model on an augmented dataset of lagged time series. Our model is inspired by dynamic regression models (Pankratz 2012, with the response variable’s lags included as predictors, and is known as Random Vector Functional Link (RVFL neural networks. The RVFL neural networks have been successfully applied in the past, to solving regression and classification problems. The novelty of our approach is to apply an RVFL model to multivariate time series, under two separate regularization constraints on the regression parameters.
Reconstruction of coupling architecture of neural field networks from vector time series
Sysoev, Ilya V.; Ponomarenko, Vladimir I.; Pikovsky, Arkady
2018-04-01
We propose a method of reconstruction of the network coupling matrix for a basic voltage-model of the neural field dynamics. Assuming that the multivariate time series of observations from all nodes are available, we describe a technique to find coupling constants which is unbiased in the limit of long observations. Furthermore, the method is generalized for reconstruction of networks with time-delayed coupling, including the reconstruction of unknown time delays. The approach is compared with other recently proposed techniques.
Recurrent Neural Network For Forecasting Time Series With Long Memory Pattern
Walid; Alamsyah
2017-04-01
Recurrent Neural Network as one of the hybrid models are often used to predict and estimate the issues related to electricity, can be used to describe the cause of the swelling of electrical load which experienced by PLN. In this research will be developed RNN forecasting procedures at the time series with long memory patterns. Considering the application is the national electrical load which of course has a different trend with the condition of the electrical load in any country. This research produces the algorithm of time series forecasting which has long memory pattern using E-RNN after this referred to the algorithm of integrated fractional recurrent neural networks (FIRNN).The prediction results of long memory time series using models Fractional Integrated Recurrent Neural Network (FIRNN) showed that the model with the selection of data difference in the range of [-1,1] and the model of Fractional Integrated Recurrent Neural Network (FIRNN) (24,6,1) provides the smallest MSE value, which is 0.00149684.
Classification of time-series images using deep convolutional neural networks
Hatami, Nima; Gavet, Yann; Debayle, Johan
2018-04-01
Convolutional Neural Networks (CNN) has achieved a great success in image recognition task by automatically learning a hierarchical feature representation from raw data. While the majority of Time-Series Classification (TSC) literature is focused on 1D signals, this paper uses Recurrence Plots (RP) to transform time-series into 2D texture images and then take advantage of the deep CNN classifier. Image representation of time-series introduces different feature types that are not available for 1D signals, and therefore TSC can be treated as texture image recognition task. CNN model also allows learning different levels of representations together with a classifier, jointly and automatically. Therefore, using RP and CNN in a unified framework is expected to boost the recognition rate of TSC. Experimental results on the UCR time-series classification archive demonstrate competitive accuracy of the proposed approach, compared not only to the existing deep architectures, but also to the state-of-the art TSC algorithms.
Artificial neural networks for modeling time series of beach litter in the southern North Sea.
Schulz, Marcus; Matthies, Michael
2014-07-01
In European marine waters, existing monitoring programs of beach litter need to be improved concerning litter items used as indicators of pollution levels, efficiency, and effectiveness. In order to ease and focus future monitoring of beach litter on few important litter items, feed-forward neural networks consisting of three layers were developed to relate single litter items to general categories of marine litter. The neural networks developed were applied to seven beaches in the southern North Sea and modeled time series of five general categories of marine litter, such as litter from fishing, shipping, and tourism. Results of regression analyses show that general categories were predicted significantly moderately to well. Measured and modeled data were in the same order of magnitude, and minima and maxima overlapped well. Neural networks were found to be eligible tools to deliver reliable predictions of marine litter with low computational effort and little input of information. Copyright © 2014 Elsevier Ltd. All rights reserved.
Lohani, A. K.; Kumar, Rakesh; Singh, R. D.
2012-06-01
SummaryTime series modeling is necessary for the planning and management of reservoirs. More recently, the soft computing techniques have been used in hydrological modeling and forecasting. In this study, the potential of artificial neural networks and neuro-fuzzy system in monthly reservoir inflow forecasting are examined by developing and comparing monthly reservoir inflow prediction models, based on autoregressive (AR), artificial neural networks (ANNs) and adaptive neural-based fuzzy inference system (ANFIS). To take care the effect of monthly periodicity in the flow data, cyclic terms are also included in the ANN and ANFIS models. Working with time series flow data of the Sutlej River at Bhakra Dam, India, several ANN and adaptive neuro-fuzzy models are trained with different input vectors. To evaluate the performance of the selected ANN and adaptive neural fuzzy inference system (ANFIS) models, comparison is made with the autoregressive (AR) models. The ANFIS model trained with the input data vector including previous inflows and cyclic terms of monthly periodicity has shown a significant improvement in the forecast accuracy in comparison with the ANFIS models trained with the input vectors considering only previous inflows. In all cases ANFIS gives more accurate forecast than the AR and ANN models. The proposed ANFIS model coupled with the cyclic terms is shown to provide better representation of the monthly inflow forecasting for planning and operation of reservoir.
Hayashi, Hideaki; Shibanoki, Taro; Shima, Keisuke; Kurita, Yuichi; Tsuji, Toshio
2015-12-01
This paper proposes a probabilistic neural network (NN) developed on the basis of time-series discriminant component analysis (TSDCA) that can be used to classify high-dimensional time-series patterns. TSDCA involves the compression of high-dimensional time series into a lower dimensional space using a set of orthogonal transformations and the calculation of posterior probabilities based on a continuous-density hidden Markov model with a Gaussian mixture model expressed in the reduced-dimensional space. The analysis can be incorporated into an NN, which is named a time-series discriminant component network (TSDCN), so that parameters of dimensionality reduction and classification can be obtained simultaneously as network coefficients according to a backpropagation through time-based learning algorithm with the Lagrange multiplier method. The TSDCN is considered to enable high-accuracy classification of high-dimensional time-series patterns and to reduce the computation time taken for network training. The validity of the TSDCN is demonstrated for high-dimensional artificial data and electroencephalogram signals in the experiments conducted during the study.
Mining Gene Regulatory Networks by Neural Modeling of Expression Time-Series.
Rubiolo, Mariano; Milone, Diego H; Stegmayer, Georgina
2015-01-01
Discovering gene regulatory networks from data is one of the most studied topics in recent years. Neural networks can be successfully used to infer an underlying gene network by modeling expression profiles as times series. This work proposes a novel method based on a pool of neural networks for obtaining a gene regulatory network from a gene expression dataset. They are used for modeling each possible interaction between pairs of genes in the dataset, and a set of mining rules is applied to accurately detect the subjacent relations among genes. The results obtained on artificial and real datasets confirm the method effectiveness for discovering regulatory networks from a proper modeling of the temporal dynamics of gene expression profiles.
CSIR Research Space (South Africa)
Olivier, JC
2007-11-01
Full Text Available An Artificial Neural Network (ANN) is proposed to detect human-induced land cover change using a sliding window through a time-series of Moderate Resolution Imaging Spectroradiometer (MODIS) satellite surface reflectance pixel values. Training...
Data on copula modeling of mixed discrete and continuous neural time series.
Hu, Meng; Li, Mingyao; Li, Wu; Liang, Hualou
2016-06-01
Copula is an important tool for modeling neural dependence. Recent work on copula has been expanded to jointly model mixed time series in neuroscience ("Hu et al., 2016, Joint Analysis of Spikes and Local Field Potentials using Copula" [1]). Here we present further data for joint analysis of spike and local field potential (LFP) with copula modeling. In particular, the details of different model orders and the influence of possible spike contamination in LFP data from the same and different electrode recordings are presented. To further facilitate the use of our copula model for the analysis of mixed data, we provide the Matlab codes, together with example data.
Li, Qiongge; Chan, Maria F
2017-01-01
Over half of cancer patients receive radiotherapy (RT) as partial or full cancer treatment. Daily quality assurance (QA) of RT in cancer treatment closely monitors the performance of the medical linear accelerator (Linac) and is critical for continuous improvement of patient safety and quality of care. Cumulative longitudinal QA measurements are valuable for understanding the behavior of the Linac and allow physicists to identify trends in the output and take preventive actions. In this study, artificial neural networks (ANNs) and autoregressive moving average (ARMA) time-series prediction modeling techniques were both applied to 5-year daily Linac QA data. Verification tests and other evaluations were then performed for all models. Preliminary results showed that ANN time-series predictive modeling has more advantages over ARMA techniques for accurate and effective applicability in the dosimetry and QA field. © 2016 New York Academy of Sciences.
Directory of Open Access Journals (Sweden)
Narayanan Manikandan
2016-01-01
Full Text Available Software development life cycle has been characterized by destructive disconnects between activities like planning, analysis, design, and programming. Particularly software developed with prediction based results is always a big challenge for designers. Time series data forecasting like currency exchange, stock prices, and weather report are some of the areas where an extensive research is going on for the last three decades. In the initial days, the problems with financial analysis and prediction were solved by statistical models and methods. For the last two decades, a large number of Artificial Neural Networks based learning models have been proposed to solve the problems of financial data and get accurate results in prediction of the future trends and prices. This paper addressed some architectural design related issues for performance improvement through vectorising the strengths of multivariate econometric time series models and Artificial Neural Networks. It provides an adaptive approach for predicting exchange rates and it can be called hybrid methodology for predicting exchange rates. This framework is tested for finding the accuracy and performance of parallel algorithms used.
Optimizing the De-Noise Neural Network Model for GPS Time-Series Monitoring of Structures
Directory of Open Access Journals (Sweden)
Mosbeh R. Kaloop
2015-09-01
Full Text Available The Global Positioning System (GPS is recently used widely in structures and other applications. Notwithstanding, the GPS accuracy still suffers from the errors afflicting the measurements, particularly the short-period displacement of structural components. Previously, the multi filter method is utilized to remove the displacement errors. This paper aims at using a novel application for the neural network prediction models to improve the GPS monitoring time series data. Four prediction models for the learning algorithms are applied and used with neural network solutions: back-propagation, Cascade-forward back-propagation, adaptive filter and extended Kalman filter, to estimate which model can be recommended. The noise simulation and bridge’s short-period GPS of the monitoring displacement component of one Hz sampling frequency are used to validate the four models and the previous method. The results show that the Adaptive neural networks filter is suggested for de-noising the observations, specifically for the GPS displacement components of structures. Also, this model is expected to have significant influence on the design of structures in the low frequency responses and measurements’ contents.
International Nuclear Information System (INIS)
Chai, Soo H.; Lim, Joon S.
2016-01-01
This study presents a forecasting model of cyclical fluctuations of the economy based on the time delay coordinate embedding method. The model uses a neuro-fuzzy network called neural network with weighted fuzzy membership functions (NEWFM). The preprocessed time series of the leading composite index using the time delay coordinate embedding method are used as input data to the NEWFM to forecast the business cycle. A comparative study is conducted using other methods based on wavelet transform and Principal Component Analysis for the performance comparison. The forecasting results are tested using a linear regression analysis to compare the approximation of the input data against the target class, gross domestic product (GDP). The chaos based model captures nonlinear dynamics and interactions within the system, which other two models ignore. The test results demonstrated that chaos based method significantly improved the prediction capability, thereby demonstrating superior performance to the other methods.
Non-linear auto-regressive models for cross-frequency coupling in neural time series
Tallot, Lucille; Grabot, Laetitia; Doyère, Valérie; Grenier, Yves; Gramfort, Alexandre
2017-01-01
We address the issue of reliably detecting and quantifying cross-frequency coupling (CFC) in neural time series. Based on non-linear auto-regressive models, the proposed method provides a generative and parametric model of the time-varying spectral content of the signals. As this method models the entire spectrum simultaneously, it avoids the pitfalls related to incorrect filtering or the use of the Hilbert transform on wide-band signals. As the model is probabilistic, it also provides a score of the model “goodness of fit” via the likelihood, enabling easy and legitimate model selection and parameter comparison; this data-driven feature is unique to our model-based approach. Using three datasets obtained with invasive neurophysiological recordings in humans and rodents, we demonstrate that these models are able to replicate previous results obtained with other metrics, but also reveal new insights such as the influence of the amplitude of the slow oscillation. Using simulations, we demonstrate that our parametric method can reveal neural couplings with shorter signals than non-parametric methods. We also show how the likelihood can be used to find optimal filtering parameters, suggesting new properties on the spectrum of the driving signal, but also to estimate the optimal delay between the coupled signals, enabling a directionality estimation in the coupling. PMID:29227989
Marginally Stable Triangular Recurrent Neural Network Architecture for Time Series Prediction.
Sivakumar, Seshadri; Sivakumar, Shyamala
2017-09-25
This paper introduces a discrete-time recurrent neural network architecture using triangular feedback weight matrices that allows a simplified approach to ensuring network and training stability. The triangular structure of the weight matrices is exploited to readily ensure that the eigenvalues of the feedback weight matrix represented by the block diagonal elements lie on the unit circle in the complex z-plane by updating these weights based on the differential of the angular error variable. Such placement of the eigenvalues together with the extended close interaction between state variables facilitated by the nondiagonal triangular elements, enhances the learning ability of the proposed architecture. Simulation results show that the proposed architecture is highly effective in time-series prediction tasks associated with nonlinear and chaotic dynamic systems with underlying oscillatory modes. This modular architecture with dual upper and lower triangular feedback weight matrices mimics fully recurrent network architectures, while maintaining learning stability with a simplified training process. While training, the block-diagonal weights (hence the eigenvalues) of the dual triangular matrices are constrained to the same values during weight updates aimed at minimizing the possibility of overfitting. The dual triangular architecture also exploits the benefit of parsing the input and selectively applying the parsed inputs to the two subnetworks to facilitate enhanced learning performance.
Kolokythas, Kostantinos; Vasileios, Salamalikis; Athanassios, Argiriou; Kazantzidis, Andreas
2015-04-01
The wind is a result of complex interactions of numerous mechanisms taking place in small or large scales, so, the better knowledge of its behavior is essential in a variety of applications, especially in the field of power production coming from wind turbines. In the literature there is a considerable number of models, either physical or statistical ones, dealing with the problem of simulation and prediction of wind speed. Among others, Artificial Neural Networks (ANNs) are widely used for the purpose of wind forecasting and, in the great majority of cases, outperform other conventional statistical models. In this study, a number of ANNs with different architectures, which have been created and applied in a dataset of wind time series, are compared to Auto Regressive Integrated Moving Average (ARIMA) statistical models. The data consist of mean hourly wind speeds coming from a wind farm on a hilly Greek region and cover a period of one year (2013). The main goal is to evaluate the models ability to simulate successfully the wind speed at a significant point (target). Goodness-of-fit statistics are performed for the comparison of the different methods. In general, the ANN showed the best performance in the estimation of wind speed prevailing over the ARIMA models.
Directory of Open Access Journals (Sweden)
M. A. Porta-Garcia
2018-01-01
Full Text Available Most EEG phase synchrony measures are of bivariate nature. Those that are multivariate focus on producing global indices of the synchronization state of the system. Thus, better descriptions of spatial and temporal local interactions are still in demand. A framework for characterization of phase synchrony relationships between multivariate neural time series is presented, applied either in a single epoch or over an intertrial assessment, relying on a proposed clustering algorithm, termed Multivariate Time Series Clustering by Phase Synchrony, which generates fuzzy clusters for each multivalued time sample and thereupon obtains hard clusters according to a circular variance threshold; such cluster modes are then depicted in Time-Frequency-Topography representations of synchrony state beyond mere global indices. EEG signals from P300 Speller sessions of four subjects were analyzed, obtaining useful insights of synchrony patterns related to the ERP and even revealing steady-state artifacts at 7.6 Hz. Further, contrast maps of Levenshtein Distance highlight synchrony differences between ERP and no-ERP epochs, mainly at delta and theta bands. The framework, which is not limited to one synchrony measure, allows observing dynamics of phase changes and interactions among channels and can be applied to analyze other cognitive states rather than ERP versus no ERP.
Efficient Transfer Entropy Analysis of Non-Stationary Neural Time Series
Vicente, Raul; Díaz-Pernas, Francisco J.; Wibral, Michael
2014-01-01
Information theory allows us to investigate information processing in neural systems in terms of information transfer, storage and modification. Especially the measure of information transfer, transfer entropy, has seen a dramatic surge of interest in neuroscience. Estimating transfer entropy from two processes requires the observation of multiple realizations of these processes to estimate associated probability density functions. To obtain these necessary observations, available estimators typically assume stationarity of processes to allow pooling of observations over time. This assumption however, is a major obstacle to the application of these estimators in neuroscience as observed processes are often non-stationary. As a solution, Gomez-Herrero and colleagues theoretically showed that the stationarity assumption may be avoided by estimating transfer entropy from an ensemble of realizations. Such an ensemble of realizations is often readily available in neuroscience experiments in the form of experimental trials. Thus, in this work we combine the ensemble method with a recently proposed transfer entropy estimator to make transfer entropy estimation applicable to non-stationary time series. We present an efficient implementation of the approach that is suitable for the increased computational demand of the ensemble method's practical application. In particular, we use a massively parallel implementation for a graphics processing unit to handle the computationally most heavy aspects of the ensemble method for transfer entropy estimation. We test the performance and robustness of our implementation on data from numerical simulations of stochastic processes. We also demonstrate the applicability of the ensemble method to magnetoencephalographic data. While we mainly evaluate the proposed method for neuroscience data, we expect it to be applicable in a variety of fields that are concerned with the analysis of information transfer in complex biological, social, and
Directory of Open Access Journals (Sweden)
Subanar Subanar
2006-01-01
Full Text Available Recently, one of the central topics for the neural networks (NN community is the issue of data preprocessing on the use of NN. In this paper, we will investigate this topic particularly on the effect of Decomposition method as data processing and the use of NN for modeling effectively time series with both trend and seasonal patterns. Limited empirical studies on seasonal time series forecasting with neural networks show that some find neural networks are able to model seasonality directly and prior deseasonalization is not necessary, and others conclude just the opposite. In this research, we study particularly on the effectiveness of data preprocessing, including detrending and deseasonalization by applying Decomposition method on NN modeling and forecasting performance. We use two kinds of data, simulation and real data. Simulation data are examined on multiplicative of trend and seasonality patterns. The results are compared to those obtained from the classical time series model. Our result shows that a combination of detrending and deseasonalization by applying Decomposition method is the effective data preprocessing on the use of NN for forecasting trend and seasonal time series.
Directory of Open Access Journals (Sweden)
Ozge Cagcag Yolcu
2013-01-01
Full Text Available Particularly in recent years, artificial intelligence optimization techniques have been used to make fuzzy time series approaches more systematic and improve forecasting performance. Besides, some fuzzy clustering methods and artificial neural networks with different structures are used in the fuzzification of observations and determination of fuzzy relationships, respectively. In approaches considering the membership values, the membership values are determined subjectively or fuzzy outputs of the system are obtained by considering that there is a relation between membership values in identification of relation. This necessitates defuzzification step and increases the model error. In this study, membership values were obtained more systematically by using Gustafson-Kessel fuzzy clustering technique. The use of artificial neural network with single multiplicative neuron model in identification of fuzzy relation eliminated the architecture selection problem as well as the necessity for defuzzification step by constituting target values from real observations of time series. The training of artificial neural network with single multiplicative neuron model which is used for identification of fuzzy relation step is carried out with particle swarm optimization. The proposed method is implemented using various time series and the results are compared with those of previous studies to demonstrate the performance of the proposed method.
Directory of Open Access Journals (Sweden)
Levi Lopes Teixeira
2015-12-01
Full Text Available Time series forecasting is widely used in various areas of human knowledge, especially in the planning and strategic direction of companies. The success of this task depends on the forecasting techniques applied. In this paper, a hybrid approach to project time series is suggested. To validate the methodology, a time series already modeled by other authors was chosen, allowing the comparison of results. The proposed methodology includes the following techniques: wavelet shrinkage, wavelet decomposition at level r, and artificial neural networks (ANN. Firstly, a time series to be forecasted is submitted to the proposed wavelet filtering method, which decomposes it to components of trend and linear residue. Then, both are decomposed via level r wavelet decomposition, generating r + 1 Wavelet Components (WCs for each one; and then each WC is individually modeled by an ANN. Finally, the predictions for all WCs are linearly combined, producing forecasts to the underlying time series. For evaluating purposes, the time series of Canadian Lynx has been used, and all results achieved by the proposed method were better than others in existing literature.
Training and evaluation of neural networks for multi-variate time series processing
DEFF Research Database (Denmark)
Fog, Torben L.; Larsen, Jan; Hansen, Lars Kai
1995-01-01
We study the training and generalization for multi-variate time series processing. It is suggested to used a quasi-maximum likelihood approach rather than the standard sum of squared errors, thus taking dependencies among the errors of the individual time series into account. This may lead...... to improved generalization performance. Further, we extend the optimal brain damage pruning technique to the multi-variate case. A key ingredient is an algebraic expression for the generalization ability of a multi-variate model. The variability of the suggested techniques are successfully demonstrated...
International Nuclear Information System (INIS)
Yoshino, Ryuji
2006-01-01
Disruption prediction of tokamak plasma has been studied by neural network. The disruption prediction performances by neural network are estimated by the prediction success rate, false alarm rate, and time prior to disruption. The current driving type disruption is predicted by time series data, and plasma lifetime, risk of disruption and plasma stability. Some disruptions generated by density limit, impurity mixture, error magnetic field can be predicted 100 % of prediction success rate by the premonitory symptoms. The pressure driving type disruption phenomena generate some hundred micro seconds before, so that the operation limits such as β N limit of DIII-D and density limit of ADITYA were investigated. The false alarm rate was decreased by β N limit training under stable discharge. The pressure driving disruption generated with increasing plasma pressure can be predicted about 90 % by evaluating plasma stability. (S.Y.)
Chen, C P; Wan, J Z
1999-01-01
A fast learning algorithm is proposed to find an optimal weights of the flat neural networks (especially, the functional-link network). Although the flat networks are used for nonlinear function approximation, they can be formulated as linear systems. Thus, the weights of the networks can be solved easily using a linear least-square method. This formulation makes it easier to update the weights instantly for both a new added pattern and a new added enhancement node. A dynamic stepwise updating algorithm is proposed to update the weights of the system on-the-fly. The model is tested on several time-series data including an infrared laser data set, a chaotic time-series, a monthly flour price data set, and a nonlinear system identification problem. The simulation results are compared to existing models in which more complex architectures and more costly training are needed. The results indicate that the proposed model is very attractive to real-time processes.
Energy Technology Data Exchange (ETDEWEB)
Torres Junior, Rubiao G.; Machado, Maria Augusta S. [Instituto Brasileiro de Mercado de Capitais (IBMEC), Rio de Janeiro, RJ (Brazil); Souza, Reinaldo C. [Pontificia Univ. Catolica do Rio de Janeiro, RJ (Brazil)
2005-07-01
The objective of this work is the application of two failure prediction models in industrial maintenance with the use of Artificial Neural Networks (ANN). A characteristic of the modern industrial environment is a strong competition which leads companies to search for costs minimization methods. Thus, dada gathering and maintenance dada treatment becomes extremely important in this scenario for it aims the equipment and plant systems real repair necessity. Therefore, the objective becomes the widening of the system's full activity in a continuous manner, in the required period, without problems in their integrating parts. A daily time series is modeled based on maintenance interventions pauses dada from a five years period derived form many productive systems in the finalization areas of PETROFLEX Ind. and Com. S.A. Thus, the purpose is to introduce models based on neural networks and verify its system's pauses prediction capacity, so as to intervene with adequate timing before the system fails, extend the operational period and consequently increase its availability. The results obtained in this work demonstrate the employment of Neural Networks in the prediction of pauses in PETROFLEX industrial area maintenance. The ANN's prediction capacity in a group of dada with strong non-linear component where other statistical techniques have shown little efficient has also been confirmed. Discover neural models to predict failure systems time series has enable a breakthrough in the research field, especially due to the market demand. It's no doubt a technique that will evolve in the industrial maintenance area financing important managing decision. Prediction techniques, such as the ones illustrated in this study, work side by side maintenance planning and if carefully implemented and followed up can in the medium run supply a substantial increase in the available operational hours. (author)
Directory of Open Access Journals (Sweden)
Yun-Long Kong
2018-03-01
Full Text Available A satellite image time series (SITS contains a significant amount of temporal information. By analysing this type of data, the pattern of the changes in the object of concern can be explored. The natural change in the Earth’s surface is relatively slow and exhibits a pronounced pattern. Some natural events (for example, fires, floods, plant diseases, and insect pests and human activities (for example, deforestation and urbanisation will disturb this pattern and cause a relatively profound change on the Earth’s surface. These events are usually referred to as disturbances. However, disturbances in ecosystems are not easy to detect from SITS data, because SITS contain combined information on disturbances, phenological variations and noise in remote sensing data. In this paper, a novel framework is proposed for online disturbance detection from SITS. The framework is based on long short-term memory (LSTM networks. First, LSTM networks are trained by historical SITS. The trained LSTM networks are then used to predict new time series data. Last, the predicted data are compared with real data, and the noticeable deviations reveal disturbances. Experimental results using 16-day compositions of the moderate resolution imaging spectroradiometer (MOD13Q1 illustrate the effectiveness and stability of the proposed approach for online disturbance detection.
Directory of Open Access Journals (Sweden)
Chih-Chieh Young
2015-01-01
Full Text Available Accurate prediction of water level fluctuation is important in lake management due to its significant impacts in various aspects. This study utilizes four model approaches to predict water levels in the Yuan-Yang Lake (YYL in Taiwan: a three-dimensional hydrodynamic model, an artificial neural network (ANN model (back propagation neural network, BPNN, a time series forecasting (autoregressive moving average with exogenous inputs, ARMAX model, and a combined hydrodynamic and ANN model. Particularly, the black-box ANN model and physically based hydrodynamic model are coupled to more accurately predict water level fluctuation. Hourly water level data (a total of 7296 observations was collected for model calibration (training and validation. Three statistical indicators (mean absolute error, root mean square error, and coefficient of correlation were adopted to evaluate model performances. Overall, the results demonstrate that the hydrodynamic model can satisfactorily predict hourly water level changes during the calibration stage but not for the validation stage. The ANN and ARMAX models better predict the water level than the hydrodynamic model does. Meanwhile, the results from an ANN model are superior to those by the ARMAX model in both training and validation phases. The novel proposed concept using a three-dimensional hydrodynamic model in conjunction with an ANN model has clearly shown the improved prediction accuracy for the water level fluctuation.
Wang, K W; Deng, C; Li, J P; Zhang, Y Y; Li, X Y; Wu, M C
2017-04-01
Tuberculosis (TB) affects people globally and is being reconsidered as a serious public health problem in China. Reliable forecasting is useful for the prevention and control of TB. This study proposes a hybrid model combining autoregressive integrated moving average (ARIMA) with a nonlinear autoregressive (NAR) neural network for forecasting the incidence of TB from January 2007 to March 2016. Prediction performance was compared between the hybrid model and the ARIMA model. The best-fit hybrid model was combined with an ARIMA (3,1,0) × (0,1,1)12 and NAR neural network with four delays and 12 neurons in the hidden layer. The ARIMA-NAR hybrid model, which exhibited lower mean square error, mean absolute error, and mean absolute percentage error of 0·2209, 0·1373, and 0·0406, respectively, in the modelling performance, could produce more accurate forecasting of TB incidence compared to the ARIMA model. This study shows that developing and applying the ARIMA-NAR hybrid model is an effective method to fit the linear and nonlinear patterns of time-series data, and this model could be helpful in the prevention and control of TB.
International Nuclear Information System (INIS)
Voyant, Cyril
2011-01-01
As Corsica is a non-interconnected island, its energy supply is very special case. Indeed, as all islands, a large part of the electricity production must be generated locally. Often, renewable energies are considered as a good solution to overcome the isolation problem. However, because of their intermittent nature, they are included in a limited way in power systems. Thus, it is necessary to use in addition other energy productions, with main problem the management of the dispatch between these two energy types. This study is related to the solar and PV prediction in order to quantify available energy and to allow the optimal transition between intermittent and conventional energies sources. Throughout this work, we tested different techniques of prediction concerning four horizons interesting the power manager: d+1; h+24, h+1 and m+5. After all these manipulations, we can conclude that according the considered horizon, the prioritization of the different predictors varies. Note that for the d+1 horizon, it is interesting to use an approach based on neural network being careful to make stationary the time series, and to use exogenous variables. For the h+1 horizon, a hybrid methodology combining the robustness of the autoregressive models and the non-linearity of the connectionist models provides satisfactory results. For the h+24 case, neural networks with multiple outputs give very good results. About the m+5 horizon, our conclusions are different. Thus, even if neural networks are the most effective, the simplicity and the relatively good results shown by the persistence-based approach, lead us to recommend it. All the proposed methodologies and results are complementary to the prediction studies available in the literature. In conclusion, we can say that methodologies developed could eventually be included as prediction tools in the global command - control systems of energy sources. (author) [fr
Forecasting Natural Gas Prices Using Wavelets, Time Series, and Artificial Neural Networks.
Jin, Junghwan; Kim, Jinsoo
2015-01-01
Following the unconventional gas revolution, the forecasting of natural gas prices has become increasingly important because the association of these prices with those of crude oil has weakened. With this as motivation, we propose some modified hybrid models in which various combinations of the wavelet approximation, detail components, autoregressive integrated moving average, generalized autoregressive conditional heteroskedasticity, and artificial neural network models are employed to predict natural gas prices. We also emphasize the boundary problem in wavelet decomposition, and compare results that consider the boundary problem case with those that do not. The empirical results show that our suggested approach can handle the boundary problem, such that it facilitates the extraction of the appropriate forecasting results. The performance of the wavelet-hybrid approach was superior in all cases, whereas the application of detail components in the forecasting was only able to yield a small improvement in forecasting performance. Therefore, forecasting with only an approximation component would be acceptable, in consideration of forecasting efficiency.
Forecasting Natural Gas Prices Using Wavelets, Time Series, and Artificial Neural Networks.
Directory of Open Access Journals (Sweden)
Junghwan Jin
Full Text Available Following the unconventional gas revolution, the forecasting of natural gas prices has become increasingly important because the association of these prices with those of crude oil has weakened. With this as motivation, we propose some modified hybrid models in which various combinations of the wavelet approximation, detail components, autoregressive integrated moving average, generalized autoregressive conditional heteroskedasticity, and artificial neural network models are employed to predict natural gas prices. We also emphasize the boundary problem in wavelet decomposition, and compare results that consider the boundary problem case with those that do not. The empirical results show that our suggested approach can handle the boundary problem, such that it facilitates the extraction of the appropriate forecasting results. The performance of the wavelet-hybrid approach was superior in all cases, whereas the application of detail components in the forecasting was only able to yield a small improvement in forecasting performance. Therefore, forecasting with only an approximation component would be acceptable, in consideration of forecasting efficiency.
Plazas-Nossa, Leonardo; Hofer, Thomas; Gruber, Günter; Torres, Andres
2017-02-01
This work proposes a methodology for the forecasting of online water quality data provided by UV-Vis spectrometry. Therefore, a combination of principal component analysis (PCA) to reduce the dimensionality of a data set and artificial neural networks (ANNs) for forecasting purposes was used. The results obtained were compared with those obtained by using discrete Fourier transform (DFT). The proposed methodology was applied to four absorbance time series data sets composed by a total number of 5705 UV-Vis spectra. Absolute percentage errors obtained by applying the proposed PCA/ANN methodology vary between 10% and 13% for all four study sites. In general terms, the results obtained were hardly generalizable, as they appeared to be highly dependent on specific dynamics of the water system; however, some trends can be outlined. PCA/ANN methodology gives better results than PCA/DFT forecasting procedure by using a specific spectra range for the following conditions: (i) for Salitre wastewater treatment plant (WWTP) (first hour) and Graz West R05 (first 18 min), from the last part of UV range to all visible range; (ii) for Gibraltar pumping station (first 6 min) for all UV-Vis absorbance spectra; and (iii) for San Fernando WWTP (first 24 min) for all of UV range to middle part of visible range.
Directory of Open Access Journals (Sweden)
R. Zamani
2015-06-01
Full Text Available Today, the daily flow forecasting of rivers is an important issue in hydrology and water resources and thus can be used the results of daily river flow modeling in water resources management, droughts and floods monitoring. In this study, due to the importance of this issue, using nonlinear time series models and artificial intelligence (Artificial Neural Network and Gen Expression Programming, the daily flow modeling has been at the time interval (1981-2012 in the Armand hydrometric station on the Karun River. Armand station upstream basin is one of the most basins in the North Karun basin and includes four sub basins (Vanak, Middle Karun, Beheshtabad and Kohrang.The results of this study shown that artificial intelligence models have superior than nonlinear time series in flow daily simulation in the Karun River. As well as, modeling and comparison of artificial intelligence models showed that the Gen Expression Programming have evaluation criteria better than artificial neural network.
International Nuclear Information System (INIS)
Marseguerra, M.; Minoggio, S.; Rossi, A.; Zio, E.
1992-01-01
The correlated noise affecting many industrial plants under stationary or cyclo-stationary conditions - nuclear reactors included -has been successfully modeled by autoregressive moving average (ARMA) due to the versatility of this technique. The relatively recent neural network methods have similar features and much effort is being devoted to exploring their usefulness in forecasting and control. Identifying a signal by means of an ARMA model gives rise to the problem of selecting its correct order. Similar difficulties must be faced when applying neural network methods and, specifically, particular care must be given to the setting up of the appropriate network topology, the data normalization procedure and the learning code. In the present paper the capability of some neural networks of learning ARMA and seasonal ARMA processes is investigated. The results of the tested cases look promising since they indicate that the neural networks learn the underlying process with relative ease so that their forecasting capability may represent a convenient fault diagnosis tool. (Author)
Zhang, Yingying; Wang, Juncheng; Vorontsov, A M; Hou, Guangli; Nikanorova, M N; Wang, Hongliang
2014-01-01
The international marine ecological safety monitoring demonstration station in the Yellow Sea was developed as a collaborative project between China and Russia. It is a nonprofit technical workstation designed as a facility for marine scientific research for public welfare. By undertaking long-term monitoring of the marine environment and automatic data collection, this station will provide valuable information for marine ecological protection and disaster prevention and reduction. The results of some initial research by scientists at the research station into predictive modeling of marine ecological environments and early warning are described in this paper. Marine ecological processes are influenced by many factors including hydrological and meteorological conditions, biological factors, and human activities. Consequently, it is very difficult to incorporate all these influences and their interactions in a deterministic or analysis model. A prediction model integrating a time series prediction approach with neural network nonlinear modeling is proposed for marine ecological parameters. The model explores the natural fluctuations in marine ecological parameters by learning from the latest observed data automatically, and then predicting future values of the parameter. The model is updated in a "rolling" fashion with new observed data from the monitoring station. Prediction experiments results showed that the neural network prediction model based on time series data is effective for marine ecological prediction and can be used for the development of early warning systems.
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.
National Research Council Canada - National Science Library
Adler, Robert
1997-01-01
We describe how to take a stable, ARMA, time series through the various stages of model identification, parameter estimation, and diagnostic checking, and accompany the discussion with a goodly number...
Multivariate Time Series Search
National Aeronautics and Space Administration — Multivariate Time-Series (MTS) are ubiquitous, and are generated in areas as disparate as sensor recordings in aerospace systems, music and video streams, medical...
DEFF Research Database (Denmark)
Hisdal, H.; Holmqvist, E.; Hyvärinen, V.
Awareness that emission of greenhouse gases will raise the global temperature and change the climate has led to studies trying to identify such changes in long-term climate and hydrologic time series. This report, written by the......Awareness that emission of greenhouse gases will raise the global temperature and change the climate has led to studies trying to identify such changes in long-term climate and hydrologic time series. This report, written by the...
Directory of Open Access Journals (Sweden)
J D Velásquez
2012-06-01
Full Text Available Many time series with trend and seasonal pattern are successfully modeled and forecasted by the airline model of Box and Jenkins; however, this model neglects the presence of nonlinearity on data. In this paper, we propose a new nonlinear version of the airline model; for this, we replace the moving average linear component by a multilayer perceptron neural network. The proposedmodel is used for forecasting two benchmark time series; we found that theproposed model is able to forecast the time series with more accuracy that other traditional approaches.Muchas series de tiempo con tendencia y ciclos estacionales son exitosamente modeladas y pronosticadas usando el modelo airline de Box y Jenkins; sin embargo, la presencia de no linealidades en los datos son despreciadas por este modelo. En este artículo, se propone una nueva versión no lineal del modelo airline; para esto, se reemplaza la componente lineal de promedios móviles por un perceptrón multicapa. El modelo propuesto es usado para pronosticar dos series de tiempo benchmark; se encontró que el modelo propuesto es capaz de pronosticar las series de tiempo con mayor precisión que otras aproximaciones tradicionales.
BRITS: Bidirectional Recurrent Imputation for Time Series
Cao, Wei; Wang, Dong; Li, Jian; Zhou, Hao; Li, Lei; Li, Yitan
2018-01-01
Time series are widely used as signals in many classification/regression tasks. It is ubiquitous that time series contains many missing values. Given multiple correlated time series data, how to fill in missing values and to predict their class labels? Existing imputation methods often impose strong assumptions of the underlying data generating process, such as linear dynamics in the state space. In this paper, we propose BRITS, a novel method based on recurrent neural networks for missing va...
DEFF Research Database (Denmark)
Fischer, Paul; Hilbert, Astrid
2012-01-01
We introduce a platform which supplies an easy-to-handle, interactive, extendable, and fast analysis tool for time series analysis. In contrast to other software suits like Maple, Matlab, or R, which use a command-line-like interface and where the user has to memorize/look-up the appropriate...... commands, our application is select-and-click-driven. It allows to derive many different sequences of deviations for a given time series and to visualize them in different ways in order to judge their expressive power and to reuse the procedure found. For many transformations or model-ts, the user may...... choose between manual and automated parameter selection. The user can dene new transformations and add them to the system. The application contains efficient implementations of advanced and recent techniques for time series analysis including techniques related to extreme value analysis and filtering...
DEFF Research Database (Denmark)
Moskowitz, Tobias J.; Ooi, Yao Hua; Heje Pedersen, Lasse
2012-01-01
We document significant “time series momentum” in equity index, currency, commodity, and bond futures for each of the 58 liquid instruments we consider. We find persistence in returns for one to 12 months that partially reverses over longer horizons, consistent with sentiment theories of initial...... under-reaction and delayed over-reaction. A diversified portfolio of time series momentum strategies across all asset classes delivers substantial abnormal returns with little exposure to standard asset pricing factors and performs best during extreme markets. Examining the trading activities...
Woodward, Wayne A; Elliott, Alan C
2011-01-01
""There is scarcely a standard technique that the reader will find left out … this book is highly recommended for those requiring a ready introduction to applicable methods in time series and serves as a useful resource for pedagogical purposes.""-International Statistical Review (2014), 82""Current time series theory for practice is well summarized in this book.""-Emmanuel Parzen, Texas A&M University""What an extraordinary range of topics covered, all very insightfully. I like [the authors'] innovations very much, such as the AR factor table.""-David Findley, U.S. Census Bureau (retired)""…
Predicting chaotic time series
International Nuclear Information System (INIS)
Farmer, J.D.; Sidorowich, J.J.
1987-01-01
We present a forecasting technique for chaotic data. After embedding a time series in a state space using delay coordinates, we ''learn'' the induced nonlinear mapping using local approximation. This allows us to make short-term predictions of the future behavior of a time series, using information based only on past values. We present an error estimate for this technique, and demonstrate its effectiveness by applying it to several examples, including data from the Mackey-Glass delay differential equation, Rayleigh-Benard convection, and Taylor-Couette flow
Singh, S.; Jaishi, H. P.; Tiwari, R. P.; Tiwari, R. C.
2017-07-01
This paper reports the analysis of soil radon data recorded in the seismic zone-V, located in the northeastern part of India (latitude 23.73N, longitude 92.73E). Continuous measurements of soil-gas emission along Chite fault in Mizoram (India) were carried out with the replacement of solid-state nuclear track detectors at weekly interval. The present study was done for the period from March 2013 to May 2015 using LR-115 Type II detectors, manufactured by Kodak Pathe, France. In order to reduce the influence of meteorological parameters, statistical analysis tools such as multiple linear regression and artificial neural network have been used. Decrease in radon concentration was recorded prior to some earthquakes that occurred during the observation period. Some false anomalies were also recorded which may be attributed to the ongoing crustal deformation which was not major enough to produce an earthquake.
International Nuclear Information System (INIS)
Wu Xue-Dong; Liu Wei-Ting; Zhu Zhi-Yu; Wang Yao-Nan
2011-01-01
On the assumption that random interruptions in the observation process are modeled by a sequence of independent Bernoulli random variables, we firstly generalize two kinds of nonlinear filtering methods with random interruption failures in the observation based on the extended Kalman filtering (EKF) and the unscented Kalman filtering (UKF), which were shortened as GEKF and GUKF in this paper, respectively. Then the nonlinear filtering model is established by using the radial basis function neural network (RBFNN) prototypes and the network weights as state equation and the output of RBFNN to present the observation equation. Finally, we take the filtering problem under missing observed data as a special case of nonlinear filtering with random intermittent failures by setting each missing data to be zero without needing to pre-estimate the missing data, and use the GEKF-based RBFNN and the GUKF-based RBFNN to predict the ground radioactivity time series with missing data. Experimental results demonstrate that the prediction results of GUKF-based RBFNN accord well with the real ground radioactivity time series while the prediction results of GEKF-based RBFNN are divergent. (geophysics, astronomy, and astrophysics)
Time series analysis of barometric pressure data
International Nuclear Information System (INIS)
La Rocca, Paola; Riggi, Francesco; Riggi, Daniele
2010-01-01
Time series of atmospheric pressure data, collected over a period of several years, were analysed to provide undergraduate students with educational examples of application of simple statistical methods of analysis. In addition to basic methods for the analysis of periodicities, a comparison of two forecast models, one based on autoregression algorithms, and the other making use of an artificial neural network, was made. Results show that the application of artificial neural networks may give slightly better results compared to traditional methods.
International Nuclear Information System (INIS)
Vajna, Szabolcs; Kertész, János; Tóth, Bálint
2013-01-01
Many human-related activities show power-law decaying interevent time distribution with exponents usually varying between 1 and 2. We study a simple task-queuing model, which produces bursty time series due to the non-trivial dynamics of the task list. The model is characterized by a priority distribution as an input parameter, which describes the choice procedure from the list. We give exact results on the asymptotic behaviour of the model and we show that the interevent time distribution is power-law decaying for any kind of input distributions that remain normalizable in the infinite list limit, with exponents tunable between 1 and 2. The model satisfies a scaling law between the exponents of interevent time distribution (β) and autocorrelation function (α): α + β = 2. This law is general for renewal processes with power-law decaying interevent time distribution. We conclude that slowly decaying autocorrelation function indicates long-range dependence only if the scaling law is violated. (paper)
Introduction to Time Series Modeling
Kitagawa, Genshiro
2010-01-01
In time series modeling, the behavior of a certain phenomenon is expressed in relation to the past values of itself and other covariates. Since many important phenomena in statistical analysis are actually time series and the identification of conditional distribution of the phenomenon is an essential part of the statistical modeling, it is very important and useful to learn fundamental methods of time series modeling. Illustrating how to build models for time series using basic methods, "Introduction to Time Series Modeling" covers numerous time series models and the various tools f
GPS Position Time Series @ JPL
Owen, Susan; Moore, Angelyn; Kedar, Sharon; Liu, Zhen; Webb, Frank; Heflin, Mike; Desai, Shailen
2013-01-01
Different flavors of GPS time series analysis at JPL - Use same GPS Precise Point Positioning Analysis raw time series - Variations in time series analysis/post-processing driven by different users. center dot JPL Global Time Series/Velocities - researchers studying reference frame, combining with VLBI/SLR/DORIS center dot JPL/SOPAC Combined Time Series/Velocities - crustal deformation for tectonic, volcanic, ground water studies center dot ARIA Time Series/Coseismic Data Products - Hazard monitoring and response focused center dot ARIA data system designed to integrate GPS and InSAR - GPS tropospheric delay used for correcting InSAR - Caltech's GIANT time series analysis uses GPS to correct orbital errors in InSAR - Zhen Liu's talking tomorrow on InSAR Time Series analysis
Directory of Open Access Journals (Sweden)
Giovanni Salini Calderón
2006-12-01
Full Text Available Se diseñó una red neuronal artificial (RNA para hacer predicciones de valores de concentraciones horarias de material particulado fino en la atmósfera. El estudio está basado en los datos de tres años de series de tiempo de pm2.5 (material particulado suspendido de 2,5 micrones de diámetro, obtenidos en una estación céntrica de la Red MACAM de la ciudad de Santiago de Chile, entre los años 1994 y 1996. Para obtener el espaciamiento óptimo de los datos, así como el número de datos hacia atrás necesarios para pronosticar el valor futuro, se aplicaron dos test estándar usados en estudio de sistemas dinámicos, como Información Mutua promedio (AMI y Falsos Vecinos más Cercanos (FNN. De esta manera se encontró que lo más conveniente era considerar como entrada los datos de PM2.5 cada seis horas durante un día (cuatro datos, y en base a ellos predecir el dato siguiente. Una vez fijo el número de variables de entrada y elegida la variable a pronosticar, se diseñó un modelo predictivo basado en la técnica de RNA. El tipo de modelo de RNA usado fue uno de multicapas, alimentado hacia adelante y entrenado mediante la técnica de propagación hacia atrás. Se probaron redes sin capa oculta y con una y dos capas ocultas. El mejor modelo resultó ser con una capa oculta, a diferencia de lo obtenido en trabajo anterior que reportaba que la red sin capa oculta era más eficiente. Los resultados fueron más precisos que los obtenidos con un modelo de persistencia (el valor en seis horas más será el mismo que el actual.An artificial neural network for the forecasting of concentrations of fine particulate matter in the atmosphere was designed. The data set analyzed corresponds to three years of pm2.5 time series (particulate matter in suspension with aerodynamic diameter less than 2,5 microns, measured in a station that belongs to Santiago's monitoring network (Red MACAM and is located near downtown. We consider measurements of
Directory of Open Access Journals (Sweden)
Zheng Lu
2017-06-01
Full Text Available A method using a nonlinear auto-regressive neural network with exogenous input (NARXnn to retrieve time series soil moisture (SM that is spatially and temporally continuous and high quality over the Heihe River Basin (HRB in China was investigated in this study. The input training data consisted of the X-band dual polarization brightness temperature (TB and the Ka-band V polarization TB from the Advanced Microwave Scanning Radiometer II (AMSR2, Global Land Satellite product (GLASS Leaf Area Index (LAI, precipitation from the Tropical Rainfall Measuring Mission (TRMM and the Global Precipitation Measurement (GPM, and a global 30 arc-second elevation (GTOPO-30. The output training data were generated from fused SM products of the Japan Aerospace Exploration Agency (JAXA and the Land Surface Parameter Model (LPRM. The reprocessed fused SM from two years (2013 and 2014 was inputted into the NARXnn for training; subsequently, SM during a third year (2015 was estimated. Direct and indirect validations were then performed during the period 2015 by comparing with in situ measurements, SM from JAXA, LPRM and the Global Land Data Assimilation System (GLDAS, as well as precipitation data from TRMM and GPM. The results showed that the SM predictions from NARXnn performed best, as indicated by their higher correlation coefficients (R ≥ 0.85 for the whole year of 2015, lower Bias values (absolute value of Bias ≤ 0.02 and root mean square error values (RMSE ≤ 0.06, and their improved response to precipitation. This method is being used to produce the NARXnn SM product over the HRB in China.
Shimada, Yutaka; Ikeguchi, Tohru; Shigehara, Takaomi
2012-10-01
In this Letter, we propose a framework to transform a complex network to a time series. The transformation from complex networks to time series is realized by the classical multidimensional scaling. Applying the transformation method to a model proposed by Watts and Strogatz [Nature (London) 393, 440 (1998)], we show that ring lattices are transformed to periodic time series, small-world networks to noisy periodic time series, and random networks to random time series. We also show that these relationships are analytically held by using the circulant-matrix theory and the perturbation theory of linear operators. The results are generalized to several high-dimensional lattices.
Neural Network Predictions of the 4-Quadrant Wageningen Propeller Series
National Research Council Canada - National Science Library
Roddy, Robert F; Hess, David E; Faller, Will
2006-01-01
.... This report describes the development of feedforward neural network (FFNN) predictions of four-quadrant thrust and torque behavior for the Wageningen B-Screw Series of propellers and for two Wageningen ducted propeller series...
西埜, 晴久
2004-01-01
The paper investigates an application of long-memory processes to economic time series. We show properties of long-memory processes, which are motivated to model a long-memory phenomenon in economic time series. An FARIMA model is described as an example of long-memory model in statistical terms. The paper explains basic limit theorems and estimation methods for long-memory processes in order to apply long-memory models to economic time series.
Directory of Open Access Journals (Sweden)
Marek Vochozka
2017-12-01
Full Text Available Purpose of the article: Palladium is presently used for producing electronics, industrial products or jewellery, as well as products in the medical field. Its value is raised especially by its unique physical and chemical characteristics. Predicting the value of such a metal is not an easy matter (with regard to the fact that prices may change significantly in time. Methodology/methods: To carry out the analysis, London Fix Price PM data was used, i.e. amounts reported in the afternoon for a period longer than 10 years. To process the data, Statistica software is used. Linear regression is carried out using a whole range of functions, and subsequently regression via neural structures is performed, where several distributional functions are used again. Subsequently, 1000 neural networks are generated, out of which 5 proving the best characteristics are chosen. Scientific aim: The aim of the paper is to perform a regression analysis of the development of the palladium price on the New York Stock Exchange using neural structures and linear regression, then to compare the two methods and determine the more suitable one for a possible prediction of the future development of the palladium price on the New York Stock Exchange. Findings: Results are compared on the level of an expert perspective and the evaluator’s – economist’s experience. Within regression time lines, the curve obtained by the least squares methods via negative-exponential smoothing gets closest to Palladium price line development. Out of the neural networks, all 5 chosen networks prove to be the most practically useful. Conclusions: Because it is not possible to predict extraordinary situations and their impact on the palladium price (at most in the short term, but certainly not over a long period of time, simplification and the creation of a relatively simple model is appropriate and the result is useful.
Forecasting Cryptocurrencies Financial Time Series
DEFF Research Database (Denmark)
Catania, Leopoldo; Grassi, Stefano; Ravazzolo, Francesco
2018-01-01
This paper studies the predictability of cryptocurrencies time series. We compare several alternative univariate and multivariate models in point and density forecasting of four of the most capitalized series: Bitcoin, Litecoin, Ripple and Ethereum. We apply a set of crypto–predictors and rely...
Time series with tailored nonlinearities
Räth, C.; Laut, I.
2015-10-01
It is demonstrated how to generate time series with tailored nonlinearities by inducing well-defined constraints on the Fourier phases. Correlations between the phase information of adjacent phases and (static and dynamic) measures of nonlinearities are established and their origin is explained. By applying a set of simple constraints on the phases of an originally linear and uncorrelated Gaussian time series, the observed scaling behavior of the intensity distribution of empirical time series can be reproduced. The power law character of the intensity distributions being typical for, e.g., turbulence and financial data can thus be explained in terms of phase correlations.
Models for dependent time series
Tunnicliffe Wilson, Granville; Haywood, John
2015-01-01
Models for Dependent Time Series addresses the issues that arise and the methodology that can be applied when the dependence between time series is described and modeled. Whether you work in the economic, physical, or life sciences, the book shows you how to draw meaningful, applicable, and statistically valid conclusions from multivariate (or vector) time series data.The first four chapters discuss the two main pillars of the subject that have been developed over the last 60 years: vector autoregressive modeling and multivariate spectral analysis. These chapters provide the foundational mater
Seasonal time series forecasting: a comparative study of arima and ...
African Journals Online (AJOL)
This paper addresses the concerns of Faraway and Chatfield (1998) who questioned the forecasting ability of Artificial Neural Networks (ANN). In particular the paper compares the performance of Artificial Neural Networks (ANN) and ARIMA models in forecasting of seasonal (monthly) Time series. Using the Airline data ...
Clustering of financial time series
D'Urso, Pierpaolo; Cappelli, Carmela; Di Lallo, Dario; Massari, Riccardo
2013-05-01
This paper addresses the topic of classifying financial time series in a fuzzy framework proposing two fuzzy clustering models both based on GARCH models. In general clustering of financial time series, due to their peculiar features, needs the definition of suitable distance measures. At this aim, the first fuzzy clustering model exploits the autoregressive representation of GARCH models and employs, in the framework of a partitioning around medoids algorithm, the classical autoregressive metric. The second fuzzy clustering model, also based on partitioning around medoids algorithm, uses the Caiado distance, a Mahalanobis-like distance, based on estimated GARCH parameters and covariances that takes into account the information about the volatility structure of time series. In order to illustrate the merits of the proposed fuzzy approaches an application to the problem of classifying 29 time series of Euro exchange rates against international currencies is presented and discussed, also comparing the fuzzy models with their crisp version.
Time series analysis time series analysis methods and applications
Rao, Tata Subba; Rao, C R
2012-01-01
The field of statistics not only affects all areas of scientific activity, but also many other matters such as public policy. It is branching rapidly into so many different subjects that a series of handbooks is the only way of comprehensively presenting the various aspects of statistical methodology, applications, and recent developments. The Handbook of Statistics is a series of self-contained reference books. Each volume is devoted to a particular topic in statistics, with Volume 30 dealing with time series. The series is addressed to the entire community of statisticians and scientists in various disciplines who use statistical methodology in their work. At the same time, special emphasis is placed on applications-oriented techniques, with the applied statistician in mind as the primary audience. Comprehensively presents the various aspects of statistical methodology Discusses a wide variety of diverse applications and recent developments Contributors are internationally renowened experts in their respect...
Forecasting Cryptocurrencies Financial Time Series
Catania, Leopoldo; Grassi, Stefano; Ravazzolo, Francesco
2018-01-01
This paper studies the predictability of cryptocurrencies time series. We compare several alternative univariate and multivariate models in point and density forecasting of four of the most capitalized series: Bitcoin, Litecoin, Ripple and Ethereum. We apply a set of crypto–predictors and rely on Dynamic Model Averaging to combine a large set of univariate Dynamic Linear Models and several multivariate Vector Autoregressive models with different forms of time variation. We find statistical si...
Time series forecasting based on deep extreme learning machine
Guo, Xuqi; Pang, Y.; Yan, Gaowei; Qiao, Tiezhu; Yang, Guang-Hong; Yang, Dan
2017-01-01
Multi-layer Artificial Neural Networks (ANN) has caught widespread attention as a new method for time series forecasting due to the ability of approximating any nonlinear function. In this paper, a new local time series prediction model is established with the nearest neighbor domain theory, in
International Nuclear Information System (INIS)
Mirzaee, Hossein
2009-01-01
The Levenberg-Marquardt learning algorithm is applied for training a multilayer perception with three hidden layer each with ten neurons in order to carefully map the structure of chaotic time series such as Mackey-Glass time series. First the MLP network is trained with 1000 data, and then it is tested with next 500 data. After that the trained and tested network is applied for long-term prediction of next 120 data which come after test data. The prediction is such a way that, the first inputs to network for prediction are the four last data of test data, then the predicted value is shifted to the regression vector which is the input to the network, then after first four-step of prediction, the input regression vector to network is fully predicted values and in continue, each predicted data is shifted to input vector for subsequent prediction.
Layered Ensemble Architecture for Time Series Forecasting.
Rahman, Md Mustafizur; Islam, Md Monirul; Murase, Kazuyuki; Yao, Xin
2016-01-01
Time series forecasting (TSF) has been widely used in many application areas such as science, engineering, and finance. The phenomena generating time series are usually unknown and information available for forecasting is only limited to the past values of the series. It is, therefore, necessary to use an appropriate number of past values, termed lag, for forecasting. This paper proposes a layered ensemble architecture (LEA) for TSF problems. Our LEA consists of two layers, each of which uses an ensemble of multilayer perceptron (MLP) networks. While the first ensemble layer tries to find an appropriate lag, the second ensemble layer employs the obtained lag for forecasting. Unlike most previous work on TSF, the proposed architecture considers both accuracy and diversity of the individual networks in constructing an ensemble. LEA trains different networks in the ensemble by using different training sets with an aim of maintaining diversity among the networks. However, it uses the appropriate lag and combines the best trained networks to construct the ensemble. This indicates LEAs emphasis on accuracy of the networks. The proposed architecture has been tested extensively on time series data of neural network (NN)3 and NN5 competitions. It has also been tested on several standard benchmark time series data. In terms of forecasting accuracy, our experimental results have revealed clearly that LEA is better than other ensemble and nonensemble methods.
Stochastic models for time series
Doukhan, Paul
2018-01-01
This book presents essential tools for modelling non-linear time series. The first part of the book describes the main standard tools of probability and statistics that directly apply to the time series context to obtain a wide range of modelling possibilities. Functional estimation and bootstrap are discussed, and stationarity is reviewed. The second part describes a number of tools from Gaussian chaos and proposes a tour of linear time series models. It goes on to address nonlinearity from polynomial or chaotic models for which explicit expansions are available, then turns to Markov and non-Markov linear models and discusses Bernoulli shifts time series models. Finally, the volume focuses on the limit theory, starting with the ergodic theorem, which is seen as the first step for statistics of time series. It defines the distributional range to obtain generic tools for limit theory under long or short-range dependences (LRD/SRD) and explains examples of LRD behaviours. More general techniques (central limit ...
Forecasting with nonlinear time series models
DEFF Research Database (Denmark)
Kock, Anders Bredahl; Teräsvirta, Timo
In this paper, nonlinear models are restricted to mean nonlinear parametric models. Several such models popular in time series econo- metrics are presented and some of their properties discussed. This in- cludes two models based on universal approximators: the Kolmogorov- Gabor polynomial model...... applied to economic fore- casting problems, is briefly highlighted. A number of large published studies comparing macroeconomic forecasts obtained using different time series models are discussed, and the paper also contains a small simulation study comparing recursive and direct forecasts in a partic...... and two versions of a simple artificial neural network model. Techniques for generating multi-period forecasts from nonlinear models recursively are considered, and the direct (non-recursive) method for this purpose is mentioned as well. Forecasting with com- plex dynamic systems, albeit less frequently...
van den Akker, R.
2007-01-01
This thesis adresses statistical problems in econometrics. The first part contributes statistical methodology for nonnegative integer-valued time series. The second part of this thesis discusses semiparametric estimation in copula models and develops semiparametric lower bounds for a large class of
Building Chaotic Model From Incomplete Time Series
Siek, Michael; Solomatine, Dimitri
2010-05-01
This paper presents a number of novel techniques for building a predictive chaotic model from incomplete time series. A predictive chaotic model is built by reconstructing the time-delayed phase space from observed time series and the prediction is made by a global model or adaptive local models based on the dynamical neighbors found in the reconstructed phase space. In general, the building of any data-driven models depends on the completeness and quality of the data itself. However, the completeness of the data availability can not always be guaranteed since the measurement or data transmission is intermittently not working properly due to some reasons. We propose two main solutions dealing with incomplete time series: using imputing and non-imputing methods. For imputing methods, we utilized the interpolation methods (weighted sum of linear interpolations, Bayesian principle component analysis and cubic spline interpolation) and predictive models (neural network, kernel machine, chaotic model) for estimating the missing values. After imputing the missing values, the phase space reconstruction and chaotic model prediction are executed as a standard procedure. For non-imputing methods, we reconstructed the time-delayed phase space from observed time series with missing values. This reconstruction results in non-continuous trajectories. However, the local model prediction can still be made from the other dynamical neighbors reconstructed from non-missing values. We implemented and tested these methods to construct a chaotic model for predicting storm surges at Hoek van Holland as the entrance of Rotterdam Port. The hourly surge time series is available for duration of 1990-1996. For measuring the performance of the proposed methods, a synthetic time series with missing values generated by a particular random variable to the original (complete) time series is utilized. There exist two main performance measures used in this work: (1) error measures between the actual
A Time Series Forecasting Method
Directory of Open Access Journals (Sweden)
Wang Zhao-Yu
2017-01-01
Full Text Available This paper proposes a novel time series forecasting method based on a weighted self-constructing clustering technique. The weighted self-constructing clustering processes all the data patterns incrementally. If a data pattern is not similar enough to an existing cluster, it forms a new cluster of its own. However, if a data pattern is similar enough to an existing cluster, it is removed from the cluster it currently belongs to and added to the most similar cluster. During the clustering process, weights are learned for each cluster. Given a series of time-stamped data up to time t, we divide it into a set of training patterns. By using the weighted self-constructing clustering, the training patterns are grouped into a set of clusters. To estimate the value at time t + 1, we find the k nearest neighbors of the input pattern and use these k neighbors to decide the estimation. Experimental results are shown to demonstrate the effectiveness of the proposed approach.
International Work-Conference on Time Series
Pomares, Héctor; Valenzuela, Olga
2017-01-01
This volume of selected and peer-reviewed contributions on the latest developments in time series analysis and forecasting updates the reader on topics such as analysis of irregularly sampled time series, multi-scale analysis of univariate and multivariate time series, linear and non-linear time series models, advanced time series forecasting methods, applications in time series analysis and forecasting, advanced methods and online learning in time series and high-dimensional and complex/big data time series. The contributions were originally presented at the International Work-Conference on Time Series, ITISE 2016, held in Granada, Spain, June 27-29, 2016. The series of ITISE conferences provides a forum for scientists, engineers, educators and students to discuss the latest ideas and implementations in the foundations, theory, models and applications in the field of time series analysis and forecasting. It focuses on interdisciplinary and multidisciplinary rese arch encompassing the disciplines of comput...
Multiple Indicator Stationary Time Series Models.
Sivo, Stephen A.
2001-01-01
Discusses the propriety and practical advantages of specifying multivariate time series models in the context of structural equation modeling for time series and longitudinal panel data. For time series data, the multiple indicator model specification improves on classical time series analysis. For panel data, the multiple indicator model…
Time Series Decomposition into Oscillation Components and Phase Estimation.
Matsuda, Takeru; Komaki, Fumiyasu
2017-02-01
Many time series are naturally considered as a superposition of several oscillation components. For example, electroencephalogram (EEG) time series include oscillation components such as alpha, beta, and gamma. We propose a method for decomposing time series into such oscillation components using state-space models. Based on the concept of random frequency modulation, gaussian linear state-space models for oscillation components are developed. In this model, the frequency of an oscillator fluctuates by noise. Time series decomposition is accomplished by this model like the Bayesian seasonal adjustment method. Since the model parameters are estimated from data by the empirical Bayes' method, the amplitudes and the frequencies of oscillation components are determined in a data-driven manner. Also, the appropriate number of oscillation components is determined with the Akaike information criterion (AIC). In this way, the proposed method provides a natural decomposition of the given time series into oscillation components. In neuroscience, the phase of neural time series plays an important role in neural information processing. The proposed method can be used to estimate the phase of each oscillation component and has several advantages over a conventional method based on the Hilbert transform. Thus, the proposed method enables an investigation of the phase dynamics of time series. Numerical results show that the proposed method succeeds in extracting intermittent oscillations like ripples and detecting the phase reset phenomena. We apply the proposed method to real data from various fields such as astronomy, ecology, tidology, and neuroscience.
A Course in Time Series Analysis
Peña, Daniel; Tsay, Ruey S
2011-01-01
New statistical methods and future directions of research in time series A Course in Time Series Analysis demonstrates how to build time series models for univariate and multivariate time series data. It brings together material previously available only in the professional literature and presents a unified view of the most advanced procedures available for time series model building. The authors begin with basic concepts in univariate time series, providing an up-to-date presentation of ARIMA models, including the Kalman filter, outlier analysis, automatic methods for building ARIMA models, a
Periodicity and stability for variable-time impulsive neural networks.
Li, Hongfei; Li, Chuandong; Huang, Tingwen
2017-10-01
The paper considers a general neural networks model with variable-time impulses. It is shown that each solution of the system intersects with every discontinuous surface exactly once via several new well-proposed assumptions. Moreover, based on the comparison principle, this paper shows that neural networks with variable-time impulse can be reduced to the corresponding neural network with fixed-time impulses under well-selected conditions. Meanwhile, the fixed-time impulsive systems can be regarded as the comparison system of the variable-time impulsive neural networks. Furthermore, a series of sufficient criteria are derived to ensure the existence and global exponential stability of periodic solution of variable-time impulsive neural networks, and to illustrate the same stability properties between variable-time impulsive neural networks and the fixed-time ones. The new criteria are established by applying Schaefer's fixed point theorem combined with the use of inequality technique. Finally, a numerical example is presented to show the effectiveness of the proposed results. Copyright © 2017 Elsevier Ltd. All rights reserved.
The analysis of time series: an introduction
National Research Council Canada - National Science Library
Chatfield, Christopher
1989-01-01
.... A variety of practical examples are given to support the theory. The book covers a wide range of time-series topics, including probability models for time series, Box-Jenkins forecasting, spectral analysis, linear systems and system identification...
Prediction and Geometry of Chaotic Time Series
National Research Council Canada - National Science Library
Leonardi, Mary
1997-01-01
This thesis examines the topic of chaotic time series. An overview of chaos, dynamical systems, and traditional approaches to time series analysis is provided, followed by an examination of state space reconstruction...
Global Population Density Grid Time Series Estimates
National Aeronautics and Space Administration — Global Population Density Grid Time Series Estimates provide a back-cast time series of population density grids based on the year 2000 population grid from SEDAC's...
Kolmogorov Space in Time Series Data
Kanjamapornkul, K.; Pinčák, R.
2016-01-01
We provide the proof that the space of time series data is a Kolmogorov space with $T_{0}$-separation axiom using the loop space of time series data. In our approach we define a cyclic coordinate of intrinsic time scale of time series data after empirical mode decomposition. A spinor field of time series data comes from the rotation of data around price and time axis by defining a new extradimension to time series data. We show that there exist hidden eight dimensions in Kolmogorov space for ...
Effective Feature Preprocessing for Time Series Forecasting
DEFF Research Database (Denmark)
Zhao, Junhua; Dong, Zhaoyang; Xu, Zhao
2006-01-01
Time series forecasting is an important area in data mining research. Feature preprocessing techniques have significant influence on forecasting accuracy, therefore are essential in a forecasting model. Although several feature preprocessing techniques have been applied in time series forecasting...... performance in time series forecasting. It is demonstrated in our experiment that, effective feature preprocessing can significantly enhance forecasting accuracy. This research can be a useful guidance for researchers on effectively selecting feature preprocessing techniques and integrating them with time...... series forecasting models....
Time Series Analysis and Forecasting by Example
Bisgaard, Soren
2011-01-01
An intuition-based approach enables you to master time series analysis with ease Time Series Analysis and Forecasting by Example provides the fundamental techniques in time series analysis using various examples. By introducing necessary theory through examples that showcase the discussed topics, the authors successfully help readers develop an intuitive understanding of seemingly complicated time series models and their implications. The book presents methodologies for time series analysis in a simplified, example-based approach. Using graphics, the authors discuss each presented example in
Duality between Time Series and Networks
Campanharo, Andriana S. L. O.; Sirer, M. Irmak; Malmgren, R. Dean; Ramos, Fernando M.; Amaral, Luís A. Nunes.
2011-01-01
Studying the interaction between a system's components and the temporal evolution of the system are two common ways to uncover and characterize its internal workings. Recently, several maps from a time series to a network have been proposed with the intent of using network metrics to characterize time series. Although these maps demonstrate that different time series result in networks with distinct topological properties, it remains unclear how these topological properties relate to the original time series. Here, we propose a map from a time series to a network with an approximate inverse operation, making it possible to use network statistics to characterize time series and time series statistics to characterize networks. As a proof of concept, we generate an ensemble of time series ranging from periodic to random and confirm that application of the proposed map retains much of the information encoded in the original time series (or networks) after application of the map (or its inverse). Our results suggest that network analysis can be used to distinguish different dynamic regimes in time series and, perhaps more importantly, time series analysis can provide a powerful set of tools that augment the traditional network analysis toolkit to quantify networks in new and useful ways. PMID:21858093
A Review of Subsequence Time Series Clustering
Directory of Open Access Journals (Sweden)
Seyedjamal Zolhavarieh
2014-01-01
Full Text Available Clustering of subsequence time series remains an open issue in time series clustering. Subsequence time series clustering is used in different fields, such as e-commerce, outlier detection, speech recognition, biological systems, DNA recognition, and text mining. One of the useful fields in the domain of subsequence time series clustering is pattern recognition. To improve this field, a sequence of time series data is used. This paper reviews some definitions and backgrounds related to subsequence time series clustering. The categorization of the literature reviews is divided into three groups: preproof, interproof, and postproof period. Moreover, various state-of-the-art approaches in performing subsequence time series clustering are discussed under each of the following categories. The strengths and weaknesses of the employed methods are evaluated as potential issues for future studies.
A review of subsequence time series clustering.
Zolhavarieh, Seyedjamal; Aghabozorgi, Saeed; Teh, Ying Wah
2014-01-01
Clustering of subsequence time series remains an open issue in time series clustering. Subsequence time series clustering is used in different fields, such as e-commerce, outlier detection, speech recognition, biological systems, DNA recognition, and text mining. One of the useful fields in the domain of subsequence time series clustering is pattern recognition. To improve this field, a sequence of time series data is used. This paper reviews some definitions and backgrounds related to subsequence time series clustering. The categorization of the literature reviews is divided into three groups: preproof, interproof, and postproof period. Moreover, various state-of-the-art approaches in performing subsequence time series clustering are discussed under each of the following categories. The strengths and weaknesses of the employed methods are evaluated as potential issues for future studies.
A Review of Subsequence Time Series Clustering
Teh, Ying Wah
2014-01-01
Clustering of subsequence time series remains an open issue in time series clustering. Subsequence time series clustering is used in different fields, such as e-commerce, outlier detection, speech recognition, biological systems, DNA recognition, and text mining. One of the useful fields in the domain of subsequence time series clustering is pattern recognition. To improve this field, a sequence of time series data is used. This paper reviews some definitions and backgrounds related to subsequence time series clustering. The categorization of the literature reviews is divided into three groups: preproof, interproof, and postproof period. Moreover, various state-of-the-art approaches in performing subsequence time series clustering are discussed under each of the following categories. The strengths and weaknesses of the employed methods are evaluated as potential issues for future studies. PMID:25140332
Data mining in time series databases
Kandel, Abraham; Bunke, Horst
2004-01-01
Adding the time dimension to real-world databases produces Time SeriesDatabases (TSDB) and introduces new aspects and difficulties to datamining and knowledge discovery. This book covers the state-of-the-artmethodology for mining time series databases. The novel data miningmethods presented in the book include techniques for efficientsegmentation, indexing, and classification of noisy and dynamic timeseries. A graph-based method for anomaly detection in time series isdescribed and the book also studies the implications of a novel andpotentially useful representation of time series as strings. Theproblem of detecting changes in data mining models that are inducedfrom temporal databases is additionally discussed.
International Work-Conference on Time Series
Pomares, Héctor
2016-01-01
This volume presents selected peer-reviewed contributions from The International Work-Conference on Time Series, ITISE 2015, held in Granada, Spain, July 1-3, 2015. It discusses topics in time series analysis and forecasting, advanced methods and online learning in time series, high-dimensional and complex/big data time series as well as forecasting in real problems. The International Work-Conferences on Time Series (ITISE) provide a forum for scientists, engineers, educators and students to discuss the latest ideas and implementations in the foundations, theory, models and applications in the field of time series analysis and forecasting. It focuses on interdisciplinary and multidisciplinary research encompassing the disciplines of computer science, mathematics, statistics and econometrics.
Geometric noise reduction for multivariate time series.
Mera, M Eugenia; Morán, Manuel
2006-03-01
We propose an algorithm for the reduction of observational noise in chaotic multivariate time series. The algorithm is based on a maximum likelihood criterion, and its goal is to reduce the mean distance of the points of the cleaned time series to the attractor. We give evidence of the convergence of the empirical measure associated with the cleaned time series to the underlying invariant measure, implying the possibility to predict the long run behavior of the true dynamics.
Frontiers in Time Series and Financial Econometrics
Ling, S.; McAleer, M.J.; Tong, H.
2015-01-01
__Abstract__ Two of the fastest growing frontiers in econometrics and quantitative finance are time series and financial econometrics. Significant theoretical contributions to financial econometrics have been made by experts in statistics, econometrics, mathematics, and time series analysis. The purpose of this special issue of the journal on “Frontiers in Time Series and Financial Econometrics” is to highlight several areas of research by leading academics in which novel methods have contrib...
Forecasting Enrollments with Fuzzy Time Series.
Song, Qiang; Chissom, Brad S.
The concept of fuzzy time series is introduced and used to forecast the enrollment of a university. Fuzzy time series, an aspect of fuzzy set theory, forecasts enrollment using a first-order time-invariant model. To evaluate the model, the conventional linear regression technique is applied and the predicted values obtained are compared to the…
Analysis of Heavy-Tailed Time Series
DEFF Research Database (Denmark)
Xie, Xiaolei
This thesis is about analysis of heavy-tailed time series. We discuss tail properties of real-world equity return series and investigate the possibility that a single tail index is shared by all return series of actively traded equities in a market. Conditions for this hypothesis to be true...... are identified. We study the eigenvalues and eigenvectors of sample covariance and sample auto-covariance matrices of multivariate heavy-tailed time series, and particularly for time series with very high dimensions. Asymptotic approximations of the eigenvalues and eigenvectors of such matrices are found...... and expressed in terms of the parameters of the dependence structure, among others. Furthermore, we study an importance sampling method for estimating rare-event probabilities of multivariate heavy-tailed time series generated by matrix recursion. We show that the proposed algorithm is efficient in the sense...
Statistical criteria for characterizing irradiance time series.
Energy Technology Data Exchange (ETDEWEB)
Stein, Joshua S.; Ellis, Abraham; Hansen, Clifford W.
2010-10-01
We propose and examine several statistical criteria for characterizing time series of solar irradiance. Time series of irradiance are used in analyses that seek to quantify the performance of photovoltaic (PV) power systems over time. Time series of irradiance are either measured or are simulated using models. Simulations of irradiance are often calibrated to or generated from statistics for observed irradiance and simulations are validated by comparing the simulation output to the observed irradiance. Criteria used in this comparison should derive from the context of the analyses in which the simulated irradiance is to be used. We examine three statistics that characterize time series and their use as criteria for comparing time series. We demonstrate these statistics using observed irradiance data recorded in August 2007 in Las Vegas, Nevada, and in June 2009 in Albuquerque, New Mexico.
The foundations of modern time series analysis
Mills, Terence C
2011-01-01
This book develops the analysis of Time Series from its formal beginnings in the 1890s through to the publication of Box and Jenkins' watershed publication in 1970, showing how these methods laid the foundations for the modern techniques of Time Series analysis that are in use today.
Lag space estimation in time series modelling
DEFF Research Database (Denmark)
Goutte, Cyril
1997-01-01
The purpose of this article is to investigate some techniques for finding the relevant lag-space, i.e. input information, for time series modelling. This is an important aspect of time series modelling, as it conditions the design of the model through the regressor vector a.k.a. the input layer...
Track Irregularity Time Series Analysis and Trend Forecasting
Directory of Open Access Journals (Sweden)
Jia Chaolong
2012-01-01
Full Text Available The combination of linear and nonlinear methods is widely used in the prediction of time series data. This paper analyzes track irregularity time series data by using gray incidence degree models and methods of data transformation, trying to find the connotative relationship between the time series data. In this paper, GM (1,1 is based on first-order, single variable linear differential equations; after an adaptive improvement and error correction, it is used to predict the long-term changing trend of track irregularity at a fixed measuring point; the stochastic linear AR, Kalman filtering model, and artificial neural network model are applied to predict the short-term changing trend of track irregularity at unit section. Both long-term and short-term changes prove that the model is effective and can achieve the expected accuracy.
Entropic Analysis of Electromyography Time Series
Kaufman, Miron; Sung, Paul
2005-03-01
We are in the process of assessing the effectiveness of fractal and entropic measures for the diagnostic of low back pain from surface electromyography (EMG) time series. Surface electromyography (EMG) is used to assess patients with low back pain. In a typical EMG measurement, the voltage is measured every millisecond. We observed back muscle fatiguing during one minute, which results in a time series with 60,000 entries. We characterize the complexity of time series by computing the Shannon entropy time dependence. The analysis of the time series from different relevant muscles from healthy and low back pain (LBP) individuals provides evidence that the level of variability of back muscle activities is much larger for healthy individuals than for individuals with LBP. In general the time dependence of the entropy shows a crossover from a diffusive regime to a regime characterized by long time correlations (self organization) at about 0.01s.
Correlation and multifractality in climatological time series
International Nuclear Information System (INIS)
Pedron, I T
2010-01-01
Climate can be described by statistical analysis of mean values of atmospheric variables over a period. It is possible to detect correlations in climatological time series and to classify its behavior. In this work the Hurst exponent, which can characterize correlation and persistence in time series, is obtained by using the Detrended Fluctuation Analysis (DFA) method. Data series of temperature, precipitation, humidity, solar radiation, wind speed, maximum squall, atmospheric pressure and randomic series are studied. Furthermore, the multifractality of such series is analyzed applying the Multifractal Detrended Fluctuation Analysis (MF-DFA) method. The results indicate presence of correlation (persistent character) in all climatological series and multifractality as well. A larger set of data, and longer, could provide better results indicating the universality of the exponents.
Homogenising time series: beliefs, dogmas and facts
Domonkos, P.
2011-06-01
In the recent decades various homogenisation methods have been developed, but the real effects of their application on time series are still not known sufficiently. The ongoing COST action HOME (COST ES0601) is devoted to reveal the real impacts of homogenisation methods more detailed and with higher confidence than earlier. As a part of the COST activity, a benchmark dataset was built whose characteristics approach well the characteristics of real networks of observed time series. This dataset offers much better opportunity than ever before to test the wide variety of homogenisation methods, and analyse the real effects of selected theoretical recommendations. Empirical results show that real observed time series usually include several inhomogeneities of different sizes. Small inhomogeneities often have similar statistical characteristics than natural changes caused by climatic variability, thus the pure application of the classic theory that change-points of observed time series can be found and corrected one-by-one is impossible. However, after homogenisation the linear trends, seasonal changes and long-term fluctuations of time series are usually much closer to the reality than in raw time series. Some problems around detecting multiple structures of inhomogeneities, as well as that of time series comparisons within homogenisation procedures are discussed briefly in the study.
Network structure of multivariate time series.
Lacasa, Lucas; Nicosia, Vincenzo; Latora, Vito
2015-10-21
Our understanding of a variety of phenomena in physics, biology and economics crucially depends on the analysis of multivariate time series. While a wide range tools and techniques for time series analysis already exist, the increasing availability of massive data structures calls for new approaches for multidimensional signal processing. We present here a non-parametric method to analyse multivariate time series, based on the mapping of a multidimensional time series into a multilayer network, which allows to extract information on a high dimensional dynamical system through the analysis of the structure of the associated multiplex network. The method is simple to implement, general, scalable, does not require ad hoc phase space partitioning, and is thus suitable for the analysis of large, heterogeneous and non-stationary time series. We show that simple structural descriptors of the associated multiplex networks allow to extract and quantify nontrivial properties of coupled chaotic maps, including the transition between different dynamical phases and the onset of various types of synchronization. As a concrete example we then study financial time series, showing that a multiplex network analysis can efficiently discriminate crises from periods of financial stability, where standard methods based on time-series symbolization often fail.
Modeling Time Series Data for Supervised Learning
Baydogan, Mustafa Gokce
2012-01-01
Temporal data are increasingly prevalent and important in analytics. Time series (TS) data are chronological sequences of observations and an important class of temporal data. Fields such as medicine, finance, learning science and multimedia naturally generate TS data. Each series provide a high-dimensional data vector that challenges the learning…
Time series modeling, computation, and inference
Prado, Raquel
2010-01-01
The authors systematically develop a state-of-the-art analysis and modeling of time series. … this book is well organized and well written. The authors present various statistical models for engineers to solve problems in time series analysis. Readers no doubt will learn state-of-the-art techniques from this book.-Hsun-Hsien Chang, Computing Reviews, March 2012My favorite chapters were on dynamic linear models and vector AR and vector ARMA models.-William Seaver, Technometrics, August 2011… a very modern entry to the field of time-series modelling, with a rich reference list of the current lit
Time Series Analysis Forecasting and Control
Box, George E P; Reinsel, Gregory C
2011-01-01
A modernized new edition of one of the most trusted books on time series analysis. Since publication of the first edition in 1970, Time Series Analysis has served as one of the most influential and prominent works on the subject. This new edition maintains its balanced presentation of the tools for modeling and analyzing time series and also introduces the latest developments that have occurred n the field over the past decade through applications from areas such as business, finance, and engineering. The Fourth Edition provides a clearly written exploration of the key methods for building, cl
Visibility Graph Based Time Series Analysis.
Stephen, Mutua; Gu, Changgui; Yang, Huijie
2015-01-01
Network based time series analysis has made considerable achievements in the recent years. By mapping mono/multivariate time series into networks, one can investigate both it's microscopic and macroscopic behaviors. However, most proposed approaches lead to the construction of static networks consequently providing limited information on evolutionary behaviors. In the present paper we propose a method called visibility graph based time series analysis, in which series segments are mapped to visibility graphs as being descriptions of the corresponding states and the successively occurring states are linked. This procedure converts a time series to a temporal network and at the same time a network of networks. Findings from empirical records for stock markets in USA (S&P500 and Nasdaq) and artificial series generated by means of fractional Gaussian motions show that the method can provide us rich information benefiting short-term and long-term predictions. Theoretically, we propose a method to investigate time series from the viewpoint of network of networks.
Visibility Graph Based Time Series Analysis.
Directory of Open Access Journals (Sweden)
Mutua Stephen
Full Text Available Network based time series analysis has made considerable achievements in the recent years. By mapping mono/multivariate time series into networks, one can investigate both it's microscopic and macroscopic behaviors. However, most proposed approaches lead to the construction of static networks consequently providing limited information on evolutionary behaviors. In the present paper we propose a method called visibility graph based time series analysis, in which series segments are mapped to visibility graphs as being descriptions of the corresponding states and the successively occurring states are linked. This procedure converts a time series to a temporal network and at the same time a network of networks. Findings from empirical records for stock markets in USA (S&P500 and Nasdaq and artificial series generated by means of fractional Gaussian motions show that the method can provide us rich information benefiting short-term and long-term predictions. Theoretically, we propose a method to investigate time series from the viewpoint of network of networks.
Data Mining Smart Energy Time Series
Directory of Open Access Journals (Sweden)
Janina POPEANGA
2015-07-01
Full Text Available With the advent of smart metering technology the amount of energy data will increase significantly and utilities industry will have to face another big challenge - to find relationships within time-series data and even more - to analyze such huge numbers of time series to find useful patterns and trends with fast or even real-time response. This study makes a small review of the literature in the field, trying to demonstrate how essential is the application of data mining techniques in the time series to make the best use of this large quantity of data, despite all the difficulties. Also, the most important Time Series Data Mining techniques are presented, highlighting their applicability in the energy domain.
Neural Network Predictions of the 4-Quadrant Wageningen Propeller Series (CD-ROM)
National Research Council Canada - National Science Library
Roddy, Robert F; Hess, David E; Faller, Will
2006-01-01
.... This report describes the development of feedforward neural network (FFNN) predictions of four-quadrant thrust and torque behavior for the Wageningen B-Screw Series of propellers and for two Wageningen ducted propeller series...
Detecting nonlinear structure in time series
International Nuclear Information System (INIS)
Theiler, J.
1991-01-01
We describe an approach for evaluating the statistical significance of evidence for nonlinearity in a time series. The formal application of our method requires the careful statement of a null hypothesis which characterizes a candidate linear process, the generation of an ensemble of ''surrogate'' data sets which are similar to the original time series but consistent with the null hypothesis, and the computation of a discriminating statistic for the original and for each of the surrogate data sets. The idea is to test the original time series against the null hypothesis by checking whether the discriminating statistic computed for the original time series differs significantly from the statistics computed for each of the surrogate sets. While some data sets very cleanly exhibit low-dimensional chaos, there are many cases where the evidence is sketchy and difficult to evaluate. We hope to provide a framework within which such claims of nonlinearity can be evaluated. 5 refs., 4 figs
Nonparametric factor analysis of time series
Rodríguez-Poo, Juan M.; Linton, Oliver Bruce
1998-01-01
We introduce a nonparametric smoothing procedure for nonparametric factor analaysis of multivariate time series. The asymptotic properties of the proposed procedures are derived. We present an application based on the residuals from the Fair macromodel.
Applied time series analysis and innovative computing
Ao, Sio-Iong
2010-01-01
This text is a systematic, state-of-the-art introduction to the use of innovative computing paradigms as an investigative tool for applications in time series analysis. It includes frontier case studies based on recent research.
Measuring multiscaling in financial time-series
International Nuclear Information System (INIS)
Buonocore, R.J.; Aste, T.; Di Matteo, T.
2016-01-01
We discuss the origin of multiscaling in financial time-series and investigate how to best quantify it. Our methodology consists in separating the different sources of measured multifractality by analyzing the multi/uni-scaling behavior of synthetic time-series with known properties. We use the results from the synthetic time-series to interpret the measure of multifractality of real log-returns time-series. The main finding is that the aggregation horizon of the returns can introduce a strong bias effect on the measure of multifractality. This effect can become especially important when returns distributions have power law tails with exponents in the range (2, 5). We discuss the right aggregation horizon to mitigate this bias.
Complex network approach to fractional time series
Energy Technology Data Exchange (ETDEWEB)
Manshour, Pouya [Physics Department, Persian Gulf University, Bushehr 75169 (Iran, Islamic Republic of)
2015-10-15
In order to extract correlation information inherited in stochastic time series, the visibility graph algorithm has been recently proposed, by which a time series can be mapped onto a complex network. We demonstrate that the visibility algorithm is not an appropriate one to study the correlation aspects of a time series. We then employ the horizontal visibility algorithm, as a much simpler one, to map fractional processes onto complex networks. The degree distributions are shown to have parabolic exponential forms with Hurst dependent fitting parameter. Further, we take into account other topological properties such as maximum eigenvalue of the adjacency matrix and the degree assortativity, and show that such topological quantities can also be used to predict the Hurst exponent, with an exception for anti-persistent fractional Gaussian noises. To solve this problem, we take into account the Spearman correlation coefficient between nodes' degrees and their corresponding data values in the original time series.
A Literature Survey of Early Time Series Classification and Deep Learning
Santos, Tiago; Kern, Roman
2017-01-01
This paper provides an overview of current literature on time series classification approaches, in particular of early time series classification. A very common and effective time series classification approach is the 1-Nearest Neighbor classier, with different distance measures such as the Euclidean or dynamic time warping distances. This paper starts by reviewing these baseline methods. More recently, with the gain in popularity in the application of deep neural networks to the eld of...
Multivariate Time Series Decomposition into Oscillation Components.
Matsuda, Takeru; Komaki, Fumiyasu
2017-08-01
Many time series are considered to be a superposition of several oscillation components. We have proposed a method for decomposing univariate time series into oscillation components and estimating their phases (Matsuda & Komaki, 2017 ). In this study, we extend that method to multivariate time series. We assume that several oscillators underlie the given multivariate time series and that each variable corresponds to a superposition of the projections of the oscillators. Thus, the oscillators superpose on each variable with amplitude and phase modulation. Based on this idea, we develop gaussian linear state-space models and use them to decompose the given multivariate time series. The model parameters are estimated from data using the empirical Bayes method, and the number of oscillators is determined using the Akaike information criterion. Therefore, the proposed method extracts underlying oscillators in a data-driven manner and enables investigation of phase dynamics in a given multivariate time series. Numerical results show the effectiveness of the proposed method. From monthly mean north-south sunspot number data, the proposed method reveals an interesting phase relationship.
Introduction to time series analysis and forecasting
Montgomery, Douglas C; Kulahci, Murat
2008-01-01
An accessible introduction to the most current thinking in and practicality of forecasting techniques in the context of time-oriented data. Analyzing time-oriented data and forecasting are among the most important problems that analysts face across many fields, ranging from finance and economics to production operations and the natural sciences. As a result, there is a widespread need for large groups of people in a variety of fields to understand the basic concepts of time series analysis and forecasting. Introduction to Time Series Analysis and Forecasting presents the time series analysis branch of applied statistics as the underlying methodology for developing practical forecasts, and it also bridges the gap between theory and practice by equipping readers with the tools needed to analyze time-oriented data and construct useful, short- to medium-term, statistically based forecasts.
Detecting chaos in irregularly sampled time series.
Kulp, C W
2013-09-01
Recently, Wiebe and Virgin [Chaos 22, 013136 (2012)] developed an algorithm which detects chaos by analyzing a time series' power spectrum which is computed using the Discrete Fourier Transform (DFT). Their algorithm, like other time series characterization algorithms, requires that the time series be regularly sampled. Real-world data, however, are often irregularly sampled, thus, making the detection of chaotic behavior difficult or impossible with those methods. In this paper, a characterization algorithm is presented, which effectively detects chaos in irregularly sampled time series. The work presented here is a modification of Wiebe and Virgin's algorithm and uses the Lomb-Scargle Periodogram (LSP) to compute a series' power spectrum instead of the DFT. The DFT is not appropriate for irregularly sampled time series. However, the LSP is capable of computing the frequency content of irregularly sampled data. Furthermore, a new method of analyzing the power spectrum is developed, which can be useful for differentiating between chaotic and non-chaotic behavior. The new characterization algorithm is successfully applied to irregularly sampled data generated by a model as well as data consisting of observations of variable stars.
Clinical and epidemiological rounds. Time series
Directory of Open Access Journals (Sweden)
León-Álvarez, Alba Luz
2016-07-01
Full Text Available Analysis of time series is a technique that implicates the study of individuals or groups observed in successive moments in time. This type of analysis allows the study of potential causal relationships between different variables that change over time and relate to each other. It is the most important technique to make inferences about the future, predicting, on the basis or what has happened in the past and it is applied in different disciplines of knowledge. Here we discuss different components of time series, the analysis technique and specific examples in health research.
Time Series Forecasting with Missing Values
Directory of Open Access Journals (Sweden)
Shin-Fu Wu
2015-11-01
Full Text Available Time series prediction has become more popular in various kinds of applications such as weather prediction, control engineering, financial analysis, industrial monitoring, etc. To deal with real-world problems, we are often faced with missing values in the data due to sensor malfunctions or human errors. Traditionally, the missing values are simply omitted or replaced by means of imputation methods. However, omitting those missing values may cause temporal discontinuity. Imputation methods, on the other hand, may alter the original time series. In this study, we propose a novel forecasting method based on least squares support vector machine (LSSVM. We employ the input patterns with the temporal information which is defined as local time index (LTI. Time series data as well as local time indexes are fed to LSSVM for doing forecasting without imputation. We compare the forecasting performance of our method with other imputation methods. Experimental results show that the proposed method is promising and is worth further investigations.
Efficient Approximate OLAP Querying Over Time Series
DEFF Research Database (Denmark)
Perera, Kasun Baruhupolage Don Kasun Sanjeewa; Hahmann, Martin; Lehner, Wolfgang
2016-01-01
The ongoing trend for data gathering not only produces larger volumes of data, but also increases the variety of recorded data types. Out of these, especially time series, e.g. various sensor readings, have attracted attention in the domains of business intelligence and decision making. As OLAP...... queries play a major role in these domains, it is desirable to also execute them on time series data. While this is not a problem on the conceptual level, it can become a bottleneck with regards to query run-time. In general, processing OLAP queries gets more computationally intensive as the volume...... of data grows. This is a particular problem when querying time series data, which generally contains multiple measures recorded at fine time granularities. Usually, this issue is addressed either by scaling up hardware or by employing workload based query optimization techniques. However, these solutions...
Time averaging, ageing and delay analysis of financial time series
Cherstvy, Andrey G.; Vinod, Deepak; Aghion, Erez; Chechkin, Aleksei V.; Metzler, Ralf
2017-06-01
We introduce three strategies for the analysis of financial time series based on time averaged observables. These comprise the time averaged mean squared displacement (MSD) as well as the ageing and delay time methods for varying fractions of the financial time series. We explore these concepts via statistical analysis of historic time series for several Dow Jones Industrial indices for the period from the 1960s to 2015. Remarkably, we discover a simple universal law for the delay time averaged MSD. The observed features of the financial time series dynamics agree well with our analytical results for the time averaged measurables for geometric Brownian motion, underlying the famed Black-Scholes-Merton model. The concepts we promote here are shown to be useful for financial data analysis and enable one to unveil new universal features of stock market dynamics.
Hybrid discrete-time neural networks.
Cao, Hongjun; Ibarz, Borja
2010-11-13
Hybrid dynamical systems combine evolution equations with state transitions. When the evolution equations are discrete-time (also called map-based), the result is a hybrid discrete-time system. A class of biological neural network models that has recently received some attention falls within this category: map-based neuron models connected by means of fast threshold modulation (FTM). FTM is a connection scheme that aims to mimic the switching dynamics of a neuron subject to synaptic inputs. The dynamic equations of the neuron adopt different forms according to the state (either firing or not firing) and type (excitatory or inhibitory) of their presynaptic neighbours. Therefore, the mathematical model of one such network is a combination of discrete-time evolution equations with transitions between states, constituting a hybrid discrete-time (map-based) neural network. In this paper, we review previous work within the context of these models, exemplifying useful techniques to analyse them. Typical map-based neuron models are low-dimensional and amenable to phase-plane analysis. In bursting models, fast-slow decomposition can be used to reduce dimensionality further, so that the dynamics of a pair of connected neurons can be easily understood. We also discuss a model that includes electrical synapses in addition to chemical synapses with FTM. Furthermore, we describe how master stability functions can predict the stability of synchronized states in these networks. The main results are extended to larger map-based neural networks.
Highly comparative time-series analysis: the empirical structure of time series and their methods.
Fulcher, Ben D; Little, Max A; Jones, Nick S
2013-06-06
The process of collecting and organizing sets of observations represents a common theme throughout the history of science. However, despite the ubiquity of scientists measuring, recording and analysing the dynamics of different processes, an extensive organization of scientific time-series data and analysis methods has never been performed. Addressing this, annotated collections of over 35 000 real-world and model-generated time series, and over 9000 time-series analysis algorithms are analysed in this work. We introduce reduced representations of both time series, in terms of their properties measured by diverse scientific methods, and of time-series analysis methods, in terms of their behaviour on empirical time series, and use them to organize these interdisciplinary resources. This new approach to comparing across diverse scientific data and methods allows us to organize time-series datasets automatically according to their properties, retrieve alternatives to particular analysis methods developed in other scientific disciplines and automate the selection of useful methods for time-series classification and regression tasks. The broad scientific utility of these tools is demonstrated on datasets of electroencephalograms, self-affine time series, heartbeat intervals, speech signals and others, in each case contributing novel analysis techniques to the existing literature. Highly comparative techniques that compare across an interdisciplinary literature can thus be used to guide more focused research in time-series analysis for applications across the scientific disciplines.
Turbulencelike Behavior of Seismic Time Series
International Nuclear Information System (INIS)
Manshour, P.; Saberi, S.; Sahimi, Muhammad; Peinke, J.; Pacheco, Amalio F.; Rahimi Tabar, M. Reza
2009-01-01
We report on a stochastic analysis of Earth's vertical velocity time series by using methods originally developed for complex hierarchical systems and, in particular, for turbulent flows. Analysis of the fluctuations of the detrended increments of the series reveals a pronounced transition in their probability density function from Gaussian to non-Gaussian. The transition occurs 5-10 hours prior to a moderate or large earthquake, hence representing a new and reliable precursor for detecting such earthquakes
Introduction to time series analysis and forecasting
Montgomery, Douglas C; Kulahci, Murat
2015-01-01
Praise for the First Edition ""…[t]he book is great for readers who need to apply the methods and models presented but have little background in mathematics and statistics."" -MAA Reviews Thoroughly updated throughout, Introduction to Time Series Analysis and Forecasting, Second Edition presents the underlying theories of time series analysis that are needed to analyze time-oriented data and construct real-world short- to medium-term statistical forecasts. Authored by highly-experienced academics and professionals in engineering statistics, the Second Edition features discussions on both
Time series modeling in traffic safety research.
Lavrenz, Steven M; Vlahogianni, Eleni I; Gkritza, Konstantina; Ke, Yue
2018-08-01
The use of statistical models for analyzing traffic safety (crash) data has been well-established. However, time series techniques have traditionally been underrepresented in the corresponding literature, due to challenges in data collection, along with a limited knowledge of proper methodology. In recent years, new types of high-resolution traffic safety data, especially in measuring driver behavior, have made time series modeling techniques an increasingly salient topic of study. Yet there remains a dearth of information to guide analysts in their use. This paper provides an overview of the state of the art in using time series models in traffic safety research, and discusses some of the fundamental techniques and considerations in classic time series modeling. It also presents ongoing and future opportunities for expanding the use of time series models, and explores newer modeling techniques, including computational intelligence models, which hold promise in effectively handling ever-larger data sets. The information contained herein is meant to guide safety researchers in understanding this broad area of transportation data analysis, and provide a framework for understanding safety trends that can influence policy-making. Copyright © 2017 Elsevier Ltd. All rights reserved.
Forecasting autoregressive time series under changing persistence
DEFF Research Database (Denmark)
Kruse, Robinson
Changing persistence in time series models means that a structural change from nonstationarity to stationarity or vice versa occurs over time. Such a change has important implications for forecasting, as negligence may lead to inaccurate model predictions. This paper derives generally applicable...
Ensemble Deep Learning for Biomedical Time Series Classification
Directory of Open Access Journals (Sweden)
Lin-peng Jin
2016-01-01
Full Text Available Ensemble learning has been proved to improve the generalization ability effectively in both theory and practice. In this paper, we briefly outline the current status of research on it first. Then, a new deep neural network-based ensemble method that integrates filtering views, local views, distorted views, explicit training, implicit training, subview prediction, and Simple Average is proposed for biomedical time series classification. Finally, we validate its effectiveness on the Chinese Cardiovascular Disease Database containing a large number of electrocardiogram recordings. The experimental results show that the proposed method has certain advantages compared to some well-known ensemble methods, such as Bagging and AdaBoost.
Time series clustering in large data sets
Directory of Open Access Journals (Sweden)
Jiří Fejfar
2011-01-01
Full Text Available The clustering of time series is a widely researched area. There are many methods for dealing with this task. We are actually using the Self-organizing map (SOM with the unsupervised learning algorithm for clustering of time series. After the first experiment (Fejfar, Weinlichová, Šťastný, 2009 it seems that the whole concept of the clustering algorithm is correct but that we have to perform time series clustering on much larger dataset to obtain more accurate results and to find the correlation between configured parameters and results more precisely. The second requirement arose in a need for a well-defined evaluation of results. It seems useful to use sound recordings as instances of time series again. There are many recordings to use in digital libraries, many interesting features and patterns can be found in this area. We are searching for recordings with the similar development of information density in this experiment. It can be used for musical form investigation, cover songs detection and many others applications.The objective of the presented paper is to compare clustering results made with different parameters of feature vectors and the SOM itself. We are describing time series in a simplistic way evaluating standard deviations for separated parts of recordings. The resulting feature vectors are clustered with the SOM in batch training mode with different topologies varying from few neurons to large maps.There are other algorithms discussed, usable for finding similarities between time series and finally conclusions for further research are presented. We also present an overview of the related actual literature and projects.
Introduction to time series and forecasting
Brockwell, Peter J
2016-01-01
This book is aimed at the reader who wishes to gain a working knowledge of time series and forecasting methods as applied to economics, engineering and the natural and social sciences. It assumes knowledge only of basic calculus, matrix algebra and elementary statistics. This third edition contains detailed instructions for the use of the professional version of the Windows-based computer package ITSM2000, now available as a free download from the Springer Extras website. The logic and tools of time series model-building are developed in detail. Numerous exercises are included and the software can be used to analyze and forecast data sets of the user's own choosing. The book can also be used in conjunction with other time series packages such as those included in R. The programs in ITSM2000 however are menu-driven and can be used with minimal investment of time in the computational details. The core of the book covers stationary processes, ARMA and ARIMA processes, multivariate time series and state-space mod...
Complex dynamic in ecological time series
Peter Turchin; Andrew D. Taylor
1992-01-01
Although the possibility of complex dynamical behaviors-limit cycles, quasiperiodic oscillations, and aperiodic chaos-has been recognized theoretically, most ecologists are skeptical of their importance in nature. In this paper we develop a methodology for reconstructing endogenous (or deterministic) dynamics from ecological time series. Our method consists of fitting...
Inferring interdependencies from short time series
Indian Academy of Sciences (India)
Abstract. Complex networks provide an invaluable framework for the study of interlinked dynamical systems. In many cases, such networks are constructed from observed time series by first estimating the ...... does not quantify causal relations (unlike IOTA, or .... Africa_map_regions.svg, which is under public domain.
On modeling panels of time series
Ph.H.B.F. Franses (Philip Hans)
2002-01-01
textabstractThis paper reviews research issues in modeling panels of time series. Examples of this type of data are annually observed macroeconomic indicators for all countries in the world, daily returns on the individual stocks listed in the S&P500, and the sales records of all items in a
25 years of time series forecasting
de Gooijer, J.G.; Hyndman, R.J.
2006-01-01
We review the past 25 years of research into time series forecasting. In this silver jubilee issue, we naturally highlight results published in journals managed by the International Institute of Forecasters (Journal of Forecasting 1982-1985 and International Journal of Forecasting 1985-2005). During
Markov Trends in Macroeconomic Time Series
R. Paap (Richard)
1997-01-01
textabstractMany macroeconomic time series are characterised by long periods of positive growth, expansion periods, and short periods of negative growth, recessions. A popular model to describe this phenomenon is the Markov trend, which is a stochastic segmented trend where the slope depends on the
Modeling vector nonlinear time series using POLYMARS
de Gooijer, J.G.; Ray, B.K.
2003-01-01
A modified multivariate adaptive regression splines method for modeling vector nonlinear time series is investigated. The method results in models that can capture certain types of vector self-exciting threshold autoregressive behavior, as well as provide good predictions for more general vector
Modeling seasonality in bimonthly time series
Ph.H.B.F. Franses (Philip Hans)
1992-01-01
textabstractA recurring issue in modeling seasonal time series variables is the choice of the most adequate model for the seasonal movements. One selection method for quarterly data is proposed in Hylleberg et al. (1990). Market response models are often constructed for bimonthly variables, and
Time Series Modelling using Proc Varmax
DEFF Research Database (Denmark)
Milhøj, Anders
2007-01-01
In this paper it will be demonstrated how various time series problems could be met using Proc Varmax. The procedure is rather new and hence new features like cointegration, testing for Granger causality are included, but it also means that more traditional ARIMA modelling as outlined by Box...
On clustering fMRI time series
DEFF Research Database (Denmark)
Goutte, Cyril; Toft, Peter Aundal; Rostrup, E.
1999-01-01
Analysis of fMRI time series is often performed by extracting one or more parameters for the individual voxels. Methods based, e.g., on various statistical tests are then used to yield parameters corresponding to probability of activation or activation strength. However, these methods do...
Robust Control Charts for Time Series Data
Croux, C.; Gelper, S.; Mahieu, K.
2010-01-01
This article presents a control chart for time series data, based on the one-step- ahead forecast errors of the Holt-Winters forecasting method. We use robust techniques to prevent that outliers affect the estimation of the control limits of the chart. Moreover, robustness is important to maintain
Optimal transformations for categorical autoregressive time series
Buuren, S. van
1996-01-01
This paper describes a method for finding optimal transformations for analyzing time series by autoregressive models. 'Optimal' implies that the agreement between the autoregressive model and the transformed data is maximal. Such transformations help 1) to increase the model fit, and 2) to analyze
Lecture notes for Advanced Time Series Analysis
DEFF Research Database (Denmark)
Madsen, Henrik; Holst, Jan
1997-01-01
A first version of this notes was used at the lectures in Grenoble, and they are now extended and improved (together with Jan Holst), and used in Ph.D. courses on Advanced Time Series Analysis at IMM and at the Department of Mathematical Statistics, University of Lund, 1994, 1997, ...
Forecasting with periodic autoregressive time series models
Ph.H.B.F. Franses (Philip Hans); R. Paap (Richard)
1999-01-01
textabstractThis paper is concerned with forecasting univariate seasonal time series data using periodic autoregressive models. We show how one should account for unit roots and deterministic terms when generating out-of-sample forecasts. We illustrate the models for various quarterly UK consumption
Stochastic nature of series of waiting times
Anvari, Mehrnaz; Aghamohammadi, Cina; Dashti-Naserabadi, H.; Salehi, E.; Behjat, E.; Qorbani, M.; Khazaei Nezhad, M.; Zirak, M.; Hadjihosseini, Ali; Peinke, Joachim; Tabar, M. Reza Rahimi
2013-06-01
Although fluctuations in the waiting time series have been studied for a long time, some important issues such as its long-range memory and its stochastic features in the presence of nonstationarity have so far remained unstudied. Here we find that the “waiting times” series for a given increment level have long-range correlations with Hurst exponents belonging to the interval 1/2
The Statistical Analysis of Time Series
Anderson, T W
2011-01-01
The Wiley Classics Library consists of selected books that have become recognized classics in their respective fields. With these new unabridged and inexpensive editions, Wiley hopes to extend the life of these important works by making them available to future generations of mathematicians and scientists. Currently available in the Series: T. W. Anderson Statistical Analysis of Time Series T. S. Arthanari & Yadolah Dodge Mathematical Programming in Statistics Emil Artin Geometric Algebra Norman T. J. Bailey The Elements of Stochastic Processes with Applications to the Natural Sciences George
Horváth, Csilla; Kornelis, Marcel; Leeflang, Peter S.H.
2002-01-01
In this review, we give a comprehensive summary of time series techniques in marketing, and discuss a variety of time series analysis (TSA) techniques and models. We classify them in the sets (i) univariate TSA, (ii) multivariate TSA, and (iii) multiple TSA. We provide relevant marketing
Algorithm for Compressing Time-Series Data
Hawkins, S. Edward, III; Darlington, Edward Hugo
2012-01-01
An algorithm based on Chebyshev polynomials effects lossy compression of time-series data or other one-dimensional data streams (e.g., spectral data) that are arranged in blocks for sequential transmission. The algorithm was developed for use in transmitting data from spacecraft scientific instruments to Earth stations. In spite of its lossy nature, the algorithm preserves the information needed for scientific analysis. The algorithm is computationally simple, yet compresses data streams by factors much greater than two. The algorithm is not restricted to spacecraft or scientific uses: it is applicable to time-series data in general. The algorithm can also be applied to general multidimensional data that have been converted to time-series data, a typical example being image data acquired by raster scanning. However, unlike most prior image-data-compression algorithms, this algorithm neither depends on nor exploits the two-dimensional spatial correlations that are generally present in images. In order to understand the essence of this compression algorithm, it is necessary to understand that the net effect of this algorithm and the associated decompression algorithm is to approximate the original stream of data as a sequence of finite series of Chebyshev polynomials. For the purpose of this algorithm, a block of data or interval of time for which a Chebyshev polynomial series is fitted to the original data is denoted a fitting interval. Chebyshev approximation has two properties that make it particularly effective for compressing serial data streams with minimal loss of scientific information: The errors associated with a Chebyshev approximation are nearly uniformly distributed over the fitting interval (this is known in the art as the "equal error property"); and the maximum deviations of the fitted Chebyshev polynomial from the original data have the smallest possible values (this is known in the art as the "min-max property").
Inverse statistical approach in heartbeat time series
International Nuclear Information System (INIS)
Ebadi, H; Shirazi, A H; Mani, Ali R; Jafari, G R
2011-01-01
We present an investigation on heart cycle time series, using inverse statistical analysis, a concept borrowed from studying turbulence. Using this approach, we studied the distribution of the exit times needed to achieve a predefined level of heart rate alteration. Such analysis uncovers the most likely waiting time needed to reach a certain change in the rate of heart beat. This analysis showed a significant difference between the raw data and shuffled data, when the heart rate accelerates or decelerates to a rare event. We also report that inverse statistical analysis can distinguish between the electrocardiograms taken from healthy volunteers and patients with heart failure
Visibility graphlet approach to chaotic time series
Energy Technology Data Exchange (ETDEWEB)
Mutua, Stephen [Business School, University of Shanghai for Science and Technology, Shanghai 200093 (China); Computer Science Department, Masinde Muliro University of Science and Technology, P.O. Box 190-50100, Kakamega (Kenya); Gu, Changgui, E-mail: gu-changgui@163.com, E-mail: hjyang@ustc.edu.cn; Yang, Huijie, E-mail: gu-changgui@163.com, E-mail: hjyang@ustc.edu.cn [Business School, University of Shanghai for Science and Technology, Shanghai 200093 (China)
2016-05-15
Many novel methods have been proposed for mapping time series into complex networks. Although some dynamical behaviors can be effectively captured by existing approaches, the preservation and tracking of the temporal behaviors of a chaotic system remains an open problem. In this work, we extended the visibility graphlet approach to investigate both discrete and continuous chaotic time series. We applied visibility graphlets to capture the reconstructed local states, so that each is treated as a node and tracked downstream to create a temporal chain link. Our empirical findings show that the approach accurately captures the dynamical properties of chaotic systems. Networks constructed from periodic dynamic phases all converge to regular networks and to unique network structures for each model in the chaotic zones. Furthermore, our results show that the characterization of chaotic and non-chaotic zones in the Lorenz system corresponds to the maximal Lyapunov exponent, thus providing a simple and straightforward way to analyze chaotic systems.
Time-Series Analysis: A Cautionary Tale
Damadeo, Robert
2015-01-01
Time-series analysis has often been a useful tool in atmospheric science for deriving long-term trends in various atmospherically important parameters (e.g., temperature or the concentration of trace gas species). In particular, time-series analysis has been repeatedly applied to satellite datasets in order to derive the long-term trends in stratospheric ozone, which is a critical atmospheric constituent. However, many of the potential pitfalls relating to the non-uniform sampling of the datasets were often ignored and the results presented by the scientific community have been unknowingly biased. A newly developed and more robust application of this technique is applied to the Stratospheric Aerosol and Gas Experiment (SAGE) II version 7.0 ozone dataset and the previous biases and newly derived trends are presented.
Time Series Analysis Using Geometric Template Matching.
Frank, Jordan; Mannor, Shie; Pineau, Joelle; Precup, Doina
2013-03-01
We present a novel framework for analyzing univariate time series data. At the heart of the approach is a versatile algorithm for measuring the similarity of two segments of time series called geometric template matching (GeTeM). First, we use GeTeM to compute a similarity measure for clustering and nearest-neighbor classification. Next, we present a semi-supervised learning algorithm that uses the similarity measure with hierarchical clustering in order to improve classification performance when unlabeled training data are available. Finally, we present a boosting framework called TDEBOOST, which uses an ensemble of GeTeM classifiers. TDEBOOST augments the traditional boosting approach with an additional step in which the features used as inputs to the classifier are adapted at each step to improve the training error. We empirically evaluate the proposed approaches on several datasets, such as accelerometer data collected from wearable sensors and ECG data.
Nonlinear time series analysis with R
Huffaker, Ray; Rosa, Rodolfo
2017-01-01
In the process of data analysis, the investigator is often facing highly-volatile and random-appearing observed data. A vast body of literature shows that the assumption of underlying stochastic processes was not necessarily representing the nature of the processes under investigation and, when other tools were used, deterministic features emerged. Non Linear Time Series Analysis (NLTS) allows researchers to test whether observed volatility conceals systematic non linear behavior, and to rigorously characterize governing dynamics. Behavioral patterns detected by non linear time series analysis, along with scientific principles and other expert information, guide the specification of mechanistic models that serve to explain real-world behavior rather than merely reproducing it. Often there is a misconception regarding the complexity of the level of mathematics needed to understand and utilize the tools of NLTS (for instance Chaos theory). However, mathematics used in NLTS is much simpler than many other subjec...
Reconstruction of tritium time series in precipitation
International Nuclear Information System (INIS)
Celle-Jeanton, H.; Gourcy, L.; Aggarwal, P.K.
2002-01-01
Tritium is commonly used in groundwaters studies to calculate the recharge rate and to identify the presence of a modern recharge. The knowledge of 3 H precipitation time series is then very important for the study of groundwater recharge. Rozanski and Araguas provided good information on precipitation tritium content in 180 stations of the GNIP network to the end of 1987, but it shows some lacks of measurements either within one chronicle or within one region (the Southern hemisphere for instance). Therefore, it seems to be essential to find a method to recalculate data for a region where no measurement is available.To solve this problem, we propose another method which is based on triangulation. It needs the knowledge of 3 H time series of 3 stations surrounding geographically the 4-th station for which tritium input curve has to be reconstructed
Time Series Forecasting with Missing Values
Shin-Fu Wu; Chia-Yung Chang; Shie-Jue Lee
2015-01-01
Time series prediction has become more popular in various kinds of applications such as weather prediction, control engineering, financial analysis, industrial monitoring, etc. To deal with real-world problems, we are often faced with missing values in the data due to sensor malfunctions or human errors. Traditionally, the missing values are simply omitted or replaced by means of imputation methods. However, omitting those missing values may cause temporal discontinuity. Imputation methods, o...
Particle Swarm Based Approach of a Real-Time Discrete Neural Identifier for Linear Induction Motors
Directory of Open Access Journals (Sweden)
Alma Y. Alanis
2013-01-01
Full Text Available This paper focusses on a discrete-time neural identifier applied to a linear induction motor (LIM model, whose model is assumed to be unknown. This neural identifier is robust in presence of external and internal uncertainties. The proposed scheme is based on a discrete-time recurrent high-order neural network (RHONN trained with a novel algorithm based on extended Kalman filter (EKF and particle swarm optimization (PSO, using an online series-parallel con figuration. Real-time results are included in order to illustrate the applicability of the proposed scheme.
Causal strength induction from time series data.
Soo, Kevin W; Rottman, Benjamin M
2018-04-01
One challenge when inferring the strength of cause-effect relations from time series data is that the cause and/or effect can exhibit temporal trends. If temporal trends are not accounted for, a learner could infer that a causal relation exists when it does not, or even infer that there is a positive causal relation when the relation is negative, or vice versa. We propose that learners use a simple heuristic to control for temporal trends-that they focus not on the states of the cause and effect at a given instant, but on how the cause and effect change from one observation to the next, which we call transitions. Six experiments were conducted to understand how people infer causal strength from time series data. We found that participants indeed use transitions in addition to states, which helps them to reach more accurate causal judgments (Experiments 1A and 1B). Participants use transitions more when the stimuli are presented in a naturalistic visual format than a numerical format (Experiment 2), and the effect of transitions is not driven by primacy or recency effects (Experiment 3). Finally, we found that participants primarily use the direction in which variables change rather than the magnitude of the change for estimating causal strength (Experiments 4 and 5). Collectively, these studies provide evidence that people often use a simple yet effective heuristic for inferring causal strength from time series data. (PsycINFO Database Record (c) 2018 APA, all rights reserved).
Interpretable Categorization of Heterogeneous Time Series Data
Lee, Ritchie; Kochenderfer, Mykel J.; Mengshoel, Ole J.; Silbermann, Joshua
2017-01-01
We analyze data from simulated aircraft encounters to validate and inform the development of a prototype aircraft collision avoidance system. The high-dimensional and heterogeneous time series dataset is analyzed to discover properties of near mid-air collisions (NMACs) and categorize the NMAC encounters. Domain experts use these properties to better organize and understand NMAC occurrences. Existing solutions either are not capable of handling high-dimensional and heterogeneous time series datasets or do not provide explanations that are interpretable by a domain expert. The latter is critical to the acceptance and deployment of safety-critical systems. To address this gap, we propose grammar-based decision trees along with a learning algorithm. Our approach extends decision trees with a grammar framework for classifying heterogeneous time series data. A context-free grammar is used to derive decision expressions that are interpretable, application-specific, and support heterogeneous data types. In addition to classification, we show how grammar-based decision trees can also be used for categorization, which is a combination of clustering and generating interpretable explanations for each cluster. We apply grammar-based decision trees to a simulated aircraft encounter dataset and evaluate the performance of four variants of our learning algorithm. The best algorithm is used to analyze and categorize near mid-air collisions in the aircraft encounter dataset. We describe each discovered category in detail and discuss its relevance to aircraft collision avoidance.
Interpretation of a compositional time series
Tolosana-Delgado, R.; van den Boogaart, K. G.
2012-04-01
Common methods for multivariate time series analysis use linear operations, from the definition of a time-lagged covariance/correlation to the prediction of new outcomes. However, when the time series response is a composition (a vector of positive components showing the relative importance of a set of parts in a total, like percentages and proportions), then linear operations are afflicted of several problems. For instance, it has been long recognised that (auto/cross-)correlations between raw percentages are spurious, more dependent on which other components are being considered than on any natural link between the components of interest. Also, a long-term forecast of a composition in models with a linear trend will ultimately predict negative components. In general terms, compositional data should not be treated in a raw scale, but after a log-ratio transformation (Aitchison, 1986: The statistical analysis of compositional data. Chapman and Hill). This is so because the information conveyed by a compositional data is relative, as stated in their definition. The principle of working in coordinates allows to apply any sort of multivariate analysis to a log-ratio transformed composition, as long as this transformation is invertible. This principle is of full application to time series analysis. We will discuss how results (both auto/cross-correlation functions and predictions) can be back-transformed, viewed and interpreted in a meaningful way. One view is to use the exhaustive set of all possible pairwise log-ratios, which allows to express the results into D(D - 1)/2 separate, interpretable sets of one-dimensional models showing the behaviour of each possible pairwise log-ratios. Another view is the interpretation of estimated coefficients or correlations back-transformed in terms of compositions. These two views are compatible and complementary. These issues are illustrated with time series of seasonal precipitation patterns at different rain gauges of the USA
Timing calibration and spectral cleaning of LOFAR time series data
Corstanje, A.; Buitink, S.; Enriquez, J. E.; Falcke, H.; Horandel, J. R.; Krause, M.; Nelles, A.; Rachen, J. P.; Schellart, P.; Scholten, O.; ter Veen, S.; Thoudam, S.; Trinh, T. N. G.
We describe a method for spectral cleaning and timing calibration of short time series data of the voltage in individual radio interferometer receivers. It makes use of phase differences in fast Fourier transform (FFT) spectra across antenna pairs. For strong, localized terrestrial sources these are
Outlier Detection in Structural Time Series Models
DEFF Research Database (Denmark)
Marczak, Martyna; Proietti, Tommaso
investigate via Monte Carlo simulations how this approach performs for detecting additive outliers and level shifts in the analysis of nonstationary seasonal time series. The reference model is the basic structural model, featuring a local linear trend, possibly integrated of order two, stochastic seasonality......Structural change affects the estimation of economic signals, like the underlying growth rate or the seasonally adjusted series. An important issue, which has attracted a great deal of attention also in the seasonal adjustment literature, is its detection by an expert procedure. The general......–to–specific approach to the detection of structural change, currently implemented in Autometrics via indicator saturation, has proven to be both practical and effective in the context of stationary dynamic regression models and unit–root autoregressions. By focusing on impulse– and step–indicator saturation, we...
Analysis of JET ELMy time series
International Nuclear Information System (INIS)
Zvejnieks, G.; Kuzovkov, V.N.
2005-01-01
Full text: Achievement of the planned operational regime in the next generation tokamaks (such as ITER) still faces principal problems. One of the main challenges is obtaining the control of edge localized modes (ELMs), which should lead to both long plasma pulse times and reasonable divertor life time. In order to control ELMs the hypothesis was proposed by Degeling [1] that ELMs exhibit features of chaotic dynamics and thus a standard chaos control methods might be applicable. However, our findings which are based on the nonlinear autoregressive (NAR) model contradict this hypothesis for JET ELMy time-series. In turn, it means that ELM behavior is of a relaxation or random type. These conclusions coincide with our previous results obtained for ASDEX Upgrade time series [2]. [1] A.W. Degeling, Y.R. Martin, P.E. Bak, J. B.Lister, and X. Llobet, Plasma Phys. Control. Fusion 43, 1671 (2001). [2] G. Zvejnieks, V.N. Kuzovkov, O. Dumbrajs, A.W. Degeling, W. Suttrop, H. Urano, and H. Zohm, Physics of Plasmas 11, 5658 (2004)
A comparison of various forecasting techniques applied to mean hourly wind speed time series
Energy Technology Data Exchange (ETDEWEB)
Sfetsos, A. [7 Pirsou Street, Athens (Greece)
2000-09-01
This paper presents a comparison of various forecasting approaches, using time series analysis, on mean hourly wind speed data. In addition to the traditional linear (ARMA) models and the commonly used feed forward and recurrent neural networks, other approaches are also examined including the Adaptive Neuro-Fuzzy Inference Systems (ANFIS) and Neural Logic Networks. The developed models are evaluated for their ability to produce accurate and fast forecasts. (Author)
Linear and nonlinear dynamic systems in financial time series prediction
Directory of Open Access Journals (Sweden)
Salim Lahmiri
2012-10-01
Full Text Available Autoregressive moving average (ARMA process and dynamic neural networks namely the nonlinear autoregressive moving average with exogenous inputs (NARX are compared by evaluating their ability to predict financial time series; for instance the S&P500 returns. Two classes of ARMA are considered. The first one is the standard ARMA model which is a linear static system. The second one uses Kalman filter (KF to estimate and predict ARMA coefficients. This model is a linear dynamic system. The forecasting ability of each system is evaluated by means of mean absolute error (MAE and mean absolute deviation (MAD statistics. Simulation results indicate that the ARMA-KF system performs better than the standard ARMA alone. Thus, introducing dynamics into the ARMA process improves the forecasting accuracy. In addition, the ARMA-KF outperformed the NARX. This result may suggest that the linear component found in the S&P500 return series is more dominant than the nonlinear part. In sum, we conclude that introducing dynamics into the ARMA process provides an effective system for S&P500 time series prediction.
Fourier analysis of time series an introduction
Bloomfield, Peter
2000-01-01
A new, revised edition of a yet unrivaled work on frequency domain analysis Long recognized for his unique focus on frequency domain methods for the analysis of time series data as well as for his applied, easy-to-understand approach, Peter Bloomfield brings his well-known 1976 work thoroughly up to date. With a minimum of mathematics and an engaging, highly rewarding style, Bloomfield provides in-depth discussions of harmonic regression, harmonic analysis, complex demodulation, and spectrum analysis. All methods are clearly illustrated using examples of specific data sets, while ample
Estimating High-Dimensional Time Series Models
DEFF Research Database (Denmark)
Medeiros, Marcelo C.; Mendes, Eduardo F.
We study the asymptotic properties of the Adaptive LASSO (adaLASSO) in sparse, high-dimensional, linear time-series models. We assume both the number of covariates in the model and candidate variables can increase with the number of observations and the number of candidate variables is, possibly......, larger than the number of observations. We show the adaLASSO consistently chooses the relevant variables as the number of observations increases (model selection consistency), and has the oracle property, even when the errors are non-Gaussian and conditionally heteroskedastic. A simulation study shows...
Inferring causality from noisy time series data
DEFF Research Database (Denmark)
Mønster, Dan; Fusaroli, Riccardo; Tylén, Kristian
2016-01-01
Convergent Cross-Mapping (CCM) has shown high potential to perform causal inference in the absence of models. We assess the strengths and weaknesses of the method by varying coupling strength and noise levels in coupled logistic maps. We find that CCM fails to infer accurate coupling strength...... and even causality direction in synchronized time-series and in the presence of intermediate coupling. We find that the presence of noise deterministically reduces the level of cross-mapping fidelity, while the convergence rate exhibits higher levels of robustness. Finally, we propose that controlled noise...
Useful Pattern Mining on Time Series
DEFF Research Database (Denmark)
Goumatianos, Nikitas; Christou, Ioannis T; Lindgren, Peter
2013-01-01
We present the architecture of a “useful pattern” mining system that is capable of detecting thousands of different candlestick sequence patterns at the tick or any higher granularity levels. The system architecture is highly distributed and performs most of its highly compute-intensive aggregation...... calculations as complex but efficient distributed SQL queries on the relational databases that store the time-series. We present initial results from mining all frequent candlestick sequences with the characteristic property that when they occur then, with an average at least 60% probability, they signal a 2...
Deep neural networks to enable real-time multimessenger astrophysics
George, Daniel; Huerta, E. A.
2018-02-01
Gravitational wave astronomy has set in motion a scientific revolution. To further enhance the science reach of this emergent field of research, there is a pressing need to increase the depth and speed of the algorithms used to enable these ground-breaking discoveries. We introduce Deep Filtering—a new scalable machine learning method for end-to-end time-series signal processing. Deep Filtering is based on deep learning with two deep convolutional neural networks, which are designed for classification and regression, to detect gravitational wave signals in highly noisy time-series data streams and also estimate the parameters of their sources in real time. Acknowledging that some of the most sensitive algorithms for the detection of gravitational waves are based on implementations of matched filtering, and that a matched filter is the optimal linear filter in Gaussian noise, the application of Deep Filtering using whitened signals in Gaussian noise is investigated in this foundational article. The results indicate that Deep Filtering outperforms conventional machine learning techniques, achieves similar performance compared to matched filtering, while being several orders of magnitude faster, allowing real-time signal processing with minimal resources. Furthermore, we demonstrate that Deep Filtering can detect and characterize waveform signals emitted from new classes of eccentric or spin-precessing binary black holes, even when trained with data sets of only quasicircular binary black hole waveforms. The results presented in this article, and the recent use of deep neural networks for the identification of optical transients in telescope data, suggests that deep learning can facilitate real-time searches of gravitational wave sources and their electromagnetic and astroparticle counterparts. In the subsequent article, the framework introduced herein is directly applied to identify and characterize gravitational wave events in real LIGO data.
Trottini, Mario; Vigo, Isabel; Belda, Santiago
2015-01-01
Given a time series, running trends analysis (RTA) involves evaluating least squares trends over overlapping time windows of L consecutive time points, with overlap by all but one observation. This produces a new series called the “running trends series,” which is used as summary statistics of the original series for further analysis. In recent years, RTA has been widely used in climate applied research as summary statistics for time series and time series association. There is no doubt that ...
Time series analysis of temporal networks
Sikdar, Sandipan; Ganguly, Niloy; Mukherjee, Animesh
2016-01-01
A common but an important feature of all real-world networks is that they are temporal in nature, i.e., the network structure changes over time. Due to this dynamic nature, it becomes difficult to propose suitable growth models that can explain the various important characteristic properties of these networks. In fact, in many application oriented studies only knowing these properties is sufficient. For instance, if one wishes to launch a targeted attack on a network, this can be done even without the knowledge of the full network structure; rather an estimate of some of the properties is sufficient enough to launch the attack. We, in this paper show that even if the network structure at a future time point is not available one can still manage to estimate its properties. We propose a novel method to map a temporal network to a set of time series instances, analyze them and using a standard forecast model of time series, try to predict the properties of a temporal network at a later time instance. To our aim, we consider eight properties such as number of active nodes, average degree, clustering coefficient etc. and apply our prediction framework on them. We mainly focus on the temporal network of human face-to-face contacts and observe that it represents a stochastic process with memory that can be modeled as Auto-Regressive-Integrated-Moving-Average (ARIMA). We use cross validation techniques to find the percentage accuracy of our predictions. An important observation is that the frequency domain properties of the time series obtained from spectrogram analysis could be used to refine the prediction framework by identifying beforehand the cases where the error in prediction is likely to be high. This leads to an improvement of 7.96% (for error level ≤20%) in prediction accuracy on an average across all datasets. As an application we show how such prediction scheme can be used to launch targeted attacks on temporal networks. Contribution to the Topical Issue
Detecting switching and intermittent causalities in time series
Zanin, Massimiliano; Papo, David
2017-04-01
During the last decade, complex network representations have emerged as a powerful instrument for describing the cross-talk between different brain regions both at rest and as subjects are carrying out cognitive tasks, in healthy brains and neurological pathologies. The transient nature of such cross-talk has nevertheless by and large been neglected, mainly due to the inherent limitations of some metrics, e.g., causality ones, which require a long time series in order to yield statistically significant results. Here, we present a methodology to account for intermittent causal coupling in neural activity, based on the identification of non-overlapping windows within the original time series in which the causality is strongest. The result is a less coarse-grained assessment of the time-varying properties of brain interactions, which can be used to create a high temporal resolution time-varying network. We apply the proposed methodology to the analysis of the brain activity of control subjects and alcoholic patients performing an image recognition task. Our results show that short-lived, intermittent, local-scale causality is better at discriminating both groups than global network metrics. These results highlight the importance of the transient nature of brain activity, at least under some pathological conditions.
Anomaly on Superspace of Time Series Data
Capozziello, Salvatore; Pincak, Richard; Kanjamapornkul, Kabin
2017-11-01
We apply the G-theory and anomaly of ghost and antighost fields in the theory of supersymmetry to study a superspace over time series data for the detection of hidden general supply and demand equilibrium in the financial market. We provide proof of the existence of a general equilibrium point over 14 extradimensions of the new G-theory compared with the M-theory of the 11 dimensions model of Edward Witten. We found that the process of coupling between nonequilibrium and equilibrium spinor fields of expectation ghost fields in the superspace of time series data induces an infinitely long exact sequence of cohomology from a short exact sequence of moduli state space model. If we assume that the financial market is separated into two topological spaces of supply and demand as the D-brane and anti-D-brane model, then we can use a cohomology group to compute the stability of the market as a stable point of the general equilibrium of the interaction between D-branes of the market. We obtain the result that the general equilibrium will exist if and only if the 14th Batalin-Vilkovisky cohomology group with the negative dimensions underlying 14 major hidden factors influencing the market is zero.
Real-time applications of neural nets
International Nuclear Information System (INIS)
Spencer, J.E.
1989-05-01
Producing, accelerating and colliding very high power, low emittance beams for long periods is a formidable problem in real-time control. As energy has grown exponentially in time so has the complexity of the machines and their control systems. Similar growth rates have occurred in many areas, e.g., improved integrated circuits have been paid for with comparable increases in complexity. However, in this case, reliability, capability and cost have improved due to reduced size, high production and increased integration which allow various kinds of feedback. In contrast, most large complex systems (LCS) are perceived to lack such possibilities because only one copy is made. Neural nets, as a metaphor for LCS, suggest ways to circumvent such limitations. It is argued that they are logically equivalent to multi-loop feedback/forward control of faulty systems. While complimentary to AI, they mesh nicely with characteristics desired for real-time systems. Such issues are considered, examples given and possibilities discussed. 21 refs., 6 figs
Real-time applications of neural nets
Energy Technology Data Exchange (ETDEWEB)
Spencer, J.E.
1989-05-01
Producing, accelerating and colliding very high power, low emittance beams for long periods is a formidable problem in real-time control. As energy has grown exponentially in time so has the complexity of the machines and their control systems. Similar growth rates have occurred in many areas, e.g., improved integrated circuits have been paid for with comparable increases in complexity. However, in this case, reliability, capability and cost have improved due to reduced size, high production and increased integration which allow various kinds of feedback. In contrast, most large complex systems (LCS) are perceived to lack such possibilities because only one copy is made. Neural nets, as a metaphor for LCS, suggest ways to circumvent such limitations. It is argued that they are logically equivalent to multi-loop feedback/forward control of faulty systems. While complimentary to AI, they mesh nicely with characteristics desired for real-time systems. Such issues are considered, examples given and possibilities discussed. 21 refs., 6 figs.
Real-time applications of neural nets
International Nuclear Information System (INIS)
Spencer, J.E.
1989-01-01
Producing, accelerating and colliding very high power, low emittance beams for long periods is a formidable problem in real-time control. As energy has grown exponentially in time so has the complexity of the machines and their control systems. Similar growth rates have occurred in many areas e.g. improved integrated circuits have been paid for with comparable increases in complexity. However, in this case, reliability, capability and cost have improved due to reduced size, high production and increased integration which allow various kinds of feedback. In contrast, most large complex systems (LCS) are perceived to lack such possibilities because only one copy is made. Neural nets, as a metaphor for LCS, suggest ways to circumvent such limitations. It is argued that they are logically equivalent to multi-loop feedback/forward control of faulty systems. While complimentary to AI, they mesh nicely with characteristics desired for real-time systems. In this paper, such issues are considered, examples given and possibilities discussed
Tool Wear Monitoring Using Time Series Analysis
Song, Dong Yeul; Ohara, Yasuhiro; Tamaki, Haruo; Suga, Masanobu
A tool wear monitoring approach considering the nonlinear behavior of cutting mechanism caused by tool wear and/or localized chipping is proposed, and its effectiveness is verified through the cutting experiment and actual turning machining. Moreover, the variation in the surface roughness of the machined workpiece is also discussed using this approach. In this approach, the residual error between the actually measured vibration signal and the estimated signal obtained from the time series model corresponding to dynamic model of cutting is introduced as the feature of diagnosis. Consequently, it is found that the early tool wear state (i.e. flank wear under 40µm) can be monitored, and also the optimal tool exchange time and the tool wear state for actual turning machining can be judged by this change in the residual error. Moreover, the variation of surface roughness Pz in the range of 3 to 8µm can be estimated by the monitoring of the residual error.
Time Series Based for Online Signature Verification
Directory of Open Access Journals (Sweden)
I Ketut Gede Darma Putra
2013-11-01
Full Text Available Signature verification system is to match the tested signature with a claimed signature. This paper proposes time series based for feature extraction method and dynamic time warping for match method. The system made by process of testing 900 signatures belong to 50 participants, 3 signatures for reference and 5 signatures from original user, simple imposters and trained imposters for signatures test. The final result system was tested with 50 participants with 3 references. This test obtained that system accuracy without imposters is 90,44897959% at threshold 44 with rejection errors (FNMR is 5,2% and acceptance errors (FMR is 4,35102%, when with imposters system accuracy is 80,1361% at threshold 27 with error rejection (FNMR is 15,6% and acceptance errors (average FMR is 4,263946%, with details as follows: acceptance errors is 0,391837%, acceptance errors simple imposters is 3,2% and acceptance errors trained imposters is 9,2%.
Automated time series forecasting for biosurveillance.
Burkom, Howard S; Murphy, Sean Patrick; Shmueli, Galit
2007-09-30
For robust detection performance, traditional control chart monitoring for biosurveillance is based on input data free of trends, day-of-week effects, and other systematic behaviour. Time series forecasting methods may be used to remove this behaviour by subtracting forecasts from observations to form residuals for algorithmic input. We describe three forecast methods and compare their predictive accuracy on each of 16 authentic syndromic data streams. The methods are (1) a non-adaptive regression model using a long historical baseline, (2) an adaptive regression model with a shorter, sliding baseline, and (3) the Holt-Winters method for generalized exponential smoothing. Criteria for comparing the forecasts were the root-mean-square error, the median absolute per cent error (MedAPE), and the median absolute deviation. The median-based criteria showed best overall performance for the Holt-Winters method. The MedAPE measures over the 16 test series averaged 16.5, 11.6, and 9.7 for the non-adaptive regression, adaptive regression, and Holt-Winters methods, respectively. The non-adaptive regression forecasts were degraded by changes in the data behaviour in the fixed baseline period used to compute model coefficients. The mean-based criterion was less conclusive because of the effects of poor forecasts on a small number of calendar holidays. The Holt-Winters method was also most effective at removing serial autocorrelation, with most 1-day-lag autocorrelation coefficients below 0.15. The forecast methods were compared without tuning them to the behaviour of individual series. We achieved improved predictions with such tuning of the Holt-Winters method, but practical use of such improvements for routine surveillance will require reliable data classification methods.
Palmprint Verification Using Time Series Method
Directory of Open Access Journals (Sweden)
A. A. Ketut Agung Cahyawan Wiranatha
2013-11-01
Full Text Available The use of biometrics as an automatic recognition system is growing rapidly in solving security problems, palmprint is one of biometric system which often used. This paper used two steps in center of mass moment method for region of interest (ROI segmentation and apply the time series method combined with block window method as feature representation. Normalized Euclidean Distance is used to measure the similarity degrees of two feature vectors of palmprint. System testing is done using 500 samples palms, with 4 samples as the reference image and the 6 samples as test images. Experiment results show that this system can achieve a high performance with success rate about 97.33% (FNMR=1.67%, FMR=1.00 %, T=0.036.
Deconvolution of time series in the laboratory
John, Thomas; Pietschmann, Dirk; Becker, Volker; Wagner, Christian
2016-10-01
In this study, we present two practical applications of the deconvolution of time series in Fourier space. First, we reconstruct a filtered input signal of sound cards that has been heavily distorted by a built-in high-pass filter using a software approach. Using deconvolution, we can partially bypass the filter and extend the dynamic frequency range by two orders of magnitude. Second, we construct required input signals for a mechanical shaker in order to obtain arbitrary acceleration waveforms, referred to as feedforward control. For both situations, experimental and theoretical approaches are discussed to determine the system-dependent frequency response. Moreover, for the shaker, we propose a simple feedback loop as an extension to the feedforward control in order to handle nonlinearities of the system.
Using entropy to cut complex time series
Mertens, David; Poncela Casasnovas, Julia; Spring, Bonnie; Amaral, L. A. N.
2013-03-01
Using techniques from statistical physics, physicists have modeled and analyzed human phenomena varying from academic citation rates to disease spreading to vehicular traffic jams. The last decade's explosion of digital information and the growing ubiquity of smartphones has led to a wealth of human self-reported data. This wealth of data comes at a cost, including non-uniform sampling and statistically significant but physically insignificant correlations. In this talk I present our work using entropy to identify stationary sub-sequences of self-reported human weight from a weight management web site. Our entropic approach-inspired by the infomap network community detection algorithm-is far less biased by rare fluctuations than more traditional time series segmentation techniques. Supported by the Howard Hughes Medical Institute
Normalizing the causality between time series
Liang, X. San
2015-08-01
Recently, a rigorous yet concise formula was derived to evaluate information flow, and hence the causality in a quantitative sense, between time series. To assess the importance of a resulting causality, it needs to be normalized. The normalization is achieved through distinguishing a Lyapunov exponent-like, one-dimensional phase-space stretching rate and a noise-to-signal ratio from the rate of information flow in the balance of the marginal entropy evolution of the flow recipient. It is verified with autoregressive models and applied to a real financial analysis problem. An unusually strong one-way causality is identified from IBM (International Business Machines Corporation) to GE (General Electric Company) in their early era, revealing to us an old story, which has almost faded into oblivion, about "Seven Dwarfs" competing with a giant for the mainframe computer market.
Phase correlation of foreign exchange time series
Wu, Ming-Chya
2007-03-01
Correlation of foreign exchange rates in currency markets is investigated based on the empirical data of USD/DEM and USD/JPY exchange rates for a period from February 1 1986 to December 31 1996. The return of exchange time series is first decomposed into a number of intrinsic mode functions (IMFs) by the empirical mode decomposition method. The instantaneous phases of the resultant IMFs calculated by the Hilbert transform are then used to characterize the behaviors of pricing transmissions, and the correlation is probed by measuring the phase differences between two IMFs in the same order. From the distribution of phase differences, our results show explicitly that the correlations are stronger in daily time scale than in longer time scales. The demonstration for the correlations in periods of 1986-1989 and 1990-1993 indicates two exchange rates in the former period were more correlated than in the latter period. The result is consistent with the observations from the cross-correlation calculation.
Costationarity of Locally Stationary Time Series Using costat
Cardinali, Alessandro; Nason, Guy P.
2013-01-01
This article describes the R package costat. This package enables a user to (i) perform a test for time series stationarity; (ii) compute and plot time-localized autocovariances, and (iii) to determine and explore any costationary relationship between two locally stationary time series. Two locally stationary time series are said to be costationary if there exists two time-varying combination functions such that the linear combination of the two series with the functions produces another time...
Fisher information framework for time series modeling
Venkatesan, R. C.; Plastino, A.
2017-08-01
A robust prediction model invoking the Takens embedding theorem, whose working hypothesis is obtained via an inference procedure based on the minimum Fisher information principle, is presented. The coefficients of the ansatz, central to the working hypothesis satisfy a time independent Schrödinger-like equation in a vector setting. The inference of (i) the probability density function of the coefficients of the working hypothesis and (ii) the establishing of constraint driven pseudo-inverse condition for the modeling phase of the prediction scheme, is made, for the case of normal distributions, with the aid of the quantum mechanical virial theorem. The well-known reciprocity relations and the associated Legendre transform structure for the Fisher information measure (FIM, hereafter)-based model in a vector setting (with least square constraints) are self-consistently derived. These relations are demonstrated to yield an intriguing form of the FIM for the modeling phase, which defines the working hypothesis, solely in terms of the observed data. Cases for prediction employing time series' obtained from the: (i) the Mackey-Glass delay-differential equation, (ii) one ECG signal from the MIT-Beth Israel Deaconess Hospital (MIT-BIH) cardiac arrhythmia database, and (iii) one ECG signal from the Creighton University ventricular tachyarrhythmia database. The ECG samples were obtained from the Physionet online repository. These examples demonstrate the efficiency of the prediction model. Numerical examples for exemplary cases are provided.
Time series modeling for syndromic surveillance
Directory of Open Access Journals (Sweden)
Mandl Kenneth D
2003-01-01
Full Text Available Abstract Background Emergency department (ED based syndromic surveillance systems identify abnormally high visit rates that may be an early signal of a bioterrorist attack. For example, an anthrax outbreak might first be detectable as an unusual increase in the number of patients reporting to the ED with respiratory symptoms. Reliably identifying these abnormal visit patterns requires a good understanding of the normal patterns of healthcare usage. Unfortunately, systematic methods for determining the expected number of (ED visits on a particular day have not yet been well established. We present here a generalized methodology for developing models of expected ED visit rates. Methods Using time-series methods, we developed robust models of ED utilization for the purpose of defining expected visit rates. The models were based on nearly a decade of historical data at a major metropolitan academic, tertiary care pediatric emergency department. The historical data were fit using trimmed-mean seasonal models, and additional models were fit with autoregressive integrated moving average (ARIMA residuals to account for recent trends in the data. The detection capabilities of the model were tested with simulated outbreaks. Results Models were built both for overall visits and for respiratory-related visits, classified according to the chief complaint recorded at the beginning of each visit. The mean absolute percentage error of the ARIMA models was 9.37% for overall visits and 27.54% for respiratory visits. A simple detection system based on the ARIMA model of overall visits was able to detect 7-day-long simulated outbreaks of 30 visits per day with 100% sensitivity and 97% specificity. Sensitivity decreased with outbreak size, dropping to 94% for outbreaks of 20 visits per day, and 57% for 10 visits per day, all while maintaining a 97% benchmark specificity. Conclusions Time series methods applied to historical ED utilization data are an important tool
Monthly electric energy demand forecasting with neural networks and Fourier series
International Nuclear Information System (INIS)
Gonzalez-Romera, E.; Jaramillo-Moran, M.A.; Carmona-Fernandez, D.
2008-01-01
Medium-term electric energy demand forecasting is a useful tool for grid maintenance planning and market research of electric energy companies. Several methods, such as ARIMA, regression or artificial intelligence, have been usually used to carry out those predictions. Some approaches include weather or economic variables, which strongly influence electric energy demand. Economic variables usually influence the general series trend, while weather provides a periodic behavior because of its seasonal nature. This work investigates the periodic behavior of the Spanish monthly electric demand series, obtained by rejecting the trend from the consumption series. A novel hybrid approach is proposed: the periodic behavior is forecasted with a Fourier series while the trend is predicted with a neural network. Satisfactory results have been obtained, with a lower than 2% MAPE, which improve those reached when only neural networks or ARIMA were used for the same purpose. (author)
Psychological and neural mechanisms of subjective time dilation
Directory of Open Access Journals (Sweden)
Virginie evan Wassenhove
2011-04-01
Full Text Available For a given physical duration, certain events can be experienced as subjectively longer in duration than others. Try this for yourself: take a quick glance at the second hand of a clock. Immediately, the tick will pause momentarily and appear to be longer than the subsequent ticks. Yet, they all last exactly one second. By and large, a deviant or an unexpected stimulus in a series of similar events (same duration, same features can elicit a relative overestimation of subjective time (or "time dilation" but, as is shown here, this is not always the case. We conducted an event-related functional magnetic neuroimaging (fMRI study on the time dilation effect. Participants were presented with a series of five visual discs, all static and of equal duration (standards except for the fourth one, a looming or a receding target. The duration of the target was systematically varied and participants judged whether it was shorter or longer than all other standards in the sequence. Subjective time dilation was observed for the looming stimulus but not for the receding one, which was estimated to be of equal duration to the standards. The neural activation for targets (looming and receding contrasted with the standards revealed an increased activation of the anterior insula and of the anterior cingulate cortex. Contrasting the looming with the receding targets (i.e. capturing the time dilation effect proper revealed a specific activation of cortical midline structures. The implication of midline structures in the time dilation illusion is here interpreted in the context of self-referential processes.
Climate Prediction Center (CPC) Global Temperature Time Series
National Oceanic and Atmospheric Administration, Department of Commerce — The global temperature time series provides time series charts using station based observations of daily temperature. These charts provide information about the...
Climate Prediction Center (CPC) Global Precipitation Time Series
National Oceanic and Atmospheric Administration, Department of Commerce — The global precipitation time series provides time series charts showing observations of daily precipitation as well as accumulated precipitation compared to normal...
Time response of temperature sensors using neural networks
International Nuclear Information System (INIS)
Santos, Roberto Carlos dos
2010-01-01
In a PWR nuclear power plant, the primary coolant temperature and feedwater temperature are measured using RTDs (Resistance Temperature Detectors). These RTDs typically feed the plant's control and safety systems and must, therefore, be very accurate and have good dynamic performance. The response time of RTDs is characterized by a single parameter called the Plunge Time Constant defined as the time it takes the sensor output to achieve 63.2 percent of its final value after a step change in temperature. Nuclear reactor service conditions are difficult to reproduce in the laboratory, and an in-situ test method called LCSR (Loop Current Step Response) test was developed to measure remotely the response time of RTDs. >From this test, the time constant of the sensor is identified by means of the LCSR transformation that involves the dynamic response modal time constants determination using a nodal heat-transfer model. This calculation is not simple and requires specialized personnel. For this reason an Artificial Neural Network has been developed to predict the time constant of RTD from LCSR test transient. It eliminates the transformations involved in the LCSR application. A series of LCSR tests on RTDs generates the response transients of the sensors, the input data of the networks. Plunge tests are used to determine the time constants of the RTDs, the desired output of the ANN, trained using these sets of input/output data. This methodology was firstly applied to theoretical data simulating 10 RTDs with different time constant values, resulting in an average error of about 0.74 %. Experimental data from three different RTDs was used to predict time constant resulting in a maximum error of 3,34 %. The time constants values predicted from ANN were compared with those obtained from traditional way resulting in an average error of about 18 % and that shows the network is able to predict accurately the sensor time constant. (author)
Foundations of Sequence-to-Sequence Modeling for Time Series
Kuznetsov, Vitaly; Mariet, Zelda
2018-01-01
The availability of large amounts of time series data, paired with the performance of deep-learning algorithms on a broad class of problems, has recently led to significant interest in the use of sequence-to-sequence models for time series forecasting. We provide the first theoretical analysis of this time series forecasting framework. We include a comparison of sequence-to-sequence modeling to classical time series models, and as such our theory can serve as a quantitative guide for practiti...
Gao, Xiangyun; An, Haizhong; Fang, Wei; Huang, Xuan; Li, Huajiao; Zhong, Weiqiong; Ding, Yinghui
2014-07-01
The linear regression parameters between two time series can be different under different lengths of observation period. If we study the whole period by the sliding window of a short period, the change of the linear regression parameters is a process of dynamic transmission over time. We tackle fundamental research that presents a simple and efficient computational scheme: a linear regression patterns transmission algorithm, which transforms linear regression patterns into directed and weighted networks. The linear regression patterns (nodes) are defined by the combination of intervals of the linear regression parameters and the results of the significance testing under different sizes of the sliding window. The transmissions between adjacent patterns are defined as edges, and the weights of the edges are the frequency of the transmissions. The major patterns, the distance, and the medium in the process of the transmission can be captured. The statistical results of weighted out-degree and betweenness centrality are mapped on timelines, which shows the features of the distribution of the results. Many measurements in different areas that involve two related time series variables could take advantage of this algorithm to characterize the dynamic relationships between the time series from a new perspective.
Time Series Observations in the North Indian Ocean
Digital Repository Service at National Institute of Oceanography (India)
Shenoy, D.M.; Naik, H.; Kurian, S.; Naqvi, S.W.A.; Khare, N.
Ocean and the ongoing time series study (Candolim Time Series; CaTS) off Goa. In addition, this article also focuses on the new time series initiative in the Arabian Sea and the Bay of Bengal under Sustained Indian Ocean Biogeochemistry and Ecosystem...
Modeling of Volatility with Non-linear Time Series Model
Kim Song Yon; Kim Mun Chol
2013-01-01
In this paper, non-linear time series models are used to describe volatility in financial time series data. To describe volatility, two of the non-linear time series are combined into form TAR (Threshold Auto-Regressive Model) with AARCH (Asymmetric Auto-Regressive Conditional Heteroskedasticity) error term and its parameter estimation is studied.
Neural network modeling of nonlinear systems based on Volterra series extension of a linear model
Soloway, Donald I.; Bialasiewicz, Jan T.
1992-01-01
A Volterra series approach was applied to the identification of nonlinear systems which are described by a neural network model. A procedure is outlined by which a mathematical model can be developed from experimental data obtained from the network structure. Applications of the results to the control of robotic systems are discussed.
Discrete-time BAM neural networks with variable delays
Liu, Xin-Ge; Tang, Mei-Lan; Martin, Ralph; Liu, Xin-Bi
2007-07-01
This Letter deals with the global exponential stability of discrete-time bidirectional associative memory (BAM) neural networks with variable delays. Using a Lyapunov functional, and linear matrix inequality techniques (LMI), we derive a new delay-dependent exponential stability criterion for BAM neural networks with variable delays. As this criterion has no extra constraints on the variable delay functions, it can be applied to quite general BAM neural networks with a broad range of time delay functions. It is also easy to use in practice. An example is provided to illustrate the theoretical development.
Discrete-time BAM neural networks with variable delays
International Nuclear Information System (INIS)
Liu Xinge; Tang Meilan; Martin, Ralph; Liu Xinbi
2007-01-01
This Letter deals with the global exponential stability of discrete-time bidirectional associative memory (BAM) neural networks with variable delays. Using a Lyapunov functional, and linear matrix inequality techniques (LMI), we derive a new delay-dependent exponential stability criterion for BAM neural networks with variable delays. As this criterion has no extra constraints on the variable delay functions, it can be applied to quite general BAM neural networks with a broad range of time delay functions. It is also easy to use in practice. An example is provided to illustrate the theoretical development
Hidden Markov Models for Time Series An Introduction Using R
Zucchini, Walter
2009-01-01
Illustrates the flexibility of HMMs as general-purpose models for time series data. This work presents an overview of HMMs for analyzing time series data, from continuous-valued, circular, and multivariate series to binary data, bounded and unbounded counts and categorical observations.
Volatility Analysis of Bitcoin Price Time Series
Directory of Open Access Journals (Sweden)
Lukáš Pichl
2017-12-01
Full Text Available Bitcoin has the largest share in the total capitalization of cryptocurrency markets currently reaching above 70 billion USD. In this work we focus on the price of Bitcoin in terms of standard currencies and their volatility over the last five years. The average day-to-day return throughout this period is 0.328%, amounting in exponential growth from 6 USD to over 4,000 USD per 1 BTC at present. Multi-scale analysis is performed from the level of the tick data, through the 5 min, 1 hour and 1 day scales. Distribution of trading volumes (1 sec, 1 min, 1 hour and 1 day aggregated from the Kraken BTCEUR tick data is provided that shows the artifacts of algorithmic trading (selling transactions with volume peaks distributed at integer multiples of BTC unit. Arbitrage opportunities are studied using the EUR, USD and CNY currencies. Whereas the arbitrage spread for EUR-USD currency pair is found narrow at the order of a percent, at the 1 hour sampling period the arbitrage spread for USD-CNY (and similarly EUR-CNY is found to be more substantial, reaching as high as above 5 percent on rare occasions. The volatility of BTC exchange rates is modeled using the day-to-day distribution of logarithmic return, and the Realized Volatility, sum of the squared logarithmic returns on 5-minute basis. In this work we demonstrate that the Heterogeneous Autoregressive model for Realized Volatility Andersen et al. (2007 applies reasonably well to the BTCUSD dataset. Finally, a feed-forward neural network with 2 hidden layers using 10-day moving window sampling daily return predictors is applied to estimate the next-day logarithmic return. The results show that such an artificial neural network prediction is capable of approximate capture of the actual log return distribution; more sophisticated methods, such as recurrent neural networks and LSTM (Long Short Term Memory techniques from deep learning may be necessary for higher prediction accuracy.
Forecasting air quality time series using deep learning.
Freeman, Brian S; Taylor, Graham; Gharabaghi, Bahram; Thé, Jesse
2018-04-13
This paper presents one of the first applications of deep learning (DL) techniques to predict air pollution time series. Air quality management relies extensively on time series data captured at air monitoring stations as the basis of identifying population exposure to airborne pollutants and determining compliance with local ambient air standards. In this paper, 8 hr averaged surface ozone (O 3 ) concentrations were predicted using deep learning consisting of a recurrent neural network (RNN) with long short-term memory (LSTM). Hourly air quality and meteorological data were used to train and forecast values up to 72 hours with low error rates. The LSTM was able to forecast the duration of continuous O 3 exceedances as well. Prior to training the network, the dataset was reviewed for missing data and outliers. Missing data were imputed using a novel technique that averaged gaps less than eight time steps with incremental steps based on first-order differences of neighboring time periods. Data were then used to train decision trees to evaluate input feature importance over different time prediction horizons. The number of features used to train the LSTM model was reduced from 25 features to 5 features, resulting in improved accuracy as measured by Mean Absolute Error (MAE). Parameter sensitivity analysis identified look-back nodes associated with the RNN proved to be a significant source of error if not aligned with the prediction horizon. Overall, MAE's less than 2 were calculated for predictions out to 72 hours. Novel deep learning techniques were used to train an 8-hour averaged ozone forecast model. Missing data and outliers within the captured data set were replaced using a new imputation method that generated calculated values closer to the expected value based on the time and season. Decision trees were used to identify input variables with the greatest importance. The methods presented in this paper allow air managers to forecast long range air pollution
ECO INVESTMENT PROJECT MANAGEMENT THROUGH TIME APPLYING ARTIFICIAL NEURAL NETWORKS
Directory of Open Access Journals (Sweden)
Tamara Gvozdenović
2007-06-01
Full Text Available he concept of project management expresses an indispensable approach to investment projects. Time is often the most important factor in these projects. The artificial neural network is the paradigm of data processing, which is inspired by the one used by the biological brain, and it is used in numerous, different fields, among which is the project management. This research is oriented to application of artificial neural networks in managing time of investment project. The artificial neural networks are used to define the optimistic, the most probable and the pessimistic time in PERT method. The program package Matlab: Neural Network Toolbox is used in data simulation. The feed-forward back propagation network is chosen.
Efficient Algorithms for Segmentation of Item-Set Time Series
Chundi, Parvathi; Rosenkrantz, Daniel J.
We propose a special type of time series, which we call an item-set time series, to facilitate the temporal analysis of software version histories, email logs, stock market data, etc. In an item-set time series, each observed data value is a set of discrete items. We formalize the concept of an item-set time series and present efficient algorithms for segmenting a given item-set time series. Segmentation of a time series partitions the time series into a sequence of segments where each segment is constructed by combining consecutive time points of the time series. Each segment is associated with an item set that is computed from the item sets of the time points in that segment, using a function which we call a measure function. We then define a concept called the segment difference, which measures the difference between the item set of a segment and the item sets of the time points in that segment. The segment difference values are required to construct an optimal segmentation of the time series. We describe novel and efficient algorithms to compute segment difference values for each of the measure functions described in the paper. We outline a dynamic programming based scheme to construct an optimal segmentation of the given item-set time series. We use the item-set time series segmentation techniques to analyze the temporal content of three different data sets—Enron email, stock market data, and a synthetic data set. The experimental results show that an optimal segmentation of item-set time series data captures much more temporal content than a segmentation constructed based on the number of time points in each segment, without examining the item set data at the time points, and can be used to analyze different types of temporal data.
FPGA-Based Stochastic Echo State Networks for Time-Series Forecasting.
Alomar, Miquel L; Canals, Vincent; Perez-Mora, Nicolas; Martínez-Moll, Víctor; Rosselló, Josep L
2016-01-01
Hardware implementation of artificial neural networks (ANNs) allows exploiting the inherent parallelism of these systems. Nevertheless, they require a large amount of resources in terms of area and power dissipation. Recently, Reservoir Computing (RC) has arisen as a strategic technique to design recurrent neural networks (RNNs) with simple learning capabilities. In this work, we show a new approach to implement RC systems with digital gates. The proposed method is based on the use of probabilistic computing concepts to reduce the hardware required to implement different arithmetic operations. The result is the development of a highly functional system with low hardware resources. The presented methodology is applied to chaotic time-series forecasting.
TIME SERIES ANALYSIS USING A UNIQUE MODEL OF TRANSFORMATION
Directory of Open Access Journals (Sweden)
Goran Klepac
2007-12-01
Full Text Available REFII1 model is an authorial mathematical model for time series data mining. The main purpose of that model is to automate time series analysis, through a unique transformation model of time series. An advantage of this approach of time series analysis is the linkage of different methods for time series analysis, linking traditional data mining tools in time series, and constructing new algorithms for analyzing time series. It is worth mentioning that REFII model is not a closed system, which means that we have a finite set of methods. At first, this is a model for transformation of values of time series, which prepares data used by different sets of methods based on the same model of transformation in a domain of problem space. REFII model gives a new approach in time series analysis based on a unique model of transformation, which is a base for all kind of time series analysis. The advantage of REFII model is its possible application in many different areas such as finance, medicine, voice recognition, face recognition and text mining.
An Energy-Based Similarity Measure for Time Series
Directory of Open Access Journals (Sweden)
Pierre Brunagel
2007-11-01
Full Text Available A new similarity measure, called SimilB, for time series analysis, based on the cross-ÃŽÂ¨B-energy operator (2004, is introduced. ÃŽÂ¨B is a nonlinear measure which quantifies the interaction between two time series. Compared to Euclidean distance (ED or the Pearson correlation coefficient (CC, SimilB includes the temporal information and relative changes of the time series using the first and second derivatives of the time series. SimilB is well suited for both nonstationary and stationary time series and particularly those presenting discontinuities. Some new properties of ÃŽÂ¨B are presented. Particularly, we show that ÃŽÂ¨B as similarity measure is robust to both scale and time shift. SimilB is illustrated with synthetic time series and an artificial dataset and compared to the CC and the ED measures.
Time-series prediction and applications a machine intelligence approach
Konar, Amit
2017-01-01
This book presents machine learning and type-2 fuzzy sets for the prediction of time-series with a particular focus on business forecasting applications. It also proposes new uncertainty management techniques in an economic time-series using type-2 fuzzy sets for prediction of the time-series at a given time point from its preceding value in fluctuating business environments. It employs machine learning to determine repetitively occurring similar structural patterns in the time-series and uses stochastic automaton to predict the most probabilistic structure at a given partition of the time-series. Such predictions help in determining probabilistic moves in a stock index time-series Primarily written for graduate students and researchers in computer science, the book is equally useful for researchers/professionals in business intelligence and stock index prediction. A background of undergraduate level mathematics is presumed, although not mandatory, for most of the sections. Exercises with tips are provided at...
Vector bilinear autoregressive time series model and its superiority ...
African Journals Online (AJOL)
In this research, a vector bilinear autoregressive time series model was proposed and used to model three revenue series (X1, X2, X3) . The “orders” of the three series were identified on the basis of the distribution of autocorrelation and partial autocorrelation functions and were used to construct the vector bilinear models.
A novel weight determination method for time series data aggregation
Xu, Paiheng; Zhang, Rong; Deng, Yong
2017-09-01
Aggregation in time series is of great importance in time series smoothing, predicting and other time series analysis process, which makes it crucial to address the weights in times series correctly and reasonably. In this paper, a novel method to obtain the weights in time series is proposed, in which we adopt induced ordered weighted aggregation (IOWA) operator and visibility graph averaging (VGA) operator and linearly combine the weights separately generated by the two operator. The IOWA operator is introduced to the weight determination of time series, through which the time decay factor is taken into consideration. The VGA operator is able to generate weights with respect to the degree distribution in the visibility graph constructed from the corresponding time series, which reflects the relative importance of vertices in time series. The proposed method is applied to two practical datasets to illustrate its merits. The aggregation of Construction Cost Index (CCI) demonstrates the ability of proposed method to smooth time series, while the aggregation of The Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) illustrate how proposed method maintain the variation tendency of original data.
Capturing Structure Implicitly from Time-Series having Limited Data
Emaasit, Daniel; Johnson, Matthew
2018-01-01
Scientific fields such as insider-threat detection and highway-safety planning often lack sufficient amounts of time-series data to estimate statistical models for the purpose of scientific discovery. Moreover, the available limited data are quite noisy. This presents a major challenge when estimating time-series models that are robust to overfitting and have well-calibrated uncertainty estimates. Most of the current literature in these fields involve visualizing the time-series for noticeabl...
Mathematical foundations of time series analysis a concise introduction
Beran, Jan
2017-01-01
This book provides a concise introduction to the mathematical foundations of time series analysis, with an emphasis on mathematical clarity. The text is reduced to the essential logical core, mostly using the symbolic language of mathematics, thus enabling readers to very quickly grasp the essential reasoning behind time series analysis. It appeals to anybody wanting to understand time series in a precise, mathematical manner. It is suitable for graduate courses in time series analysis but is equally useful as a reference work for students and researchers alike.
Time series analysis in the social sciences the fundamentals
Shin, Youseop
2017-01-01
Times Series Analysis in the Social Sciences is a practical and highly readable introduction written exclusively for students and researchers whose mathematical background is limited to basic algebra. The book focuses on fundamental elements of time series analysis that social scientists need to understand so they can employ time series analysis for their research and practice. Through step-by-step explanations and using monthly violent crime rates as case studies, this book explains univariate time series from the preliminary visual analysis through the modeling of seasonality, trends, and re
Stochastic time series analysis of hydrology data for water resources
Sathish, S.; Khadar Babu, S. K.
2017-11-01
The prediction to current publication of stochastic time series analysis in hydrology and seasonal stage. The different statistical tests for predicting the hydrology time series on Thomas-Fiering model. The hydrology time series of flood flow have accept a great deal of consideration worldwide. The concentration of stochastic process areas of time series analysis method are expanding with develop concerns about seasonal periods and global warming. The recent trend by the researchers for testing seasonal periods in the hydrologic flowseries using stochastic process on Thomas-Fiering model. The present article proposed to predict the seasonal periods in hydrology using Thomas-Fiering model.
Generation of hourly irradiation synthetic series using the neural network multilayer perceptron
Energy Technology Data Exchange (ETDEWEB)
Hontoria, L.; Aguilera, J. [Universidad de Jaen, Linares-Jaen (Spain). Dpto. de Electronica; Zufiria, P. [Ciudad Universitaria, Madrid (Spain). Grupo de Redes Neuronales
2002-05-01
In this work, a methodology based on the neural network model called multilayer perceptron (MLP) to solve a typical problem in solar energy is presented. This methodology consists of the generation of synthetic series of hourly solar irradiation. The model presented is based on the capacity of the MLP for finding relations between variables for which interrelation is unknown explicitly. The information available can be included progressively at the series generator at different stages. A comparative study with other solar irradiation synthetic generation methods has been done in order to demonstrate the validity of the one proposed. (author)
Interpretable Early Classification of Multivariate Time Series
Ghalwash, Mohamed F.
2013-01-01
Recent advances in technology have led to an explosion in data collection over time rather than in a single snapshot. For example, microarray technology allows us to measure gene expression levels in different conditions over time. Such temporal data grants the opportunity for data miners to develop algorithms to address domain-related problems,…
Global dissipativity of continuous-time recurrent neural networks with time delay
International Nuclear Information System (INIS)
Liao Xiaoxin; Wang Jun
2003-01-01
This paper addresses the global dissipativity of a general class of continuous-time recurrent neural networks. First, the concepts of global dissipation and global exponential dissipation are defined and elaborated. Next, the sets of global dissipativity and global exponentially dissipativity are characterized using the parameters of recurrent neural network models. In particular, it is shown that the Hopfield network and cellular neural networks with or without time delays are dissipative systems
Studies on time series applications in environmental sciences
Bărbulescu, Alina
2016-01-01
Time series analysis and modelling represent a large study field, implying the approach from the perspective of the time and frequency, with applications in different domains. Modelling hydro-meteorological time series is difficult due to the characteristics of these series, as long range dependence, spatial dependence, the correlation with other series. Continuous spatial data plays an important role in planning, risk assessment and decision making in environmental management. In this context, in this book we present various statistical tests and modelling techniques used for time series analysis, as well as applications to hydro-meteorological series from Dobrogea, a region situated in the south-eastern part of Romania, less studied till now. Part of the results are accompanied by their R code. .
DTW-APPROACH FOR UNCORRELATED MULTIVARIATE TIME SERIES IMPUTATION
Phan , Thi-Thu-Hong; Poisson Caillault , Emilie; Bigand , André; Lefebvre , Alain
2017-01-01
International audience; Missing data are inevitable in almost domains of applied sciences. Data analysis with missing values can lead to a loss of efficiency and unreliable results, especially for large missing sub-sequence(s). Some well-known methods for multivariate time series imputation require high correlations between series or their features. In this paper , we propose an approach based on the shape-behaviour relation in low/un-correlated multivariate time series under an assumption of...
Cycles of a discrete time bipolar artificial neural network
International Nuclear Information System (INIS)
Cheng Suisun; Chen, J.-S.; Yueh, W.-C.
2009-01-01
A discrete time bipolar neural network depending on two parameters is studied. It is observed that its dynamical behaviors can be classified into six cases. For each case, the long time behaviors can be summarized in terms of fixed points, periodic points, basin of attractions, and related initial distributions. Mathematical reasons are supplied for these observations and applications in cellular automata are illustrated.
A model of interval timing by neural integration.
Simen, Patrick; Balci, Fuat; de Souza, Laura; Cohen, Jonathan D; Holmes, Philip
2011-06-22
We show that simple assumptions about neural processing lead to a model of interval timing as a temporal integration process, in which a noisy firing-rate representation of time rises linearly on average toward a response threshold over the course of an interval. Our assumptions include: that neural spike trains are approximately independent Poisson processes, that correlations among them can be largely cancelled by balancing excitation and inhibition, that neural populations can act as integrators, and that the objective of timed behavior is maximal accuracy and minimal variance. The model accounts for a variety of physiological and behavioral findings in rodents, monkeys, and humans, including ramping firing rates between the onset of reward-predicting cues and the receipt of delayed rewards, and universally scale-invariant response time distributions in interval timing tasks. It furthermore makes specific, well-supported predictions about the skewness of these distributions, a feature of timing data that is usually ignored. The model also incorporates a rapid (potentially one-shot) duration-learning procedure. Human behavioral data support the learning rule's predictions regarding learning speed in sequences of timed responses. These results suggest that simple, integration-based models should play as prominent a role in interval timing theory as they do in theories of perceptual decision making, and that a common neural mechanism may underlie both types of behavior.
Self-organising mixture autoregressive model for non-stationary time series modelling.
Ni, He; Yin, Hujun
2008-12-01
Modelling non-stationary time series has been a difficult task for both parametric and nonparametric methods. One promising solution is to combine the flexibility of nonparametric models with the simplicity of parametric models. In this paper, the self-organising mixture autoregressive (SOMAR) network is adopted as a such mixture model. It breaks time series into underlying segments and at the same time fits local linear regressive models to the clusters of segments. In such a way, a global non-stationary time series is represented by a dynamic set of local linear regressive models. Neural gas is used for a more flexible structure of the mixture model. Furthermore, a new similarity measure has been introduced in the self-organising network to better quantify the similarity of time series segments. The network can be used naturally in modelling and forecasting non-stationary time series. Experiments on artificial, benchmark time series (e.g. Mackey-Glass) and real-world data (e.g. numbers of sunspots and Forex rates) are presented and the results show that the proposed SOMAR network is effective and superior to other similar approaches.
Long Range Dependence Prognostics for Bearing Vibration Intensity Chaotic Time Series
Directory of Open Access Journals (Sweden)
Qing Li
2016-01-01
Full Text Available According to the chaotic features and typical fractional order characteristics of the bearing vibration intensity time series, a forecasting approach based on long range dependence (LRD is proposed. In order to reveal the internal chaotic properties, vibration intensity time series are reconstructed based on chaos theory in phase-space, the delay time is computed with C-C method and the optimal embedding dimension and saturated correlation dimension are calculated via the Grassberger–Procaccia (G-P method, respectively, so that the chaotic characteristics of vibration intensity time series can be jointly determined by the largest Lyapunov exponent and phase plane trajectory of vibration intensity time series, meanwhile, the largest Lyapunov exponent is calculated by the Wolf method and phase plane trajectory is illustrated using Duffing-Holmes Oscillator (DHO. The Hurst exponent and long range dependence prediction method are proposed to verify the typical fractional order features and improve the prediction accuracy of bearing vibration intensity time series, respectively. Experience shows that the vibration intensity time series have chaotic properties and the LRD prediction method is better than the other prediction methods (largest Lyapunov, auto regressive moving average (ARMA and BP neural network (BPNN model in prediction accuracy and prediction performance, which provides a new approach for running tendency predictions for rotating machinery and provide some guidance value to the engineering practice.
Some new results for recurrent neural networks with varying-time coefficients and delays
International Nuclear Information System (INIS)
Jiang Haijun; Teng Zhidong
2005-01-01
In this Letter, we consider the recurrent neural networks with varying-time coefficients and delays. By constructing new Lyapunov functional, introducing ingeniously many real parameters and applying the technique of Young inequality, we establish a series of criteria on the boundedness, global exponential stability and the existence of periodic solutions. In these criteria, we do not require that the response functions are differentiable, bounded and monotone nondecreasing. Some previous works are improved and extended
Chattopadhyay, Surajit; Chattopadhyay, Goutami
The present paper reports studies on the association between the mean annual sunspot numbers and the summer monsoon rainfall over India. The cross correlations have been studied. After Box-Cox transformation, the time spectral analysis has been executed and it has been found that both of the time series have an important spectrum at the fifth harmonic. An artificial neural network (ANN) model has been developed on the data series averaged continuously by five years and the neural network could establish a predictor-predict and relationship between the sunspot numbers and the mean yearly summer monsoon rainfall over India.
Two-fractal overlap time series: Earthquakes and market crashes
Indian Academy of Sciences (India)
velocity over the other and time series of stock prices. An anticipation method for some of the crashes have been proposed here, based on these observations. Keywords. Cantor set; time series; earthquake; market crash. PACS Nos 05.00; 02.50.-r; 64.60; 89.65.Gh; 95.75.Wx. 1. Introduction. Capturing dynamical patterns of ...
Metagenomics meets time series analysis: unraveling microbial community dynamics
Faust, K.; Lahti, L.M.; Gonze, D.; Vos, de W.M.; Raes, J.
2015-01-01
The recent increase in the number of microbial time series studies offers new insights into the stability and dynamics of microbial communities, from the world's oceans to human microbiota. Dedicated time series analysis tools allow taking full advantage of these data. Such tools can reveal periodic
forecasting with nonlinear time series model: a monte-carlo
African Journals Online (AJOL)
PUBLICATIONS1
erated recursively up to any step greater than one. For nonlinear time series model, point forecast for step one can be done easily like in the linear case but forecast for a step greater than or equal to ..... London. Franses, P. H. (1998). Time series models for business and Economic forecasting, Cam- bridge University press.
Critical values for unit root tests in seasonal time series
Ph.H.B.F. Franses (Philip Hans); B. Hobijn (Bart)
1997-01-01
textabstractIn this paper, we present tables with critical values for a variety of tests for seasonal and non-seasonal unit roots in seasonal time series. We consider (extensions of) the Hylleberg et al. and Osborn et al. test procedures. These extensions concern time series with increasing seasonal
Measurements of spatial population synchrony: influence of time series transformations.
Chevalier, Mathieu; Laffaille, Pascal; Ferdy, Jean-Baptiste; Grenouillet, Gaël
2015-09-01
Two mechanisms have been proposed to explain spatial population synchrony: dispersal among populations, and the spatial correlation of density-independent factors (the "Moran effect"). To identify which of these two mechanisms is driving spatial population synchrony, time series transformations (TSTs) of abundance data have been used to remove the signature of one mechanism, and highlight the effect of the other. However, several issues with TSTs remain, and to date no consensus has emerged about how population time series should be handled in synchrony studies. Here, by using 3131 time series involving 34 fish species found in French rivers, we computed several metrics commonly used in synchrony studies to determine whether a large-scale climatic factor (temperature) influenced fish population dynamics at the regional scale, and to test the effect of three commonly used TSTs (detrending, prewhitening and a combination of both) on these metrics. We also tested whether the influence of TSTs on time series and population synchrony levels was related to the features of the time series using both empirical and simulated time series. For several species, and regardless of the TST used, we evidenced a Moran effect on freshwater fish populations. However, these results were globally biased downward by TSTs which reduced our ability to detect significant signals. Depending on the species and the features of the time series, we found that TSTs could lead to contradictory results, regardless of the metric considered. Finally, we suggest guidelines on how population time series should be processed in synchrony studies.
Transition Icons for Time-Series Visualization and Exploratory Analysis.
Nickerson, Paul V; Baharloo, Raheleh; Wanigatunga, Amal A; Manini, Todd M; Tighe, Patrick J; Rashidi, Parisa
2018-03-01
The modern healthcare landscape has seen the rapid emergence of techniques and devices that temporally monitor and record physiological signals. The prevalence of time-series data within the healthcare field necessitates the development of methods that can analyze the data in order to draw meaningful conclusions. Time-series behavior is notoriously difficult to intuitively understand due to its intrinsic high-dimensionality, which is compounded in the case of analyzing groups of time series collected from different patients. Our framework, which we call transition icons, renders common patterns in a visual format useful for understanding the shared behavior within groups of time series. Transition icons are adept at detecting and displaying subtle differences and similarities, e.g., between measurements taken from patients receiving different treatment strategies or stratified by demographics. We introduce various methods that collectively allow for exploratory analysis of groups of time series, while being free of distribution assumptions and including simple heuristics for parameter determination. Our technique extracts discrete transition patterns from symbolic aggregate approXimation representations, and compiles transition frequencies into a bag of patterns constructed for each group. These transition frequencies are normalized and aligned in icon form to intuitively display the underlying patterns. We demonstrate the transition icon technique for two time-series datasets-postoperative pain scores, and hip-worn accelerometer activity counts. We believe transition icons can be an important tool for researchers approaching time-series data, as they give rich and intuitive information about collective time-series behaviors.
Time Series Econometrics for the 21st Century
Hansen, Bruce E.
2017-01-01
The field of econometrics largely started with time series analysis because many early datasets were time-series macroeconomic data. As the field developed, more cross-sectional and longitudinal datasets were collected, which today dominate the majority of academic empirical research. In nonacademic (private sector, central bank, and governmental)…
The Prediction of Teacher Turnover Employing Time Series Analysis.
Costa, Crist H.
The purpose of this study was to combine knowledge of teacher demographic data with time-series forecasting methods to predict teacher turnover. Moving averages and exponential smoothing were used to forecast discrete time series. The study used data collected from the 22 largest school districts in Iowa, designated as FACT schools. Predictions…
Small Sample Properties of Bayesian Multivariate Autoregressive Time Series Models
Price, Larry R.
2012-01-01
The aim of this study was to compare the small sample (N = 1, 3, 5, 10, 15) performance of a Bayesian multivariate vector autoregressive (BVAR-SEM) time series model relative to frequentist power and parameter estimation bias. A multivariate autoregressive model was developed based on correlated autoregressive time series vectors of varying…
Parameterizing unconditional skewness in models for financial time series
DEFF Research Database (Denmark)
He, Changli; Silvennoinen, Annastiina; Teräsvirta, Timo
In this paper we consider the third-moment structure of a class of time series models. It is often argued that the marginal distribution of financial time series such as returns is skewed. Therefore it is of importance to know what properties a model should possess if it is to accommodate...
Robust Forecasting of Non-Stationary Time Series
Croux, C.; Fried, R.; Gijbels, I.; Mahieu, K.
2010-01-01
This paper proposes a robust forecasting method for non-stationary time series. The time series is modelled using non-parametric heteroscedastic regression, and fitted by a localized MM-estimator, combining high robustness and large efficiency. The proposed method is shown to produce reliable
Efficient use of correlation entropy for analysing time series data
Indian Academy of Sciences (India)
Abstract. The correlation dimension D2 and correlation entropy K2 are both important quantifiers in nonlinear time series analysis. However, use of D2 has been more common compared to K2 as a discriminating measure. One reason for this is that D2 is a static measure and can be easily evaluated from a time series.
Time series prediction of apple scab using meteorological ...
African Journals Online (AJOL)
A new prediction model for the early warning of apple scab is proposed in this study. The method is based on artificial intelligence and time series prediction. The infection period of apple scab was evaluated as the time series prediction model instead of summation of wetness duration. Also, the relations of different ...
A Dynamic Fuzzy Cluster Algorithm for Time Series
Directory of Open Access Journals (Sweden)
Min Ji
2013-01-01
clustering time series by introducing the definition of key point and improving FCM algorithm. The proposed algorithm works by determining those time series whose class labels are vague and further partitions them into different clusters over time. The main advantage of this approach compared with other existing algorithms is that the property of some time series belonging to different clusters over time can be partially revealed. Results from simulation-based experiments on geographical data demonstrate the excellent performance and the desired results have been obtained. The proposed algorithm can be applied to solve other clustering problems in data mining.
Variable Selection in Time Series Forecasting Using Random Forests
Directory of Open Access Journals (Sweden)
Hristos Tyralis
2017-10-01
Full Text Available Time series forecasting using machine learning algorithms has gained popularity recently. Random forest is a machine learning algorithm implemented in time series forecasting; however, most of its forecasting properties have remained unexplored. Here we focus on assessing the performance of random forests in one-step forecasting using two large datasets of short time series with the aim to suggest an optimal set of predictor variables. Furthermore, we compare its performance to benchmarking methods. The first dataset is composed by 16,000 simulated time series from a variety of Autoregressive Fractionally Integrated Moving Average (ARFIMA models. The second dataset consists of 135 mean annual temperature time series. The highest predictive performance of RF is observed when using a low number of recent lagged predictor variables. This outcome could be useful in relevant future applications, with the prospect to achieve higher predictive accuracy.
Frontiers in Time Series and Financial Econometrics : An overview
S. Ling (Shiqing); M.J. McAleer (Michael); H. Tong (Howell)
2015-01-01
markdownabstract__Abstract__ Two of the fastest growing frontiers in econometrics and quantitative finance are time series and financial econometrics. Significant theoretical contributions to financial econometrics have been made by experts in statistics, econometrics, mathematics, and time
Frontiers in Time Series and Financial Econometrics: An Overview
S. Ling (Shiqing); M.J. McAleer (Michael); H. Tong (Howell)
2015-01-01
markdownabstract__Abstract__ Two of the fastest growing frontiers in econometrics and quantitative finance are time series and financial econometrics. Significant theoretical contributions to financial econometrics have been made by experts in statistics, econometrics, mathematics, and time
vector bilinear autoregressive time series model and its superiority
African Journals Online (AJOL)
KEYWORDS: Linear time series, Autoregressive process, Autocorrelation function, Partial autocorrelation function,. Vector time .... important result on matrix algebra with respect to the spectral ..... application to covariance analysis of super-.
Effectiveness of Multivariate Time Series Classification Using Shapelets
Directory of Open Access Journals (Sweden)
A. P. Karpenko
2015-01-01
Full Text Available Typically, time series classifiers require signal pre-processing (filtering signals from noise and artifact removal, etc., enhancement of signal features (amplitude, frequency, spectrum, etc., classification of signal features in space using the classical techniques and classification algorithms of multivariate data. We consider a method of classifying time series, which does not require enhancement of the signal features. The method uses the shapelets of time series (time series shapelets i.e. small fragments of this series, which reflect properties of one of its classes most of all.Despite the significant number of publications on the theory and shapelet applications for classification of time series, the task to evaluate the effectiveness of this technique remains relevant. An objective of this publication is to study the effectiveness of a number of modifications of the original shapelet method as applied to the multivariate series classification that is a littlestudied problem. The paper presents the problem statement of multivariate time series classification using the shapelets and describes the shapelet–based basic method of binary classification, as well as various generalizations and proposed modification of the method. It also offers the software that implements a modified method and results of computational experiments confirming the effectiveness of the algorithmic and software solutions.The paper shows that the modified method and the software to use it allow us to reach the classification accuracy of about 85%, at best. The shapelet search time increases in proportion to input data dimension.
Directory of Open Access Journals (Sweden)
Jiří Fejfar
2012-01-01
Full Text Available We are presenting results comparison of three artificial intelligence algorithms in a classification of time series derived from musical excerpts in this paper. Algorithms were chosen to represent different principles of classification – statistic approach, neural networks and competitive learning. The first algorithm is a classical k-Nearest neighbours algorithm, the second algorithm is Multilayer Perceptron (MPL, an example of artificial neural network and the third one is a Learning Vector Quantization (LVQ algorithm representing supervised counterpart to unsupervised Self Organizing Map (SOM.After our own former experiments with unlabelled data we moved forward to the data labels utilization, which generally led to a better accuracy of classification results. As we need huge data set of labelled time series (a priori knowledge of correct class which each time series instance belongs to, we used, with a good experience in former studies, musical excerpts as a source of real-world time series. We are using standard deviation of the sound signal as a descriptor of a musical excerpts volume level.We are describing principle of each algorithm as well as its implementation briefly, giving links for further research. Classification results of each algorithm are presented in a confusion matrix showing numbers of misclassifications and allowing to evaluate overall accuracy of the algorithm. Results are compared and particular misclassifications are discussed for each algorithm. Finally the best solution is chosen and further research goals are given.
Pseudo-random bit generator based on lag time series
García-Martínez, M.; Campos-Cantón, E.
2014-12-01
In this paper, we present a pseudo-random bit generator (PRBG) based on two lag time series of the logistic map using positive and negative values in the bifurcation parameter. In order to hidden the map used to build the pseudo-random series we have used a delay in the generation of time series. These new series when they are mapped xn against xn+1 present a cloud of points unrelated to the logistic map. Finally, the pseudo-random sequences have been tested with the suite of NIST giving satisfactory results for use in stream ciphers.
Fuzzy time-series based on Fibonacci sequence for stock price forecasting
Chen, Tai-Liang; Cheng, Ching-Hsue; Jong Teoh, Hia
2007-07-01
Time-series models have been utilized to make reasonably accurate predictions in the areas of stock price movements, academic enrollments, weather, etc. For promoting the forecasting performance of fuzzy time-series models, this paper proposes a new model, which incorporates the concept of the Fibonacci sequence, the framework of Song and Chissom's model and the weighted method of Yu's model. This paper employs a 5-year period TSMC (Taiwan Semiconductor Manufacturing Company) stock price data and a 13-year period of TAIEX (Taiwan Stock Exchange Capitalization Weighted Stock Index) stock index data as experimental datasets. By comparing our forecasting performances with Chen's (Forecasting enrollments based on fuzzy time-series. Fuzzy Sets Syst. 81 (1996) 311-319), Yu's (Weighted fuzzy time-series models for TAIEX forecasting. Physica A 349 (2004) 609-624) and Huarng's (The application of neural networks to forecast fuzzy time series. Physica A 336 (2006) 481-491) models, we conclude that the proposed model surpasses in accuracy these conventional fuzzy time-series models.
Analysis of time series and size of equivalent sample
International Nuclear Information System (INIS)
Bernal, Nestor; Molina, Alicia; Pabon, Daniel; Martinez, Jorge
2004-01-01
In a meteorological context, a first approach to the modeling of time series is to use models of autoregressive type. This allows one to take into account the meteorological persistence or temporal behavior, thereby identifying the memory of the analyzed process. This article seeks to pre-sent the concept of the size of an equivalent sample, which helps to identify in the data series sub periods with a similar structure. Moreover, in this article we examine the alternative of adjusting the variance of the series, keeping in mind its temporal structure, as well as an adjustment to the covariance of two time series. This article presents two examples, the first one corresponding to seven simulated series with autoregressive structure of first order, and the second corresponding to seven meteorological series of anomalies of the air temperature at the surface in two Colombian regions
Characterizing time series: when Granger causality triggers complex networks
International Nuclear Information System (INIS)
Ge Tian; Cui Yindong; Lin Wei; Liu Chong; Kurths, Jürgen
2012-01-01
In this paper, we propose a new approach to characterize time series with noise perturbations in both the time and frequency domains by combining Granger causality and complex networks. We construct directed and weighted complex networks from time series and use representative network measures to describe their physical and topological properties. Through analyzing the typical dynamical behaviors of some physical models and the MIT-BIH human electrocardiogram data sets, we show that the proposed approach is able to capture and characterize various dynamics and has much potential for analyzing real-world time series of rather short length. (paper)
Characterizing time series: when Granger causality triggers complex networks
Ge, Tian; Cui, Yindong; Lin, Wei; Kurths, Jürgen; Liu, Chong
2012-08-01
In this paper, we propose a new approach to characterize time series with noise perturbations in both the time and frequency domains by combining Granger causality and complex networks. We construct directed and weighted complex networks from time series and use representative network measures to describe their physical and topological properties. Through analyzing the typical dynamical behaviors of some physical models and the MIT-BIHMassachusetts Institute of Technology-Beth Israel Hospital. human electrocardiogram data sets, we show that the proposed approach is able to capture and characterize various dynamics and has much potential for analyzing real-world time series of rather short length.
Sensor-Generated Time Series Events: A Definition Language
Anguera, Aurea; Lara, Juan A.; Lizcano, David; Martínez, Maria Aurora; Pazos, Juan
2012-01-01
There are now a great many domains where information is recorded by sensors over a limited time period or on a permanent basis. This data flow leads to sequences of data known as time series. In many domains, like seismography or medicine, time series analysis focuses on particular regions of interest, known as events, whereas the remainder of the time series contains hardly any useful information. In these domains, there is a need for mechanisms to identify and locate such events. In this paper, we propose an events definition language that is general enough to be used to easily and naturally define events in time series recorded by sensors in any domain. The proposed language has been applied to the definition of time series events generated within the branch of medicine dealing with balance-related functions in human beings. A device, called posturograph, is used to study balance-related functions. The platform has four sensors that record the pressure intensity being exerted on the platform, generating four interrelated time series. As opposed to the existing ad hoc proposals, the results confirm that the proposed language is valid, that is generally applicable and accurate, for identifying the events contained in the time series.
The neural substrates of subjective time dilation
Directory of Open Access Journals (Sweden)
Marc Wittmann
2010-02-01
Full Text Available An object moving towards an observer is subjectively perceived as longer in duration than the same object that is static or moving away. This 'time dilation effect' has been shown for a number of stimuli that differ from standard events along different feature dimensions (e.g. color, size, and dynamics. We performed an event-related functional magnetic resonance imaging (fMRI, while subjects viewed a stream of five visual events, all of which were static and of identical duration except the fourth one, which was a deviant target consisting of either a looming or a receding disc. The duration of the target was systematically varied and participants judged whether the target was shorter or longer than all other events. A time dilation effect was observed only for looming targets. Relative to the static standards, the looming as well as the receding targets induced increased activation of the anterior insula and anterior cingulate cortices (the “core control network”. The decisive contrast between looming and receding targets representing the time dilation effect showed strong asymmetric activation and, specifically, activation of cortical midline structures (the “default network”. These results provide the first evidence that the illusion of temporal dilation is due to activation of areas that are important for cognitive control and subjective awareness. The involvement of midline structures in the temporal dilation illusion is interpreted as evidence that time perception is related to self-referential processing.
Signal Processing for Time-Series Functions on a Graph
2018-02-01
Figures Fig. 1 Time -series function on a fixed graph.............................................2 iv Approved for public release; distribution is...φi〉`2(V)φi (39) 6= f̄ (40) Instead, we simply recover the average of f over time . 13 Approved for public release; distribution is unlimited. This...ARL-TR-8276• FEB 2018 US Army Research Laboratory Signal Processing for Time -Series Functions on a Graph by Humberto Muñoz-Barona, Jean Vettel, and
Clinical time series prediction: Toward a hierarchical dynamical system framework.
Liu, Zitao; Hauskrecht, Milos
2015-09-01
Developing machine learning and data mining algorithms for building temporal models of clinical time series is important for understanding of the patient condition, the dynamics of a disease, effect of various patient management interventions and clinical decision making. In this work, we propose and develop a novel hierarchical framework for modeling clinical time series data of varied length and with irregularly sampled observations. Our hierarchical dynamical system framework for modeling clinical time series combines advantages of the two temporal modeling approaches: the linear dynamical system and the Gaussian process. We model the irregularly sampled clinical time series by using multiple Gaussian process sequences in the lower level of our hierarchical framework and capture the transitions between Gaussian processes by utilizing the linear dynamical system. The experiments are conducted on the complete blood count (CBC) panel data of 1000 post-surgical cardiac patients during their hospitalization. Our framework is evaluated and compared to multiple baseline approaches in terms of the mean absolute prediction error and the absolute percentage error. We tested our framework by first learning the time series model from data for the patients in the training set, and then using it to predict future time series values for the patients in the test set. We show that our model outperforms multiple existing models in terms of its predictive accuracy. Our method achieved a 3.13% average prediction accuracy improvement on ten CBC lab time series when it was compared against the best performing baseline. A 5.25% average accuracy improvement was observed when only short-term predictions were considered. A new hierarchical dynamical system framework that lets us model irregularly sampled time series data is a promising new direction for modeling clinical time series and for improving their predictive performance. Copyright © 2014 Elsevier B.V. All rights reserved.
Clinical time series prediction: towards a hierarchical dynamical system framework
Liu, Zitao; Hauskrecht, Milos
2014-01-01
Objective Developing machine learning and data mining algorithms for building temporal models of clinical time series is important for understanding of the patient condition, the dynamics of a disease, effect of various patient management interventions and clinical decision making. In this work, we propose and develop a novel hierarchical framework for modeling clinical time series data of varied length and with irregularly sampled observations. Materials and methods Our hierarchical dynamical system framework for modeling clinical time series combines advantages of the two temporal modeling approaches: the linear dynamical system and the Gaussian process. We model the irregularly sampled clinical time series by using multiple Gaussian process sequences in the lower level of our hierarchical framework and capture the transitions between Gaussian processes by utilizing the linear dynamical system. The experiments are conducted on the complete blood count (CBC) panel data of 1000 post-surgical cardiac patients during their hospitalization. Our framework is evaluated and compared to multiple baseline approaches in terms of the mean absolute prediction error and the absolute percentage error. Results We tested our framework by first learning the time series model from data for the patient in the training set, and then applying the model in order to predict future time series values on the patients in the test set. We show that our model outperforms multiple existing models in terms of its predictive accuracy. Our method achieved a 3.13% average prediction accuracy improvement on ten CBC lab time series when it was compared against the best performing baseline. A 5.25% average accuracy improvement was observed when only short-term predictions were considered. Conclusion A new hierarchical dynamical system framework that lets us model irregularly sampled time series data is a promising new direction for modeling clinical time series and for improving their predictive
The neural substrates of subjective time dilation
Marc Wittmann; Marc Wittmann; Marc Wittmann; Virginie Van Wassenhove; Bud Craig; Martin P Paulus; Martin P Paulus
2010-01-01
An object moving towards an observer is subjectively perceived as longer in duration than the same object that is static or moving away. This 'time dilation effect' has been shown for a number of stimuli that differ from standard events along different feature dimensions (e.g. color, size, and dynamics). We performed an event-related functional magnetic resonance imaging (fMRI), while subjects viewed a stream of five visual events, all of which were static and of identical duration except the...
The Neural Substrates of Subjective Time Dilation
Wittmann, Marc; van Wassenhove, Virginie; Craig, A. D. (Bud); Paulus, Martin P.
2010-01-01
An object moving towards an observer is subjectively perceived as longer in duration than the same object that is static or moving away. This ”time dilation effect” has been shown for a number of stimuli that differ from standard events along different feature dimensions (e.g. color, size, and dynamics). We performed an event-related functional magnetic resonance imaging (fMRI) study, while subjects viewed a stream of five visual events, all of which were static and of identical duration exce...
Analysis of complex time series using refined composite multiscale entropy
International Nuclear Information System (INIS)
Wu, Shuen-De; Wu, Chiu-Wen; Lin, Shiou-Gwo; Lee, Kung-Yen; Peng, Chung-Kang
2014-01-01
Multiscale entropy (MSE) is an effective algorithm for measuring the complexity of a time series that has been applied in many fields successfully. However, MSE may yield an inaccurate estimation of entropy or induce undefined entropy because the coarse-graining procedure reduces the length of a time series considerably at large scales. Composite multiscale entropy (CMSE) was recently proposed to improve the accuracy of MSE, but it does not resolve undefined entropy. Here we propose a refined composite multiscale entropy (RCMSE) to improve CMSE. For short time series analyses, we demonstrate that RCMSE increases the accuracy of entropy estimation and reduces the probability of inducing undefined entropy.
Forecasting daily meteorological time series using ARIMA and regression models
Murat, Małgorzata; Malinowska, Iwona; Gos, Magdalena; Krzyszczak, Jaromir
2018-04-01
The daily air temperature and precipitation time series recorded between January 1, 1980 and December 31, 2010 in four European sites (Jokioinen, Dikopshof, Lleida and Lublin) from different climatic zones were modeled and forecasted. In our forecasting we used the methods of the Box-Jenkins and Holt- Winters seasonal auto regressive integrated moving-average, the autoregressive integrated moving-average with external regressors in the form of Fourier terms and the time series regression, including trend and seasonality components methodology with R software. It was demonstrated that obtained models are able to capture the dynamics of the time series data and to produce sensible forecasts.
Segmentation of Nonstationary Time Series with Geometric Clustering
DEFF Research Database (Denmark)
Bocharov, Alexei; Thiesson, Bo
2013-01-01
We introduce a non-parametric method for segmentation in regimeswitching time-series models. The approach is based on spectral clustering of target-regressor tuples and derives a switching regression tree, where regime switches are modeled by oblique splits. Such models can be learned efficiently...... from data, where clustering is used to propose one single split candidate at each split level. We use the class of ART time series models to serve as illustration, but because of the non-parametric nature of our segmentation approach, it readily generalizes to a wide range of time-series models that go...
Modelling road accidents: An approach using structural time series
Junus, Noor Wahida Md; Ismail, Mohd Tahir
2014-09-01
In this paper, the trend of road accidents in Malaysia for the years 2001 until 2012 was modelled using a structural time series approach. The structural time series model was identified using a stepwise method, and the residuals for each model were tested. The best-fitted model was chosen based on the smallest Akaike Information Criterion (AIC) and prediction error variance. In order to check the quality of the model, a data validation procedure was performed by predicting the monthly number of road accidents for the year 2012. Results indicate that the best specification of the structural time series model to represent road accidents is the local level with a seasonal model.
Multivariate time series analysis with R and financial applications
Tsay, Ruey S
2013-01-01
Since the publication of his first book, Analysis of Financial Time Series, Ruey Tsay has become one of the most influential and prominent experts on the topic of time series. Different from the traditional and oftentimes complex approach to multivariate (MV) time series, this sequel book emphasizes structural specification, which results in simplified parsimonious VARMA modeling and, hence, eases comprehension. Through a fundamental balance between theory and applications, the book supplies readers with an accessible approach to financial econometric models and their applications to real-worl
Scalable Prediction of Energy Consumption using Incremental Time Series Clustering
Energy Technology Data Exchange (ETDEWEB)
Simmhan, Yogesh; Noor, Muhammad Usman
2013-10-09
Time series datasets are a canonical form of high velocity Big Data, and often generated by pervasive sensors, such as found in smart infrastructure. Performing predictive analytics on time series data can be computationally complex, and requires approximation techniques. In this paper, we motivate this problem using a real application from the smart grid domain. We propose an incremental clustering technique, along with a novel affinity score for determining cluster similarity, which help reduce the prediction error for cumulative time series within a cluster. We evaluate this technique, along with optimizations, using real datasets from smart meters, totaling ~700,000 data points, and show the efficacy of our techniques in improving the prediction error of time series data within polynomial time.
Characterizing interdependencies of multiple time series theory and applications
Hosoya, Yuzo; Takimoto, Taro; Kinoshita, Ryo
2017-01-01
This book introduces academic researchers and professionals to the basic concepts and methods for characterizing interdependencies of multiple time series in the frequency domain. Detecting causal directions between a pair of time series and the extent of their effects, as well as testing the non existence of a feedback relation between them, have constituted major focal points in multiple time series analysis since Granger introduced the celebrated definition of causality in view of prediction improvement. Causality analysis has since been widely applied in many disciplines. Although most analyses are conducted from the perspective of the time domain, a frequency domain method introduced in this book sheds new light on another aspect that disentangles the interdependencies between multiple time series in terms of long-term or short-term effects, quantitatively characterizing them. The frequency domain method includes the Granger noncausality test as a special case. Chapters 2 and 3 of the book introduce an i...
Scale-dependent intrinsic entropies of complex time series.
Yeh, Jia-Rong; Peng, Chung-Kang; Huang, Norden E
2016-04-13
Multi-scale entropy (MSE) was developed as a measure of complexity for complex time series, and it has been applied widely in recent years. The MSE algorithm is based on the assumption that biological systems possess the ability to adapt and function in an ever-changing environment, and these systems need to operate across multiple temporal and spatial scales, such that their complexity is also multi-scale and hierarchical. Here, we present a systematic approach to apply the empirical mode decomposition algorithm, which can detrend time series on various time scales, prior to analysing a signal's complexity by measuring the irregularity of its dynamics on multiple time scales. Simulated time series of fractal Gaussian noise and human heartbeat time series were used to study the performance of this new approach. We show that our method can successfully quantify the fractal properties of the simulated time series and can accurately distinguish modulations in human heartbeat time series in health and disease. © 2016 The Author(s).
Quantifying memory in complex physiological time-series.
Shirazi, Amir H; Raoufy, Mohammad R; Ebadi, Haleh; De Rui, Michele; Schiff, Sami; Mazloom, Roham; Hajizadeh, Sohrab; Gharibzadeh, Shahriar; Dehpour, Ahmad R; Amodio, Piero; Jafari, G Reza; Montagnese, Sara; Mani, Ali R
2013-01-01
In a time-series, memory is a statistical feature that lasts for a period of time and distinguishes the time-series from a random, or memory-less, process. In the present study, the concept of "memory length" was used to define the time period, or scale over which rare events within a physiological time-series do not appear randomly. The method is based on inverse statistical analysis and provides empiric evidence that rare fluctuations in cardio-respiratory time-series are 'forgotten' quickly in healthy subjects while the memory for such events is significantly prolonged in pathological conditions such as asthma (respiratory time-series) and liver cirrhosis (heart-beat time-series). The memory length was significantly higher in patients with uncontrolled asthma compared to healthy volunteers. Likewise, it was significantly higher in patients with decompensated cirrhosis compared to those with compensated cirrhosis and healthy volunteers. We also observed that the cardio-respiratory system has simple low order dynamics and short memory around its average, and high order dynamics around rare fluctuations.
Elements of nonlinear time series analysis and forecasting
De Gooijer, Jan G
2017-01-01
This book provides an overview of the current state-of-the-art of nonlinear time series analysis, richly illustrated with examples, pseudocode algorithms and real-world applications. Avoiding a “theorem-proof” format, it shows concrete applications on a variety of empirical time series. The book can be used in graduate courses in nonlinear time series and at the same time also includes interesting material for more advanced readers. Though it is largely self-contained, readers require an understanding of basic linear time series concepts, Markov chains and Monte Carlo simulation methods. The book covers time-domain and frequency-domain methods for the analysis of both univariate and multivariate (vector) time series. It makes a clear distinction between parametric models on the one hand, and semi- and nonparametric models/methods on the other. This offers the reader the option of concentrating exclusively on one of these nonlinear time series analysis methods. To make the book as user friendly as possible...
Neural Computations in a Dynamical System with Multiple Time Scales.
Mi, Yuanyuan; Lin, Xiaohan; Wu, Si
2016-01-01
Neural systems display rich short-term dynamics at various levels, e.g., spike-frequency adaptation (SFA) at the single-neuron level, and short-term facilitation (STF) and depression (STD) at the synapse level. These dynamical features typically cover a broad range of time scales and exhibit large diversity in different brain regions. It remains unclear what is the computational benefit for the brain to have such variability in short-term dynamics. In this study, we propose that the brain can exploit such dynamical features to implement multiple seemingly contradictory computations in a single neural circuit. To demonstrate this idea, we use continuous attractor neural network (CANN) as a working model and include STF, SFA and STD with increasing time constants in its dynamics. Three computational tasks are considered, which are persistent activity, adaptation, and anticipative tracking. These tasks require conflicting neural mechanisms, and hence cannot be implemented by a single dynamical feature or any combination with similar time constants. However, with properly coordinated STF, SFA and STD, we show that the network is able to implement the three computational tasks concurrently. We hope this study will shed light on the understanding of how the brain orchestrates its rich dynamics at various levels to realize diverse cognitive functions.
A Four-Stage Hybrid Model for Hydrological Time Series Forecasting
Di, Chongli; Yang, Xiaohua; Wang, Xiaochao
2014-01-01
Hydrological time series forecasting remains a difficult task due to its complicated nonlinear, non-stationary and multi-scale characteristics. To solve this difficulty and improve the prediction accuracy, a novel four-stage hybrid model is proposed for hydrological time series forecasting based on the principle of ‘denoising, decomposition and ensemble’. The proposed model has four stages, i.e., denoising, decomposition, components prediction and ensemble. In the denoising stage, the empirical mode decomposition (EMD) method is utilized to reduce the noises in the hydrological time series. Then, an improved method of EMD, the ensemble empirical mode decomposition (EEMD), is applied to decompose the denoised series into a number of intrinsic mode function (IMF) components and one residual component. Next, the radial basis function neural network (RBFNN) is adopted to predict the trend of all of the components obtained in the decomposition stage. In the final ensemble prediction stage, the forecasting results of all of the IMF and residual components obtained in the third stage are combined to generate the final prediction results, using a linear neural network (LNN) model. For illustration and verification, six hydrological cases with different characteristics are used to test the effectiveness of the proposed model. The proposed hybrid model performs better than conventional single models, the hybrid models without denoising or decomposition and the hybrid models based on other methods, such as the wavelet analysis (WA)-based hybrid models. In addition, the denoising and decomposition strategies decrease the complexity of the series and reduce the difficulties of the forecasting. With its effective denoising and accurate decomposition ability, high prediction precision and wide applicability, the new model is very promising for complex time series forecasting. This new forecast model is an extension of nonlinear prediction models. PMID:25111782
A four-stage hybrid model for hydrological time series forecasting.
Di, Chongli; Yang, Xiaohua; Wang, Xiaochao
2014-01-01
Hydrological time series forecasting remains a difficult task due to its complicated nonlinear, non-stationary and multi-scale characteristics. To solve this difficulty and improve the prediction accuracy, a novel four-stage hybrid model is proposed for hydrological time series forecasting based on the principle of 'denoising, decomposition and ensemble'. The proposed model has four stages, i.e., denoising, decomposition, components prediction and ensemble. In the denoising stage, the empirical mode decomposition (EMD) method is utilized to reduce the noises in the hydrological time series. Then, an improved method of EMD, the ensemble empirical mode decomposition (EEMD), is applied to decompose the denoised series into a number of intrinsic mode function (IMF) components and one residual component. Next, the radial basis function neural network (RBFNN) is adopted to predict the trend of all of the components obtained in the decomposition stage. In the final ensemble prediction stage, the forecasting results of all of the IMF and residual components obtained in the third stage are combined to generate the final prediction results, using a linear neural network (LNN) model. For illustration and verification, six hydrological cases with different characteristics are used to test the effectiveness of the proposed model. The proposed hybrid model performs better than conventional single models, the hybrid models without denoising or decomposition and the hybrid models based on other methods, such as the wavelet analysis (WA)-based hybrid models. In addition, the denoising and decomposition strategies decrease the complexity of the series and reduce the difficulties of the forecasting. With its effective denoising and accurate decomposition ability, high prediction precision and wide applicability, the new model is very promising for complex time series forecasting. This new forecast model is an extension of nonlinear prediction models.
Rodgers, Joseph Lee; Beasley, William Howard; Schuelke, Matthew
2014-01-01
Many data structures, particularly time series data, are naturally seasonal, cyclical, or otherwise circular. Past graphical methods for time series have focused on linear plots. In this article, we move graphical analysis onto the circle. We focus on 2 particular methods, one old and one new. Rose diagrams are circular histograms and can be produced in several different forms using the RRose software system. In addition, we propose, develop, illustrate, and provide software support for a new circular graphical method, called Wrap-Around Time Series Plots (WATS Plots), which is a graphical method useful to support time series analyses in general but in particular in relation to interrupted time series designs. We illustrate the use of WATS Plots with an interrupted time series design evaluating the effect of the Oklahoma City bombing on birthrates in Oklahoma County during the 10 years surrounding the bombing of the Murrah Building in Oklahoma City. We compare WATS Plots with linear time series representations and overlay them with smoothing and error bands. Each method is shown to have advantages in relation to the other; in our example, the WATS Plots more clearly show the existence and effect size of the fertility differential.
Growth And Export Expansion In Mauritius - A Time Series Analysis ...
African Journals Online (AJOL)
Growth And Export Expansion In Mauritius - A Time Series Analysis. ... RV Sannassee, R Pearce ... Using Granger Causality tests, the short-run analysis results revealed that there is significant reciprocal causality between real export earnings ...
On robust forecasting of autoregressive time series under censoring
Kharin, Y.; Badziahin, I.
2009-01-01
Problems of robust statistical forecasting are considered for autoregressive time series observed under distortions generated by interval censoring. Three types of robust forecasting statistics are developed; meansquare risk is evaluated for the developed forecasting statistics. Numerical results are given.
AFSC/ABL: Ugashik sockeye salmon scale time series
National Oceanic and Atmospheric Administration, Department of Commerce — A time series of scale samples (1956 b?? 2002) collected from adult sockeye salmon returning to Ugashik River were retrieved from the Alaska Department of Fish and...
Unsupervised land cover change detection: meaningful sequential time series analysis
CSIR Research Space (South Africa)
Salmon, BP
2011-06-01
Full Text Available An automated land cover change detection method is proposed that uses coarse spatial resolution hyper-temporal earth observation satellite time series data. The study compared three different unsupervised clustering approaches that operate on short...
Fast and Flexible Multivariate Time Series Subsequence Search
National Aeronautics and Space Administration — Multivariate Time-Series (MTS) are ubiquitous, and are generated in areas as disparate as sensor recordings in aerospace systems, music and video streams, medical...
AFSC/ABL: Naknek sockeye salmon scale time series
National Oceanic and Atmospheric Administration, Department of Commerce — A time series of scale samples (1956 2002) collected from adult sockeye salmon returning to Naknek River were retrieved from the Alaska Department of Fish and Game....
Constructing ordinal partition transition networks from multivariate time series.
Zhang, Jiayang; Zhou, Jie; Tang, Ming; Guo, Heng; Small, Michael; Zou, Yong
2017-08-10
A growing number of algorithms have been proposed to map a scalar time series into ordinal partition transition networks. However, most observable phenomena in the empirical sciences are of a multivariate nature. We construct ordinal partition transition networks for multivariate time series. This approach yields weighted directed networks representing the pattern transition properties of time series in velocity space, which hence provides dynamic insights of the underling system. Furthermore, we propose a measure of entropy to characterize ordinal partition transition dynamics, which is sensitive to capturing the possible local geometric changes of phase space trajectories. We demonstrate the applicability of pattern transition networks to capture phase coherence to non-coherence transitions, and to characterize paths to phase synchronizations. Therefore, we conclude that the ordinal partition transition network approach provides complementary insight to the traditional symbolic analysis of nonlinear multivariate time series.
forecasting with nonlinear time series model: a monte-carlo
African Journals Online (AJOL)
PUBLICATIONS1
Carlo method of forecasting using a special nonlinear time series model, called logistic smooth transition ... We illustrate this new method using some simulation ..... in MATLAB 7.5.0. ... process (DGP) using the logistic smooth transi-.
Evolutionary neural network modeling for software cumulative failure time prediction
International Nuclear Information System (INIS)
Tian Liang; Noore, Afzel
2005-01-01
An evolutionary neural network modeling approach for software cumulative failure time prediction based on multiple-delayed-input single-output architecture is proposed. Genetic algorithm is used to globally optimize the number of the delayed input neurons and the number of neurons in the hidden layer of the neural network architecture. Modification of Levenberg-Marquardt algorithm with Bayesian regularization is used to improve the ability to predict software cumulative failure time. The performance of our proposed approach has been compared using real-time control and flight dynamic application data sets. Numerical results show that both the goodness-of-fit and the next-step-predictability of our proposed approach have greater accuracy in predicting software cumulative failure time compared to existing approaches
Directory of Open Access Journals (Sweden)
David Afolabi
2017-11-01
Full Text Available The importance of an interference-less machine learning scheme in time series prediction is crucial, as an oversight can have a negative cumulative effect, especially when predicting many steps ahead of the currently available data. The on-going research on noise elimination in time series forecasting has led to a successful approach of decomposing the data sequence into component trends to identify noise-inducing information. The empirical mode decomposition method separates the time series/signal into a set of intrinsic mode functions ranging from high to low frequencies, which can be summed up to reconstruct the original data. The usual assumption that random noises are only contained in the high-frequency component has been shown not to be the case, as observed in our previous findings. The results from that experiment reveal that noise can be present in a low frequency component, and this motivates the newly-proposed algorithm. Additionally, to prevent the erosion of periodic trends and patterns within the series, we perform the learning of local and global trends separately in a hierarchical manner which succeeds in detecting and eliminating short/long term noise. The algorithm is tested on four datasets from financial market data and physical science data. The simulation results are compared with the conventional and state-of-the-art approaches for time series machine learning, such as the non-linear autoregressive neural network and the long short-term memory recurrent neural network, respectively. Statistically significant performance gains are recorded when the meta-learning algorithm for noise reduction is used in combination with these artificial neural networks. For time series data which cannot be decomposed into meaningful trends, applying the moving average method to create meta-information for guiding the learning process is still better than the traditional approach. Therefore, this new approach is applicable to the forecasting
Wei, Ruoyu; Cao, Jinde; Alsaedi, Ahmed
2018-02-01
This paper investigates the finite-time synchronization and fixed-time synchronization problems of inertial memristive neural networks with time-varying delays. By utilizing the Filippov discontinuous theory and Lyapunov stability theory, several sufficient conditions are derived to ensure finite-time synchronization of inertial memristive neural networks. Then, for the purpose of making the setting time independent of initial condition, we consider the fixed-time synchronization. A novel criterion guaranteeing the fixed-time synchronization of inertial memristive neural networks is derived. Finally, three examples are provided to demonstrate the effectiveness of our main results.
International Nuclear Information System (INIS)
Xu Chang-Jin; Li Pei-Luan; Pang Yi-Cheng
2017-01-01
This paper is concerned with fractional-order bidirectional associative memory (BAM) neural networks with time delays. Applying Laplace transform, the generalized Gronwall inequality and estimates of Mittag–Leffler functions, some sufficient conditions which ensure the finite-time stability of fractional-order bidirectional associative memory neural networks with time delays are obtained. Two examples with their simulations are given to illustrate the theoretical findings. Our results are new and complement previously known results. (paper)
Chaotic time series prediction: From one to another
International Nuclear Information System (INIS)
Zhao Pengfei; Xing Lei; Yu Jun
2009-01-01
In this Letter, a new local linear prediction model is proposed to predict a chaotic time series of a component x(t) by using the chaotic time series of another component y(t) in the same system with x(t). Our approach is based on the phase space reconstruction coming from the Takens embedding theorem. To illustrate our results, we present an example of Lorenz system and compare with the performance of the original local linear prediction model.
The use of synthetic input sequences in time series modeling
International Nuclear Information System (INIS)
Oliveira, Dair Jose de; Letellier, Christophe; Gomes, Murilo E.D.; Aguirre, Luis A.
2008-01-01
In many situations time series models obtained from noise-like data settle to trivial solutions under iteration. This Letter proposes a way of producing a synthetic (dummy) input, that is included to prevent the model from settling down to a trivial solution, while maintaining features of the original signal. Simulated benchmark models and a real time series of RR intervals from an ECG are used to illustrate the procedure
Advances in Antithetic Time Series Analysis : Separating Fact from Artifact
Directory of Open Access Journals (Sweden)
Dennis Ridley
2016-01-01
Full Text Available The problem of biased time series mathematical model parameter estimates is well known to be insurmountable. When used to predict future values by extrapolation, even a de minimis bias will eventually grow into a large bias, with misleading results. This paper elucidates how combining antithetic time series' solves this baffling problem of bias in the fitted and forecast values by dynamic bias cancellation. Instead of growing to infinity, the average error can converge to a constant. (original abstract
Multiple Time Series Ising Model for Financial Market Simulations
International Nuclear Information System (INIS)
Takaishi, Tetsuya
2015-01-01
In this paper we propose an Ising model which simulates multiple financial time series. Our model introduces the interaction which couples to spins of other systems. Simulations from our model show that time series exhibit the volatility clustering that is often observed in the real financial markets. Furthermore we also find non-zero cross correlations between the volatilities from our model. Thus our model can simulate stock markets where volatilities of stocks are mutually correlated
Robust Forecasting of Non-Stationary Time Series
Croux, C.; Fried, R.; Gijbels, I.; Mahieu, K.
2010-01-01
This paper proposes a robust forecasting method for non-stationary time series. The time series is modelled using non-parametric heteroscedastic regression, and fitted by a localized MM-estimator, combining high robustness and large efficiency. The proposed method is shown to produce reliable forecasts in the presence of outliers, non-linearity, and heteroscedasticity. In the absence of outliers, the forecasts are only slightly less precise than those based on a localized Least Squares estima...
Automated Feature Design for Time Series Classification by Genetic Programming
Harvey, Dustin Yewell
2014-01-01
Time series classification (TSC) methods discover and exploit patterns in time series and other one-dimensional signals. Although many accurate, robust classifiers exist for multivariate feature sets, general approaches are needed to extend machine learning techniques to make use of signal inputs. Numerous applications of TSC can be found in structural engineering, especially in the areas of structural health monitoring and non-destructive evaluation. Additionally, the fields of process contr...
Geomechanical time series and its singularity spectrum analysis
Czech Academy of Sciences Publication Activity Database
Lyubushin, Alexei A.; Kaláb, Zdeněk; Lednická, Markéta
2012-01-01
Roč. 47, č. 1 (2012), s. 69-77 ISSN 1217-8977 R&D Projects: GA ČR GA105/09/0089 Institutional research plan: CEZ:AV0Z30860518 Keywords : geomechanical time series * singularity spectrum * time series segmentation * laser distance meter Subject RIV: DC - Siesmology, Volcanology, Earth Structure Impact factor: 0.347, year: 2012 http://www.akademiai.com/content/88v4027758382225/fulltext.pdf
Time Series Analysis of Insar Data: Methods and Trends
Osmanoglu, Batuhan; Sunar, Filiz; Wdowinski, Shimon; Cano-Cabral, Enrique
2015-01-01
Time series analysis of InSAR data has emerged as an important tool for monitoring and measuring the displacement of the Earth's surface. Changes in the Earth's surface can result from a wide range of phenomena such as earthquakes, volcanoes, landslides, variations in ground water levels, and changes in wetland water levels. Time series analysis is applied to interferometric phase measurements, which wrap around when the observed motion is larger than one-half of the radar wavelength. Thus, the spatio-temporal ''unwrapping" of phase observations is necessary to obtain physically meaningful results. Several different algorithms have been developed for time series analysis of InSAR data to solve for this ambiguity. These algorithms may employ different models for time series analysis, but they all generate a first-order deformation rate, which can be compared to each other. However, there is no single algorithm that can provide optimal results in all cases. Since time series analyses of InSAR data are used in a variety of applications with different characteristics, each algorithm possesses inherently unique strengths and weaknesses. In this review article, following a brief overview of InSAR technology, we discuss several algorithms developed for time series analysis of InSAR data using an example set of results for measuring subsidence rates in Mexico City.
A Markovian Entropy Measure for the Analysis of Calcium Activity Time Series.
Marken, John P; Halleran, Andrew D; Rahman, Atiqur; Odorizzi, Laura; LeFew, Michael C; Golino, Caroline A; Kemper, Peter; Saha, Margaret S
2016-01-01
Methods to analyze the dynamics of calcium activity often rely on visually distinguishable features in time series data such as spikes, waves, or oscillations. However, systems such as the developing nervous system display a complex, irregular type of calcium activity which makes the use of such methods less appropriate. Instead, for such systems there exists a class of methods (including information theoretic, power spectral, and fractal analysis approaches) which use more fundamental properties of the time series to analyze the observed calcium dynamics. We present a new analysis method in this class, the Markovian Entropy measure, which is an easily implementable calcium time series analysis method which represents the observed calcium activity as a realization of a Markov Process and describes its dynamics in terms of the level of predictability underlying the transitions between the states of the process. We applied our and other commonly used calcium analysis methods on a dataset from Xenopus laevis neural progenitors which displays irregular calcium activity and a dataset from murine synaptic neurons which displays activity time series that are well-described by visually-distinguishable features. We find that the Markovian Entropy measure is able to distinguish between biologically distinct populations in both datasets, and that it can separate biologically distinct populations to a greater extent than other methods in the dataset exhibiting irregular calcium activity. These results support the benefit of using the Markovian Entropy measure to analyze calcium dynamics, particularly for studies using time series data which do not exhibit easily distinguishable features.
A Markovian Entropy Measure for the Analysis of Calcium Activity Time Series.
Directory of Open Access Journals (Sweden)
John P Marken
Full Text Available Methods to analyze the dynamics of calcium activity often rely on visually distinguishable features in time series data such as spikes, waves, or oscillations. However, systems such as the developing nervous system display a complex, irregular type of calcium activity which makes the use of such methods less appropriate. Instead, for such systems there exists a class of methods (including information theoretic, power spectral, and fractal analysis approaches which use more fundamental properties of the time series to analyze the observed calcium dynamics. We present a new analysis method in this class, the Markovian Entropy measure, which is an easily implementable calcium time series analysis method which represents the observed calcium activity as a realization of a Markov Process and describes its dynamics in terms of the level of predictability underlying the transitions between the states of the process. We applied our and other commonly used calcium analysis methods on a dataset from Xenopus laevis neural progenitors which displays irregular calcium activity and a dataset from murine synaptic neurons which displays activity time series that are well-described by visually-distinguishable features. We find that the Markovian Entropy measure is able to distinguish between biologically distinct populations in both datasets, and that it can separate biologically distinct populations to a greater extent than other methods in the dataset exhibiting irregular calcium activity. These results support the benefit of using the Markovian Entropy measure to analyze calcium dynamics, particularly for studies using time series data which do not exhibit easily distinguishable features.
Bayesian Modelling of fMRI Time Series
DEFF Research Database (Denmark)
Højen-Sørensen, Pedro; Hansen, Lars Kai; Rasmussen, Carl Edward
2000-01-01
We present a Hidden Markov Model (HMM) for inferring the hidden psychological state (or neural activity) during single trial fMRI activation experiments with blocked task paradigms. Inference is based on Bayesian methodology, using a combination of analytical and a variety of Markov Chain Monte...... Carlo (MCMC) sampling techniques. The advantage of this method is that detection of short time learning effects between repeated trials is possible since inference is based only on single trial experiments....
Similarity estimators for irregular and age uncertain time series
Rehfeld, K.; Kurths, J.
2013-09-01
Paleoclimate time series are often irregularly sampled and age uncertain, which is an important technical challenge to overcome for successful reconstruction of past climate variability and dynamics. Visual comparison and interpolation-based linear correlation approaches have been used to infer dependencies from such proxy time series. While the first is subjective, not measurable and not suitable for the comparison of many datasets at a time, the latter introduces interpolation bias, and both face difficulties if the underlying dependencies are nonlinear. In this paper we investigate similarity estimators that could be suitable for the quantitative investigation of dependencies in irregular and age uncertain time series. We compare the Gaussian-kernel based cross correlation (gXCF, Rehfeld et al., 2011) and mutual information (gMI, Rehfeld et al., 2013) against their interpolation-based counterparts and the new event synchronization function (ESF). We test the efficiency of the methods in estimating coupling strength and coupling lag numerically, using ensembles of synthetic stalagmites with short, autocorrelated, linear and nonlinearly coupled proxy time series, and in the application to real stalagmite time series. In the linear test case coupling strength increases are identified consistently for all estimators, while in the nonlinear test case the correlation-based approaches fail. The lag at which the time series are coupled is identified correctly as the maximum of the similarity functions in around 60-55% (in the linear case) to 53-42% (for the nonlinear processes) of the cases when the dating of the synthetic stalagmite is perfectly precise. If the age uncertainty increases beyond 5% of the time series length, however, the true coupling lag is not identified more often than the others for which the similarity function was estimated. Age uncertainty contributes up to half of the uncertainty in the similarity estimation process. Time series irregularity
Similarity estimators for irregular and age-uncertain time series
Rehfeld, K.; Kurths, J.
2014-01-01
Paleoclimate time series are often irregularly sampled and age uncertain, which is an important technical challenge to overcome for successful reconstruction of past climate variability and dynamics. Visual comparison and interpolation-based linear correlation approaches have been used to infer dependencies from such proxy time series. While the first is subjective, not measurable and not suitable for the comparison of many data sets at a time, the latter introduces interpolation bias, and both face difficulties if the underlying dependencies are nonlinear. In this paper we investigate similarity estimators that could be suitable for the quantitative investigation of dependencies in irregular and age-uncertain time series. We compare the Gaussian-kernel-based cross-correlation (gXCF, Rehfeld et al., 2011) and mutual information (gMI, Rehfeld et al., 2013) against their interpolation-based counterparts and the new event synchronization function (ESF). We test the efficiency of the methods in estimating coupling strength and coupling lag numerically, using ensembles of synthetic stalagmites with short, autocorrelated, linear and nonlinearly coupled proxy time series, and in the application to real stalagmite time series. In the linear test case, coupling strength increases are identified consistently for all estimators, while in the nonlinear test case the correlation-based approaches fail. The lag at which the time series are coupled is identified correctly as the maximum of the similarity functions in around 60-55% (in the linear case) to 53-42% (for the nonlinear processes) of the cases when the dating of the synthetic stalagmite is perfectly precise. If the age uncertainty increases beyond 5% of the time series length, however, the true coupling lag is not identified more often than the others for which the similarity function was estimated. Age uncertainty contributes up to half of the uncertainty in the similarity estimation process. Time series irregularity
Data imputation analysis for Cosmic Rays time series
Fernandes, R. C.; Lucio, P. S.; Fernandez, J. H.
2017-05-01
The occurrence of missing data concerning Galactic Cosmic Rays time series (GCR) is inevitable since loss of data is due to mechanical and human failure or technical problems and different periods of operation of GCR stations. The aim of this study was to perform multiple dataset imputation in order to depict the observational dataset. The study has used the monthly time series of GCR Climax (CLMX) and Roma (ROME) from 1960 to 2004 to simulate scenarios of 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80% and 90% of missing data compared to observed ROME series, with 50 replicates. Then, the CLMX station as a proxy for allocation of these scenarios was used. Three different methods for monthly dataset imputation were selected: AMÉLIA II - runs the bootstrap Expectation Maximization algorithm, MICE - runs an algorithm via Multivariate Imputation by Chained Equations and MTSDI - an Expectation Maximization algorithm-based method for imputation of missing values in multivariate normal time series. The synthetic time series compared with the observed ROME series has also been evaluated using several skill measures as such as RMSE, NRMSE, Agreement Index, R, R2, F-test and t-test. The results showed that for CLMX and ROME, the R2 and R statistics were equal to 0.98 and 0.96, respectively. It was observed that increases in the number of gaps generate loss of quality of the time series. Data imputation was more efficient with MTSDI method, with negligible errors and best skill coefficients. The results suggest a limit of about 60% of missing data for imputation, for monthly averages, no more than this. It is noteworthy that CLMX, ROME and KIEL stations present no missing data in the target period. This methodology allowed reconstructing 43 time series.
Correlation measure to detect time series distances, whence economy globalization
Miśkiewicz, Janusz; Ausloos, Marcel
2008-11-01
An instantaneous time series distance is defined through the equal time correlation coefficient. The idea is applied to the Gross Domestic Product (GDP) yearly increments of 21 rich countries between 1950 and 2005 in order to test the process of economic globalisation. Some data discussion is first presented to decide what (EKS, GK, or derived) GDP series should be studied. Distances are then calculated from the correlation coefficient values between pairs of series. The role of time averaging of the distances over finite size windows is discussed. Three network structures are next constructed based on the hierarchy of distances. It is shown that the mean distance between the most developed countries on several networks actually decreases in time, -which we consider as a proof of globalization. An empirical law is found for the evolution after 1990, similar to that found in flux creep. The optimal observation time window size is found ≃15 years.
Multiresolution analysis of Bursa Malaysia KLCI time series
Ismail, Mohd Tahir; Dghais, Amel Abdoullah Ahmed
2017-05-01
In general, a time series is simply a sequence of numbers collected at regular intervals over a period. Financial time series data processing is concerned with the theory and practice of processing asset price over time, such as currency, commodity data, and stock market data. The primary aim of this study is to understand the fundamental characteristics of selected financial time series by using the time as well as the frequency domain analysis. After that prediction can be executed for the desired system for in sample forecasting. In this study, multiresolution analysis which the assist of discrete wavelet transforms (DWT) and maximal overlap discrete wavelet transform (MODWT) will be used to pinpoint special characteristics of Bursa Malaysia KLCI (Kuala Lumpur Composite Index) daily closing prices and return values. In addition, further case study discussions include the modeling of Bursa Malaysia KLCI using linear ARIMA with wavelets to address how multiresolution approach improves fitting and forecasting results.
Time domain series system definition and gear set reliability modeling
International Nuclear Information System (INIS)
Xie, Liyang; Wu, Ningxiang; Qian, Wenxue
2016-01-01
Time-dependent multi-configuration is a typical feature for mechanical systems such as gear trains and chain drives. As a series system, a gear train is distinct from a traditional series system, such as a chain, in load transmission path, system-component relationship, system functioning manner, as well as time-dependent system configuration. Firstly, the present paper defines time-domain series system to which the traditional series system reliability model is not adequate. Then, system specific reliability modeling technique is proposed for gear sets, including component (tooth) and subsystem (tooth-pair) load history description, material priori/posterior strength expression, time-dependent and system specific load-strength interference analysis, as well as statistically dependent failure events treatment. Consequently, several system reliability models are developed for gear sets with different tooth numbers in the scenario of tooth root material ultimate tensile strength failure. The application of the models is discussed in the last part, and the differences between the system specific reliability model and the traditional series system reliability model are illustrated by virtue of several numerical examples. - Highlights: • A new type of series system, i.e. time-domain multi-configuration series system is defined, that is of great significance to reliability modeling. • Multi-level statistical analysis based reliability modeling method is presented for gear transmission system. • Several system specific reliability models are established for gear set reliability estimation. • The differences between the traditional series system reliability model and the new model are illustrated.
Evaluation of scaling invariance embedded in short time series.
Directory of Open Access Journals (Sweden)
Xue Pan
Full Text Available Scaling invariance of time series has been making great contributions in diverse research fields. But how to evaluate scaling exponent from a real-world series is still an open problem. Finite length of time series may induce unacceptable fluctuation and bias to statistical quantities and consequent invalidation of currently used standard methods. In this paper a new concept called correlation-dependent balanced estimation of diffusion entropy is developed to evaluate scale-invariance in very short time series with length ~10(2. Calculations with specified Hurst exponent values of 0.2,0.3,...,0.9 show that by using the standard central moving average de-trending procedure this method can evaluate the scaling exponents for short time series with ignorable bias (≤0.03 and sharp confidential interval (standard deviation ≤0.05. Considering the stride series from ten volunteers along an approximate oval path of a specified length, we observe that though the averages and deviations of scaling exponents are close, their evolutionary behaviors display rich patterns. It has potential use in analyzing physiological signals, detecting early warning signals, and so on. As an emphasis, the our core contribution is that by means of the proposed method one can estimate precisely shannon entropy from limited records.
Evaluation of scaling invariance embedded in short time series.
Pan, Xue; Hou, Lei; Stephen, Mutua; Yang, Huijie; Zhu, Chenping
2014-01-01
Scaling invariance of time series has been making great contributions in diverse research fields. But how to evaluate scaling exponent from a real-world series is still an open problem. Finite length of time series may induce unacceptable fluctuation and bias to statistical quantities and consequent invalidation of currently used standard methods. In this paper a new concept called correlation-dependent balanced estimation of diffusion entropy is developed to evaluate scale-invariance in very short time series with length ~10(2). Calculations with specified Hurst exponent values of 0.2,0.3,...,0.9 show that by using the standard central moving average de-trending procedure this method can evaluate the scaling exponents for short time series with ignorable bias (≤0.03) and sharp confidential interval (standard deviation ≤0.05). Considering the stride series from ten volunteers along an approximate oval path of a specified length, we observe that though the averages and deviations of scaling exponents are close, their evolutionary behaviors display rich patterns. It has potential use in analyzing physiological signals, detecting early warning signals, and so on. As an emphasis, the our core contribution is that by means of the proposed method one can estimate precisely shannon entropy from limited records.
Modeling Non-Gaussian Time Series with Nonparametric Bayesian Model.
Xu, Zhiguang; MacEachern, Steven; Xu, Xinyi
2015-02-01
We present a class of Bayesian copula models whose major components are the marginal (limiting) distribution of a stationary time series and the internal dynamics of the series. We argue that these are the two features with which an analyst is typically most familiar, and hence that these are natural components with which to work. For the marginal distribution, we use a nonparametric Bayesian prior distribution along with a cdf-inverse cdf transformation to obtain large support. For the internal dynamics, we rely on the traditionally successful techniques of normal-theory time series. Coupling the two components gives us a family of (Gaussian) copula transformed autoregressive models. The models provide coherent adjustments of time scales and are compatible with many extensions, including changes in volatility of the series. We describe basic properties of the models, show their ability to recover non-Gaussian marginal distributions, and use a GARCH modification of the basic model to analyze stock index return series. The models are found to provide better fit and improved short-range and long-range predictions than Gaussian competitors. The models are extensible to a large variety of fields, including continuous time models, spatial models, models for multiple series, models driven by external covariate streams, and non-stationary models.
Drunk driving detection based on classification of multivariate time series.
Li, Zhenlong; Jin, Xue; Zhao, Xiaohua
2015-09-01
This paper addresses the problem of detecting drunk driving based on classification of multivariate time series. First, driving performance measures were collected from a test in a driving simulator located in the Traffic Research Center, Beijing University of Technology. Lateral position and steering angle were used to detect drunk driving. Second, multivariate time series analysis was performed to extract the features. A piecewise linear representation was used to represent multivariate time series. A bottom-up algorithm was then employed to separate multivariate time series. The slope and time interval of each segment were extracted as the features for classification. Third, a support vector machine classifier was used to classify driver's state into two classes (normal or drunk) according to the extracted features. The proposed approach achieved an accuracy of 80.0%. Drunk driving detection based on the analysis of multivariate time series is feasible and effective. The approach has implications for drunk driving detection. Copyright © 2015 Elsevier Ltd and National Safety Council. All rights reserved.
Self-affinity in the dengue fever time series
Azevedo, S. M.; Saba, H.; Miranda, J. G. V.; Filho, A. S. Nascimento; Moret, M. A.
2016-06-01
Dengue is a complex public health problem that is common in tropical and subtropical regions. This disease has risen substantially in the last three decades, and the physical symptoms depict the self-affine behavior of the occurrences of reported dengue cases in Bahia, Brazil. This study uses detrended fluctuation analysis (DFA) to verify the scale behavior in a time series of dengue cases and to evaluate the long-range correlations that are characterized by the power law α exponent for different cities in Bahia, Brazil. The scaling exponent (α) presents different long-range correlations, i.e. uncorrelated, anti-persistent, persistent and diffusive behaviors. The long-range correlations highlight the complex behavior of the time series of this disease. The findings show that there are two distinct types of scale behavior. In the first behavior, the time series presents a persistent α exponent for a one-month period. For large periods, the time series signal approaches subdiffusive behavior. The hypothesis of the long-range correlations in the time series of the occurrences of reported dengue cases was validated. The observed self-affinity is useful as a forecasting tool for future periods through extrapolation of the α exponent behavior. This complex system has a higher predictability in a relatively short time (approximately one month), and it suggests a new tool in epidemiological control strategies. However, predictions for large periods using DFA are hidden by the subdiffusive behavior.
Stochastic modeling of hourly rainfall times series in Campania (Italy)
Giorgio, M.; Greco, R.
2009-04-01
Occurrence of flowslides and floods in small catchments is uneasy to predict, since it is affected by a number of variables, such as mechanical and hydraulic soil properties, slope morphology, vegetation coverage, rainfall spatial and temporal variability. Consequently, landslide risk assessment procedures and early warning systems still rely on simple empirical models based on correlation between recorded rainfall data and observed landslides and/or river discharges. Effectiveness of such systems could be improved by reliable quantitative rainfall prediction, which can allow gaining larger lead-times. Analysis of on-site recorded rainfall height time series represents the most effective approach for a reliable prediction of local temporal evolution of rainfall. Hydrological time series analysis is a widely studied field in hydrology, often carried out by means of autoregressive models, such as AR, ARMA, ARX, ARMAX (e.g. Salas [1992]). Such models gave the best results when applied to the analysis of autocorrelated hydrological time series, like river flow or level time series. Conversely, they are not able to model the behaviour of intermittent time series, like point rainfall height series usually are, especially when recorded with short sampling time intervals. More useful for this issue are the so-called DRIP (Disaggregated Rectangular Intensity Pulse) and NSRP (Neymann-Scott Rectangular Pulse) model [Heneker et al., 2001; Cowpertwait et al., 2002], usually adopted to generate synthetic point rainfall series. In this paper, the DRIP model approach is adopted, in which the sequence of rain storms and dry intervals constituting the structure of rainfall time series is modeled as an alternating renewal process. Final aim of the study is to provide a useful tool to implement an early warning system for hydrogeological risk management. Model calibration has been carried out with hourly rainfall hieght data provided by the rain gauges of Campania Region civil
Arbitrage, market definition and monitoring a time series approach
Burke, S; Hunter, J
2012-01-01
This article considers the application to regional price data of time series methods to test stationarity, multivariate cointegration and exogeneity. The discovery of stationary price differentials in a bivariate setting implies that the series are rendered stationary by capturing a common trend and we observe through this mechanism long-run arbitrage. This is indicative of a broader market definition and efficiency. The problem is considered in relation to more than 700 weekly data points on...
Real-time regression analysis with deep convolutional neural networks
Huerta, E. A.; George, Daniel; Zhao, Zhizhen; Allen, Gabrielle
2018-01-01
We discuss the development of novel deep learning algorithms to enable real-time regression analysis for time series data. We showcase the application of this new method with a timely case study, and then discuss the applicability of this approach to tackle similar challenges across science domains.
Time Series Analysis of Wheat Futures Reward in China
Institute of Scientific and Technical Information of China (English)
无
2005-01-01
Different from the fact that the main researches are focused on single futures contract and lack of the comparison of different periods, this paper described the statistical characteristics of wheat futures reward time series of Zhengzhou Commodity Exchange in recent three years. Besides the basic statistic analysis, the paper used the GARCH and EGARCH model to describe the time series which had the ARCH effect and analyzed the persistence of volatility shocks and the leverage effect. The results showed that compared with that of normal one,wheat futures reward series were abnormality, leptokurtic and thick tail distribution. The study also found that two-part of the reward series had no autocorrelation. Among the six correlative series, three ones presented the ARCH effect. By using of the Auto-regressive Distributed Lag Model, GARCH model and EGARCH model, the paper demonstrates the persistence of volatility shocks and the leverage effect on the wheat futures reward time series. The results reveal that on the one hand, the statistical characteristics of the wheat futures reward are similar to the aboard mature futures market as a whole. But on the other hand, the results reflect some shortages such as the immatureness and the over-control by the government in the Chinese future market.
Unstable Periodic Orbit Analysis of Histograms of Chaotic Time Series
International Nuclear Information System (INIS)
Zoldi, S.M.
1998-01-01
Using the Lorenz equations, we have investigated whether unstable periodic orbits (UPOs) associated with a strange attractor may predict the occurrence of the robust sharp peaks in histograms of some experimental chaotic time series. Histograms with sharp peaks occur for the Lorenz parameter value r=60.0 but not for r=28.0 , and the sharp peaks for r=60.0 do not correspond to a histogram derived from any single UPO. However, we show that histograms derived from the time series of a non-Axiom-A chaotic system can be accurately predicted by an escape-time weighting of UPO histograms. copyright 1998 The American Physical Society
Minimum entropy density method for the time series analysis
Lee, Jeong Won; Park, Joongwoo Brian; Jo, Hang-Hyun; Yang, Jae-Suk; Moon, Hie-Tae
2009-01-01
The entropy density is an intuitive and powerful concept to study the complicated nonlinear processes derived from physical systems. We develop the minimum entropy density method (MEDM) to detect the structure scale of a given time series, which is defined as the scale in which the uncertainty is minimized, hence the pattern is revealed most. The MEDM is applied to the financial time series of Standard and Poor’s 500 index from February 1983 to April 2006. Then the temporal behavior of structure scale is obtained and analyzed in relation to the information delivery time and efficient market hypothesis.
Multi-Scale Dissemination of Time Series Data
DEFF Research Database (Denmark)
Guo, Qingsong; Zhou, Yongluan; Su, Li
2013-01-01
In this paper, we consider the problem of continuous dissemination of time series data, such as sensor measurements, to a large number of subscribers. These subscribers fall into multiple subscription levels, where each subscription level is specified by the bandwidth constraint of a subscriber......, which is an abstract indicator for both the physical limits and the amount of data that the subscriber would like to handle. To handle this problem, we propose a system framework for multi-scale time series data dissemination that employs a typical tree-based dissemination network and existing time...
Compounding approach for univariate time series with nonstationary variances
Schäfer, Rudi; Barkhofen, Sonja; Guhr, Thomas; Stöckmann, Hans-Jürgen; Kuhl, Ulrich
2015-12-01
A defining feature of nonstationary systems is the time dependence of their statistical parameters. Measured time series may exhibit Gaussian statistics on short time horizons, due to the central limit theorem. The sample statistics for long time horizons, however, averages over the time-dependent variances. To model the long-term statistical behavior, we compound the local distribution with the distribution of its parameters. Here, we consider two concrete, but diverse, examples of such nonstationary systems: the turbulent air flow of a fan and a time series of foreign exchange rates. Our main focus is to empirically determine the appropriate parameter distribution for the compounding approach. To this end, we extract the relevant time scales by decomposing the time signals into windows and determine the distribution function of the thus obtained local variances.
A continuous-time neural model for sequential action.
Kachergis, George; Wyatte, Dean; O'Reilly, Randall C; de Kleijn, Roy; Hommel, Bernhard
2014-11-05
Action selection, planning and execution are continuous processes that evolve over time, responding to perceptual feedback as well as evolving top-down constraints. Existing models of routine sequential action (e.g. coffee- or pancake-making) generally fall into one of two classes: hierarchical models that include hand-built task representations, or heterarchical models that must learn to represent hierarchy via temporal context, but thus far lack goal-orientedness. We present a biologically motivated model of the latter class that, because it is situated in the Leabra neural architecture, affords an opportunity to include both unsupervised and goal-directed learning mechanisms. Moreover, we embed this neurocomputational model in the theoretical framework of the theory of event coding (TEC), which posits that actions and perceptions share a common representation with bidirectional associations between the two. Thus, in this view, not only does perception select actions (along with task context), but actions are also used to generate perceptions (i.e. intended effects). We propose a neural model that implements TEC to carry out sequential action control in hierarchically structured tasks such as coffee-making. Unlike traditional feedforward discrete-time neural network models, which use static percepts to generate static outputs, our biological model accepts continuous-time inputs and likewise generates non-stationary outputs, making short-timescale dynamic predictions. © 2014 The Author(s) Published by the Royal Society. All rights reserved.
Characterizing time series via complexity-entropy curves
Ribeiro, Haroldo V.; Jauregui, Max; Zunino, Luciano; Lenzi, Ervin K.
2017-06-01
The search for patterns in time series is a very common task when dealing with complex systems. This is usually accomplished by employing a complexity measure such as entropies and fractal dimensions. However, such measures usually only capture a single aspect of the system dynamics. Here, we propose a family of complexity measures for time series based on a generalization of the complexity-entropy causality plane. By replacing the Shannon entropy by a monoparametric entropy (Tsallis q entropy) and after considering the proper generalization of the statistical complexity (q complexity), we build up a parametric curve (the q -complexity-entropy curve) that is used for characterizing and classifying time series. Based on simple exact results and numerical simulations of stochastic processes, we show that these curves can distinguish among different long-range, short-range, and oscillating correlated behaviors. Also, we verify that simulated chaotic and stochastic time series can be distinguished based on whether these curves are open or closed. We further test this technique in experimental scenarios related to chaotic laser intensity, stock price, sunspot, and geomagnetic dynamics, confirming its usefulness. Finally, we prove that these curves enhance the automatic classification of time series with long-range correlations and interbeat intervals of healthy subjects and patients with heart disease.
A neuro-fuzzy computing technique for modeling hydrological time series
Nayak, P. C.; Sudheer, K. P.; Rangan, D. M.; Ramasastri, K. S.
2004-05-01
Intelligent computing tools such as artificial neural network (ANN) and fuzzy logic approaches are proven to be efficient when applied individually to a variety of problems. Recently there has been a growing interest in combining both these approaches, and as a result, neuro-fuzzy computing techniques have evolved. This approach has been tested and evaluated in the field of signal processing and related areas, but researchers have only begun evaluating the potential of this neuro-fuzzy hybrid approach in hydrologic modeling studies. This paper presents the application of an adaptive neuro fuzzy inference system (ANFIS) to hydrologic time series modeling, and is illustrated by an application to model the river flow of Baitarani River in Orissa state, India. An introduction to the ANFIS modeling approach is also presented. The advantage of the method is that it does not require the model structure to be known a priori, in contrast to most of the time series modeling techniques. The results showed that the ANFIS forecasted flow series preserves the statistical properties of the original flow series. The model showed good performance in terms of various statistical indices. The results are highly promising, and a comparative analysis suggests that the proposed modeling approach outperforms ANNs and other traditional time series models in terms of computational speed, forecast errors, efficiency, peak flow estimation etc. It was observed that the ANFIS model preserves the potential of the ANN approach fully, and eases the model building process.
Multi-granular trend detection for time-series analysis
van Goethem, A.I.; Staals, F.; Löffler, M.; Dykes, J.; Speckmann, B.
2017-01-01
Time series (such as stock prices) and ensembles (such as model runs for weather forecasts) are two important types of one-dimensional time-varying data. Such data is readily available in large quantities but visual analysis of the raw data quickly becomes infeasible, even for moderately sized data
Time Series Analysis Based on Running Mann Whitney Z Statistics
A sensitive and objective time series analysis method based on the calculation of Mann Whitney U statistics is described. This method samples data rankings over moving time windows, converts those samples to Mann-Whitney U statistics, and then normalizes the U statistics to Z statistics using Monte-...
The Photoplethismographic Signal Processed with Nonlinear Time Series Analysis Tools
International Nuclear Information System (INIS)
Hernandez Caceres, Jose Luis; Hong, Rolando; Garcia Lanz, Abel; Garcia Dominguez, Luis; Cabannas, Karelia
2001-01-01
Finger photoplethismography (PPG) signals were submitted to nonlinear time series analysis. The applied analytical techniques were: (i) High degree polynomial fitting for baseline estimation; (ii) FFT analysis for estimating power spectra; (iii) fractal dimension estimation via the Higuchi's time-domain method, and (iv) kernel nonparametric estimation for reconstructing noise free-attractors and also for estimating signal's stochastic components
FPGA-Based Stochastic Echo State Networks for Time-Series Forecasting
Directory of Open Access Journals (Sweden)
Miquel L. Alomar
2016-01-01
Full Text Available Hardware implementation of artificial neural networks (ANNs allows exploiting the inherent parallelism of these systems. Nevertheless, they require a large amount of resources in terms of area and power dissipation. Recently, Reservoir Computing (RC has arisen as a strategic technique to design recurrent neural networks (RNNs with simple learning capabilities. In this work, we show a new approach to implement RC systems with digital gates. The proposed method is based on the use of probabilistic computing concepts to reduce the hardware required to implement different arithmetic operations. The result is the development of a highly functional system with low hardware resources. The presented methodology is applied to chaotic time-series forecasting.
High-Density Liquid-State Machine Circuitry for Time-Series Forecasting.
Rosselló, Josep L; Alomar, Miquel L; Morro, Antoni; Oliver, Antoni; Canals, Vincent
2016-08-01
Spiking neural networks (SNN) are the last neural network generation that try to mimic the real behavior of biological neurons. Although most research in this area is done through software applications, it is in hardware implementations in which the intrinsic parallelism of these computing systems are more efficiently exploited. Liquid state machines (LSM) have arisen as a strategic technique to implement recurrent designs of SNN with a simple learning methodology. In this work, we show a new low-cost methodology to implement high-density LSM by using Boolean gates. The proposed method is based on the use of probabilistic computing concepts to reduce hardware requirements, thus considerably increasing the neuron count per chip. The result is a highly functional system that is applied to high-speed time series forecasting.
Wen, Dong; Xue, Qing; Lu, Chengbiao; Guan, Xinyong; Wang, Yuping; Li, Xiaoli
2014-08-01
Recently, the synchronization between neural signals has been widely used as a key indicator of brain function. To understand comprehensively the effect of synchronization on the brain function, accurate computation of the synchronization strength among multivariate neural series from the whole brain is necessary. In this study, we proposed a method named global coupling index (GCI) to estimate the synchronization strength of multiple neural signals. First of all, performance of the GCI method was evaluated by analyzing simulated EEG signals from a multi-channel neural mass model, including the effects of the frequency band, the coupling coefficient, and the signal noise ratio. Then, the GCI method was applied to analyze the EEG signals from 12 mild cognitive impairment (MCI) subjects and 12 normal controls (NC). The results showed that GCI method had two major advantages over the global synchronization index (GSI) or S-estimator. Firstly, simulation data showed that the GCI method provided both a more robust result on the frequency band and a better performance on the coupling coefficients. Secondly, the actual EEG data demonstrated that GCI method was more sensitive in differentiating the MCI from control subjects, in terms of the global synchronization strength of neural series of specific alpha, beta1 and beta2 frequency bands. Hence, it is suggested that GCI is a better method over GSI and S-estimator to estimate the synchronization strength of multivariate neural series for predicting the MCI from the whole brain EEG recordings. Copyright © 2014. Published by Elsevier Ltd.
Directory of Open Access Journals (Sweden)
Huaiqin Wu
2012-01-01
Full Text Available By combing the theories of the switched systems and the interval neural networks, the mathematics model of the switched interval neural networks with discrete and distributed time-varying delays of neural type is presented. A set of the interval parameter uncertainty neural networks with discrete and distributed time-varying delays of neural type are used as the individual subsystem, and an arbitrary switching rule is assumed to coordinate the switching between these networks. By applying the augmented Lyapunov-Krasovskii functional approach and linear matrix inequality (LMI techniques, a delay-dependent criterion is achieved to ensure to such switched interval neural networks to be globally asymptotically robustly stable in terms of LMIs. The unknown gain matrix is determined by solving this delay-dependent LMIs. Finally, an illustrative example is given to demonstrate the validity of the theoretical results.
Time Series Outlier Detection Based on Sliding Window Prediction
Directory of Open Access Journals (Sweden)
Yufeng Yu
2014-01-01
Full Text Available In order to detect outliers in hydrological time series data for improving data quality and decision-making quality related to design, operation, and management of water resources, this research develops a time series outlier detection method for hydrologic data that can be used to identify data that deviate from historical patterns. The method first built a forecasting model on the history data and then used it to predict future values. Anomalies are assumed to take place if the observed values fall outside a given prediction confidence interval (PCI, which can be calculated by the predicted value and confidence coefficient. The use of PCI as threshold is mainly on the fact that it considers the uncertainty in the data series parameters in the forecasting model to address the suitable threshold selection problem. The method performs fast, incremental evaluation of data as it becomes available, scales to large quantities of data, and requires no preclassification of anomalies. Experiments with different hydrologic real-world time series showed that the proposed methods are fast and correctly identify abnormal data and can be used for hydrologic time series analysis.
Grammar-based feature generation for time-series prediction
De Silva, Anthony Mihirana
2015-01-01
This book proposes a novel approach for time-series prediction using machine learning techniques with automatic feature generation. Application of machine learning techniques to predict time-series continues to attract considerable attention due to the difficulty of the prediction problems compounded by the non-linear and non-stationary nature of the real world time-series. The performance of machine learning techniques, among other things, depends on suitable engineering of features. This book proposes a systematic way for generating suitable features using context-free grammar. A number of feature selection criteria are investigated and a hybrid feature generation and selection algorithm using grammatical evolution is proposed. The book contains graphical illustrations to explain the feature generation process. The proposed approaches are demonstrated by predicting the closing price of major stock market indices, peak electricity load and net hourly foreign exchange client trade volume. The proposed method ...
Learning of time series through neuron-to-neuron instruction
Energy Technology Data Exchange (ETDEWEB)
Miyazaki, Y [Department of Physics, Kyoto University, Kyoto 606-8502, (Japan); Kinzel, W [Institut fuer Theoretische Physik, Universitaet Wurzburg, 97074 Wurzburg (Germany); Shinomoto, S [Department of Physics, Kyoto University, Kyoto (Japan)
2003-02-07
A model neuron with delayline feedback connections can learn a time series generated by another model neuron. It has been known that some student neurons that have completed such learning under the instruction of a teacher's quasi-periodic sequence mimic the teacher's time series over a long interval, even after instruction has ceased. We found that in addition to such faithful students, there are unfaithful students whose time series eventually diverge exponentially from that of the teacher. In order to understand the circumstances that allow for such a variety of students, the orbit dimension was estimated numerically. The quasi-periodic orbits in question were found to be confined in spaces with dimensions significantly smaller than that of the full phase space.
Learning of time series through neuron-to-neuron instruction
International Nuclear Information System (INIS)
Miyazaki, Y; Kinzel, W; Shinomoto, S
2003-01-01
A model neuron with delayline feedback connections can learn a time series generated by another model neuron. It has been known that some student neurons that have completed such learning under the instruction of a teacher's quasi-periodic sequence mimic the teacher's time series over a long interval, even after instruction has ceased. We found that in addition to such faithful students, there are unfaithful students whose time series eventually diverge exponentially from that of the teacher. In order to understand the circumstances that allow for such a variety of students, the orbit dimension was estimated numerically. The quasi-periodic orbits in question were found to be confined in spaces with dimensions significantly smaller than that of the full phase space
Time series analysis and its applications with R examples
Shumway, Robert H
2017-01-01
The fourth edition of this popular graduate textbook, like its predecessors, presents a balanced and comprehensive treatment of both time and frequency domain methods with accompanying theory. Numerous examples using nontrivial data illustrate solutions to problems such as discovering natural and anthropogenic climate change, evaluating pain perception experiments using functional magnetic resonance imaging, and monitoring a nuclear test ban treaty. The book is designed as a textbook for graduate level students in the physical, biological, and social sciences and as a graduate level text in statistics. Some parts may also serve as an undergraduate introductory course. Theory and methodology are separated to allow presentations on different levels. In addition to coverage of classical methods of time series regression, ARIMA models, spectral analysis and state-space models, the text includes modern developments including categorical time series analysis, multivariate spectral methods, long memory series, nonli...
Nonlinear time series analysis of the human electrocardiogram
International Nuclear Information System (INIS)
Perc, Matjaz
2005-01-01
We analyse the human electrocardiogram with simple nonlinear time series analysis methods that are appropriate for graduate as well as undergraduate courses. In particular, attention is devoted to the notions of determinism and stationarity in physiological data. We emphasize that methods of nonlinear time series analysis can be successfully applied only if the studied data set originates from a deterministic stationary system. After positively establishing the presence of determinism and stationarity in the studied electrocardiogram, we calculate the maximal Lyapunov exponent, thus providing interesting insights into the dynamics of the human heart. Moreover, to facilitate interest and enable the integration of nonlinear time series analysis methods into the curriculum at an early stage of the educational process, we also provide user-friendly programs for each implemented method
Sensitivity analysis of machine-learning models of hydrologic time series
O'Reilly, A. M.
2017-12-01
Sensitivity analysis traditionally has been applied to assessing model response to perturbations in model parameters, where the parameters are those model input variables adjusted during calibration. Unlike physics-based models where parameters represent real phenomena, the equivalent of parameters for machine-learning models are simply mathematical "knobs" that are automatically adjusted during training/testing/verification procedures. Thus the challenge of extracting knowledge of hydrologic system functionality from machine-learning models lies in their very nature, leading to the label "black box." Sensitivity analysis of the forcing-response behavior of machine-learning models, however, can provide understanding of how the physical phenomena represented by model inputs affect the physical phenomena represented by model outputs.As part of a previous study, hybrid spectral-decomposition artificial neural network (ANN) models were developed to simulate the observed behavior of hydrologic response contained in multidecadal datasets of lake water level, groundwater level, and spring flow. Model inputs used moving window averages (MWA) to represent various frequencies and frequency-band components of time series of rainfall and groundwater use. Using these forcing time series, the MWA-ANN models were trained to predict time series of lake water level, groundwater level, and spring flow at 51 sites in central Florida, USA. A time series of sensitivities for each MWA-ANN model was produced by perturbing forcing time-series and computing the change in response time-series per unit change in perturbation. Variations in forcing-response sensitivities are evident between types (lake, groundwater level, or spring), spatially (among sites of the same type), and temporally. Two generally common characteristics among sites are more uniform sensitivities to rainfall over time and notable increases in sensitivities to groundwater usage during significant drought periods.
The string prediction models as an invariants of time series in forex market
Richard Pincak; Marian Repasan
2011-01-01
In this paper we apply a new approach of the string theory to the real financial market. It is direct extension and application of the work [1] into prediction of prices. The models are constructed with an idea of prediction models based on the string invariants (PMBSI). The performance of PMBSI is compared to support vector machines (SVM) and artificial neural networks (ANN) on an artificial and a financial time series. Brief overview of the results and analysis is given. The first model is ...
Nguyen, Hien D; Ullmann, Jeremy F P; McLachlan, Geoffrey J; Voleti, Venkatakaushik; Li, Wenze; Hillman, Elizabeth M C; Reutens, David C; Janke, Andrew L
2018-02-01
Calcium is a ubiquitous messenger in neural signaling events. An increasing number of techniques are enabling visualization of neurological activity in animal models via luminescent proteins that bind to calcium ions. These techniques generate large volumes of spatially correlated time series. A model-based functional data analysis methodology via Gaussian mixtures is suggested for the clustering of data from such visualizations is proposed. The methodology is theoretically justified and a computationally efficient approach to estimation is suggested. An example analysis of a zebrafish imaging experiment is presented.
A multidisciplinary database for geophysical time series management
Montalto, P.; Aliotta, M.; Cassisi, C.; Prestifilippo, M.; Cannata, A.
2013-12-01
The variables collected by a sensor network constitute a heterogeneous data source that needs to be properly organized in order to be used in research and geophysical monitoring. With the time series term we refer to a set of observations of a given phenomenon acquired sequentially in time. When the time intervals are equally spaced one speaks of period or sampling frequency. Our work describes in detail a possible methodology for storage and management of time series using a specific data structure. We designed a framework, hereinafter called TSDSystem (Time Series Database System), in order to acquire time series from different data sources and standardize them within a relational database. The operation of standardization provides the ability to perform operations, such as query and visualization, of many measures synchronizing them using a common time scale. The proposed architecture follows a multiple layer paradigm (Loaders layer, Database layer and Business Logic layer). Each layer is specialized in performing particular operations for the reorganization and archiving of data from different sources such as ASCII, Excel, ODBC (Open DataBase Connectivity), file accessible from the Internet (web pages, XML). In particular, the loader layer performs a security check of the working status of each running software through an heartbeat system, in order to automate the discovery of acquisition issues and other warning conditions. Although our system has to manage huge amounts of data, performance is guaranteed by using a smart partitioning table strategy, that keeps balanced the percentage of data stored in each database table. TSDSystem also contains modules for the visualization of acquired data, that provide the possibility to query different time series on a specified time range, or follow the realtime signal acquisition, according to a data access policy from the users.
Time to address the problems at the neural interface
Durand, Dominique M.; Ghovanloo, Maysam; Krames, Elliot
2014-04-01
Neural engineers have made significant, if not remarkable, progress in interfacing with the nervous system in the last ten years. In particular, neuromodulation of the brain has generated significant therapeutic benefits [1-5]. EEG electrodes can be used to communicate with patients with locked-in syndrome [6]. In the central nervous system (CNS), electrode arrays placed directly over or within the cortex can record neural signals related to the intent of the subject or patient [7, 8]. A similar technology has allowed paralyzed patients to control an otherwise normal skeletal system with brain signals [9, 10]. This technology has significant potential to restore function in these and other patients with neural disorders such as stroke [11]. Although there are several multichannel arrays described in the literature, the workhorse for these cortical interfaces has been the Utah array [12]. This 100-channel electrode array has been used in most studies on animals and humans since the 1990s and is commercially available. This array and other similar microelectrode arrays can record neural signals with high quality (high signal-to-noise ratio), but these signals fade and disappear after a few months and therefore the current technology is not reliable for extended periods of time. Therefore, despite these major advances in communicating with the brain, clinical translation cannot be implemented. The reasons for this failure are not known but clearly involve the interface between the electrode and the neural tissue. The Defense Advanced Research Project Agency (DARPA) as well as other federal funding agencies such as the National Science Foundation (NSF) and the National Institutes of Health have provided significant financial support to investigate this problem without much success. A recent funding program from DARPA was designed to establish the failure modes in order to generate a reliable neural interface technology and again was unsuccessful at producing a robust
Power Forecasting of Combined Heating and Cooling Systems Based on Chaotic Time Series
Directory of Open Access Journals (Sweden)
Liu Hai
2015-01-01
Full Text Available Theoretic analysis shows that the output power of the distributed generation system is nonlinear and chaotic. And it is coupled with the microenvironment meteorological data. Chaos is an inherent property of nonlinear dynamic system. A predicator of the output power of the distributed generation system is to establish a nonlinear model of the dynamic system based on real time series in the reconstructed phase space. Firstly, chaos should be detected and quantified for the intensive studies of nonlinear systems. If the largest Lyapunov exponent is positive, the dynamical system must be chaotic. Then, the embedding dimension and the delay time are chosen based on the improved C-C method. The attractor of chaotic power time series can be reconstructed based on the embedding dimension and delay time in the phase space. By now, the neural network can be trained based on the training samples, which are observed from the distributed generation system. The neural network model will approximate the curve of output power adequately. Experimental results show that the maximum power point of the distributed generation system will be predicted based on the meteorological data. The system can be controlled effectively based on the prediction.
A novel time series link prediction method: Learning automata approach
Moradabadi, Behnaz; Meybodi, Mohammad Reza
2017-09-01
Link prediction is a main social network challenge that uses the network structure to predict future links. The common link prediction approaches to predict hidden links use a static graph representation where a snapshot of the network is analyzed to find hidden or future links. For example, similarity metric based link predictions are a common traditional approach that calculates the similarity metric for each non-connected link and sort the links based on their similarity metrics and label the links with higher similarity scores as the future links. Because people activities in social networks are dynamic and uncertainty, and the structure of the networks changes over time, using deterministic graphs for modeling and analysis of the social network may not be appropriate. In the time-series link prediction problem, the time series link occurrences are used to predict the future links In this paper, we propose a new time series link prediction based on learning automata. In the proposed algorithm for each link that must be predicted there is one learning automaton and each learning automaton tries to predict the existence or non-existence of the corresponding link. To predict the link occurrence in time T, there is a chain consists of stages 1 through T - 1 and the learning automaton passes from these stages to learn the existence or non-existence of the corresponding link. Our preliminary link prediction experiments with co-authorship and email networks have provided satisfactory results when time series link occurrences are considered.
Time series patterns and language support in DBMS
Telnarova, Zdenka
2017-07-01
This contribution is focused on pattern type Time Series as a rich in semantics representation of data. Some example of implementation of this pattern type in traditional Data Base Management Systems is briefly presented. There are many approaches how to manipulate with patterns and query patterns. Crucial issue can be seen in systematic approach to pattern management and specific pattern query language which takes into consideration semantics of patterns. Query language SQL-TS for manipulating with patterns is shown on Time Series data.
Testing for intracycle determinism in pseudoperiodic time series.
Coelho, Mara C S; Mendes, Eduardo M A M; Aguirre, Luis A
2008-06-01
A determinism test is proposed based on the well-known method of the surrogate data. Assuming predictability to be a signature of determinism, the proposed method checks for intracycle (e.g., short-term) determinism in the pseudoperiodic time series for which standard methods of surrogate analysis do not apply. The approach presented is composed of two steps. First, the data are preprocessed to reduce the effects of seasonal and trend components. Second, standard tests of surrogate analysis can then be used. The determinism test is applied to simulated and experimental pseudoperiodic time series and the results show the applicability of the proposed test.
Bootstrap Power of Time Series Goodness of fit tests
Directory of Open Access Journals (Sweden)
Sohail Chand
2013-10-01
Full Text Available In this article, we looked at power of various versions of Box and Pierce statistic and Cramer von Mises test. An extensive simulation study has been conducted to compare the power of these tests. Algorithms have been provided for the power calculations and comparison has also been made between the semi parametric bootstrap methods used for time series. Results show that Box-Pierce statistic and its various versions have good power against linear time series models but poor power against non linear models while situation reverses for Cramer von Mises test. Moreover, we found that dynamic bootstrap method is better than xed design bootstrap method.
Handbook of Time Series Analysis Recent Theoretical Developments and Applications
Schelter, Björn; Timmer, Jens
2006-01-01
This handbook provides an up-to-date survey of current research topics and applications of time series analysis methods written by leading experts in their fields. It covers recent developments in univariate as well as bivariate and multivariate time series analysis techniques ranging from physics' to life sciences' applications. Each chapter comprises both methodological aspects and applications to real world complex systems, such as the human brain or Earth's climate. Covering an exceptionally broad spectrum of topics, beginners, experts and practitioners who seek to understand the latest de
A Higher-Order Neural Network Design for Improving Segmentation Performance in Medical Image Series
International Nuclear Information System (INIS)
Selvi, Eşref; Selver, M Alper; Güzeliş, Cüneyt; Dicle, Oǧuz
2014-01-01
Segmentation of anatomical structures from medical image series is an ongoing field of research. Although, organs of interest are three-dimensional in nature, slice-by-slice approaches are widely used in clinical applications because of their ease of integration with the current manual segmentation scheme. To be able to use slice-by-slice techniques effectively, adjacent slice information, which represents likelihood of a region to be the structure of interest, plays critical role. Recent studies focus on using distance transform directly as a feature or to increase the feature values at the vicinity of the search area. This study presents a novel approach by constructing a higher order neural network, the input layer of which receives features together with their multiplications with the distance transform. This allows higher-order interactions between features through the non-linearity introduced by the multiplication. The application of the proposed method to 9 CT datasets for segmentation of the liver shows higher performance than well-known higher order classification neural networks
Hybrid model for forecasting time series with trend, seasonal and salendar variation patterns
Suhartono; Rahayu, S. P.; Prastyo, D. D.; Wijayanti, D. G. P.; Juliyanto
2017-09-01
Most of the monthly time series data in economics and business in Indonesia and other Moslem countries not only contain trend and seasonal, but also affected by two types of calendar variation effects, i.e. the effect of the number of working days or trading and holiday effects. The purpose of this research is to develop a hybrid model or a combination of several forecasting models to predict time series that contain trend, seasonal and calendar variation patterns. This hybrid model is a combination of classical models (namely time series regression and ARIMA model) and/or modern methods (artificial intelligence method, i.e. Artificial Neural Networks). A simulation study was used to show that the proposed procedure for building the hybrid model could work well for forecasting time series with trend, seasonal and calendar variation patterns. Furthermore, the proposed hybrid model is applied for forecasting real data, i.e. monthly data about inflow and outflow of currency at Bank Indonesia. The results show that the hybrid model tend to provide more accurate forecasts than individual forecasting models. Moreover, this result is also in line with the third results of the M3 competition, i.e. the hybrid model on average provides a more accurate forecast than the individual model.
Robust and Adaptive Online Time Series Prediction with Long Short-Term Memory
Directory of Open Access Journals (Sweden)
Haimin Yang
2017-01-01
Full Text Available Online time series prediction is the mainstream method in a wide range of fields, ranging from speech analysis and noise cancelation to stock market analysis. However, the data often contains many outliers with the increasing length of time series in real world. These outliers can mislead the learned model if treated as normal points in the process of prediction. To address this issue, in this paper, we propose a robust and adaptive online gradient learning method, RoAdam (Robust Adam, for long short-term memory (LSTM to predict time series with outliers. This method tunes the learning rate of the stochastic gradient algorithm adaptively in the process of prediction, which reduces the adverse effect of outliers. It tracks the relative prediction error of the loss function with a weighted average through modifying Adam, a popular stochastic gradient method algorithm for training deep neural networks. In our algorithm, the large value of the relative prediction error corresponds to a small learning rate, and vice versa. The experiments on both synthetic data and real time series show that our method achieves better performance compared to the existing methods based on LSTM.
Robust and Adaptive Online Time Series Prediction with Long Short-Term Memory.
Yang, Haimin; Pan, Zhisong; Tao, Qing
2017-01-01
Online time series prediction is the mainstream method in a wide range of fields, ranging from speech analysis and noise cancelation to stock market analysis. However, the data often contains many outliers with the increasing length of time series in real world. These outliers can mislead the learned model if treated as normal points in the process of prediction. To address this issue, in this paper, we propose a robust and adaptive online gradient learning method, RoAdam (Robust Adam), for long short-term memory (LSTM) to predict time series with outliers. This method tunes the learning rate of the stochastic gradient algorithm adaptively in the process of prediction, which reduces the adverse effect of outliers. It tracks the relative prediction error of the loss function with a weighted average through modifying Adam, a popular stochastic gradient method algorithm for training deep neural networks. In our algorithm, the large value of the relative prediction error corresponds to a small learning rate, and vice versa. The experiments on both synthetic data and real time series show that our method achieves better performance compared to the existing methods based on LSTM.
EEG Eye State Identification Using Incremental Attribute Learning with Time-Series Classification
Directory of Open Access Journals (Sweden)
Ting Wang
2014-01-01
Full Text Available Eye state identification is a kind of common time-series classification problem which is also a hot spot in recent research. Electroencephalography (EEG is widely used in eye state classification to detect human's cognition state. Previous research has validated the feasibility of machine learning and statistical approaches for EEG eye state classification. This paper aims to propose a novel approach for EEG eye state identification using incremental attribute learning (IAL based on neural networks. IAL is a novel machine learning strategy which gradually imports and trains features one by one. Previous studies have verified that such an approach is applicable for solving a number of pattern recognition problems. However, in these previous works, little research on IAL focused on its application to time-series problems. Therefore, it is still unknown whether IAL can be employed to cope with time-series problems like EEG eye state classification. Experimental results in this study demonstrates that, with proper feature extraction and feature ordering, IAL can not only efficiently cope with time-series classification problems, but also exhibit better classification performance in terms of classification error rates in comparison with conventional and some other approaches.
Quantifying Selection with Pool-Seq Time Series Data.
Taus, Thomas; Futschik, Andreas; Schlötterer, Christian
2017-11-01
Allele frequency time series data constitute a powerful resource for unraveling mechanisms of adaptation, because the temporal dimension captures important information about evolutionary forces. In particular, Evolve and Resequence (E&R), the whole-genome sequencing of replicated experimentally evolving populations, is becoming increasingly popular. Based on computer simulations several studies proposed experimental parameters to optimize the identification of the selection targets. No such recommendations are available for the underlying parameters selection strength and dominance. Here, we introduce a highly accurate method to estimate selection parameters from replicated time series data, which is fast enough to be applied on a genome scale. Using this new method, we evaluate how experimental parameters can be optimized to obtain the most reliable estimates for selection parameters. We show that the effective population size (Ne) and the number of replicates have the largest impact. Because the number of time points and sequencing coverage had only a minor effect, we suggest that time series analysis is feasible without major increase in sequencing costs. We anticipate that time series analysis will become routine in E&R studies. © The Author 2017. Published by Oxford University Press on behalf of the Society for Molecular Biology and Evolution.
A window-based time series feature extraction method.
Katircioglu-Öztürk, Deniz; Güvenir, H Altay; Ravens, Ursula; Baykal, Nazife
2017-10-01
This study proposes a robust similarity score-based time series feature extraction method that is termed as Window-based Time series Feature ExtraCtion (WTC). Specifically, WTC generates domain-interpretable results and involves significantly low computational complexity thereby rendering itself useful for densely sampled and populated time series datasets. In this study, WTC is applied to a proprietary action potential (AP) time series dataset on human cardiomyocytes and three precordial leads from a publicly available electrocardiogram (ECG) dataset. This is followed by comparing WTC in terms of predictive accuracy and computational complexity with shapelet transform and fast shapelet transform (which constitutes an accelerated variant of the shapelet transform). The results indicate that WTC achieves a slightly higher classification performance with significantly lower execution time when compared to its shapelet-based alternatives. With respect to its interpretable features, WTC has a potential to enable medical experts to explore definitive common trends in novel datasets. Copyright © 2017 Elsevier Ltd. All rights reserved.
Stochastic generation of hourly wind speed time series
International Nuclear Information System (INIS)
Shamshad, A.; Wan Mohd Ali Wan Hussin; Bawadi, M.A.; Mohd Sanusi, S.A.
2006-01-01
In the present study hourly wind speed data of Kuala Terengganu in Peninsular Malaysia are simulated by using transition matrix approach of Markovian process. The wind speed time series is divided into various states based on certain criteria. The next wind speed states are selected based on the previous states. The cumulative probability transition matrix has been formed in which each row ends with 1. Using the uniform random numbers between 0 and 1, a series of future states is generated. These states have been converted to the corresponding wind speed values using another uniform random number generator. The accuracy of the model has been determined by comparing the statistical characteristics such as average, standard deviation, root mean square error, probability density function and autocorrelation function of the generated data to those of the original data. The generated wind speed time series data is capable to preserve the wind speed characteristics of the observed data
Segmentation of time series with long-range fractal correlations
Bernaola-Galván, P.; Oliver, J.L.; Hackenberg, M.; Coronado, A.V.; Ivanov, P.Ch.; Carpena, P.
2012-01-01
Segmentation is a standard method of data analysis to identify change-points dividing a nonstationary time series into homogeneous segments. However, for long-range fractal correlated series, most of the segmentation techniques detect spurious change-points which are simply due to the heterogeneities induced by the correlations and not to real nonstationarities. To avoid this oversegmentation, we present a segmentation algorithm which takes as a reference for homogeneity, instead of a random i.i.d. series, a correlated series modeled by a fractional noise with the same degree of correlations as the series to be segmented. We apply our algorithm to artificial series with long-range correlations and show that it systematically detects only the change-points produced by real nonstationarities and not those created by the correlations of the signal. Further, we apply the method to the sequence of the long arm of human chromosome 21, which is known to have long-range fractal correlations. We obtain only three segments that clearly correspond to the three regions of different G + C composition revealed by means of a multi-scale wavelet plot. Similar results have been obtained when segmenting all human chromosome sequences, showing the existence of previously unknown huge compositional superstructures in the human genome. PMID:23645997
Segmentation of time series with long-range fractal correlations.
Bernaola-Galván, P; Oliver, J L; Hackenberg, M; Coronado, A V; Ivanov, P Ch; Carpena, P
2012-06-01
Segmentation is a standard method of data analysis to identify change-points dividing a nonstationary time series into homogeneous segments. However, for long-range fractal correlated series, most of the segmentation techniques detect spurious change-points which are simply due to the heterogeneities induced by the correlations and not to real nonstationarities. To avoid this oversegmentation, we present a segmentation algorithm which takes as a reference for homogeneity, instead of a random i.i.d. series, a correlated series modeled by a fractional noise with the same degree of correlations as the series to be segmented. We apply our algorithm to artificial series with long-range correlations and show that it systematically detects only the change-points produced by real nonstationarities and not those created by the correlations of the signal. Further, we apply the method to the sequence of the long arm of human chromosome 21, which is known to have long-range fractal correlations. We obtain only three segments that clearly correspond to the three regions of different G + C composition revealed by means of a multi-scale wavelet plot. Similar results have been obtained when segmenting all human chromosome sequences, showing the existence of previously unknown huge compositional superstructures in the human genome.
Neural Computations in a Dynamical System with Multiple Time Scales
Directory of Open Access Journals (Sweden)
Yuanyuan Mi
2016-09-01
Full Text Available Neural systems display rich short-term dynamics at various levels, e.g., spike-frequencyadaptation (SFA at single neurons, and short-term facilitation (STF and depression (STDat neuronal synapses. These dynamical features typically covers a broad range of time scalesand exhibit large diversity in different brain regions. It remains unclear what the computationalbenefit for the brain to have such variability in short-term dynamics is. In this study, we proposethat the brain can exploit such dynamical features to implement multiple seemingly contradictorycomputations in a single neural circuit. To demonstrate this idea, we use continuous attractorneural network (CANN as a working model and include STF, SFA and STD with increasing timeconstants in their dynamics. Three computational tasks are considered, which are persistent activity,adaptation, and anticipative tracking. These tasks require conflicting neural mechanisms, andhence cannot be implemented by a single dynamical feature or any combination with similar timeconstants. However, with properly coordinated STF, SFA and STD, we show that the network isable to implement the three computational tasks concurrently. We hope this study will shed lighton the understanding of how the brain orchestrates its rich dynamics at various levels to realizediverse cognitive functions.
Finite time convergent learning law for continuous neural networks.
Chairez, Isaac
2014-02-01
This paper addresses the design of a discontinuous finite time convergent learning law for neural networks with continuous dynamics. The neural network was used here to obtain a non-parametric model for uncertain systems described by a set of ordinary differential equations. The source of uncertainties was the presence of some external perturbations and poor knowledge of the nonlinear function describing the system dynamics. A new adaptive algorithm based on discontinuous algorithms was used to adjust the weights of the neural network. The adaptive algorithm was derived by means of a non-standard Lyapunov function that is lower semi-continuous and differentiable in almost the whole space. A compensator term was included in the identifier to reject some specific perturbations using a nonlinear robust algorithm. Two numerical examples demonstrated the improvements achieved by the learning algorithm introduced in this paper compared to classical schemes with continuous learning methods. The first one dealt with a benchmark problem used in the paper to explain how the discontinuous learning law works. The second one used the methane production model to show the benefits in engineering applications of the learning law proposed in this paper. Copyright © 2013 Elsevier Ltd. All rights reserved.
Ocean time-series near Bermuda: Hydrostation S and the US JGOFS Bermuda Atlantic time-series study
Michaels, Anthony F.; Knap, Anthony H.
1992-01-01
Bermuda is the site of two ocean time-series programs. At Hydrostation S, the ongoing biweekly profiles of temperature, salinity and oxygen now span 37 years. This is one of the longest open-ocean time-series data sets and provides a view of decadal scale variability in ocean processes. In 1988, the U.S. JGOFS Bermuda Atlantic Time-series Study began a wide range of measurements at a frequency of 14-18 cruises each year to understand temporal variability in ocean biogeochemistry. On each cruise, the data range from chemical analyses of discrete water samples to data from electronic packages of hydrographic and optics sensors. In addition, a range of biological and geochemical rate measurements are conducted that integrate over time-periods of minutes to days. This sampling strategy yields a reasonable resolution of the major seasonal patterns and of decadal scale variability. The Sargasso Sea also has a variety of episodic production events on scales of days to weeks and these are only poorly resolved. In addition, there is a substantial amount of mesoscale variability in this region and some of the perceived temporal patterns are caused by the intersection of the biweekly sampling with the natural spatial variability. In the Bermuda time-series programs, we have added a series of additional cruises to begin to assess these other sources of variation and their impacts on the interpretation of the main time-series record. However, the adequate resolution of higher frequency temporal patterns will probably require the introduction of new sampling strategies and some emerging technologies such as biogeochemical moorings and autonomous underwater vehicles.
Complexity analysis of the turbulent environmental fluid flow time series
Mihailović, D. T.; Nikolić-Đorić, E.; Drešković, N.; Mimić, G.
2014-02-01
We have used the Kolmogorov complexities, sample and permutation entropies to quantify the randomness degree in river flow time series of two mountain rivers in Bosnia and Herzegovina, representing the turbulent environmental fluid, for the period 1926-1990. In particular, we have examined the monthly river flow time series from two rivers (the Miljacka and the Bosnia) in the mountain part of their flow and then calculated the Kolmogorov complexity (KL) based on the Lempel-Ziv Algorithm (LZA) (lower-KLL and upper-KLU), sample entropy (SE) and permutation entropy (PE) values for each time series. The results indicate that the KLL, KLU, SE and PE values in two rivers are close to each other regardless of the amplitude differences in their monthly flow rates. We have illustrated the changes in mountain river flow complexity by experiments using (i) the data set for the Bosnia River and (ii) anticipated human activities and projected climate changes. We have explored the sensitivity of considered measures in dependence on the length of time series. In addition, we have divided the period 1926-1990 into three subintervals: (a) 1926-1945, (b) 1946-1965, (c) 1966-1990, and calculated the KLL, KLU, SE, PE values for the various time series in these subintervals. It is found that during the period 1946-1965, there is a decrease in their complexities, and corresponding changes in the SE and PE, in comparison to the period 1926-1990. This complexity loss may be primarily attributed to (i) human interventions, after the Second World War, on these two rivers because of their use for water consumption and (ii) climate change in recent times.
Outlier detection algorithms for least squares time series regression
DEFF Research Database (Denmark)
Johansen, Søren; Nielsen, Bent
We review recent asymptotic results on some robust methods for multiple regression. The regressors include stationary and non-stationary time series as well as polynomial terms. The methods include the Huber-skip M-estimator, 1-step Huber-skip M-estimators, in particular the Impulse Indicator Sat...
Tempered fractional time series model for turbulence in geophysical flows
Meerschaert, Mark M.; Sabzikar, Farzad; Phanikumar, Mantha S.; Zeleke, Aklilu
2014-09-01
We propose a new time series model for velocity data in turbulent flows. The new model employs tempered fractional calculus to extend the classical 5/3 spectral model of Kolmogorov. Application to wind speed and water velocity in a large lake are presented, to demonstrate the practical utility of the model.
Tempered fractional time series model for turbulence in geophysical flows
International Nuclear Information System (INIS)
Meerschaert, Mark M; Sabzikar, Farzad; Phanikumar, Mantha S; Zeleke, Aklilu
2014-01-01
We propose a new time series model for velocity data in turbulent flows. The new model employs tempered fractional calculus to extend the classical 5/3 spectral model of Kolmogorov. Application to wind speed and water velocity in a large lake are presented, to demonstrate the practical utility of the model. (paper)
Classical pooling of cross-section and time series data
International Nuclear Information System (INIS)
Nuamah, N.N.N.N.
2000-04-01
This paper discusses the classical pooling of cross-section and time series data. The re-expressions of the normal equations of this model are given to indicate the source of the paradox that arises in the estimation of the regression coefficient. (author)
Time series analysis in chaotic diode resonator circuit
Energy Technology Data Exchange (ETDEWEB)
Hanias, M.P. [TEI of Chalkis, GR 34400, Evia, Chalkis (Greece)] e-mail: mhanias@teihal.gr; Giannaris, G. [TEI of Chalkis, GR 34400, Evia, Chalkis (Greece); Spyridakis, A. [TEI of Chalkis, GR 34400, Evia, Chalkis (Greece); Rigas, A. [TEI of Chalkis, GR 34400, Evia, Chalkis (Greece)
2006-01-01
A diode resonator chaotic circuit is presented. Multisim is used to simulate the circuit and show the presence of chaos. Time series analysis performed by the method proposed by Grasberger and Procaccia. The correlation and minimum embedding dimension {nu} and m {sub min}, respectively, were calculated. Also the corresponding Kolmogorov entropy was calculated.
Time series analysis in chaotic diode resonator circuit
International Nuclear Information System (INIS)
Hanias, M.P.; Giannaris, G.; Spyridakis, A.; Rigas, A.
2006-01-01
A diode resonator chaotic circuit is presented. Multisim is used to simulate the circuit and show the presence of chaos. Time series analysis performed by the method proposed by Grasberger and Procaccia. The correlation and minimum embedding dimension ν and m min , respectively, were calculated. Also the corresponding Kolmogorov entropy was calculated
Time Series Factor Analysis with an Application to Measuring Money
Gilbert, Paul D.; Meijer, Erik
2005-01-01
Time series factor analysis (TSFA) and its associated statistical theory is developed. Unlike dynamic factor analysis (DFA), TSFA obviates the need for explicitly modeling the process dynamics of the underlying phenomena. It also differs from standard factor analysis (FA) in important respects: the
Time series analysis of monthly pulpwood use in the Northeast
James T. Bones
1980-01-01
Time series analysis was used to develop a model that depicts pulpwood use in the Northeast. The model is useful in forecasting future pulpwood requirements (short term) or monitoring pulpwood-use activity in relation to past use patterns. The model predicted a downturn in use during 1980.
Dynamic Factor Analysis of Nonstationary Multivariate Time Series.
Molenaar, Peter C. M.; And Others
1992-01-01
The dynamic factor model proposed by P. C. Molenaar (1985) is exhibited, and a dynamic nonstationary factor model (DNFM) is constructed with latent factor series that have time-varying mean functions. The use of a DNFM is illustrated using data from a television viewing habits study. (SLD)
Single-Index Additive Vector Autoregressive Time Series Models
LI, YEHUA; GENTON, MARC G.
2009-01-01
We study a new class of nonlinear autoregressive models for vector time series, where the current vector depends on single-indexes defined on the past lags and the effects of different lags have an additive form. A sufficient condition is provided
Daily time series evapotranspiration maps for Oklahoma and Texas panhandle
Evapotranspiration (ET) is an important process in ecosystems’ water budget and closely linked to its productivity. Therefore, regional scale daily time series ET maps developed at high and medium resolutions have large utility in studying the carbon-energy-water nexus and managing water resources. ...
United States forest disturbance trends observed with landsat time series
Jeffrey G. Masek; Samuel N. Goward; Robert E. Kennedy; Warren B. Cohen; Gretchen G. Moisen; Karen Schleweiss; Chengquan. Huang
2013-01-01
Disturbance events strongly affect the composition, structure, and function of forest ecosystems; however, existing US land management inventories were not designed to monitor disturbance. To begin addressing this gap, the North American Forest Dynamics (NAFD) project has examined a geographic sample of 50 Landsat satellite image time series to assess trends in forest...
Koopman Operator Framework for Time Series Modeling and Analysis
Surana, Amit
2018-01-01
We propose an interdisciplinary framework for time series classification, forecasting, and anomaly detection by combining concepts from Koopman operator theory, machine learning, and linear systems and control theory. At the core of this framework is nonlinear dynamic generative modeling of time series using the Koopman operator which is an infinite-dimensional but linear operator. Rather than working with the underlying nonlinear model, we propose two simpler linear representations or model forms based on Koopman spectral properties. We show that these model forms are invariants of the generative model and can be readily identified directly from data using techniques for computing Koopman spectral properties without requiring the explicit knowledge of the generative model. We also introduce different notions of distances on the space of such model forms which is essential for model comparison/clustering. We employ the space of Koopman model forms equipped with distance in conjunction with classical machine learning techniques to develop a framework for automatic feature generation for time series classification. The forecasting/anomaly detection framework is based on using Koopman model forms along with classical linear systems and control approaches. We demonstrate the proposed framework for human activity classification, and for time series forecasting/anomaly detection in power grid application.
Time series analysis in astronomy: Limits and potentialities
DEFF Research Database (Denmark)
Vio, R.; Kristensen, N.R.; Madsen, Henrik
2005-01-01
In this paper we consider the problem of the limits concerning the physical information that can be extracted from the analysis of one or more time series ( light curves) typical of astrophysical objects. On the basis of theoretical considerations and numerical simulations, we show that with no a...
Time Series Analysis of 3D Coordinates Using Nonstochastic Observations
Velsink, H.
2016-01-01
Adjustment and testing of a combination of stochastic and nonstochastic observations is applied to the deformation analysis of a time series of 3D coordinates. Nonstochastic observations are constant values that are treated as if they were observations. They are used to formulate constraints on
Time Series Analysis of 3D Coordinates Using Nonstochastic Observations
Hiddo Velsink
2016-01-01
From the article: Abstract Adjustment and testing of a combination of stochastic and nonstochastic observations is applied to the deformation analysis of a time series of 3D coordinates. Nonstochastic observations are constant values that are treated as if they were observations. They are used to
A Hybrid Joint Moment Ratio Test for Financial Time Series
P.A. Groenendijk (Patrick); A. Lucas (André); C.G. de Vries (Casper)
1998-01-01
textabstractWe advocate the use of absolute moment ratio statistics in conjunction with standard variance ratio statistics in order to disentangle linear dependence, non-linear dependence, and leptokurtosis in financial time series. Both statistics are computed for multiple return horizons
Time Series, Stochastic Processes and Completeness of Quantum Theory
International Nuclear Information System (INIS)
Kupczynski, Marian
2011-01-01
Most of physical experiments are usually described as repeated measurements of some random variables. Experimental data registered by on-line computers form time series of outcomes. The frequencies of different outcomes are compared with the probabilities provided by the algorithms of quantum theory (QT). In spite of statistical predictions of QT a claim was made that it provided the most complete description of the data and of the underlying physical phenomena. This claim could be easily rejected if some fine structures, averaged out in the standard descriptive statistical analysis, were found in time series of experimental data. To search for these structures one has to use more subtle statistical tools which were developed to study time series produced by various stochastic processes. In this talk we review some of these tools. As an example we show how the standard descriptive statistical analysis of the data is unable to reveal a fine structure in a simulated sample of AR (2) stochastic process. We emphasize once again that the violation of Bell inequalities gives no information on the completeness or the non locality of QT. The appropriate way to test the completeness of quantum theory is to search for fine structures in time series of the experimental data by means of the purity tests or by studying the autocorrelation and partial autocorrelation functions.
factor high order fuzzy time series with applications to temperature
African Journals Online (AJOL)
HOD
In this paper, a novel two – factor high – order fuzzy time series forecasting method based on .... to balance between local and global exploitations of the swarms. While, .... Although, there were a number of outliers but, the spread at the spot in ...
RADON CONCENTRATION TIME SERIES MODELING AND APPLICATION DISCUSSION.
Stránský, V; Thinová, L
2017-11-01
In the year 2010 a continual radon measurement was established at Mladeč Caves in the Czech Republic using a continual radon monitor RADIM3A. In order to model radon time series in the years 2010-15, the Box-Jenkins Methodology, often used in econometrics, was applied. Because of the behavior of radon concentrations (RCs), a seasonal integrated, autoregressive moving averages model with exogenous variables (SARIMAX) has been chosen to model the measured time series. This model uses the time series seasonality, previously acquired values and delayed atmospheric parameters, to forecast RC. The developed model for RC time series is called regARIMA(5,1,3). Model residuals could be retrospectively compared with seismic evidence of local or global earthquakes, which occurred during the RCs measurement. This technique enables us to asses if continuously measured RC could serve an earthquake precursor. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.
Identification of human operator performance models utilizing time series analysis
Holden, F. M.; Shinners, S. M.
1973-01-01
The results of an effort performed by Sperry Systems Management Division for AMRL in applying time series analysis as a tool for modeling the human operator are presented. This technique is utilized for determining the variation of the human transfer function under various levels of stress. The human operator's model is determined based on actual input and output data from a tracking experiment.
Notes on economic time series analysis system theoretic perspectives
Aoki, Masanao
1983-01-01
In seminars and graduate level courses I have had several opportunities to discuss modeling and analysis of time series with economists and economic graduate students during the past several years. These experiences made me aware of a gap between what economic graduate students are taught about vector-valued time series and what is available in recent system literature. Wishing to fill or narrow the gap that I suspect is more widely spread than my personal experiences indicate, I have written these notes to augment and reor ganize materials I have given in these courses and seminars. I have endeavored to present, in as much a self-contained way as practicable, a body of results and techniques in system theory that I judge to be relevant and useful to economists interested in using time series in their research. I have essentially acted as an intermediary and interpreter of system theoretic results and perspectives in time series by filtering out non-essential details, and presenting coherent accounts of wha...
Book Review: "Hidden Markov Models for Time Series: An ...
African Journals Online (AJOL)
Hidden Markov Models for Time Series: An Introduction using R. by Walter Zucchini and Iain L. MacDonald. Chapman & Hall (CRC Press), 2009. Full Text: EMAIL FULL TEXT EMAIL FULL TEXT · DOWNLOAD FULL TEXT DOWNLOAD FULL TEXT · http://dx.doi.org/10.4314/saaj.v10i1.61717 · AJOL African Journals Online.
Long-memory time series theory and methods
Palma, Wilfredo
2007-01-01
Wilfredo Palma, PhD, is Chairman and Professor of Statistics in the Department of Statistics at Pontificia Universidad Católica de Chile. Dr. Palma has published several refereed articles and has received over a dozen academic honors and awards. His research interests include time series analysis, prediction theory, state space systems, linear models, and econometrics.
ISO 9000 Series Certification Over Time: what have we learnt?
A. van der Wiele (Ton); A.M. Brown (Alan)
2002-01-01
textabstractThe ISO 9000 experiences of the same sample of organisations over a five year time period is examined in this paper. The responses to a questionnaire sent out at the end of 1999 to companies which had a reasonably long term experience with the ISO 9000 series quality system are analysed.
Detection of "noisy" chaos in a time series
DEFF Research Database (Denmark)
Chon, K H; Kanters, J K; Cohen, R J
1997-01-01
Time series from biological system often displays fluctuations in the measured variables. Much effort has been directed at determining whether this variability reflects deterministic chaos, or whether it is merely "noise". The output from most biological systems is probably the result of both...
Conditional mode regression: Application to functional time series prediction
Dabo-Niang, Sophie; Laksaci, Ali
2008-01-01
We consider $\\alpha$-mixing observations and deal with the estimation of the conditional mode of a scalar response variable $Y$ given a random variable $X$ taking values in a semi-metric space. We provide a convergence rate in $L^p$ norm of the estimator. A useful and typical application to functional times series prediction is given.
Tests for nonlinearity in short stationary time series
International Nuclear Information System (INIS)
Chang, T.; Sauer, T.; Schiff, S.J.
1995-01-01
To compare direct tests for detecting determinism in chaotic time series, data from Henon, Lorenz, and Mackey--Glass equations were contaminated with various levels of additive colored noise. These data were analyzed with a variety of recently developed tests for determinism, and the results compared
Multivariate time series modeling of selected childhood diseases in ...
African Journals Online (AJOL)
This paper is focused on modeling the five most prevalent childhood diseases in Akwa Ibom State using a multivariate approach to time series. An aggregate of 78,839 reported cases of malaria, upper respiratory tract infection (URTI), Pneumonia, anaemia and tetanus were extracted from five randomly selected hospitals in ...
multivariate time series modeling of selected childhood diseases
African Journals Online (AJOL)
2016-06-17
Jun 17, 2016 ... KEYWORDS: Multivariate Approach, Pre-whitening, Vector Time Series, .... Alternatively, the process may be written in mean adjusted form as .... The AIC criterion asymptotically over estimates the order with positive probability, whereas the BIC and HQC criteria ... has the same asymptotic distribution as Ǫ.
Hierarchical time series bottom-up approach for forecast the export value in Central Java
Mahkya, D. A.; Ulama, B. S.; Suhartono
2017-10-01
The purpose of this study is Getting the best modeling and predicting the export value of Central Java using a Hierarchical Time Series. The export value is one variable injection in the economy of a country, meaning that if the export value of the country increases, the country’s economy will increase even more. Therefore, it is necessary appropriate modeling to predict the export value especially in Central Java. Export Value in Central Java are grouped into 21 commodities with each commodity has a different pattern. One approach that can be used time series is a hierarchical approach. Hierarchical Time Series is used Buttom-up. To Forecast the individual series at all levels using Autoregressive Integrated Moving Average (ARIMA), Radial Basis Function Neural Network (RBFNN), and Hybrid ARIMA-RBFNN. For the selection of the best models used Symmetric Mean Absolute Percentage Error (sMAPE). Results of the analysis showed that for the Export Value of Central Java, Bottom-up approach with Hybrid ARIMA-RBFNN modeling can be used for long-term predictions. As for the short and medium-term predictions, it can be used a bottom-up approach RBFNN modeling. Overall bottom-up approach with RBFNN modeling give the best result.
Classification of time series patterns from complex dynamic systems
Energy Technology Data Exchange (ETDEWEB)
Schryver, J.C.; Rao, N.
1998-07-01
An increasing availability of high-performance computing and data storage media at decreasing cost is making possible the proliferation of large-scale numerical databases and data warehouses. Numeric warehousing enterprises on the order of hundreds of gigabytes to terabytes are a reality in many fields such as finance, retail sales, process systems monitoring, biomedical monitoring, surveillance and transportation. Large-scale databases are becoming more accessible to larger user communities through the internet, web-based applications and database connectivity. Consequently, most researchers now have access to a variety of massive datasets. This trend will probably only continue to grow over the next several years. Unfortunately, the availability of integrated tools to explore, analyze and understand the data warehoused in these archives is lagging far behind the ability to gain access to the same data. In particular, locating and identifying patterns of interest in numerical time series data is an increasingly important problem for which there are few available techniques. Temporal pattern recognition poses many interesting problems in classification, segmentation, prediction, diagnosis and anomaly detection. This research focuses on the problem of classification or characterization of numerical time series data. Highway vehicles and their drivers are examples of complex dynamic systems (CDS) which are being used by transportation agencies for field testing to generate large-scale time series datasets. Tools for effective analysis of numerical time series in databases generated by highway vehicle systems are not yet available, or have not been adapted to the target problem domain. However, analysis tools from similar domains may be adapted to the problem of classification of numerical time series data.
A novel recurrent neural network with finite-time convergence for linear programming.
Liu, Qingshan; Cao, Jinde; Chen, Guanrong
2010-11-01
In this letter, a novel recurrent neural network based on the gradient method is proposed for solving linear programming problems. Finite-time convergence of the proposed neural network is proved by using the Lyapunov method. Compared with the existing neural networks for linear programming, the proposed neural network is globally convergent to exact optimal solutions in finite time, which is remarkable and rare in the literature of neural networks for optimization. Some numerical examples are given to show the effectiveness and excellent performance of the new recurrent neural network.
Yozgatligil, Ceylan; Aslan, Sipan; Iyigun, Cem; Batmaz, Inci
2013-04-01
This study aims to compare several imputation methods to complete the missing values of spatio-temporal meteorological time series. To this end, six imputation methods are assessed with respect to various criteria including accuracy, robustness, precision, and efficiency for artificially created missing data in monthly total precipitation and mean temperature series obtained from the Turkish State Meteorological Service. Of these methods, simple arithmetic average, normal ratio (NR), and NR weighted with correlations comprise the simple ones, whereas multilayer perceptron type neural network and multiple imputation strategy adopted by Monte Carlo Markov Chain based on expectation-maximization (EM-MCMC) are computationally intensive ones. In addition, we propose a modification on the EM-MCMC method. Besides using a conventional accuracy measure based on squared errors, we also suggest the correlation dimension (CD) technique of nonlinear dynamic time series analysis which takes spatio-temporal dependencies into account for evaluating imputation performances. Depending on the detailed graphical and quantitative analysis, it can be said that although computational methods, particularly EM-MCMC method, are computationally inefficient, they seem favorable for imputation of meteorological time series with respect to different missingness periods considering both measures and both series studied. To conclude, using the EM-MCMC algorithm for imputing missing values before conducting any statistical analyses of meteorological data will definitely decrease the amount of uncertainty and give more robust results. Moreover, the CD measure can be suggested for the performance evaluation of missing data imputation particularly with computational methods since it gives more precise results in meteorological time series.
Normalization methods in time series of platelet function assays
Van Poucke, Sven; Zhang, Zhongheng; Roest, Mark; Vukicevic, Milan; Beran, Maud; Lauwereins, Bart; Zheng, Ming-Hua; Henskens, Yvonne; Lancé, Marcus; Marcus, Abraham
2016-01-01
Abstract Platelet function can be quantitatively assessed by specific assays such as light-transmission aggregometry, multiple-electrode aggregometry measuring the response to adenosine diphosphate (ADP), arachidonic acid, collagen, and thrombin-receptor activating peptide and viscoelastic tests such as rotational thromboelastometry (ROTEM). The task of extracting meaningful statistical and clinical information from high-dimensional data spaces in temporal multivariate clinical data represented in multivariate time series is complex. Building insightful visualizations for multivariate time series demands adequate usage of normalization techniques. In this article, various methods for data normalization (z-transformation, range transformation, proportion transformation, and interquartile range) are presented and visualized discussing the most suited approach for platelet function data series. Normalization was calculated per assay (test) for all time points and per time point for all tests. Interquartile range, range transformation, and z-transformation demonstrated the correlation as calculated by the Spearman correlation test, when normalized per assay (test) for all time points. When normalizing per time point for all tests, no correlation could be abstracted from the charts as was the case when using all data as 1 dataset for normalization. PMID:27428217
Wavelet transform approach for fitting financial time series data
Ahmed, Amel Abdoullah; Ismail, Mohd Tahir
2015-10-01
This study investigates a newly developed technique; a combined wavelet filtering and VEC model, to study the dynamic relationship among financial time series. Wavelet filter has been used to annihilate noise data in daily data set of NASDAQ stock market of US, and three stock markets of Middle East and North Africa (MENA) region, namely, Egypt, Jordan, and Istanbul. The data covered is from 6/29/2001 to 5/5/2009. After that, the returns of generated series by wavelet filter and original series are analyzed by cointegration test and VEC model. The results show that the cointegration test affirms the existence of cointegration between the studied series, and there is a long-term relationship between the US, stock markets and MENA stock markets. A comparison between the proposed model and traditional model demonstrates that, the proposed model (DWT with VEC model) outperforms traditional model (VEC model) to fit the financial stock markets series well, and shows real information about these relationships among the stock markets.
Complex dynamic behaviors of oriented percolation-based financial time series and Hang Seng index
International Nuclear Information System (INIS)
Niu, Hongli; Wang, Jun
2013-01-01
Highlights: • We develop a financial time series model by two-dimensional oriented percolation system. • We investigate the statistical behaviors of returns for HSI and the financial model by chaos-exploring methods. • We forecast the phase point of reconstructed phase space by RBF neural network. -- Abstract: We develop a financial price model by the two-dimensional oriented (directed) percolation system. The oriented percolation model is a directed variant of ordinary (isotropic) percolation, and it is applied to describe the fluctuations of stock prices. In this work, we assume that the price fluctuations result from the participants’ investment attitudes toward the market, and we investigate the information spreading among the traders and the corresponding effect on the price fluctuations. We study the complex dynamic behaviors of return time series of the model by using the multiaspect chaos-exploring methods. And we also explore the corresponding behaviors of the actual market index (Hang Seng Index) for comparison. Further, we introduce the radial basic function (RBF) neural network to train and forecast the phase point of reconstructed phase space
Applications of soft computing in time series forecasting simulation and modeling techniques
Singh, Pritpal
2016-01-01
This book reports on an in-depth study of fuzzy time series (FTS) modeling. It reviews and summarizes previous research work in FTS modeling and also provides a brief introduction to other soft-computing techniques, such as artificial neural networks (ANNs), rough sets (RS) and evolutionary computing (EC), focusing on how these techniques can be integrated into different phases of the FTS modeling approach. In particular, the book describes novel methods resulting from the hybridization of FTS modeling approaches with neural networks and particle swarm optimization. It also demonstrates how a new ANN-based model can be successfully applied in the context of predicting Indian summer monsoon rainfall. Thanks to its easy-to-read style and the clear explanations of the models, the book can be used as a concise yet comprehensive reference guide to fuzzy time series modeling, and will be valuable not only for graduate students, but also for researchers and professionals working for academic, business and governmen...
On the plurality of times: disunified time and the A-series | Nefdt ...
African Journals Online (AJOL)
Then, I attempt to show that disunified time is a problem for a semantics based on the A-series since A-truthmakers are hard to come by in a universe of temporally disconnected time-series. Finally, I provide a novel argument showing that presentists should be particularly fearful of such a universe. South African Journal of ...
Neural Networks for Time Perception and Working Memory
Üstün, Sertaç; Kale, Emre H.; Çiçek, Metehan
2017-01-01
Time is an important concept which determines most human behaviors, however questions remain about how time is perceived and which areas of the brain are responsible for time perception. The aim of this study was to evaluate the relationship between time perception and working memory in healthy adults. Functional magnetic resonance imaging (fMRI) was used during the application of a visual paradigm. In all of the conditions, the participants were presented with a moving black rectangle on a gray screen. The rectangle was obstructed by a black bar for a time period and then reappeared again. During different conditions, participants (n = 15, eight male) responded according to the instructions they were given, including details about time and the working memory or dual task requirements. The results showed activations in right dorsolateral prefrontal and right intraparietal cortical networks, together with the anterior cingulate cortex (ACC), anterior insula and basal ganglia (BG) during time perception. On the other hand, working memory engaged the left prefrontal cortex, ACC, left superior parietal cortex, BG and cerebellum activity. Both time perception and working memory were related to a strong peristriate cortical activity. On the other hand, the interaction of time and memory showed activity in the intraparietal sulcus (IPS) and posterior cingulate cortex (PCC). These results support a distributed neural network based model for time perception and that the intraparietal and posterior cingulate areas might play a role in the interface of memory and timing. PMID:28286475
Recurrence and symmetry of time series: Application to transition detection
International Nuclear Information System (INIS)
Girault, Jean-Marc
2015-01-01
Highlights: •A new theoretical framework based on the symmetry concept is proposed. •Four types of symmetry present in any time series were analyzed. •New descriptors make possible the analysis of regime changes in logistic systems. •Chaos–chaos, chaos–periodic, symmetry-breaking, symmetry-increasing bifurcations can be detected. -- Abstract: The study of transitions in low dimensional, nonlinear dynamical systems is a complex problem for which there is not yet a simple, global numerical method able to detect chaos–chaos, chaos–periodic bifurcations and symmetry-breaking, symmetry-increasing bifurcations. We present here for the first time a general framework focusing on the symmetry concept of time series that at the same time reveals new kinds of recurrence. We propose several numerical tools based on the symmetry concept allowing both the qualification and quantification of different kinds of possible symmetry. By using several examples based on periodic symmetrical time series and on logistic and cubic maps, we show that it is possible with simple numerical tools to detect a large number of bifurcations of chaos–chaos, chaos–periodic, broken symmetry and increased symmetry types
Directory of Open Access Journals (Sweden)
Carlos López-Franco
2015-01-01
Full Text Available We present an inverse optimal neural controller for a nonholonomic mobile robot with parameter uncertainties and unknown external disturbances. The neural controller is based on a discrete-time recurrent high order neural network (RHONN trained with an extended Kalman filter. The reference velocities for the neural controller are obtained with a visual sensor. The effectiveness of the proposed approach is tested by simulations and real-time experiments.
Reconstruction of ensembles of coupled time-delay systems from time series.
Sysoev, I V; Prokhorov, M D; Ponomarenko, V I; Bezruchko, B P
2014-06-01
We propose a method to recover from time series the parameters of coupled time-delay systems and the architecture of couplings between them. The method is based on a reconstruction of model delay-differential equations and estimation of statistical significance of couplings. It can be applied to networks composed of nonidentical nodes with an arbitrary number of unidirectional and bidirectional couplings. We test our method on chaotic and periodic time series produced by model equations of ensembles of diffusively coupled time-delay systems in the presence of noise, and apply it to experimental time series obtained from electronic oscillators with delayed feedback coupled by resistors.
Finite-Time Synchronizing Control for Chaotic Neural Networks
Directory of Open Access Journals (Sweden)
Chao Zhang
2014-01-01
Full Text Available This paper addresses the finite-time synchronizing problem for a class of chaotic neural networks. In a real communication network, parameters of the master system may be time-varying and the system may be perturbed by external disturbances. A simple high-gain observer is designed to track all the nonlinearities, unknown system functions, and disturbances. Then, a dynamic active compensatory controller is proposed and by using the singular perturbation theory, the control method can guarantee the finite-time stability of the error system between the master system and the slave system. Finally, two illustrative examples are provided to show the effectiveness and applicability of the proposed scheme.
Topological data analysis of financial time series: Landscapes of crashes
Gidea, Marian; Katz, Yuri
2018-02-01
We explore the evolution of daily returns of four major US stock market indices during the technology crash of 2000, and the financial crisis of 2007-2009. Our methodology is based on topological data analysis (TDA). We use persistence homology to detect and quantify topological patterns that appear in multidimensional time series. Using a sliding window, we extract time-dependent point cloud data sets, to which we associate a topological space. We detect transient loops that appear in this space, and we measure their persistence. This is encoded in real-valued functions referred to as a 'persistence landscapes'. We quantify the temporal changes in persistence landscapes via their Lp-norms. We test this procedure on multidimensional time series generated by various non-linear and non-equilibrium models. We find that, in the vicinity of financial meltdowns, the Lp-norms exhibit strong growth prior to the primary peak, which ascends during a crash. Remarkably, the average spectral density at low frequencies of the time series of Lp-norms of the persistence landscapes demonstrates a strong rising trend for 250 trading days prior to either dotcom crash on 03/10/2000, or to the Lehman bankruptcy on 09/15/2008. Our study suggests that TDA provides a new type of econometric analysis, which complements the standard statistical measures. The method can be used to detect early warning signals of imminent market crashes. We believe that this approach can be used beyond the analysis of financial time series presented here.
FTSPlot: fast time series visualization for large datasets.
Directory of Open Access Journals (Sweden)
Michael Riss
Full Text Available The analysis of electrophysiological recordings often involves visual inspection of time series data to locate specific experiment epochs, mask artifacts, and verify the results of signal processing steps, such as filtering or spike detection. Long-term experiments with continuous data acquisition generate large amounts of data. Rapid browsing through these massive datasets poses a challenge to conventional data plotting software because the plotting time increases proportionately to the increase in the volume of data. This paper presents FTSPlot, which is a visualization concept for large-scale time series datasets using techniques from the field of high performance computer graphics, such as hierarchic level of detail and out-of-core data handling. In a preprocessing step, time series data, event, and interval annotations are converted into an optimized data format, which then permits fast, interactive visualization. The preprocessing step has a computational complexity of O(n x log(N; the visualization itself can be done with a complexity of O(1 and is therefore independent of the amount of data. A demonstration prototype has been implemented and benchmarks show that the technology is capable of displaying large amounts of time series data, event, and interval annotations lag-free with < 20 ms ms. The current 64-bit implementation theoretically supports datasets with up to 2(64 bytes, on the x86_64 architecture currently up to 2(48 bytes are supported, and benchmarks have been conducted with 2(40 bytes/1 TiB or 1.3 x 10(11 double precision samples. The presented software is freely available and can be included as a Qt GUI component in future software projects, providing a standard visualization method for long-term electrophysiological experiments.
Dynamical analysis and visualization of tornadoes time series.
Directory of Open Access Journals (Sweden)
António M Lopes
Full Text Available In this paper we analyze the behavior of tornado time-series in the U.S. from the perspective of dynamical systems. A tornado is a violently rotating column of air extending from a cumulonimbus cloud down to the ground. Such phenomena reveal features that are well described by power law functions and unveil characteristics found in systems with long range memory effects. Tornado time series are viewed as the output of a complex system and are interpreted as a manifestation of its dynamics. Tornadoes are modeled as sequences of Dirac impulses with amplitude proportional to the events size. First, a collection of time series involving 64 years is analyzed in the frequency domain by means of the Fourier transform. The amplitude spectra are approximated by power law functions and their parameters are read as an underlying signature of the system dynamics. Second, it is adopted the concept of circular time and the collective behavior of tornadoes analyzed. Clustering techniques are then adopted to identify and visualize the emerging patterns.
Dynamical analysis and visualization of tornadoes time series.
Lopes, António M; Tenreiro Machado, J A
2015-01-01
In this paper we analyze the behavior of tornado time-series in the U.S. from the perspective of dynamical systems. A tornado is a violently rotating column of air extending from a cumulonimbus cloud down to the ground. Such phenomena reveal features that are well described by power law functions and unveil characteristics found in systems with long range memory effects. Tornado time series are viewed as the output of a complex system and are interpreted as a manifestation of its dynamics. Tornadoes are modeled as sequences of Dirac impulses with amplitude proportional to the events size. First, a collection of time series involving 64 years is analyzed in the frequency domain by means of the Fourier transform. The amplitude spectra are approximated by power law functions and their parameters are read as an underlying signature of the system dynamics. Second, it is adopted the concept of circular time and the collective behavior of tornadoes analyzed. Clustering techniques are then adopted to identify and visualize the emerging patterns.
Financial time series analysis based on information categorization method
Tian, Qiang; Shang, Pengjian; Feng, Guochen
2014-12-01
The paper mainly applies the information categorization method to analyze the financial time series. The method is used to examine the similarity of different sequences by calculating the distances between them. We apply this method to quantify the similarity of different stock markets. And we report the results of similarity in US and Chinese stock markets in periods 1991-1998 (before the Asian currency crisis), 1999-2006 (after the Asian currency crisis and before the global financial crisis), and 2007-2013 (during and after global financial crisis) by using this method. The results show the difference of similarity between different stock markets in different time periods and the similarity of the two stock markets become larger after these two crises. Also we acquire the results of similarity of 10 stock indices in three areas; it means the method can distinguish different areas' markets from the phylogenetic trees. The results show that we can get satisfactory information from financial markets by this method. The information categorization method can not only be used in physiologic time series, but also in financial time series.
"Observation Obscurer" - Time Series Viewer, Editor and Processor
Andronov, I. L.
The program is described, which contains a set of subroutines suitable for East viewing and interactive filtering and processing of regularly and irregularly spaced time series. Being a 32-bit DOS application, it may be used as a default fast viewer/editor of time series in any compute shell ("commander") or in Windows. It allows to view the data in the "time" or "phase" mode, to remove ("obscure") or filter outstanding bad points; to make scale transformations and smoothing using few methods (e.g. mean with phase binning, determination of the statistically opti- mal number of phase bins; "running parabola" (Andronov, 1997, As. Ap. Suppl, 125, 207) fit and to make time series analysis using some methods, e.g. correlation, autocorrelation and histogram analysis: determination of extrema etc. Some features have been developed specially for variable star observers, e.g. the barycentric correction, the creation and fast analysis of "OC" diagrams etc. The manual for "hot keys" is presented. The computer code was compiled with a 32-bit Free Pascal (www.freepascal.org).
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...
Directory of Open Access Journals (Sweden)
Fei Chen
2013-01-01
Full Text Available This paper deals with the finite-time stabilization problem for discrete-time Markov jump nonlinear systems with time delays and norm-bounded exogenous disturbance. The nonlinearities in different jump modes are parameterized by neural networks. Subsequently, a linear difference inclusion state space representation for a class of neural networks is established. Based on this, sufficient conditions are derived in terms of linear matrix inequalities to guarantee stochastic finite-time boundedness and stochastic finite-time stabilization of the closed-loop system. A numerical example is illustrated to verify the efficiency of the proposed technique.
Univariate Time Series Prediction of Solar Power Using a Hybrid Wavelet-ARMA-NARX Prediction Method
Energy Technology Data Exchange (ETDEWEB)
Nazaripouya, Hamidreza; Wang, Yubo; Chu, Chi-Cheng; Pota, Hemanshu; Gadh, Rajit
2016-05-02
This paper proposes a new hybrid method for super short-term solar power prediction. Solar output power usually has a complex, nonstationary, and nonlinear characteristic due to intermittent and time varying behavior of solar radiance. In addition, solar power dynamics is fast and is inertia less. An accurate super short-time prediction is required to compensate for the fluctuations and reduce the impact of solar power penetration on the power system. The objective is to predict one step-ahead solar power generation based only on historical solar power time series data. The proposed method incorporates discrete wavelet transform (DWT), Auto-Regressive Moving Average (ARMA) models, and Recurrent Neural Networks (RNN), while the RNN architecture is based on Nonlinear Auto-Regressive models with eXogenous inputs (NARX). The wavelet transform is utilized to decompose the solar power time series into a set of richer-behaved forming series for prediction. ARMA model is employed as a linear predictor while NARX is used as a nonlinear pattern recognition tool to estimate and compensate the error of wavelet-ARMA prediction. The proposed method is applied to the data captured from UCLA solar PV panels and the results are compared with some of the common and most recent solar power prediction methods. The results validate the effectiveness of the proposed approach and show a considerable improvement in the prediction precision.
GEKF, GUKF and GGPF based prediction of chaotic time-series with additive and multiplicative noises
International Nuclear Information System (INIS)
Wu Xuedong; Song Zhihuan
2008-01-01
On the assumption that random interruptions in the observation process are modelled by a sequence of independent Bernoulli random variables, this paper generalize the extended Kalman filtering (EKF), the unscented Kalman filtering (UKF) and the Gaussian particle filtering (GPF) to the case in which there is a positive probability that the observation in each time consists of noise alone and does not contain the chaotic signal (These generalized novel algorithms are referred to as GEKF, GUKF and GGPF correspondingly in this paper). Using weights and network output of neural networks to constitute state equation and observation equation for chaotic time-series prediction to obtain the linear system state transition equation with continuous update scheme in an online fashion, and the prediction results of chaotic time series represented by the predicted observation value, these proposed novel algorithms are applied to the prediction of Mackey–Glass time-series with additive and multiplicative noises. Simulation results prove that the GGPF provides a relatively better prediction performance in comparison with GEKF and GUKF. (general)
Incremental fuzzy C medoids clustering of time series data using dynamic time warping distance
Chen, Jingli; Wu, Shuai; Liu, Zhizhong; Chao, Hao
2018-01-01
Clustering time series data is of great significance since it could extract meaningful statistics and other characteristics. Especially in biomedical engineering, outstanding clustering algorithms for time series may help improve the health level of people. Considering data scale and time shifts of time series, in this paper, we introduce two incremental fuzzy clustering algorithms based on a Dynamic Time Warping (DTW) distance. For recruiting Single-Pass and Online patterns, our algorithms could handle large-scale time series data by splitting it into a set of chunks which are processed sequentially. Besides, our algorithms select DTW to measure distance of pair-wise time series and encourage higher clustering accuracy because DTW could determine an optimal match between any two time series by stretching or compressing segments of temporal data. Our new algorithms are compared to some existing prominent incremental fuzzy clustering algorithms on 12 benchmark time series datasets. The experimental results show that the proposed approaches could yield high quality clusters and were better than all the competitors in terms of clustering accuracy. PMID:29795600
Incremental fuzzy C medoids clustering of time series data using dynamic time warping distance.
Liu, Yongli; Chen, Jingli; Wu, Shuai; Liu, Zhizhong; Chao, Hao
2018-01-01
Clustering time series data is of great significance since it could extract meaningful statistics and other characteristics. Especially in biomedical engineering, outstanding clustering algorithms for time series may help improve the health level of people. Considering data scale and time shifts of time series, in this paper, we introduce two incremental fuzzy clustering algorithms based on a Dynamic Time Warping (DTW) distance. For recruiting Single-Pass and Online patterns, our algorithms could handle large-scale time series data by splitting it into a set of chunks which are processed sequentially. Besides, our algorithms select DTW to measure distance of pair-wise time series and encourage higher clustering accuracy because DTW could determine an optimal match between any two time series by stretching or compressing segments of temporal data. Our new algorithms are compared to some existing prominent incremental fuzzy clustering algorithms on 12 benchmark time series datasets. The experimental results show that the proposed approaches could yield high quality clusters and were better than all the competitors in terms of clustering accuracy.
A Non-standard Empirical Likelihood for Time Series
DEFF Research Database (Denmark)
Nordman, Daniel J.; Bunzel, Helle; Lahiri, Soumendra N.
Standard blockwise empirical likelihood (BEL) for stationary, weakly dependent time series requires specifying a fixed block length as a tuning parameter for setting confidence regions. This aspect can be difficult and impacts coverage accuracy. As an alternative, this paper proposes a new version...... of BEL based on a simple, though non-standard, data-blocking rule which uses a data block of every possible length. Consequently, the method involves no block selection and is also anticipated to exhibit better coverage performance. Its non-standard blocking scheme, however, induces non......-standard asymptotics and requires a significantly different development compared to standard BEL. We establish the large-sample distribution of log-ratio statistics from the new BEL method for calibrating confidence regions for mean or smooth function parameters of time series. This limit law is not the usual chi...
Models for Pooled Time-Series Cross-Section Data
Directory of Open Access Journals (Sweden)
Lawrence E Raffalovich
2015-07-01
Full Text Available Several models are available for the analysis of pooled time-series cross-section (TSCS data, defined as “repeated observations on fixed units” (Beck and Katz 1995. In this paper, we run the following models: (1 a completely pooled model, (2 fixed effects models, and (3 multi-level/hierarchical linear models. To illustrate these models, we use a Generalized Least Squares (GLS estimator with cross-section weights and panel-corrected standard errors (with EViews 8 on the cross-national homicide trends data of forty countries from 1950 to 2005, which we source from published research (Messner et al. 2011. We describe and discuss the similarities and differences between the models, and what information each can contribute to help answer substantive research questions. We conclude with a discussion of how the models we present may help to mitigate validity threats inherent in pooled time-series cross-section data analysis.
Time Series Analysis, Modeling and Applications A Computational Intelligence Perspective
Chen, Shyi-Ming
2013-01-01
Temporal and spatiotemporal data form an inherent fabric of the society as we are faced with streams of data coming from numerous sensors, data feeds, recordings associated with numerous areas of application embracing physical and human-generated phenomena (environmental data, financial markets, Internet activities, etc.). A quest for a thorough analysis, interpretation, modeling and prediction of time series comes with an ongoing challenge for developing models that are both accurate and user-friendly (interpretable). The volume is aimed to exploit the conceptual and algorithmic framework of Computational Intelligence (CI) to form a cohesive and comprehensive environment for building models of time series. The contributions covered in the volume are fully reflective of the wealth of the CI technologies by bringing together ideas, algorithms, and numeric studies, which convincingly demonstrate their relevance, maturity and visible usefulness. It reflects upon the truly remarkable diversity of methodological a...
Recurrence Density Enhanced Complex Networks for Nonlinear Time Series Analysis
Costa, Diego G. De B.; Reis, Barbara M. Da F.; Zou, Yong; Quiles, Marcos G.; Macau, Elbert E. N.
We introduce a new method, which is entitled Recurrence Density Enhanced Complex Network (RDE-CN), to properly analyze nonlinear time series. Our method first transforms a recurrence plot into a figure of a reduced number of points yet preserving the main and fundamental recurrence properties of the original plot. This resulting figure is then reinterpreted as a complex network, which is further characterized by network statistical measures. We illustrate the computational power of RDE-CN approach by time series by both the logistic map and experimental fluid flows, which show that our method distinguishes different dynamics sufficiently well as the traditional recurrence analysis. Therefore, the proposed methodology characterizes the recurrence matrix adequately, while using a reduced set of points from the original recurrence plots.
Time series analysis methods and applications for flight data
Zhang, Jianye
2017-01-01
This book focuses on different facets of flight data analysis, including the basic goals, methods, and implementation techniques. As mass flight data possesses the typical characteristics of time series, the time series analysis methods and their application for flight data have been illustrated from several aspects, such as data filtering, data extension, feature optimization, similarity search, trend monitoring, fault diagnosis, and parameter prediction, etc. An intelligent information-processing platform for flight data has been established to assist in aircraft condition monitoring, training evaluation and scientific maintenance. The book will serve as a reference resource for people working in aviation management and maintenance, as well as researchers and engineers in the fields of data analysis and data mining.
Nonparametric autocovariance estimation from censored time series by Gaussian imputation.
Park, Jung Wook; Genton, Marc G; Ghosh, Sujit K
2009-02-01
One of the most frequently used methods to model the autocovariance function of a second-order stationary time series is to use the parametric framework of autoregressive and moving average models developed by Box and Jenkins. However, such parametric models, though very flexible, may not always be adequate to model autocovariance functions with sharp changes. Furthermore, if the data do not follow the parametric model and are censored at a certain value, the estimation results may not be reliable. We develop a Gaussian imputation method to estimate an autocovariance structure via nonparametric estimation of the autocovariance function in order to address both censoring and incorrect model specification. We demonstrate the effectiveness of the technique in terms of bias and efficiency with simulations under various rates of censoring and underlying models. We describe its application to a time series of silicon concentrations in the Arctic.
Deviations from uniform power law scaling in nonstationary time series
Viswanathan, G. M.; Peng, C. K.; Stanley, H. E.; Goldberger, A. L.
1997-01-01
A classic problem in physics is the analysis of highly nonstationary time series that typically exhibit long-range correlations. Here we test the hypothesis that the scaling properties of the dynamics of healthy physiological systems are more stable than those of pathological systems by studying beat-to-beat fluctuations in the human heart rate. We develop techniques based on the Fano factor and Allan factor functions, as well as on detrended fluctuation analysis, for quantifying deviations from uniform power-law scaling in nonstationary time series. By analyzing extremely long data sets of up to N = 10(5) beats for 11 healthy subjects, we find that the fluctuations in the heart rate scale approximately uniformly over several temporal orders of magnitude. By contrast, we find that in data sets of comparable length for 14 subjects with heart disease, the fluctuations grow erratically, indicating a loss of scaling stability.
An integral time series on simulated labeling using fractal structure
International Nuclear Information System (INIS)
Djainal, D.D.
1997-01-01
This research deals with the detection of time series of vertical two-phase flow, in attempt to developed an objective indicator of time series flow patterns. One of new method is fractal analysis which can complement conventional methods in the description of highly irregular fluctuations. in the present work, fractal analysis applied to analyze simulated boiling coolant signal. this simulated signals built by sum random elements in small subchannels of the coolant channel. Two modes are defined and both modes are characterized by their void fractions. in the case of unimodal-PDF signals, the difference between these modes is relative small. on other hand, bimodal-PDF signals have relative large range. in this research, fractal dimension can indicate the characters of that signals simulation
Chaotic time series. Part II. System Identification and Prediction
Directory of Open Access Journals (Sweden)
Bjørn Lillekjendlie
1994-10-01
Full Text Available This paper is the second in a series of two, and describes the current state of the art in modeling and prediction of chaotic time series. Sample data from deterministic non-linear systems may look stochastic when analysed with linear methods. However, the deterministic structure may be uncovered and non-linear models constructed that allow improved prediction. We give the background for such methods from a geometrical point of view, and briefly describe the following types of methods: global polynomials, local polynomials, multilayer perceptrons and semi-local methods including radial basis functions. Some illustrative examples from known chaotic systems are presented, emphasising the increase in prediction error with time. We compare some of the algorithms with respect to prediction accuracy and storage requirements, and list applications of these methods to real data from widely different areas.
Time series analysis of ozone data in Isfahan
Omidvari, M.; Hassanzadeh, S.; Hosseinibalam, F.
2008-07-01
Time series analysis used to investigate the stratospheric ozone formation and decomposition processes. Different time series methods are applied to detect the reason for extreme high ozone concentrations for each season. Data was convert into seasonal component and frequency domain, the latter has been evaluated by using the Fast Fourier Transform (FFT), spectral analysis. The power density spectrum estimated from the ozone data showed peaks at cycle duration of 22, 20, 36, 186, 365 and 40 days. According to seasonal component analysis most fluctuation was in 1999 and 2000, but the least fluctuation was in 2003. The best correlation between ozone and sun radiation was found in 2000. Other variables which are not available cause to this fluctuation in the 1999 and 2001. The trend of ozone is increasing in 1999 and is decreasing in other years.
Detecting structural breaks in time series via genetic algorithms
DEFF Research Database (Denmark)
Doerr, Benjamin; Fischer, Paul; Hilbert, Astrid
2016-01-01
of the time series under consideration is available. Therefore, a black-box optimization approach is our method of choice for detecting structural breaks. We describe a genetic algorithm framework which easily adapts to a large number of statistical settings. To evaluate the usefulness of different crossover...... and mutation operations for this problem, we conduct extensive experiments to determine good choices for the parameters and operators of the genetic algorithm. One surprising observation is that use of uniform and one-point crossover together gave significantly better results than using either crossover...... operator alone. Moreover, we present a specific fitness function which exploits the sparse structure of the break points and which can be evaluated particularly efficiently. The experiments on artificial and real-world time series show that the resulting algorithm detects break points with high precision...
Time series analysis of nuclear instrumentation in EBR-II
International Nuclear Information System (INIS)
Imel, G.R.
1996-01-01
Results of a time series analysis of the scaler count data from the 3 wide range nuclear detectors in the Experimental Breeder Reactor-II are presented. One of the channels was replaced, and it was desired to determine if there was any statistically significant change (ie, improvement) in the channel's response after the replacement. Data were collected from all 3 channels for 16-day periods before and after detector replacement. Time series analysis and statistical tests showed that there was no significant change after the detector replacement. Also, there were no statistically significant differences among the 3 channels, either before or after the replacement. Finally, it was determined that errors in the reactivity change inferred from subcritical count monitoring during fuel handling would be on the other of 20-30 cents for single count intervals
Mathematical methods in time series analysis and digital image processing
Kurths, J; Maass, P; Timmer, J
2008-01-01
The aim of this volume is to bring together research directions in theoretical signal and imaging processing developed rather independently in electrical engineering, theoretical physics, mathematics and the computer sciences. In particular, mathematically justified algorithms and methods, the mathematical analysis of these algorithms, and methods as well as the investigation of connections between methods from time series analysis and image processing are reviewed. An interdisciplinary comparison of these methods, drawing upon common sets of test problems from medicine and geophysical/enviromental sciences, is also addressed. This volume coherently summarizes work carried out in the field of theoretical signal and image processing. It focuses on non-linear and non-parametric models for time series as well as on adaptive methods in image processing.
Modeling Philippine Stock Exchange Composite Index Using Time Series Analysis
Gayo, W. S.; Urrutia, J. D.; Temple, J. M. F.; Sandoval, J. R. D.; Sanglay, J. E. A.
2015-06-01
This study was conducted to develop a time series model of the Philippine Stock Exchange Composite Index and its volatility using the finite mixture of ARIMA model with conditional variance equations such as ARCH, GARCH, EG ARCH, TARCH and PARCH models. Also, the study aimed to find out the reason behind the behaviorof PSEi, that is, which of the economic variables - Consumer Price Index, crude oil price, foreign exchange rate, gold price, interest rate, money supply, price-earnings ratio, Producers’ Price Index and terms of trade - can be used in projecting future values of PSEi and this was examined using Granger Causality Test. The findings showed that the best time series model for Philippine Stock Exchange Composite index is ARIMA(1,1,5) - ARCH(1). Also, Consumer Price Index, crude oil price and foreign exchange rate are factors concluded to Granger cause Philippine Stock Exchange Composite Index.
Big Data impacts on stochastic Forecast Models: Evidence from FX time series
Directory of Open Access Journals (Sweden)
Sebastian Dietz
2013-12-01
Full Text Available With the rise of the Big Data paradigm new tasks for prediction models appeared. In addition to the volume problem of such data sets nonlinearity becomes important, as the more detailed data sets contain also more comprehensive information, e.g. about non regular seasonal or cyclical movements as well as jumps in time series. This essay compares two nonlinear methods for predicting a high frequency time series, the USD/Euro exchange rate. The first method investigated is Autoregressive Neural Network Processes (ARNN, a neural network based nonlinear extension of classical autoregressive process models from time series analysis (see Dietz 2011. Its advantage is its simple but scalable time series process model architecture, which is able to include all kinds of nonlinearities based on the universal approximation theorem of Hornik, Stinchcombe and White 1989 and the extensions of Hornik 1993. However, restrictions related to the numeric estimation procedures limit the flexibility of the model. The alternative is a Support Vector Machine Model (SVM, Vapnik 1995. The two methods compared have different approaches of error minimization (Empirical error minimization at the ARNN vs. structural error minimization at the SVM. Our new finding is, that time series data classified as “Big Data” need new methods for prediction. Estimation and prediction was performed using the statistical programming language R. Besides prediction results we will also discuss the impact of Big Data on data preparation and model validation steps. Normal 0 21 false false false DE X-NONE X-NONE /* Style Definitions */ table.MsoNormalTable {mso-style-name:"Normale Tabelle"; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-priority:99; mso-style-parent:""; mso-padding-alt:0cm 5.4pt 0cm 5.4pt; mso-para-margin:0cm; mso-para-margin-bottom:.0001pt; mso-pagination:widow-orphan; font-size:10.0pt; font-family:"Times New Roman","serif";}
Forecasting the Reference Evapotranspiration Using Time Series Model
Directory of Open Access Journals (Sweden)
H. Zare Abyaneh
2016-10-01
Full Text Available Introduction: Reference evapotranspiration is one of the most important factors in irrigation timing and field management. Moreover, reference evapotranspiration forecasting can play a vital role in future developments. Therefore in this study, the seasonal autoregressive integrated moving average (ARIMA model was used to forecast the reference evapotranspiration time series in the Esfahan, Semnan, Shiraz, Kerman, and Yazd synoptic stations. Materials and Methods: In the present study in all stations (characteristics of the synoptic stations are given in Table 1, the meteorological data, including mean, maximum and minimum air temperature, relative humidity, dry-and wet-bulb temperature, dew-point temperature, wind speed, precipitation, air vapor pressure and sunshine hours were collected from the Islamic Republic of Iran Meteorological Organization (IRIMO for the 41 years from 1965 to 2005. The FAO Penman-Monteith equation was used to calculate the monthly reference evapotranspiration in the five synoptic stations and the evapotranspiration time series were formed. The unit root test was used to identify whether the time series was stationary, then using the Box-Jenkins method, seasonal ARIMA models were applied to the sample data. Table 1. The geographical location and climate conditions of the synoptic stations Station\tGeographical location\tAltitude (m\tMean air temperature (°C\tMean precipitation (mm\tClimate, according to the De Martonne index classification Longitude (E\tLatitude (N Annual\tMin. and Max. Esfahan\t51° 40'\t32° 37'\t1550.4\t16.36\t9.4-23.3\t122\tArid Semnan\t53° 33'\t35° 35'\t1130.8\t18.0\t12.4-23.8\t140\tArid Shiraz\t52° 36'\t29° 32'\t1484\t18.0\t10.2-25.9\t324\tSemi-arid Kerman\t56° 58'\t30° 15'\t1753.8\t15.6\t6.7-24.6\t142\tArid Yazd\t54° 17'\t31° 54'\t1237.2\t19.2\t11.8-26.0\t61\tArid Results and Discussion: The monthly meteorological data were used as input for the Ref-ET software and monthly reference
Quality Control Procedure Based on Partitioning of NMR Time Series
Directory of Open Access Journals (Sweden)
Michał Staniszewski
2018-03-01
Full Text Available The quality of the magnetic resonance spectroscopy (MRS depends on the stability of magnetic resonance (MR system performance and optimal hardware functioning, which ensure adequate levels of signal-to-noise ratios (SNR as well as good spectral resolution and minimal artifacts in the spectral data. MRS quality control (QC protocols and methodologies are based on phantom measurements that are repeated regularly. In this work, a signal partitioning algorithm based on a dynamic programming (DP method for QC assessment of the spectral data is described. The proposed algorithm allows detection of the change points—the abrupt variations in the time series data. The proposed QC method was tested using the simulated and real phantom data. Simulated data were randomly generated time series distorted by white noise. The real data were taken from the phantom quality control studies of the MRS scanner collected for four and a half years and analyzed by LCModel software. Along with the proposed algorithm, performance of various literature methods was evaluated for the predefined number of change points based on the error values calculated by subtracting the mean values calculated for the periods between the change-points from the original data points. The time series were checked using external software, a set of external methods and the proposed tool, and the obtained results were comparable. The application of dynamic programming in the analysis of the phantom MRS data is a novel approach to QC. The obtained results confirm that the presented change-point-detection tool can be used either for independent analysis of MRS time series (or any other or as a part of quality control.
Appropriate use of the increment entropy for electrophysiological time series.
Liu, Xiaofeng; Wang, Xue; Zhou, Xu; Jiang, Aimin
2018-04-01
The increment entropy (IncrEn) is a new measure for quantifying the complexity of a time series. There are three critical parameters in the IncrEn calculation: N (length of the time series), m (dimensionality), and q (quantifying precision). However, the question of how to choose the most appropriate combination of IncrEn parameters for short datasets has not been extensively explored. The purpose of this research was to provide guidance on choosing suitable IncrEn parameters for short datasets by exploring the effects of varying the parameter values. We used simulated data, epileptic EEG data and cardiac interbeat (RR) data to investigate the effects of the parameters on the calculated IncrEn values. The results reveal that IncrEn is sensitive to changes in m, q and N for short datasets (N≤500). However, IncrEn reaches stability at a data length of N=1000 with m=2 and q=2, and for short datasets (N=100), it shows better relative consistency with 2≤m≤6 and 2≤q≤8 We suggest that the value of N should be no less than 100. To enable a clear distinction between different classes based on IncrEn, we recommend that m and q should take values between 2 and 4. With appropriate parameters, IncrEn enables the effective detection of complexity variations in physiological time series, suggesting that IncrEn should be useful for the analysis of physiological time series in clinical applications. Copyright © 2018 Elsevier Ltd. All rights reserved.
Which DTW Method Applied to Marine Univariate Time Series Imputation
Phan , Thi-Thu-Hong; Caillault , Émilie; Lefebvre , Alain; Bigand , André
2017-01-01
International audience; Missing data are ubiquitous in any domains of applied sciences. Processing datasets containing missing values can lead to a loss of efficiency and unreliable results, especially for large missing sub-sequence(s). Therefore, the aim of this paper is to build a framework for filling missing values in univariate time series and to perform a comparison of different similarity metrics used for the imputation task. This allows to suggest the most suitable methods for the imp...
Time series regression model for infectious disease and weather.
Imai, Chisato; Armstrong, Ben; Chalabi, Zaid; Mangtani, Punam; Hashizume, Masahiro
2015-10-01
Time series regression has been developed and long used to evaluate the short-term associations of air pollution and weather with mortality or morbidity of non-infectious diseases. The application of the regression approaches from this tradition to infectious diseases, however, is less well explored and raises some new issues. We discuss and present potential solutions for five issues often arising in such analyses: changes in immune population, strong autocorrelations, a wide range of plausible lag structures and association patterns, seasonality adjustments, and large overdispersion. The potential approaches are illustrated with datasets of cholera cases and rainfall from Bangladesh and influenza and temperature in Tokyo. Though this article focuses on the application of the traditional time series regression to infectious diseases and weather factors, we also briefly introduce alternative approaches, including mathematical modeling, wavelet analysis, and autoregressive integrated moving average (ARIMA) models. Modifications proposed to standard time series regression practice include using sums of past cases as proxies for the immune population, and using the logarithm of lagged disease counts to control autocorrelation due to true contagion, both of which are motivated from "susceptible-infectious-recovered" (SIR) models. The complexity of lag structures and association patterns can often be informed by biological mechanisms and explored by using distributed lag non-linear models. For overdispersed models, alternative distribution models such as quasi-Poisson and negative binomial should be considered. Time series regression can be used to investigate dependence of infectious diseases on weather, but may need modifying to allow for features specific to this context. Copyright © 2015 The Authors. Published by Elsevier Inc. All rights reserved.
Analyses of GIMMS NDVI Time Series in Kogi State, Nigeria
Palka, Jessica; Wessollek, Christine; Karrasch, Pierre
2017-10-01
The value of remote sensing data is particularly evident where an areal monitoring is needed to provide information on the earth's surface development. The use of temporal high resolution time series data allows for detecting short-term changes. In Kogi State in Nigeria different vegetation types can be found. As the major population in this region is living in rural communities with crop farming the existing vegetation is slowly being altered. The expansion of agricultural land causes loss of natural vegetation, especially in the regions close to the rivers which are suitable for crop production. With regard to these facts, two questions can be dealt with covering different aspects of the development of vegetation in the Kogi state, the determination and evaluation of the general development of the vegetation in the study area (trend estimation) and analyses on a short-term behavior of vegetation conditions, which can provide information about seasonal effects in vegetation development. For this purpose, the GIMMS-NDVI data set, provided by the NOAA, provides information on the normalized difference vegetation index (NDVI) in a geometric resolution of approx. 8 km. The temporal resolution of 15 days allows the already described analyses. For the presented analysis data for the period 1981-2012 (31 years) were used. The implemented workflow mainly applies methods of time series analysis. The results show that in addition to the classical seasonal development, artefacts of different vegetation periods (several NDVI maxima) can be found in the data. The trend component of the time series shows a consistently positive development in the entire study area considering the full investigation period of 31 years. However, the results also show that this development has not been continuous and a simple linear modeling of the NDVI increase is only possible to a limited extent. For this reason, the trend modeling was extended by procedures for detecting structural breaks in
Identification of neutral biochemical network models from time series data
Directory of Open Access Journals (Sweden)
Maia Marco
2009-05-01
Full Text Available Abstract Background The major difficulty in modeling biological systems from multivariate time series is the identification of parameter sets that endow a model with dynamical behaviors sufficiently similar to the experimental data. Directly related to this parameter estimation issue is the task of identifying the structure and regulation of ill-characterized systems. Both tasks are simplified if the mathematical model is canonical, i.e., if it is constructed according to strict guidelines. Results In this report, we propose a method for the identification of admissible parameter sets of canonical S-systems from biological time series. The method is based on a Monte Carlo process that is combined with an improved version of our previous parameter optimization algorithm. The method maps the parameter space into the network space, which characterizes the connectivity among components, by creating an ensemble of decoupled S-system models that imitate the dynamical behavior of the time series with sufficient accuracy. The concept of sloppiness is revisited in the context of these S-system models with an exploration not only of different parameter sets that produce similar dynamical behaviors but also different network topologies that yield dynamical similarity. Conclusion The proposed parameter estimation methodology was applied to actual time series data from the glycolytic pathway of the bacterium Lactococcus lactis and led to ensembles of models with different network topologies. In parallel, the parameter optimization algorithm was applied to the same dynamical data upon imposing a pre-specified network topology derived from prior biological knowledge, and the results from both strategies were compared. The results suggest that the proposed method may serve as a powerful exploration tool for testing hypotheses and the design of new experiments.
Identification of neutral biochemical network models from time series data.
Vilela, Marco; Vinga, Susana; Maia, Marco A Grivet Mattoso; Voit, Eberhard O; Almeida, Jonas S
2009-05-05
The major difficulty in modeling biological systems from multivariate time series is the identification of parameter sets that endow a model with dynamical behaviors sufficiently similar to the experimental data. Directly related to this parameter estimation issue is the task of identifying the structure and regulation of ill-characterized systems. Both tasks are simplified if the mathematical model is canonical, i.e., if it is constructed according to strict guidelines. In this report, we propose a method for the identification of admissible parameter sets of canonical S-systems from biological time series. The method is based on a Monte Carlo process that is combined with an improved version of our previous parameter optimization algorithm. The method maps the parameter space into the network space, which characterizes the connectivity among components, by creating an ensemble of decoupled S-system models that imitate the dynamical behavior of the time series with sufficient accuracy. The concept of sloppiness is revisited in the context of these S-system models with an exploration not only of different parameter sets that produce similar dynamical behaviors but also different network topologies that yield dynamical similarity. The proposed parameter estimation methodology was applied to actual time series data from the glycolytic pathway of the bacterium Lactococcus lactis and led to ensembles of models with different network topologies. In parallel, the parameter optimization algorithm was applied to the same dynamical data upon imposing a pre-specified network topology derived from prior biological knowledge, and the results from both strategies were compared. The results suggest that the proposed method may serve as a powerful exploration tool for testing hypotheses and the design of new experiments.
Comparison of correlation analysis techniques for irregularly sampled time series
Directory of Open Access Journals (Sweden)
K. Rehfeld
2011-06-01
Full Text Available Geoscientific measurements often provide time series with irregular time sampling, requiring either data reconstruction (interpolation or sophisticated methods to handle irregular sampling. We compare the linear interpolation technique and different approaches for analyzing the correlation functions and persistence of irregularly sampled time series, as Lomb-Scargle Fourier transformation and kernel-based methods. In a thorough benchmark test we investigate the performance of these techniques.
All methods have comparable root mean square errors (RMSEs for low skewness of the inter-observation time distribution. For high skewness, very irregular data, interpolation bias and RMSE increase strongly. We find a 40 % lower RMSE for the lag-1 autocorrelation function (ACF for the Gaussian kernel method vs. the linear interpolation scheme,in the analysis of highly irregular time series. For the cross correlation function (CCF the RMSE is then lower by 60 %. The application of the Lomb-Scargle technique gave results comparable to the kernel methods for the univariate, but poorer results in the bivariate case. Especially the high-frequency components of the signal, where classical methods show a strong bias in ACF and CCF magnitude, are preserved when using the kernel methods.
We illustrate the performances of interpolation vs. Gaussian kernel method by applying both to paleo-data from four locations, reflecting late Holocene Asian monsoon variability as derived from speleothem δ^{18}O measurements. Cross correlation results are similar for both methods, which we attribute to the long time scales of the common variability. The persistence time (memory is strongly overestimated when using the standard, interpolation-based, approach. Hence, the Gaussian kernel is a reliable and more robust estimator with significant advantages compared to other techniques and suitable for large scale application to paleo-data.
Acute ischaemic stroke prediction from physiological time series patterns
Directory of Open Access Journals (Sweden)
Qing Zhang,
2013-05-01
Full Text Available BackgroundStroke is one of the major diseases with human mortality. Recent clinical research has indicated that early changes in common physiological variables represent a potential therapeutic target, thus the manipulation of these variables may eventually yield an effective way to optimise stroke recovery.AimsWe examined correlations between physiological parameters of patients during the first 48 hours after a stroke, and their stroke outcomes after 3 months. We wanted to discover physiological determinants that could be used to improve health outcomes by supporting the medical decisions that need to be made early on a patient’s stroke experience.Method We applied regression-based machine learning techniques to build a prediction algorithm that can forecast 3-month outcomes from initial physiological time series data during the first 48 hours after stroke. In our method, not only did we use statistical characteristics as traditional prediction features, but also we adopted trend patterns of time series data as new key features.ResultsWe tested our prediction method on a real physiological data set of stroke patients. The experiment results revealed an average high precision rate: 90%. We also tested prediction methods only considering statistical characteristics of physiological data, and concluded an average precision rate: 71%.ConclusionWe demonstrated that using trend pattern features in prediction methods improved the accuracy of stroke outcome prediction. Therefore, trend patterns of physiological time series data have an important role in the early treatment of patients with acute ischaemic stroke.
Time series analysis for psychological research: examining and forecasting change.
Jebb, Andrew T; Tay, Louis; Wang, Wei; Huang, Qiming
2015-01-01
Psychological research has increasingly recognized the importance of integrating temporal dynamics into its theories, and innovations in longitudinal designs and analyses have allowed such theories to be formalized and tested. However, psychological researchers may be relatively unequipped to analyze such data, given its many characteristics and the general complexities involved in longitudinal modeling. The current paper introduces time series analysis to psychological research, an analytic domain that has been essential for understanding and predicting the behavior of variables across many diverse fields. First, the characteristics of time series data are discussed. Second, different time series modeling techniques are surveyed that can address various topics of interest to psychological researchers, including describing the pattern of change in a variable, modeling seasonal effects, assessing the immediate and long-term impact of a salient event, and forecasting future values. To illustrate these methods, an illustrative example based on online job search behavior is used throughout the paper, and a software tutorial in R for these analyses is provided in the Supplementary Materials.
Modeling financial time series with S-plus
Zivot, Eric
2003-01-01
The field of financial econometrics has exploded over the last decade This book represents an integration of theory, methods, and examples using the S-PLUS statistical modeling language and the S+FinMetrics module to facilitate the practice of financial econometrics This is the first book to show the power of S-PLUS for the analysis of time series data It is written for researchers and practitioners in the finance industry, academic researchers in economics and finance, and advanced MBA and graduate students in economics and finance Readers are assumed to have a basic knowledge of S-PLUS and a solid grounding in basic statistics and time series concepts Eric Zivot is an associate professor and Gary Waterman Distinguished Scholar in the Economics Department at the University of Washington, and is co-director of the nascent Professional Master's Program in Computational Finance He regularly teaches courses on econometric theory, financial econometrics and time series econometrics, and is the recipient of the He...
Time series analysis for psychological research: examining and forecasting change
Jebb, Andrew T.; Tay, Louis; Wang, Wei; Huang, Qiming
2015-01-01
Psychological research has increasingly recognized the importance of integrating temporal dynamics into its theories, and innovations in longitudinal designs and analyses have allowed such theories to be formalized and tested. However, psychological researchers may be relatively unequipped to analyze such data, given its many characteristics and the general complexities involved in longitudinal modeling. The current paper introduces time series analysis to psychological research, an analytic domain that has been essential for understanding and predicting the behavior of variables across many diverse fields. First, the characteristics of time series data are discussed. Second, different time series modeling techniques are surveyed that can address various topics of interest to psychological researchers, including describing the pattern of change in a variable, modeling seasonal effects, assessing the immediate and long-term impact of a salient event, and forecasting future values. To illustrate these methods, an illustrative example based on online job search behavior is used throughout the paper, and a software tutorial in R for these analyses is provided in the Supplementary Materials. PMID:26106341
Reconstruction of network topology using status-time-series data
Pandey, Pradumn Kumar; Badarla, Venkataramana
2018-01-01
Uncovering the heterogeneous connection pattern of a networked system from the available status-time-series (STS) data of a dynamical process on the network is of great interest in network science and known as a reverse engineering problem. Dynamical processes on a network are affected by the structure of the network. The dependency between the diffusion dynamics and structure of the network can be utilized to retrieve the connection pattern from the diffusion data. Information of the network structure can help to devise the control of dynamics on the network. In this paper, we consider the problem of network reconstruction from the available status-time-series (STS) data using matrix analysis. The proposed method of network reconstruction from the STS data is tested successfully under susceptible-infected-susceptible (SIS) diffusion dynamics on real-world and computer-generated benchmark networks. High accuracy and efficiency of the proposed reconstruction procedure from the status-time-series data define the novelty of the method. Our proposed method outperforms compressed sensing theory (CST) based method of network reconstruction using STS data. Further, the same procedure of network reconstruction is applied to the weighted networks. The ordering of the edges in the weighted networks is identified with high accuracy.
Spectral Unmixing Analysis of Time Series Landsat 8 Images
Zhuo, R.; Xu, L.; Peng, J.; Chen, Y.
2018-05-01
Temporal analysis of Landsat 8 images opens up new opportunities in the unmixing procedure. Although spectral analysis of time series Landsat imagery has its own advantage, it has rarely been studied. Nevertheless, using the temporal information can provide improved unmixing performance when compared to independent image analyses. Moreover, different land cover types may demonstrate different temporal patterns, which can aid the discrimination of different natures. Therefore, this letter presents time series K-P-Means, a new solution to the problem of unmixing time series Landsat imagery. The proposed approach is to obtain the "purified" pixels in order to achieve optimal unmixing performance. The vertex component analysis (VCA) is used to extract endmembers for endmember initialization. First, nonnegative least square (NNLS) is used to estimate abundance maps by using the endmember. Then, the estimated endmember is the mean value of "purified" pixels, which is the residual of the mixed pixel after excluding the contribution of all nondominant endmembers. Assembling two main steps (abundance estimation and endmember update) into the iterative optimization framework generates the complete algorithm. Experiments using both simulated and real Landsat 8 images show that the proposed "joint unmixing" approach provides more accurate endmember and abundance estimation results compared with "separate unmixing" approach.
Clustering Multivariate Time Series Using Hidden Markov Models
Directory of Open Access Journals (Sweden)
Shima Ghassempour
2014-03-01
Full Text Available In this paper we describe an algorithm for clustering multivariate time series with variables taking both categorical and continuous values. Time series of this type are frequent in health care, where they represent the health trajectories of individuals. The problem is challenging because categorical variables make it difficult to define a meaningful distance between trajectories. We propose an approach based on Hidden Markov Models (HMMs, where we first map each trajectory into an HMM, then define a suitable distance between HMMs and finally proceed to cluster the HMMs with a method based on a distance matrix. We test our approach on a simulated, but realistic, data set of 1,255 trajectories of individuals of age 45 and over, on a synthetic validation set with known clustering structure, and on a smaller set of 268 trajectories extracted from the longitudinal Health and Retirement Survey. The proposed method can be implemented quite simply using standard packages in R and Matlab and may be a good candidate for solving the difficult problem of clustering multivariate time series with categorical variables using tools that do not require advanced statistic knowledge, and therefore are accessible to a wide range of researchers.
Cross-sample entropy of foreign exchange time series
Liu, Li-Zhi; Qian, Xi-Yuan; Lu, Heng-Yao
2010-11-01
The correlation of foreign exchange rates in currency markets is investigated based on the empirical data of DKK/USD, NOK/USD, CAD/USD, JPY/USD, KRW/USD, SGD/USD, THB/USD and TWD/USD for a period from 1995 to 2002. Cross-SampEn (cross-sample entropy) method is used to compare the returns of every two exchange rate time series to assess their degree of asynchrony. The calculation method of confidence interval of SampEn is extended and applied to cross-SampEn. The cross-SampEn and its confidence interval for every two of the exchange rate time series in periods 1995-1998 (before the Asian currency crisis) and 1999-2002 (after the Asian currency crisis) are calculated. The results show that the cross-SampEn of every two of these exchange rates becomes higher after the Asian currency crisis, indicating a higher asynchrony between the exchange rates. Especially for Singapore, Thailand and Taiwan, the cross-SampEn values after the Asian currency crisis are significantly higher than those before the Asian currency crisis. Comparison with the correlation coefficient shows that cross-SampEn is superior to describe the correlation between time series.
Neural processing of amplitude and formant rise time in dyslexia.
Peter, Varghese; Kalashnikova, Marina; Burnham, Denis
2016-06-01
This study aimed to investigate how children with dyslexia weight amplitude rise time (ART) and formant rise time (FRT) cues in phonetic discrimination. Passive mismatch responses (MMR) were recorded for a/ba/-/wa/contrast in a multiple deviant odd-ball paradigm to identify the neural response to cue weighting in 17 children with dyslexia and 17 age-matched control children. The deviant stimuli had either partial or full ART or FRT cues. The results showed that ART did not generate an MMR in either group, whereas both partial and full FRT cues generated MMR in control children while only full FRT cues generated MMR in children with dyslexia. These findings suggest that children, both controls and those with dyslexia, discriminate speech based on FRT cues and not ART cues. However, control children have greater sensitivity to FRT cues in speech compared to children with dyslexia. Copyright © 2016 The Authors. Published by Elsevier Ltd.. All rights reserved.
Wang, Wen-Chuan; Chau, Kwok-Wing; Cheng, Chun-Tian; Qiu, Lin
2009-08-01
SummaryDeveloping a hydrological forecasting model based on past records is crucial to effective hydropower reservoir management and scheduling. Traditionally, time series analysis and modeling is used for building mathematical models to generate hydrologic records in hydrology and water resources. Artificial intelligence (AI), as a branch of computer science, is capable of analyzing long-series and large-scale hydrological data. In recent years, it is one of front issues to apply AI technology to the hydrological forecasting modeling. In this paper, autoregressive moving-average (ARMA) models, artificial neural networks (ANNs) approaches, adaptive neural-based fuzzy inference system (ANFIS) techniques, genetic programming (GP) models and support vector machine (SVM) method are examined using the long-term observations of monthly river flow discharges. The four quantitative standard statistical performance evaluation measures, the coefficient of correlation ( R), Nash-Sutcliffe efficiency coefficient ( E), root mean squared error (RMSE), mean absolute percentage error (MAPE), are employed to evaluate the performances of various models developed. Two case study river sites are also provided to illustrate their respective performances. The results indicate that the best performance can be obtained by ANFIS, GP and SVM, in terms of different evaluation criteria during the training and validation phases.
Earthquake forecasting studies using radon time series data in Taiwan
Walia, Vivek; Kumar, Arvind; Fu, Ching-Chou; Lin, Shih-Jung; Chou, Kuang-Wu; Wen, Kuo-Liang; Chen, Cheng-Hong
2017-04-01
For few decades, growing number of studies have shown usefulness of data in the field of seismogeochemistry interpreted as geochemical precursory signals for impending earthquakes and radon is idendified to be as one of the most reliable geochemical precursor. Radon is recognized as short-term precursor and is being monitored in many countries. This study is aimed at developing an effective earthquake forecasting system by inspecting long term radon time series data. The data is obtained from a network of radon monitoring stations eastblished along different faults of Taiwan. The continuous time series radon data for earthquake studies have been recorded and some significant variations associated with strong earthquakes have been observed. The data is also examined to evaluate earthquake precursory signals against environmental factors. An automated real-time database operating system has been developed recently to improve the data processing for earthquake precursory studies. In addition, the study is aimed at the appraisal and filtrations of these environmental parameters, in order to create a real-time database that helps our earthquake precursory study. In recent years, automatic operating real-time database has been developed using R, an open source programming language, to carry out statistical computation on the data. To integrate our data with our working procedure, we use the popular and famous open source web application solution, AMP (Apache, MySQL, and PHP), creating a website that could effectively show and help us manage the real-time database.
A method for generating high resolution satellite image time series
Guo, Tao
2014-10-01
There is an increasing demand for satellite remote sensing data with both high spatial and temporal resolution in many applications. But it still is a challenge to simultaneously improve spatial resolution and temporal frequency due to the technical limits of current satellite observation systems. To this end, much R&D efforts have been ongoing for years and lead to some successes roughly in two aspects, one includes super resolution, pan-sharpen etc. methods which can effectively enhance the spatial resolution and generate good visual effects, but hardly preserve spectral signatures and result in inadequate analytical value, on the other hand, time interpolation is a straight forward method to increase temporal frequency, however it increase little informative contents in fact. In this paper we presented a novel method to simulate high resolution time series data by combing low resolution time series data and a very small number of high resolution data only. Our method starts with a pair of high and low resolution data set, and then a spatial registration is done by introducing LDA model to map high and low resolution pixels correspondingly. Afterwards, temporal change information is captured through a comparison of low resolution time series data, and then projected onto the high resolution data plane and assigned to each high resolution pixel according to the predefined temporal change patterns of each type of ground objects. Finally the simulated high resolution data is generated. A preliminary experiment shows that our method can simulate a high resolution data with a reasonable accuracy. The contribution of our method is to enable timely monitoring of temporal changes through analysis of time sequence of low resolution images only, and usage of costly high resolution data can be reduces as much as possible, and it presents a highly effective way to build up an economically operational monitoring solution for agriculture, forest, land use investigation
PSO-MISMO modeling strategy for multistep-ahead time series prediction.
Bao, Yukun; Xiong, Tao; Hu, Zhongyi
2014-05-01
Multistep-ahead time series prediction is one of the most challenging research topics in the field of time series modeling and prediction, and is continually under research. Recently, the multiple-input several multiple-outputs (MISMO) modeling strategy has been proposed as a promising alternative for multistep-ahead time series prediction, exhibiting advantages compared with the two currently dominating strategies, the iterated and the direct strategies. Built on the established MISMO strategy, this paper proposes a particle swarm optimization (PSO)-based MISMO modeling strategy, which is capable of determining the number of sub-models in a self-adaptive mode, with varying prediction horizons. Rather than deriving crisp divides with equal-size s prediction horizons from the established MISMO, the proposed PSO-MISMO strategy, implemented with neural networks, employs a heuristic to create flexible divides with varying sizes of prediction horizons and to generate corresponding sub-models, providing considerable flexibility in model construction, which has been validated with simulated and real datasets.
Forecasting long memory time series under a break in persistence
DEFF Research Database (Denmark)
Heinen, Florian; Sibbertsen, Philipp; Kruse, Robinson
We consider the problem of forecasting time series with long memory when the memory parameter is subject to a structural break. By means of a large-scale Monte Carlo study we show that ignoring such a change in persistence leads to substantially reduced forecasting precision. The strength...... of this effect depends on whether the memory parameter is increasing or decreasing over time. A comparison of six forecasting strategies allows us to conclude that pre-testing for a change in persistence is highly recommendable in our setting. In addition we provide an empirical example which underlines...
Extracting the relevant delays in time series modelling
DEFF Research Database (Denmark)
Goutte, Cyril
1997-01-01
selection, and more precisely stepwise forward selection. The method is compared to other forward selection schemes, as well as to a nonparametric tests aimed at estimating the embedding dimension of time series. The final application extends these results to the efficient estimation of FIR filters on some......In this contribution, we suggest a convenient way to use generalisation error to extract the relevant delays from a time-varying process, i.e. the delays that lead to the best prediction performance. We design a generalisation-based algorithm that takes its inspiration from traditional variable...
Czech Academy of Sciences Publication Activity Database
Rudajev, Vladimír; Číž, R.
2007-01-01
Roč. 44, č. 3 (2007), s. 457-467 ISSN 1365-1609 R&D Projects: GA ČR GA205/06/0906 Institutional research plan: CEZ:AV0Z30130516; CEZ:AV0Z30460519 Keywords : ultrasonic emission * microfracturing * time series * autocorrelation * fractal dimensions * neural networks Subject RIV: DC - Siesmology, Volcanology, Earth Structure Impact factor: 0.735, year: 2007
Satellite Image Time Series Decomposition Based on EEMD
Directory of Open Access Journals (Sweden)
Yun-long Kong
2015-11-01
Full Text Available Satellite Image Time Series (SITS have recently been of great interest due to the emerging remote sensing capabilities for Earth observation. Trend and seasonal components are two crucial elements of SITS. In this paper, a novel framework of SITS decomposition based on Ensemble Empirical Mode Decomposition (EEMD is proposed. EEMD is achieved by sifting an ensemble of adaptive orthogonal components called Intrinsic Mode Functions (IMFs. EEMD is noise-assisted and overcomes the drawback of mode mixing in conventional Empirical Mode Decomposition (EMD. Inspired by these advantages, the aim of this work is to employ EEMD to decompose SITS into IMFs and to choose relevant IMFs for the separation of seasonal and trend components. In a series of simulations, IMFs extracted by EEMD achieved a clear representation with physical meaning. The experimental results of 16-day compositions of Moderate Resolution Imaging Spectroradiometer (MODIS, Normalized Difference Vegetation Index (NDVI, and Global Environment Monitoring Index (GEMI time series with disturbance illustrated the effectiveness and stability of the proposed approach to monitoring tasks, such as applications for the detection of abrupt changes.
Deriving crop calendar using NDVI time-series
Patel, J. H.; Oza, M. P.
2014-11-01
Agricultural intensification is defined in terms as cropping intensity, which is the numbers of crops (single, double and triple) per year in a unit cropland area. Information about crop calendar (i.e. number of crops in a parcel of land and their planting & harvesting dates and date of peak vegetative stage) is essential for proper management of agriculture. Remote sensing sensors provide a regular, consistent and reliable measurement of vegetation response at various growth stages of crop. Therefore it is ideally suited for monitoring purpose. The spectral response of vegetation, as measured by the Normalized Difference Vegetation Index (NDVI) and its profiles, can provide a new dimension for describing vegetation growth cycle. The analysis based on values of NDVI at regular time interval provides useful information about various crop growth stages and performance of crop in a season. However, the NDVI data series has considerable amount of local fluctuation in time domain and needs to be smoothed so that dominant seasonal behavior is enhanced. Based on temporal analysis of smoothed NDVI series, it is possible to extract number of crop cycles per year and their crop calendar. In the present study, a methodology is developed to extract key elements of crop growth cycle (i.e. number of crops per year and their planting - peak - harvesting dates). This is illustrated by analysing MODIS-NDVI data series of one agricultural year (from June 2012 to May 2013) over Gujarat. Such an analysis is very useful for analysing dynamics of kharif and rabi crops.
Finite-time stability of neutral-type neural networks with random time-varying delays
Ali, M. Syed; Saravanan, S.; Zhu, Quanxin
2017-11-01
This paper is devoted to the finite-time stability analysis of neutral-type neural networks with random time-varying delays. The randomly time-varying delays are characterised by Bernoulli stochastic variable. This result can be extended to analysis and design for neutral-type neural networks with random time-varying delays. On the basis of this paper, we constructed suitable Lyapunov-Krasovskii functional together and established a set of sufficient linear matrix inequalities approach to guarantee the finite-time stability of the system concerned. By employing the Jensen's inequality, free-weighting matrix method and Wirtinger's double integral inequality, the proposed conditions are derived and two numerical examples are addressed for the effectiveness of the developed techniques.
STUDIES IN ASTRONOMICAL TIME SERIES ANALYSIS. VI. BAYESIAN BLOCK REPRESENTATIONS
Energy Technology Data Exchange (ETDEWEB)
Scargle, Jeffrey D. [Space Science and Astrobiology Division, MS 245-3, NASA Ames Research Center, Moffett Field, CA 94035-1000 (United States); Norris, Jay P. [Physics Department, Boise State University, 2110 University Drive, Boise, ID 83725-1570 (United States); Jackson, Brad [The Center for Applied Mathematics and Computer Science, Department of Mathematics, San Jose State University, One Washington Square, MH 308, San Jose, CA 95192-0103 (United States); Chiang, James, E-mail: jeffrey.d.scargle@nasa.gov [W. W. Hansen Experimental Physics Laboratory, Kavli Institute for Particle Astrophysics and Cosmology, Department of Physics and SLAC National Accelerator Laboratory, Stanford University, Stanford, CA 94305 (United States)
2013-02-20
This paper addresses the problem of detecting and characterizing local variability in time series and other forms of sequential data. The goal is to identify and characterize statistically significant variations, at the same time suppressing the inevitable corrupting observational errors. We present a simple nonparametric modeling technique and an algorithm implementing it-an improved and generalized version of Bayesian Blocks-that finds the optimal segmentation of the data in the observation interval. The structure of the algorithm allows it to be used in either a real-time trigger mode, or a retrospective mode. Maximum likelihood or marginal posterior functions to measure model fitness are presented for events, binned counts, and measurements at arbitrary times with known error distributions. Problems addressed include those connected with data gaps, variable exposure, extension to piecewise linear and piecewise exponential representations, multivariate time series data, analysis of variance, data on the circle, other data modes, and dispersed data. Simulations provide evidence that the detection efficiency for weak signals is close to a theoretical asymptotic limit derived by Arias-Castro et al. In the spirit of Reproducible Research all of the code and data necessary to reproduce all of the figures in this paper are included as supplementary material.
Assessing Coupling Dynamics from an Ensemble of Time Series
Directory of Open Access Journals (Sweden)
Germán Gómez-Herrero
2015-04-01
Full Text Available Finding interdependency relations between time series provides valuable knowledge about the processes that generated the signals. Information theory sets a natural framework for important classes of statistical dependencies. However, a reliable estimation from information-theoretic functionals is hampered when the dependency to be assessed is brief or evolves in time. Here, we show that these limitations can be partly alleviated when we have access to an ensemble of independent repetitions of the time series. In particular, we gear a data-efficient estimator of probability densities to make use of the full structure of trial-based measures. By doing so, we can obtain time-resolved estimates for a family of entropy combinations (including mutual information, transfer entropy and their conditional counterparts, which are more accurate than the simple average of individual estimates over trials. We show with simulated and real data generated by coupled electronic circuits that the proposed approach allows one to recover the time-resolved dynamics of the coupling between different subsystems.
Studies in Astronomical Time Series Analysis. VI. Bayesian Block Representations
Scargle, Jeffrey D.; Norris, Jay P.; Jackson, Brad; Chiang, James
2013-01-01
This paper addresses the problem of detecting and characterizing local variability in time series and other forms of sequential data. The goal is to identify and characterize statistically significant variations, at the same time suppressing the inevitable corrupting observational errors. We present a simple nonparametric modeling technique and an algorithm implementing it-an improved and generalized version of Bayesian Blocks [Scargle 1998]-that finds the optimal segmentation of the data in the observation interval. The structure of the algorithm allows it to be used in either a real-time trigger mode, or a retrospective mode. Maximum likelihood or marginal posterior functions to measure model fitness are presented for events, binned counts, and measurements at arbitrary times with known error distributions. Problems addressed include those connected with data gaps, variable exposure, extension to piece- wise linear and piecewise exponential representations, multivariate time series data, analysis of variance, data on the circle, other data modes, and dispersed data. Simulations provide evidence that the detection efficiency for weak signals is close to a theoretical asymptotic limit derived by [Arias-Castro, Donoho and Huo 2003]. In the spirit of Reproducible Research [Donoho et al. (2008)] all of the code and data necessary to reproduce all of the figures in this paper are included as auxiliary material.
STUDIES IN ASTRONOMICAL TIME SERIES ANALYSIS. VI. BAYESIAN BLOCK REPRESENTATIONS
International Nuclear Information System (INIS)
Scargle, Jeffrey D.; Norris, Jay P.; Jackson, Brad; Chiang, James
2013-01-01
This paper addresses the problem of detecting and characterizing local variability in time series and other forms of sequential data. The goal is to identify and characterize statistically significant variations, at the same time suppressing the inevitable corrupting observational errors. We present a simple nonparametric modeling technique and an algorithm implementing it—an improved and generalized version of Bayesian Blocks—that finds the optimal segmentation of the data in the observation interval. The structure of the algorithm allows it to be used in either a real-time trigger mode, or a retrospective mode. Maximum likelihood or marginal posterior functions to measure model fitness are presented for events, binned counts, and measurements at arbitrary times with known error distributions. Problems addressed include those connected with data gaps, variable exposure, extension to piecewise linear and piecewise exponential representations, multivariate time series data, analysis of variance, data on the circle, other data modes, and dispersed data. Simulations provide evidence that the detection efficiency for weak signals is close to a theoretical asymptotic limit derived by Arias-Castro et al. In the spirit of Reproducible Research all of the code and data necessary to reproduce all of the figures in this paper are included as supplementary material.
Time-Series Analysis of Supergranule Characterstics at Solar Minimum
Williams, Peter E.; Pesnell, W. Dean
2013-01-01
Sixty days of Doppler images from the Solar and Heliospheric Observatory (SOHO) / Michelson Doppler Imager (MDI) investigation during the 1996 and 2008 solar minima have been analyzed to show that certain supergranule characteristics (size, size range, and horizontal velocity) exhibit fluctuations of three to five days. Cross-correlating parameters showed a good, positive correlation between supergranulation size and size range, and a moderate, negative correlation between size range and velocity. The size and velocity do exhibit a moderate, negative correlation, but with a small time lag (less than 12 hours). Supergranule sizes during five days of co-temporal data from MDI and the Solar Dynamics Observatory (SDO) / Helioseismic Magnetic Imager (HMI) exhibit similar fluctuations with a high level of correlation between them. This verifies the solar origin of the fluctuations, which cannot be caused by instrumental artifacts according to these observations. Similar fluctuations are also observed in data simulations that model the evolution of the MDI Doppler pattern over a 60-day period. Correlations between the supergranule size and size range time-series derived from the simulated data are similar to those seen in MDI data. A simple toy-model using cumulative, uncorrelated exponential growth and decay patterns at random emergence times produces a time-series similar to the data simulations. The qualitative similarities between the simulated and the observed time-series suggest that the fluctuations arise from stochastic processes occurring within the solar convection zone. This behavior, propagating to surface manifestations of supergranulation, may assist our understanding of magnetic-field-line advection, evolution, and interaction.
Time series analysis of the behavior of brazilian natural rubber
Directory of Open Access Journals (Sweden)
Antônio Donizette de Oliveira
2009-03-01
Full Text Available The natural rubber is a non-wood product obtained of the coagulation of some lattices of forest species, being Hevea brasiliensis the main one. Native from the Amazon Region, this species was already known by the Indians before the discovery of America. The natural rubber became a product globally valued due to its multiple applications in the economy, being its almost perfect substitute the synthetic rubber derived from the petroleum. Similarly to what happens with other countless products the forecast of future prices of the natural rubber has been object of many studies. The use of models of forecast of univariate timeseries stands out as the more accurate and useful to reduce the uncertainty in the economic decision making process. This studyanalyzed the historical series of prices of the Brazilian natural rubber (R$/kg, in the Jan/99 - Jun/2006 period, in order tocharacterize the rubber price behavior in the domestic market; estimated a model for the time series of monthly natural rubberprices; and foresaw the domestic prices of the natural rubber, in the Jul/2006 - Jun/2007 period, based on the estimated models.The studied models were the ones belonging to the ARIMA family. The main results were: the domestic market of the natural rubberis expanding due to the growth of the world economy; among the adjusted models, the ARIMA (1,1,1 model provided the bestadjustment of the time series of prices of the natural rubber (R$/kg; the prognosis accomplished for the series supplied statistically adequate fittings.
Razavi, Saman; Vogel, Richard
2018-02-01
Prewhitening, the process of eliminating or reducing short-term stochastic persistence to enable detection of deterministic change, has been extensively applied to time series analysis of a range of geophysical variables. Despite the controversy around its utility, methodologies for prewhitening time series continue to be a critical feature of a variety of analyses including: trend detection of hydroclimatic variables and reconstruction of climate and/or hydrology through proxy records such as tree rings. With a focus on the latter, this paper presents a generalized approach to exploring the impact of a wide range of stochastic structures of short- and long-term persistence on the variability of hydroclimatic time series. Through this approach, we examine the impact of prewhitening on the inferred variability of time series across time scales. We document how a focus on prewhitened, residual time series can be misleading, as it can drastically distort (or remove) the structure of variability across time scales. Through examples with actual data, we show how such loss of information in prewhitened time series of tree rings (so-called "residual chronologies") can lead to the underestimation of extreme conditions in climate and hydrology, particularly droughts, reconstructed for centuries preceding the historical period.
Monitoring Forest Regrowth Using a Multi-Platform Time Series
Sabol, Donald E., Jr.; Smith, Milton O.; Adams, John B.; Gillespie, Alan R.; Tucker, Compton J.
1996-01-01
Over the past 50 years, the forests of western Washington and Oregon have been extensively harvested for timber. This has resulted in a heterogeneous mosaic of remaining mature forests, clear-cuts, new plantations, and second-growth stands that now occur in areas that formerly were dominated by extensive old-growth forests and younger forests resulting from fire disturbance. Traditionally, determination of seral stage and stand condition have been made using aerial photography and spot field observations, a methodology that is not only time- and resource-intensive, but falls short of providing current information on a regional scale. These limitations may be solved, in part, through the use of multispectral images which can cover large areas at spatial resolutions in the order of tens of meters. The use of multiple images comprising a time series potentially can be used to monitor land use (e.g. cutting and replanting), and to observe natural processes such as regeneration, maturation and phenologic change. These processes are more likely to be spectrally observed in a time series composed of images taken during different seasons over a long period of time. Therefore, for many areas, it may be necessary to use a variety of images taken with different imaging systems. A common framework for interpretation is needed that reduces topographic, atmospheric, instrumental, effects as well as differences in lighting geometry between images. The present state of remote-sensing technology in general use does not realize the full potential of the multispectral data in areas of high topographic relief. For example, the primary method for analyzing images of forested landscapes in the Northwest has been with statistical classifiers (e.g. parallelepiped, nearest-neighbor, maximum likelihood, etc.), often applied to uncalibrated multispectral data. Although this approach has produced useful information from individual images in some areas, landcover classes defined by these
State-space prediction model for chaotic time series
Alparslan, A. K.; Sayar, M.; Atilgan, A. R.
1998-08-01
A simple method for predicting the continuation of scalar chaotic time series ahead in time is proposed. The false nearest neighbors technique in connection with the time-delayed embedding is employed so as to reconstruct the state space. A local forecasting model based upon the time evolution of the topological neighboring in the reconstructed phase space is suggested. A moving root-mean-square error is utilized in order to monitor the error along the prediction horizon. The model is tested for the convection amplitude of the Lorenz model. The results indicate that for approximately 100 cycles of the training data, the prediction follows the actual continuation very closely about six cycles. The proposed model, like other state-space forecasting models, captures the long-term behavior of the system due to the use of spatial neighbors in the state space.
Prediction of Classroom Reverberation Time using Neural Network
Liyana Zainudin, Fathin; Kadir Mahamad, Abd; Saon, Sharifah; Nizam Yahya, Musli
2018-04-01
In this paper, an alternative method for predicting the reverberation time (RT) using neural network (NN) for classroom was designed and explored. Classroom models were created using Google SketchUp software. The NN applied training dataset from the classroom models with RT values that were computed from ODEON 12.10 software. The NN was conducted separately for 500Hz, 1000Hz, and 2000Hz as absorption coefficient that is one of the prominent input variable is frequency dependent. Mean squared error (MSE) and regression (R) values were obtained to examine the NN efficiency. Overall, the NN shows a good result with MSE 0.9. The NN also managed to achieve a percentage of accuracy of 92.53% for 500Hz, 93.66% for 1000Hz, and 93.18% for 2000Hz and thus displays a good and efficient performance. Nevertheless, the optimum RT value is range between 0.75 – 0.9 seconds.
Discovering significant evolution patterns from satellite image time series.
Petitjean, François; Masseglia, Florent; Gançarski, Pierre; Forestier, Germain
2011-12-01
Satellite Image Time Series (SITS) provide us with precious information on land cover evolution. By studying these series of images we can both understand the changes of specific areas and discover global phenomena that spread over larger areas. Changes that can occur throughout the sensing time can spread over very long periods and may have different start time and end time depending on the location, which complicates the mining and the analysis of series of images. This work focuses on frequent sequential pattern mining (FSPM) methods, since this family of methods fits the above-mentioned issues. This family of methods consists of finding the most frequent evolution behaviors, and is actually able to extract long-term changes as well as short term ones, whenever the change may start and end. However, applying FSPM methods to SITS implies confronting two main challenges, related to the characteristics of SITS and the domain's constraints. First, satellite images associate multiple measures with a single pixel (the radiometric levels of different wavelengths corresponding to infra-red, red, etc.), which makes the search space multi-dimensional and thus requires specific mining algorithms. Furthermore, the non evolving regions, which are the vast majority and overwhelm the evolving ones, challenge the discovery of these patterns. We propose a SITS mining framework that enables discovery of these patterns despite these constraints and characteristics. Our proposal is inspired from FSPM and provides a relevant visualization principle. Experiments carried out on 35 images sensed over 20 years show the proposed approach makes it possible to extract relevant evolution behaviors.
Remote-Sensing Time Series Analysis, a Vegetation Monitoring Tool
McKellip, Rodney; Prados, Donald; Ryan, Robert; Ross, Kenton; Spruce, Joseph; Gasser, Gerald; Greer, Randall
2008-01-01
The Time Series Product Tool (TSPT) is software, developed in MATLAB , which creates and displays high signal-to- noise Vegetation Indices imagery and other higher-level products derived from remotely sensed data. This tool enables automated, rapid, large-scale regional surveillance of crops, forests, and other vegetation. TSPT temporally processes high-revisit-rate satellite imagery produced by the Moderate Resolution Imaging Spectroradiometer (MODIS) and by other remote-sensing systems. Although MODIS imagery is acquired daily, cloudiness and other sources of noise can greatly reduce the effective temporal resolution. To improve cloud statistics, the TSPT combines MODIS data from multiple satellites (Aqua and Terra). The TSPT produces MODIS products as single time-frame and multitemporal change images, as time-series plots at a selected location, or as temporally processed image videos. Using the TSPT program, MODIS metadata is used to remove and/or correct bad and suspect data. Bad pixel removal, multiple satellite data fusion, and temporal processing techniques create high-quality plots and animated image video sequences that depict changes in vegetation greenness. This tool provides several temporal processing options not found in other comparable imaging software tools. Because the framework to generate and use other algorithms is established, small modifications to this tool will enable the use of a large range of remotely sensed data types. An effective remote-sensing crop monitoring system must be able to detect subtle changes in plant health in the earliest stages, before the effects of a disease outbreak or other adverse environmental conditions can become widespread and devastating. The integration of the time series analysis tool with ground-based information, soil types, crop types, meteorological data, and crop growth models in a Geographic Information System, could provide the foundation for a large-area crop-surveillance system that could identify
What does scalar timing tell us about neural dynamics?
Directory of Open Access Journals (Sweden)
Harel Z Shouval
2014-06-01
Full Text Available The Scalar Timing Law, which is a temporal domain generalization of the well known Weber Law, states that the errors in estimating temporal intervals scale linearly with the durations of the intervals. Linear scaling has been studied extensively in human and animal models and holds over several orders of magnitude, though to date there is no agreed upon explanation for its physiological basis. Starting from the assumption that behavioral variability stems from neural variability, this work shows how to derive firing rate functions that are consistent with scalar timing. We show that firing rate functions with a log-power form, and a set of parameters that depend on spike count statistics, can account for scalar timing. Our derivation depends on a linear approximation, but we use simulations to validate the theory and show that log-power firing rate functions result in scalar timing over a large range of times and parameters.Simulation results also show that our theory as first posed exhibits a slight bias towards overestimation.We show that this bias can be corrected using a simple iterative approach to learn a decision threshold.
Weighted statistical parameters for irregularly sampled time series
Rimoldini, Lorenzo
2014-01-01
Unevenly spaced time series are common in astronomy because of the day-night cycle, weather conditions, dependence on the source position in the sky, allocated telescope time and corrupt measurements, for example, or inherent to the scanning law of satellites like Hipparcos and the forthcoming Gaia. Irregular sampling often causes clumps of measurements and gaps with no data which can severely disrupt the values of estimators. This paper aims at improving the accuracy of common statistical parameters when linear interpolation (in time or phase) can be considered an acceptable approximation of a deterministic signal. A pragmatic solution is formulated in terms of a simple weighting scheme, adapting to the sampling density and noise level, applicable to large data volumes at minimal computational cost. Tests on time series from the Hipparcos periodic catalogue led to significant improvements in the overall accuracy and precision of the estimators with respect to the unweighted counterparts and those weighted by inverse-squared uncertainties. Automated classification procedures employing statistical parameters weighted by the suggested scheme confirmed the benefits of the improved input attributes. The classification of eclipsing binaries, Mira, RR Lyrae, Delta Cephei and Alpha2 Canum Venaticorum stars employing exclusively weighted descriptive statistics achieved an overall accuracy of 92 per cent, about 6 per cent higher than with unweighted estimators.
Ngan, Chun-Kit
2013-01-01
Making decisions over multivariate time series is an important topic which has gained significant interest in the past decade. A time series is a sequence of data points which are measured and ordered over uniform time intervals. A multivariate time series is a set of multiple, related time series in a particular domain in which domain experts…
The Hierarchical Spectral Merger Algorithm: A New Time Series Clustering Procedure
Euá n, Carolina; Ombao, Hernando; Ortega, Joaquí n
2018-01-01
We present a new method for time series clustering which we call the Hierarchical Spectral Merger (HSM) method. This procedure is based on the spectral theory of time series and identifies series that share similar oscillations or waveforms
Firing patterns transition and desynchronization induced by time delay in neural networks
Huang, Shoufang; Zhang, Jiqian; Wang, Maosheng; Hu, Chin-Kun
2018-06-01
We used the Hindmarsh-Rose (HR) model (Hindmarsh and Rose, 1984) to study the effect of time delay on the transition of firing behaviors and desynchronization in neural networks. As time delay is increased, neural networks exhibit diversity of firing behaviors, including regular spiking or bursting and firing patterns transitions (FPTs). Meanwhile, the desynchronization of firing and unstable bursting with decreasing amplitude in neural system, are also increasingly enhanced with the increase of time delay. Furthermore, we also studied the effect of coupling strength and network randomness on these phenomena. Our results imply that time delays can induce transition and desynchronization of firing behaviors in neural networks. These findings provide new insight into the role of time delay in the firing activities of neural networks, and can help to better understand the firing phenomena in complex systems of neural networks. A possible mechanism in brain that can cause the increase of time delay is discussed.
Neural regions supporting lexical processing of objects and actions: A case series analysis
Directory of Open Access Journals (Sweden)
Bonnie L Breining
2014-04-01
Full Text Available Introduction. Linking semantic representations to lexical items is an important cognitive process for both producing and comprehending language. Past research has suggested that the bilateral anterior temporal lobes are critical for this process (e.g. Patterson, Nestor, & Rogers, 2007. However, the majority of studies focused on object concepts alone, ignoring actions. The few that considered actions suggest that the temporal poles are not critical for their processing (e.g. Kemmerer et al., 2010. In this case series, we investigated the neural substrates of linking object and action concepts to lexical labels by correlating the volume of defined regions of interest with behavioral performance on picture-word verification and picture naming tasks of individuals with primary progressive aphasia (PPA. PPA is a neurodegenerative condition with heterogeneous neuropathological causes, characterized by increasing language deficits for at least two years in the face of relatively intact cognitive function in other domains (Gorno-Tempini et al., 2011. This population displays appropriate heterogeneity of performance and focal atrophy for investigating the neural substrates involved in lexical semantic processing of objects and actions. Method. Twenty-one individuals with PPA participated in behavioral assessment within six months of high resolution anatomical MRI scans. Behavioral assessments consisted of four tasks: picture-word verification and picture naming of objects and actions. Performance on these assessments was correlated with brain volume measured using atlas-based analysis in twenty regions of interest that are commonly atrophied in PPA and implicated in language processing. Results. Impaired performance for all four tasks significantly correlated with atrophy in the right superior temporal pole, left anterior middle temporal gyrus, and left fusiform gyrus. No regions were identified in which volume correlated with performance for both