Maximum entropy methods for extracting the learned features of deep neural networks.

Science.gov (United States)

Finnegan, Alex; Song, Jun S

2017-10-01

New architectures of multilayer artificial neural networks and new methods for training them are rapidly revolutionizing the application of machine learning in diverse fields, including business, social science, physical sciences, and biology. Interpreting deep neural networks, however, currently remains elusive, and a critical challenge lies in understanding which meaningful features a network is actually learning. We present a general method for interpreting deep neural networks and extracting network-learned features from input data. We describe our algorithm in the context of biological sequence analysis. Our approach, based on ideas from statistical physics, samples from the maximum entropy distribution over possible sequences, anchored at an input sequence and subject to constraints implied by the empirical function learned by a network. Using our framework, we demonstrate that local transcription factor binding motifs can be identified from a network trained on ChIP-seq data and that nucleosome positioning signals are indeed learned by a network trained on chemical cleavage nucleosome maps. Imposing a further constraint on the maximum entropy distribution also allows us to probe whether a network is learning global sequence features, such as the high GC content in nucleosome-rich regions. This work thus provides valuable mathematical tools for interpreting and extracting learned features from feed-forward neural networks.

Collaborative Supervised Learning for Sensor Networks

Science.gov (United States)

Wagstaff, Kiri L.; Rebbapragada, Umaa; Lane, Terran

2011-01-01

Collaboration methods for distributed machine-learning algorithms involve the specification of communication protocols for the learners, which can query other learners and/or broadcast their findings preemptively. Each learner incorporates information from its neighbors into its own training set, and they are thereby able to bootstrap each other to higher performance. Each learner resides at a different node in the sensor network and makes observations (collects data) independently of the other learners. After being seeded with an initial labeled training set, each learner proceeds to learn in an iterative fashion. New data is collected and classified. The learner can then either broadcast its most confident classifications for use by other learners, or can query neighbors for their classifications of its least confident items. As such, collaborative learning combines elements of both passive (broadcast) and active (query) learning. It also uses ideas from ensemble learning to combine the multiple responses to a given query into a single useful label. This approach has been evaluated against current non-collaborative alternatives, including training a single classifier and deploying it at all nodes with no further learning possible, and permitting learners to learn from their own most confident judgments, absent interaction with their neighbors. On several data sets, it has been consistently found that active collaboration is the best strategy for a distributed learner network. The main advantages include the ability for learning to take place autonomously by collaboration rather than by requiring intervention from an oracle (usually human), and also the ability to learn in a distributed environment, permitting decisions to be made in situ and to yield faster response time.

Machine learning of network metrics in ATLAS Distributed Data Management

CERN Document Server

AUTHOR|(INSPIRE)INSPIRE-00218873; The ATLAS collaboration; Toler, Wesley; Vamosi, Ralf; Bogado Garcia, Joaquin Ignacio

2017-01-01

The increasing volume of physics data poses a critical challenge to the ATLAS experiment. In anticipation of high luminosity physics, automation of everyday data management tasks has become necessary. Previously many of these tasks required human decision-making and operation. Recent advances in hardware and software have made it possible to entrust more complicated duties to automated systems using models trained by machine learning algorithms. In this contribution we show results from one of our ongoing automation efforts that focuses on network metrics. First, we describe our machine learning framework built atop the ATLAS Analytics Platform. This framework can automatically extract and aggregate data, train models with various machine learning algorithms, and eventually score the resulting models and parameters. Second, we use these models to forecast metrics relevant for network-aware job scheduling and data brokering. We show the characteristics of the data and evaluate the forecasting accuracy of our m...

Learning Latent Structure in Complex Networks

DEFF Research Database (Denmark)

Mørup, Morten; Hansen, Lars Kai

such as the Modularity, it has recently been shown that latent structure in complex networks is learnable by Bayesian generative link distribution models (Airoldi et al., 2008, Hofman and Wiggins, 2008). In this paper we propose a new generative model that allows representation of latent community structure......Latent structure in complex networks, e.g., in the form of community structure, can help understand network dynamics, identify heterogeneities in network properties, and predict ‘missing’ links. While most community detection algorithms are based on optimizing heuristic clustering objectives...... as in the previous Bayesian approaches and in addition allows learning of node specific link properties similar to that in the modularity objective. We employ a new relaxation method for efficient inference in these generative models that allows us to learn the behavior of very large networks. We compare the link...

Redes de aprendizaje, aprendizaje en red Learning Networks, Networked Learning

Directory of Open Access Journals (Sweden)

Peter Sloep

2011-10-01

Full Text Available Las redes de aprendizaje (Learning Networks son redes sociales en línea mediante las cuales los participantes comparten información y colaboran para crear conocimiento. De esta manera, estas redes enriquecen la experiencia de aprendizaje en cualquier contexto de aprendizaje, ya sea de educación formal (en escuelas o universidades o educación no-formal (formación profesional. Aunque el concepto de aprendizaje en red suscita el interés de diferentes actores del ámbito educativo, aún existen muchos interrogantes sobre cómo debe diseñarse el aprendizaje en red para facilitar adecuadamente la educación y la formación. El artículo toma este interrogante como punto de partida, y posteriormente aborda cuestiones como la dinámica de la evolución de las redes de aprendizaje, la importancia de fomentar la confianza entre los participantes y el papel central que desempeña el perfil de usuario en la construcción de la confianza, así como el apoyo entre compañeros. Además, se elabora el proceso de diseño de una red de aprendizaje, y se describe un ejemplo en el contexto universitario. Basándonos en la investigación que actualmente se lleva a cabo en nuestro propio centro y en otros lugares, el capítulo concluye con una visión del futuro de las redes de aprendizaje.Learning Networks are on-line social networks through which users share knowledge with each other and jointly develop new knowledge. This way, Learning Networks may enrich the experience of formal, school-based learning and form a viable setting for professional development. Although networked learning enjoys an increasing interest, many questions remain on how exactly learning in such networked contexts can contribute to successful education and training. Put differently, how should networked learning be designed best to facilitate education and training? Taking this as its point of departure, the chapter addresses such issues as the dynamic evolution of Learning Networks

Structure of Small World Innovation Network and Learning Performance

Directory of Open Access Journals (Sweden)

Shuang Song

2014-01-01

Full Text Available This paper examines the differences of learning performance of 5 MNCs (multinational corporations that filed the largest number of patents in China. We establish the innovation network with the patent coauthorship data by these 5 MNCs and classify the networks by the tail of distribution curve of connections. To make a comparison of the learning performance of these 5 MNCs with differing network structures, we develop an organization learning model by regarding the reality as having m dimensions, which denotes the heterogeneous knowledge about the reality. We further set n innovative individuals that are mutually interactive and own unique knowledge about the reality. A longer (shorter distance between the knowledge of the individual and the reality denotes a lower (higher knowledge level of that individual. Individuals interact with and learn from each other within the small-world network. By making 1,000 numerical simulations and averaging the simulated results, we find that the differing structure of the small-world network leads to the differences of learning performance between these 5 MNCs. The network monopolization negatively impacts and network connectivity positively impacts learning performance. Policy implications in the conclusion section suggest that to improve firm learning performance, it is necessary to establish a flat and connective network.

Learning Analytics for Networked Learning Models

Science.gov (United States)

Joksimovic, Srecko; Hatala, Marek; Gaševic, Dragan

2014-01-01

Teaching and learning in networked settings has attracted significant attention recently. The central topic of networked learning research is human-human and human-information interactions occurring within a networked learning environment. The nature of these interactions is highly complex and usually requires a multi-dimensional approach to…

Bayesian Inference and Online Learning in Poisson Neuronal Networks.

Science.gov (United States)

Huang, Yanping; Rao, Rajesh P N

2016-08-01

Motivated by the growing evidence for Bayesian computation in the brain, we show how a two-layer recurrent network of Poisson neurons can perform both approximate Bayesian inference and learning for any hidden Markov model. The lower-layer sensory neurons receive noisy measurements of hidden world states. The higher-layer neurons infer a posterior distribution over world states via Bayesian inference from inputs generated by sensory neurons. We demonstrate how such a neuronal network with synaptic plasticity can implement a form of Bayesian inference similar to Monte Carlo methods such as particle filtering. Each spike in a higher-layer neuron represents a sample of a particular hidden world state. The spiking activity across the neural population approximates the posterior distribution over hidden states. In this model, variability in spiking is regarded not as a nuisance but as an integral feature that provides the variability necessary for sampling during inference. We demonstrate how the network can learn the likelihood model, as well as the transition probabilities underlying the dynamics, using a Hebbian learning rule. We present results illustrating the ability of the network to perform inference and learning for arbitrary hidden Markov models.

An Autonomous Mobile Agent-Based Distributed Learning Architecture-A Proposal and Analytical Analysis

Directory of Open Access Journals (Sweden)

I. Ahmed M. J. SADIIG

2005-10-01

Full Text Available An Autonomous Mobile Agent-Based Distributed Learning Architecture-A Proposal and Analytical Analysis Dr. I. Ahmed M. J. SADIIG Department of Electrical & Computer EngineeringInternational Islamic University GombakKuala Lumpur-MALAYSIA ABSTRACT The traditional learning paradigm invoving face-to-face interaction with students is shifting to highly data-intensive electronic learning with the advances in Information and Communication Technology. An important component of the e-learning process is the delivery of the learning contents to their intended audience over a network. A distributed learning system is dependent on the network for the efficient delivery of its contents to the user. However, as the demand of information provision and utilization increases on the Internet, the current information service provision and utilization methods are becoming increasingly inefficient. Although new technologies have been employed for efficient learning methodologies within the context of an e-learning environment, the overall efficiency of the learning system is dependent on the mode of distribution and utilization of its learning contents. It is therefore imperative to employ new techniques to meet the service demands of current and future e-learning systems. In this paper, an architecture based on autonomous mobile agents creating a Faded Information Field is proposed. Unlike the centralized information distribution in a conventional e-learning system, the information is decentralized in the proposed architecture resulting in increased efficiency of the overall system for distribution and utilization of system learning contents efficiently and fairly. This architecture holds the potential to address the heterogeneous user requirements as well as the changing conditions of the underlying network.

Networks of Learning

Science.gov (United States)

Bettencourt, Luis; Kaiser, David

2004-03-01

Based on an a historically documented example of scientific discovery - Feynman diagrams as the main calculational tool of theoretical high energy Physics - we map the time evolution of the social network of early adopters through in the US, UK, Japan and the USSR. The spread of the technique for total number of users in each region is then modelled in terms of epidemic models, highlighting parallel and divergent aspects of this analogy. We also show that transient social arrangements develop as the idea is introduced and learned, which later disappear as the technique becomes common knowledge. Such early transient is characterized by abnormally low connectivity distribution powers and by high clustering. This interesting early non-equilibrium stage of network evolution is captured by a new dynamical model for network evolution, which coincides in its long time limit with familiar preferential aggregation dynamics.

Efficient learning strategy of Chinese characters based on network approach.

Directory of Open Access Journals (Sweden)

Xiaoyong Yan

Full Text Available We develop an efficient learning strategy of Chinese characters based on the network of the hierarchical structural relations between Chinese characters. A more efficient strategy is that of learning the same number of useful Chinese characters in less effort or time. We construct a node-weighted network of Chinese characters, where character usage frequencies are used as node weights. Using this hierarchical node-weighted network, we propose a new learning method, the distributed node weight (DNW strategy, which is based on a new measure of nodes' importance that considers both the weight of the nodes and its location in the network hierarchical structure. Chinese character learning strategies, particularly their learning order, are analyzed as dynamical processes over the network. We compare the efficiency of three theoretical learning methods and two commonly used methods from mainstream Chinese textbooks, one for Chinese elementary school students and the other for students learning Chinese as a second language. We find that the DNW method significantly outperforms the others, implying that the efficiency of current learning methods of major textbooks can be greatly improved.

Learning Networks for Lifelong Learning

OpenAIRE

Sloep, Peter

2009-01-01

Presentation in a seminar organized by Christopher Hoadley at Penn State University, October 2004.Contains general introduction into the Learning Network Programme and a demonstration of the Netlogo Simulation of a Learning Network.

Development of neural network for analysis of local power distributions in BWR fuel bundles

International Nuclear Information System (INIS)

Tanabe, Akira; Yamamoto, Toru; Shinfuku, Kimihiro; Nakamae, Takuji.

1993-01-01

A neural network model has been developed to learn the local power distributions in a BWR fuel bundle. A two layers neural network with total 128 elements is used for this model. The neural network learns 33 cases of local power peaking factors of fuel rods with given enrichment distribution as the teacher signals, which were calculated by a fuel bundle nuclear analysis code based on precise physical models. This neural network model studied well the teacher signals within 1 % error. It is also able to calculate the local power distributions within several % error for the different enrichment distributions from the teacher signals when the average enrichment is close to 2 %. This neural network is simple and the computing speed of this model is 300 times faster than that of the precise nuclear analysis code. This model was applied to survey the enrichment distribution to meet a target local power distribution in a fuel bundle, and the enrichment distribution with flat power shape are obtained within short computing time. (author)

DLTAP: A Network-efficient Scheduling Method for Distributed Deep Learning Workload in Containerized Cluster Environment

Directory of Open Access Journals (Sweden)

Qiao Wei

2017-01-01

Full Text Available Deep neural networks (DNNs have recently yielded strong results on a range of applications. Training these DNNs using a cluster of commodity machines is a promising approach since training is time consuming and compute-intensive. Furthermore, putting DNN tasks into containers of clusters would enable broader and easier deployment of DNN-based algorithms. Toward this end, this paper addresses the problem of scheduling DNN tasks in the containerized cluster environment. Efficiently scheduling data-parallel computation jobs like DNN over containerized clusters is critical for job performance, system throughput, and resource utilization. It becomes even more challenging with the complex workloads. We propose a scheduling method called Deep Learning Task Allocation Priority (DLTAP which performs scheduling decisions in a distributed manner, and each of scheduling decisions takes aggregation degree of parameter sever task and worker task into account, in particularly, to reduce cross-node network transmission traffic and, correspondingly, decrease the DNN training time. We evaluate the DLTAP scheduling method using a state-of-the-art distributed DNN training framework on 3 benchmarks. The results show that the proposed method can averagely reduce 12% cross-node network traffic, and decrease the DNN training time even with the cluster of low-end servers.

Simplification of neural network model for predicting local power distributions of BWR fuel bundle using learning algorithm with forgetting

International Nuclear Information System (INIS)

Tanabe, Akira; Yamamoto, Toru; Shinfuku, Kimihiro; Nakamae, Takuji; Nishide, Fusayo.

1995-01-01

Previously a two-layered neural network model was developed to predict the relation between fissile enrichment of each fuel rod and local power distribution in a BWR fuel bundle. This model was obtained intuitively based on 33 patterns of training signals after an intensive survey of the models. Recently, a learning algorithm with forgetting was reported to simplify neural network models. It is an interesting subject what kind of model will be obtained if this algorithm is applied to the complex three-layered model which learns the same training signals. A three-layered model which is expanded to have direct connections between the 1st and the 3rd layer elements has been constructed and the learning method of normal back propagation was applied first to this model. The forgetting algorithm was then added to this learning process. The connections concerned with the 2nd layer elements disappeared and the 2nd layer has become unnecessary. It took a longer computing time by an order to learn the same training signals than the simple back propagation, but the two-layered model was obtained autonomously from the expanded three-layered model. (author)

Infrastructure and distributed learning methodology for privacy-preserving multi-centric rapid learning health care: euroCAT

Directory of Open Access Journals (Sweden)

Timo M. Deist

2017-06-01

The euroCAT infrastructure has been successfully implemented in five radiation clinics across three countries. SVM models can be learned on data distributed over all five clinics. Furthermore, the infrastructure provides a general framework to execute learning algorithms on distributed data. The ongoing expansion of the euroCAT network will facilitate machine learning in radiation oncology. The resulting access to larger datasets with sufficient variation will pave the way for generalizable prediction models and personalized medicine.

Parallel Distributed Processing Theory in the Age of Deep Networks.

Science.gov (United States)

Bowers, Jeffrey S

2017-12-01

Parallel distributed processing (PDP) models in psychology are the precursors of deep networks used in computer science. However, only PDP models are associated with two core psychological claims, namely that all knowledge is coded in a distributed format and cognition is mediated by non-symbolic computations. These claims have long been debated in cognitive science, and recent work with deep networks speaks to this debate. Specifically, single-unit recordings show that deep networks learn units that respond selectively to meaningful categories, and researchers are finding that deep networks need to be supplemented with symbolic systems to perform some tasks. Given the close links between PDP and deep networks, it is surprising that research with deep networks is challenging PDP theory. Copyright © 2017. Published by Elsevier Ltd.

Approximation model of three-dimensional power distribution in boiling water reactor using neural networks

International Nuclear Information System (INIS)

Kobayashi, Yoko; Aiyoshi, Eitaro

2001-01-01

Fast and accurate prediction of three-dimensional (3D) power distribution is essential in a boiling water reactor (BWR). The prediction method of 3D power distribution in BWR is developed using the neural network. Application of the neural network starts with selecting the learning algorithm. In the proposed method, we use the learning algorithms based on a class of Quasi-Newton optimization techniques called Self-Scaling Variable Metric (SSVM) methods. Prediction studies were done for a core of actual BWR plant with octant symmetry. Compared to classical Quasi-Newton methods, it is shown that the SSVM method reduces the number of iterations in the learning mode. The results of prediction demonstrate that the neural network can predict 3D power distribution of BWR reasonably well. The proposed method will be very useful for BWR loading pattern optimization problems where 3D power distribution for a huge number of loading patterns (LPs) must be performed. (author)

Evaluation of the information servicing in a distributed learning ...

African Journals Online (AJOL)

The authors' main idea is to organize a distributed learning environment (DLE) based on information and communication resources of global network in combination with the technologies for virtual reality and 3D simulation. In this reason a conceptual model of the DLE architecture and learning processes is defined, and ...

Integrating distributed Bayesian inference and reinforcement learning for sensor management

NARCIS (Netherlands)

Grappiolo, C.; Whiteson, S.; Pavlin, G.; Bakker, B.

2009-01-01

This paper introduces a sensor management approach that integrates distributed Bayesian inference (DBI) and reinforcement learning (RL). DBI is implemented using distributed perception networks (DPNs), a multiagent approach to performing efficient inference, while RL is used to automatically

Supervised learning of probability distributions by neural networks

Science.gov (United States)

Baum, Eric B.; Wilczek, Frank

1988-01-01

Supervised learning algorithms for feedforward neural networks are investigated analytically. The back-propagation algorithm described by Werbos (1974), Parker (1985), and Rumelhart et al. (1986) is generalized by redefining the values of the input and output neurons as probabilities. The synaptic weights are then varied to follow gradients in the logarithm of likelihood rather than in the error. This modification is shown to provide a more rigorous theoretical basis for the algorithm and to permit more accurate predictions. A typical application involving a medical-diagnosis expert system is discussed.

Research, Boundaries, and Policy in Networked Learning

DEFF Research Database (Denmark)

This book presents cutting-edge, peer reviewed research on networked learning organized by three themes: policy in networked learning, researching networked learning, and boundaries in networked learning. The "policy in networked learning" section explores networked learning in relation to policy...... networks, spaces of algorithmic governance and more. The "boundaries in networked learning" section investigates frameworks of students' digital literacy practices, among other important frameworks in digital learning. Lastly, the "research in networked learning" section delves into new research methods...

Learning Orthographic Structure With Sequential Generative Neural Networks.

Science.gov (United States)

Testolin, Alberto; Stoianov, Ivilin; Sperduti, Alessandro; Zorzi, Marco

2016-04-01

Learning the structure of event sequences is a ubiquitous problem in cognition and particularly in language. One possible solution is to learn a probabilistic generative model of sequences that allows making predictions about upcoming events. Though appealing from a neurobiological standpoint, this approach is typically not pursued in connectionist modeling. Here, we investigated a sequential version of the restricted Boltzmann machine (RBM), a stochastic recurrent neural network that extracts high-order structure from sensory data through unsupervised generative learning and can encode contextual information in the form of internal, distributed representations. We assessed whether this type of network can extract the orthographic structure of English monosyllables by learning a generative model of the letter sequences forming a word training corpus. We show that the network learned an accurate probabilistic model of English graphotactics, which can be used to make predictions about the letter following a given context as well as to autonomously generate high-quality pseudowords. The model was compared to an extended version of simple recurrent networks, augmented with a stochastic process that allows autonomous generation of sequences, and to non-connectionist probabilistic models (n-grams and hidden Markov models). We conclude that sequential RBMs and stochastic simple recurrent networks are promising candidates for modeling cognition in the temporal domain. Copyright © 2015 Cognitive Science Society, Inc.

Structure Learning and Statistical Estimation in Distribution Networks - Part II

Energy Technology Data Exchange (ETDEWEB)

Deka, Deepjyoti [Univ. of Texas, Austin, TX (United States); Backhaus, Scott N. [Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Chertkov, Michael [Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

2015-02-13

Limited placement of real-time monitoring devices in the distribution grid, recent trends notwithstanding, has prevented the easy implementation of demand-response and other smart grid applications. Part I of this paper discusses the problem of learning the operational structure of the grid from nodal voltage measurements. In this work (Part II), the learning of the operational radial structure is coupled with the problem of estimating nodal consumption statistics and inferring the line parameters in the grid. Based on a Linear-Coupled(LC) approximation of AC power flows equations, polynomial time algorithms are designed to identify the structure and estimate nodal load characteristics and/or line parameters in the grid using the available nodal voltage measurements. Then the structure learning algorithm is extended to cases with missing data, where available observations are limited to a fraction of the grid nodes. The efficacy of the presented algorithms are demonstrated through simulations on several distribution test cases.

Conditions for Productive Learning in Network Learning Environments

DEFF Research Database (Denmark)

Ponti, M.; Dirckinck-Holmfeld, Lone; Lindström, B.

2004-01-01

are designed without a deep understanding of the pedagogical, communicative and collaborative conditions embedded in networked learning. Despite the existence of good theoretical views pointing to a social understanding of learning, rather than a traditional individualistic and information processing approach......The Kaleidoscope1 Jointly Executed Integrating Research Project (JEIRP) on Conditions for Productive Networked Learning Environments is developing and elaborating conceptual understandings of Computer Supported Collaborative Learning (CSCL) emphasizing the use of cross-cultural comparative......: Pedagogical design and the dialectics of the digital artefacts, the concept of collaboration, ethics/trust, identity and the role of scaffolding of networked learning environments.   The JEIRP is motivated by the fact that many networked learning environments in various European educational settings...

Exploring the Peer Interaction Effects on Learning Achievement in a Social Learning Platform Based on Social Network Analysis

Science.gov (United States)

Lin, Yu-Tzu; Chen, Ming-Puu; Chang, Chia-Hu; Chang, Pu-Chen

2017-01-01

The benefits of social learning have been recognized by existing research. To explore knowledge distribution in social learning and its effects on learning achievement, we developed a social learning platform and explored students' behaviors of peer interactions by the proposed algorithms based on social network analysis. An empirical study was…

Learning Networks for Professional Development & Lifelong Learning

NARCIS (Netherlands)

Brouns, Francis; Sloep, Peter

2009-01-01

Brouns, F., & Sloep, P. B. (2009). Learning Networks for Professional Development & Lifelong Learning. Presentation of the Learning Network Programme for a Korean delegation of Chonnam National University and Dankook University (researchers dr. Jeeheon Ryu and dr. Minjeong Kim and a Group of PhD and

Distributed Bayesian Networks for User Modeling

DEFF Research Database (Denmark)

Tedesco, Roberto; Dolog, Peter; Nejdl, Wolfgang

2006-01-01

The World Wide Web is a popular platform for providing eLearning applications to a wide spectrum of users. However – as users differ in their preferences, background, requirements, and goals – applications should provide personalization mechanisms. In the Web context, user models used by such ada......The World Wide Web is a popular platform for providing eLearning applications to a wide spectrum of users. However – as users differ in their preferences, background, requirements, and goals – applications should provide personalization mechanisms. In the Web context, user models used...... by such adaptive applications are often partial fragments of an overall user model. The fragments have then to be collected and merged into a global user profile. In this paper we investigate and present algorithms able to cope with distributed, fragmented user models – based on Bayesian Networks – in the context...... of Web-based eLearning platforms. The scenario we are tackling assumes learners who use several systems over time, which are able to create partial Bayesian Networks for user models based on the local system context. In particular, we focus on how to merge these partial user models. Our merge mechanism...

Measurement of void fraction distribution in two-phase flow by impedance CT with neural network

International Nuclear Information System (INIS)

Hayashi, Hideaki; Sumida, Isao; Sakai, Sinji; Wakai, Kazunori

1996-01-01

This paper describes a new method for measurement of void distribution using impedance CT with a hierarchical neural network. The present method consists of four processes. First, output electric currents are calculated by simulation of various distributions of void fraction. The relationship between distribution of void fraction and electric current is called 'teaching data'. Second, the neural network learns the teaching data by the back propagation method. Third, output electric currents are measured about actual two-phase flow. Finally, distribution of void fraction is calculated by the taught neural network using the measured electric currents. In this paper, measurement and learning parameters are adjusted, experimental results obtained using the impedance CT method are compared with data obtained by the impedance probe method. The results show that our method is effective for measurement of void fraction distribution. (author)

Deep Learning for Distribution Channels' Management

Directory of Open Access Journals (Sweden)

Sabina-Cristiana NECULA

2017-01-01

Full Text Available This paper presents an experiment of using deep learning models for distribution channel management. We present an approach that combines self-organizing maps with artificial neural network with multiple hidden layers in order to identify the potential sales that might be addressed for channel distribution change/ management. Our study aims to highlight the evolution of techniques from simple features/learners to more complex learners and feature engineering or sampling techniques. This paper will allow researchers to choose best suited techniques and features to prepare their churn prediction models.

Network Learning and Innovation in SME Formal Networks

Directory of Open Access Journals (Sweden)

Jivka Deiters

2013-02-01

Full Text Available The driver for this paper is the need to better understand the potential for learning and innovation that networks canprovide especially for small and medium sized enterprises (SMEs which comprise by far the majority of enterprises in the food sector. With the challenges the food sector is facing in the near future, learning and innovation or more focused, as it is being discussed in the paper, ‘learning for innovation’ are not just opportunities but pre‐conditions for the sustainability of the sector. Network initiatives that could provide appropriate support involve social interaction and knowledge exchange, learning, competence development, and coordination (organization and management of implementation. The analysis identifies case studies in any of these orientations which serve different stages of the innovation process: invention and implementation. The variety of network case studies cover networks linked to a focus group for training, research, orconsulting, networks dealing with focused market oriented product or process development, promotional networks, and networks for open exchange and social networking.

Mocapy++ - a toolkit for inference and learning in dynamic Bayesian networks

DEFF Research Database (Denmark)

Paluszewski, Martin; Hamelryck, Thomas Wim

2010-01-01

Background Mocapy++ is a toolkit for parameter learning and inference in dynamic Bayesian networks (DBNs). It supports a wide range of DBN architectures and probability distributions, including distributions from directional statistics (the statistics of angles, directions and orientations...

Machine learning of network metrics in ATLAS Distributed Data Management

Science.gov (United States)

Lassnig, Mario; Toler, Wesley; Vamosi, Ralf; Bogado, Joaquin; ATLAS Collaboration

2017-10-01

The increasing volume of physics data poses a critical challenge to the ATLAS experiment. In anticipation of high luminosity physics, automation of everyday data management tasks has become necessary. Previously many of these tasks required human decision-making and operation. Recent advances in hardware and software have made it possible to entrust more complicated duties to automated systems using models trained by machine learning algorithms. In this contribution we show results from one of our ongoing automation efforts that focuses on network metrics. First, we describe our machine learning framework built atop the ATLAS Analytics Platform. This framework can automatically extract and aggregate data, train models with various machine learning algorithms, and eventually score the resulting models and parameters. Second, we use these models to forecast metrics relevant for networkaware job scheduling and data brokering. We show the characteristics of the data and evaluate the forecasting accuracy of our models.

Bayesian Belief Networks for predicting drinking water distribution system pipe breaks

International Nuclear Information System (INIS)

Francis, Royce A.; Guikema, Seth D.; Henneman, Lucas

2014-01-01

In this paper, we use Bayesian Belief Networks (BBNs) to construct a knowledge model for pipe breaks in a water zone. To the authors’ knowledge, this is the first attempt to model drinking water distribution system pipe breaks using BBNs. Development of expert systems such as BBNs for analyzing drinking water distribution system data is not only important for pipe break prediction, but is also a first step in preventing water loss and water quality deterioration through the application of machine learning techniques to facilitate data-based distribution system monitoring and asset management. Due to the difficulties in collecting, preparing, and managing drinking water distribution system data, most pipe break models can be classified as “statistical–physical” or “hypothesis-generating.” We develop the BBN with the hope of contributing to the “hypothesis-generating” class of models, while demonstrating the possibility that BBNs might also be used as “statistical–physical” models. Our model is learned from pipe breaks and covariate data from a mid-Atlantic United States (U.S.) drinking water distribution system network. BBN models are learned using a constraint-based method, a score-based method, and a hybrid method. Model evaluation is based on log-likelihood scoring. Sensitivity analysis using mutual information criterion is also reported. While our results indicate general agreement with prior results reported in pipe break modeling studies, they also suggest that it may be difficult to select among model alternatives. This model uncertainty may mean that more research is needed for understanding whether additional pipe break risk factors beyond age, break history, pipe material, and pipe diameter might be important for asset management planning. - Highlights: • We show Bayesian Networks for predictive and diagnostic management of water distribution systems. • Our model may enable system operators and managers to prioritize system

Voltage regulation in distribution networks with distributed generation

Science.gov (United States)

Blažič, B.; Uljanić, B.; Papič, I.

2012-11-01

The paper deals with the topic of voltage regulation in distribution networks with relatively high distributed energy resources (DER) penetration. The problem of voltage rise is described and different options for voltage regulation are given. The influence of DER on voltage profile and the effectiveness of the investigated solutions are evaluated by means of simulation in DIgSILENT. The simulated network is an actual distribution network in Slovenia with a relatively high penetration of distributed generation. Recommendations for voltage control in networks with DER penetration are given at the end.

A Database for Decision-Making in Training and Distributed Learning Technology

National Research Council Canada - National Science Library

Stouffer, Virginia

1998-01-01

.... A framework for incorporating data about distributed learning courseware into the existing training database was devised and a plan for a national electronic courseware redistribution network was recommended...

An efficient approach for electric load forecasting using distributed ART (adaptive resonance theory) and HS-ARTMAP (Hyper-spherical ARTMAP network) neural network

International Nuclear Information System (INIS)

Cai, Yuan; Wang, Jian-zhou; Tang, Yun; Yang, Yu-chen

2011-01-01

This paper presents a neural network based on adaptive resonance theory, named distributed ART (adaptive resonance theory) and HS-ARTMAP (Hyper-spherical ARTMAP network), applied to the electric load forecasting problem. The distributed ART combines the stable fast learning capabilities of winner-take-all ART systems with the noise tolerance and code compression capabilities of multi-layer perceptions. The HS-ARTMAP, a hybrid of an RBF (Radial Basis Function)-network-like module which uses hyper-sphere basis function substitute the Gaussian basis function and an ART-like module, performs incremental learning capabilities in function approximation problem. The HS-ARTMAP only receives the compressed distributed coding processed by distributed ART to deal with the proliferation problem which ARTMAP (adaptive resonance theory map) architecture often encounters and still performs well in electric load forecasting. To demonstrate the performance of the methodology, data from New South Wales and Victoria in Australia are illustrated. Results show that the developed method is much better than the traditional BP and single HS-ARTMAP neural network. -- Research highlights: → The processing of the presented network is based on compressed distributed data. It's an innovation among the adaptive resonance theory architecture. → The presented network decreases the proliferation the Fuzzy ARTMAP architectures usually encounter. → The network on-line forecasts electrical load accurately, stably. → Both one-period and multi-period load forecasting are executed using data of different cities.

Markov Chain Monte Carlo Bayesian Learning for Neural Networks

Science.gov (United States)

Goodrich, Michael S.

2011-01-01

Conventional training methods for neural networks involve starting al a random location in the solution space of the network weights, navigating an error hyper surface to reach a minimum, and sometime stochastic based techniques (e.g., genetic algorithms) to avoid entrapment in a local minimum. It is further typically necessary to preprocess the data (e.g., normalization) to keep the training algorithm on course. Conversely, Bayesian based learning is an epistemological approach concerned with formally updating the plausibility of competing candidate hypotheses thereby obtaining a posterior distribution for the network weights conditioned on the available data and a prior distribution. In this paper, we developed a powerful methodology for estimating the full residual uncertainty in network weights and therefore network predictions by using a modified Jeffery's prior combined with a Metropolis Markov Chain Monte Carlo method.

Robust Learning of High-dimensional Biological Networks with Bayesian Networks

Science.gov (United States)

Nägele, Andreas; Dejori, Mathäus; Stetter, Martin

Structure learning of Bayesian networks applied to gene expression data has become a potentially useful method to estimate interactions between genes. However, the NP-hardness of Bayesian network structure learning renders the reconstruction of the full genetic network with thousands of genes unfeasible. Consequently, the maximal network size is usually restricted dramatically to a small set of genes (corresponding with variables in the Bayesian network). Although this feature reduction step makes structure learning computationally tractable, on the downside, the learned structure might be adversely affected due to the introduction of missing genes. Additionally, gene expression data are usually very sparse with respect to the number of samples, i.e., the number of genes is much greater than the number of different observations. Given these problems, learning robust network features from microarray data is a challenging task. This chapter presents several approaches tackling the robustness issue in order to obtain a more reliable estimation of learned network features.

Communication-Free Distributed Coverage for Networked Systems

KAUST Repository

Yazicioglu, A. Yasin

2016-01-15

In this paper, we present a communication-free algorithm for distributed coverage of an arbitrary network by a group of mobile agents with local sensing capabilities. The network is represented as a graph, and the agents are arbitrarily deployed on some nodes of the graph. Any node of the graph is covered if it is within the sensing range of at least one agent. The agents are mobile devices that aim to explore the graph and to optimize their locations in a decentralized fashion by relying only on their sensory inputs. We formulate this problem in a game theoretic setting and propose a communication-free learning algorithm for maximizing the coverage.

Multiple brain networks underpinning word learning from fluent speech revealed by independent component analysis.

Science.gov (United States)

López-Barroso, Diana; Ripollés, Pablo; Marco-Pallarés, Josep; Mohammadi, Bahram; Münte, Thomas F; Bachoud-Lévi, Anne-Catherine; Rodriguez-Fornells, Antoni; de Diego-Balaguer, Ruth

2015-04-15

Although neuroimaging studies using standard subtraction-based analysis from functional magnetic resonance imaging (fMRI) have suggested that frontal and temporal regions are involved in word learning from fluent speech, the possible contribution of different brain networks during this type of learning is still largely unknown. Indeed, univariate fMRI analyses cannot identify the full extent of distributed networks that are engaged by a complex task such as word learning. Here we used Independent Component Analysis (ICA) to characterize the different brain networks subserving word learning from an artificial language speech stream. Results were replicated in a second cohort of participants with a different linguistic background. Four spatially independent networks were associated with the task in both cohorts: (i) a dorsal Auditory-Premotor network; (ii) a dorsal Sensory-Motor network; (iii) a dorsal Fronto-Parietal network; and (iv) a ventral Fronto-Temporal network. The level of engagement of these networks varied through the learning period with only the dorsal Auditory-Premotor network being engaged across all blocks. In addition, the connectivity strength of this network in the second block of the learning phase correlated with the individual variability in word learning performance. These findings suggest that: (i) word learning relies on segregated connectivity patterns involving dorsal and ventral networks; and (ii) specifically, the dorsal auditory-premotor network connectivity strength is directly correlated with word learning performance. Copyright © 2015 Elsevier Inc. All rights reserved.

Neural networks and statistical learning

CERN Document Server

Du, Ke-Lin

2014-01-01

Providing a broad but in-depth introduction to neural network and machine learning in a statistical framework, this book provides a single, comprehensive resource for study and further research. All the major popular neural network models and statistical learning approaches are covered with examples and exercises in every chapter to develop a practical working understanding of the content. Each of the twenty-five chapters includes state-of-the-art descriptions and important research results on the respective topics. The broad coverage includes the multilayer perceptron, the Hopfield network, associative memory models, clustering models and algorithms, the radial basis function network, recurrent neural networks, principal component analysis, nonnegative matrix factorization, independent component analysis, discriminant analysis, support vector machines, kernel methods, reinforcement learning, probabilistic and Bayesian networks, data fusion and ensemble learning, fuzzy sets and logic, neurofuzzy models, hardw...

Collective learning for the emergence of social norms in networked multiagent systems.

Science.gov (United States)

Yu, Chao; Zhang, Minjie; Ren, Fenghui

2014-12-01

Social norms such as social rules and conventions play a pivotal role in sustaining system order by regulating and controlling individual behaviors toward a global consensus in large-scale distributed systems. Systematic studies of efficient mechanisms that can facilitate the emergence of social norms enable us to build and design robust distributed systems, such as electronic institutions and norm-governed sensor networks. This paper studies the emergence of social norms via learning from repeated local interactions in networked multiagent systems. A collective learning framework, which imitates the opinion aggregation process in human decision making, is proposed to study the impact of agent local collective behaviors on the emergence of social norms in a number of different situations. In the framework, each agent interacts repeatedly with all of its neighbors. At each step, an agent first takes a best-response action toward each of its neighbors and then combines all of these actions into a final action using ensemble learning methods. Extensive experiments are carried out to evaluate the framework with respect to different network topologies, learning strategies, numbers of actions, influences of nonlearning agents, and so on. Experimental results reveal some significant insights into the manipulation and control of norm emergence in networked multiagent systems achieved through local collective behaviors.

Blending Formal and Informal Learning Networks for Online Learning

Science.gov (United States)

Czerkawski, Betül C.

2016-01-01

With the emergence of social software and the advance of web-based technologies, online learning networks provide invaluable opportunities for learning, whether formal or informal. Unlike top-down, instructor-centered, and carefully planned formal learning settings, informal learning networks offer more bottom-up, student-centered participatory…

Networked professional learning

NARCIS (Netherlands)

Sloep, Peter

2013-01-01

Sloep, P. B. (2013). Networked professional learning. In A. Littlejohn, & A. Margaryan (Eds.), Technology-enhanced Professional Learning: Processes, Practices and Tools (pp. 97–108). London: Routledge.

Computational Aspects of Sensor Network Protocols (Distributed Sensor Network Simulator

Directory of Open Access Journals (Sweden)

Vasanth Iyer

2009-08-01

Full Text Available In this work, we model the sensor networks as an unsupervised learning and clustering process. We classify nodes according to its static distribution to form known class densities (CCPD. These densities are chosen from specific cross-layer features which maximizes lifetime of power-aware routing algorithms. To circumvent computational complexities of a power-ware communication STACK we introduce path-loss models at the nodes only for high density deployments. We study the cluster heads and formulate the data handling capacity for an expected deployment and use localized probability models to fuse the data with its side information before transmission. So each cluster head has a unique Pmax but not all cluster heads have the same measured value. In a lossless mode if there are no faults in the sensor network then we can show that the highest probability given by Pmax is ambiguous if its frequency is ≤ n/2 otherwise it can be determined by a local function. We further show that the event detection at the cluster heads can be modelled with a pattern 2m and m, the number of bits can be a correlated pattern of 2 bits and for a tight lower bound we use 3-bit Huffman codes which have entropy < 1. These local algorithms are further studied to optimize on power, fault detection and to maximize on the distributed routing algorithm used at the higher layers. From these bounds in large network, it is observed that the power dissipation is network size invariant. The performance of the routing algorithms solely based on success of finding healthy nodes in a large distribution. It is also observed that if the network size is kept constant and the density of the nodes is kept closer then the local pathloss model effects the performance of the routing algorithms. We also obtain the maximum intensity of transmitting nodes for a given category of routing algorithms for an outage constraint, i.e., the lifetime of sensor network.

Distributed data networks: a blueprint for Big Data sharing and healthcare analytics.

Science.gov (United States)

Popovic, Jennifer R

2017-01-01

This paper defines the attributes of distributed data networks and outlines the data and analytic infrastructure needed to build and maintain a successful network. We use examples from one successful implementation of a large-scale, multisite, healthcare-related distributed data network, the U.S. Food and Drug Administration-sponsored Sentinel Initiative. Analytic infrastructure-development concepts are discussed from the perspective of promoting six pillars of analytic infrastructure: consistency, reusability, flexibility, scalability, transparency, and reproducibility. This paper also introduces one use case for machine learning algorithm development to fully utilize and advance the portfolio of population health analytics, particularly those using multisite administrative data sources. © 2016 New York Academy of Sciences.

Machine Learning for ATLAS DDM Network Metrics

CERN Document Server

Lassnig, Mario; The ATLAS collaboration; Vamosi, Ralf

2016-01-01

The increasing volume of physics data is posing a critical challenge to the ATLAS experiment. In anticipation of high luminosity physics, automation of everyday data management tasks has become necessary. Previously many of these tasks required human decision-making and operation. Recent advances in hardware and software have made it possible to entrust more complicated duties to automated systems using models trained by machine learning algorithms. In this contribution we show results from our ongoing automation efforts. First, we describe our framework for distributed data management and network metrics, automatically extract and aggregate data, train models with various machine learning algorithms, and eventually score the resulting models and parameters. Second, we use these models to forecast metrics relevant for network-aware job scheduling and data brokering. We show the characteristics of the data and evaluate the forecasting accuracy of our models.

Continuous Learning of a Multilayered Network Topology in a Video Camera Network

Directory of Open Access Journals (Sweden)

Zou Xiaotao

2009-01-01

Full Text Available Abstract A multilayered camera network architecture with nodes as entry/exit points, cameras, and clusters of cameras at different layers is proposed. Unlike existing methods that used discrete events or appearance information to infer the network topology at a single level, this paper integrates face recognition that provides robustness to appearance changes and better models the time-varying traffic patterns in the network. The statistical dependence between the nodes, indicating the connectivity and traffic patterns of the camera network, is represented by a weighted directed graph and transition times that may have multimodal distributions. The traffic patterns and the network topology may be changing in the dynamic environment. We propose a Monte Carlo Expectation-Maximization algorithm-based continuous learning mechanism to capture the latent dynamically changing characteristics of the network topology. In the experiments, a nine-camera network with twenty-five nodes (at the lowest level is analyzed both in simulation and in real-life experiments and compared with previous approaches.

Continuous Learning of a Multilayered Network Topology in a Video Camera Network

Directory of Open Access Journals (Sweden)

Xiaotao Zou

2009-01-01

Full Text Available A multilayered camera network architecture with nodes as entry/exit points, cameras, and clusters of cameras at different layers is proposed. Unlike existing methods that used discrete events or appearance information to infer the network topology at a single level, this paper integrates face recognition that provides robustness to appearance changes and better models the time-varying traffic patterns in the network. The statistical dependence between the nodes, indicating the connectivity and traffic patterns of the camera network, is represented by a weighted directed graph and transition times that may have multimodal distributions. The traffic patterns and the network topology may be changing in the dynamic environment. We propose a Monte Carlo Expectation-Maximization algorithm-based continuous learning mechanism to capture the latent dynamically changing characteristics of the network topology. In the experiments, a nine-camera network with twenty-five nodes (at the lowest level is analyzed both in simulation and in real-life experiments and compared with previous approaches.

Distributed computing methodology for training neural networks in an image-guided diagnostic application.

Science.gov (United States)

Plagianakos, V P; Magoulas, G D; Vrahatis, M N

2006-03-01

Distributed computing is a process through which a set of computers connected by a network is used collectively to solve a single problem. In this paper, we propose a distributed computing methodology for training neural networks for the detection of lesions in colonoscopy. Our approach is based on partitioning the training set across multiple processors using a parallel virtual machine. In this way, interconnected computers of varied architectures can be used for the distributed evaluation of the error function and gradient values, and, thus, training neural networks utilizing various learning methods. The proposed methodology has large granularity and low synchronization, and has been implemented and tested. Our results indicate that the parallel virtual machine implementation of the training algorithms developed leads to considerable speedup, especially when large network architectures and training sets are used.

Learning automaton newtork and its dynamics. Gakushu automaton network to sono dynamics

Energy Technology Data Exchange (ETDEWEB)

Quan, F [Hiroshima-Denki Institute of Technology, Hiroshima (Jpaan); Unno, F; Hirata, H [Chiba Univ., Chiba (Japan)

1991-10-20

In order to construct a distributed processing system having learning automata as autonomous elements, a reinforcement learning network of the automaton is proposed and it{prime}s dynamics is investigated. In this paper, it is attempted to add another level of meaning to computational cooperativity by using a reinforcement learning network with generalized leaning automata. The collection of learning automata in the team situation acts as self-interested agents that work toward improving their performance with respect to their individual preference ordering. In the global state space of the network, the case of partially synchronous stochastic process is considered. In this case, the existence of mean field is shown and a reinforcement learning algorithm which can make the dynamics on the average reinforcement trajectory is presented. This algorithm is shown to have a high convergence speed as a result of a simple experiment. 14 refs., 9 figs.

A Parameter Communication Optimization Strategy for Distributed Machine Learning in Sensors.

Science.gov (United States)

Zhang, Jilin; Tu, Hangdi; Ren, Yongjian; Wan, Jian; Zhou, Li; Li, Mingwei; Wang, Jue; Yu, Lifeng; Zhao, Chang; Zhang, Lei

2017-09-21

In order to utilize the distributed characteristic of sensors, distributed machine learning has become the mainstream approach, but the different computing capability of sensors and network delays greatly influence the accuracy and the convergence rate of the machine learning model. Our paper describes a reasonable parameter communication optimization strategy to balance the training overhead and the communication overhead. We extend the fault tolerance of iterative-convergent machine learning algorithms and propose the Dynamic Finite Fault Tolerance (DFFT). Based on the DFFT, we implement a parameter communication optimization strategy for distributed machine learning, named Dynamic Synchronous Parallel Strategy (DSP), which uses the performance monitoring model to dynamically adjust the parameter synchronization strategy between worker nodes and the Parameter Server (PS). This strategy makes full use of the computing power of each sensor, ensures the accuracy of the machine learning model, and avoids the situation that the model training is disturbed by any tasks unrelated to the sensors.

Large-Scale Cooperative Task Distribution on Peer-to-Peer Networks

Science.gov (United States)

2012-01-01

SUBTITLE Large-scale cooperative task distribution on peer-to-peer networks 5a. CONTRACT NUMBER 5b. GRANT NUMBER 5c. PROGRAM ELEMENT NUMBER 6...disadvantages of ML- Chord are its fixed size (two layers), and limited scala - bility for large-scale systems. RC-Chord extends ML- D. Karrels et al...configurable before runtime. This can be improved by incorporating a distributed learning algorithm to tune the number and range of the DLoE tracking

The neighborhood MCMC sampler for learning Bayesian networks

Science.gov (United States)

Alyami, Salem A.; Azad, A. K. M.; Keith, Jonathan M.

2016-07-01

Getting stuck in local maxima is a problem that arises while learning Bayesian networks (BNs) structures. In this paper, we studied a recently proposed Markov chain Monte Carlo (MCMC) sampler, called the Neighbourhood sampler (NS), and examined how efficiently it can sample BNs when local maxima are present. We assume that a posterior distribution f(N,E|D) has been defined, where D represents data relevant to the inference, N and E are the sets of nodes and directed edges, respectively. We illustrate the new approach by sampling from such a distribution, and inferring BNs. The simulations conducted in this paper show that the new learning approach substantially avoids getting stuck in local modes of the distribution, and achieves a more rapid rate of convergence, compared to other common algorithms e.g. the MCMC Metropolis-Hastings sampler.

Distribution-Preserving Stratified Sampling for Learning Problems.

Science.gov (United States)

Cervellera, Cristiano; Maccio, Danilo

2017-06-09

The need for extracting a small sample from a large amount of real data, possibly streaming, arises routinely in learning problems, e.g., for storage, to cope with computational limitations, obtain good training/test/validation sets, and select minibatches for stochastic gradient neural network training. Unless we have reasons to select the samples in an active way dictated by the specific task and/or model at hand, it is important that the distribution of the selected points is as similar as possible to the original data. This is obvious for unsupervised learning problems, where the goal is to gain insights on the distribution of the data, but it is also relevant for supervised problems, where the theory explains how the training set distribution influences the generalization error. In this paper, we analyze the technique of stratified sampling from the point of view of distances between probabilities. This allows us to introduce an algorithm, based on recursive binary partition of the input space, aimed at obtaining samples that are distributed as much as possible as the original data. A theoretical analysis is proposed, proving the (greedy) optimality of the procedure together with explicit error bounds. An adaptive version of the algorithm is also introduced to cope with streaming data. Simulation tests on various data sets and different learning tasks are also provided.

Elements of learning technologies designing of engineering networks heat

Directory of Open Access Journals (Sweden)

Sidorkina Irina G.

2016-01-01

Full Text Available Modern educational systems function as a medium fast analysis of shared information that defines them as analytical. The purpose of analytical information processing systems: working with distributed data on a global computer networks, mining and processing of semi structured information, knowledge. Existing mathematical and heuristic methods for the automated synthesis of electronic courses and their corresponding algorithms do not allow the full compliance of development realized in the form of adequate criteria for the totality of the properties distributed educational systems within acceptable time limits and characteristic. Therefore, the development of electronic educational applications must be accompanied by a variety of software support intelligent and adaptive functions. In addition, there is no theoretical justification for integrative aspects and their practical applications for intelligent and adaptive systems of designing distance learning courses. Currently, this type of problem may be considered as a potentially promising. The article presents the functionality of the e-learning course on the design engineering of thermal networks, process modeling in engineering networks with the solution of energy efficiency, detection of problem areas; identify the irrational layout of heaters and others.

Social Interaction in Learning Networks

NARCIS (Netherlands)

Sloep, Peter

2009-01-01

The original publication is available from www.springerlink.com. Sloep, P. (2009). Social Interaction in Learning Networks. In R. Koper (Ed.), Learning Network Services for Professional Development (pp 13-15). Berlin, Germany: Springer Verlag.

Artificial intelligence in diagnosis and supply restoration for a distribution network

Energy Technology Data Exchange (ETDEWEB)

Teo, C.Y.; Gooi, H.B. [Nanyang Technological University (Singapore). School of Electrical and Electronic Engineering

1998-07-01

The development of a PC-based integrated system, to illustrate the application of artificial intelligence in the fault diagnosis and supply restoration for an interconnected distribution network is described. The intelligent process utilises the post-fault network status, a list of the tripped breakers, main protection alarm, and the conventional event log. The fault diagnostic system is implemented by three independent mechanisms, namely the generic core rule, specific post-fault network matching, and generic relay inference rules. The intelligent restoration process is implemented by the switching check, the dynamic restoration algorithm and the mechanism for restoration by record matching and learning. By linking to a PC-based distribution simulator it has been demonstrated that the developed mechanisms enable the correct deduction of fault under different network configurations. The appropriate restoration plan can also be generated to restore supply to the entire restorable load for various post-fault networks. This system is currently used for undergraduate teaching and will be ideal for the training of network operation engineers. As the system developed is generic and can be used for a general network, it can be further developed for practical operation in a subtransmission system or an urban distribution system operated in any configuration. (author)

New designing of E-Learning systems with using network learning

OpenAIRE

Malayeri, Amin Daneshmand; Abdollahi, Jalal

2010-01-01

One of the most applied learning in virtual spaces is using E-Learning systems. Some E-Learning methodologies has been introduced, but the main subject is the most positive feedback from E-Learning systems. In this paper, we introduce a new methodology of E-Learning systems entitle "Network Learning" with review of another aspects of E-Learning systems. Also, we present benefits and advantages of using these systems in educating and fast learning programs. Network Learning can be programmable...

Practice and Learning: Spatiotemporal Differences in Thalamo-Cortical-Cerebellar Networks Engagement across Learning Phases in Schizophrenia.

Science.gov (United States)

Korostil, Michele; Remington, Gary; McIntosh, Anthony Randal

2016-01-01

Understanding how practice mediates the transition of brain-behavior networks between early and later stages of learning is constrained by the common approach to analysis of fMRI data. Prior imaging studies have mostly relied on a single scan, and parametric, task-related analyses. Our experiment incorporates a multisession fMRI lexicon-learning experiment with multivariate, whole-brain analysis to further knowledge of the distributed networks supporting practice-related learning in schizophrenia (SZ). Participants with SZ were compared with healthy control (HC) participants as they learned a novel lexicon during two fMRI scans over a several day period. All participants were trained to equal task proficiency prior to scanning. Behavioral-Partial Least Squares, a multivariate analytic approach, was used to analyze the imaging data. Permutation testing was used to determine statistical significance and bootstrap resampling to determine the reliability of the findings. With practice, HC participants transitioned to a brain-accuracy network incorporating dorsostriatal regions in late-learning stages. The SZ participants did not transition to this pattern despite comparable behavioral results. Instead, successful learners with SZ were differentiated primarily on the basis of greater engagement of perceptual and perceptual-integration brain regions. There is a different spatiotemporal unfolding of brain-learning relationships in SZ. In SZ, given the same amount of practice, the movement from networks suggestive of effortful learning toward subcortically driven procedural one differs from HC participants. Learning performance in SZ is driven by varying levels of engagement in perceptual regions, which suggests perception itself is impaired and may impact downstream, "higher level" cognition.

MACHINE LEARNING FOR THE SELF-ORGANIZATION OF DISTRIBUTED SYSTEMS IN ECONOMIC APPLICATIONS

OpenAIRE

Jerzy Balicki; Waldemar Korłub

2017-01-01

In this paper, an application of machine learning to the problem of self-organization of distributed systems has been discussed with regard to economic applications, with particular emphasis on supervised neural network learning to predict stock investments and some ratings of companies. In addition, genetic programming can play an important role in the preparation and testing of several financial information systems. For this reason, machine learning applications have been discussed because ...

Distributed sensor networks

CERN Document Server

Rubin, Donald B; Carlin, John B; Iyengar, S Sitharama; Brooks, Richard R; University, Clemson

2014-01-01

An Overview, S.S. Iyengar, Ankit Tandon, and R.R. BrooksMicrosensor Applications, David ShepherdA Taxonomy of Distributed Sensor Networks, Shivakumar Sastry and S.S. IyengarContrast with Traditional Systems, R.R. BrooksDigital Signal Processing Background, Yu Hen HuImage-Processing Background Lynne Grewe and Ben ShahshahaniObject Detection and Classification, Akbar M. SayeedParameter Estimation David FriedlanderTarget Tracking with Self-Organizing Distributed Sensors R.R. Brooks, C. Griffin, D.S. Friedlander, and J.D. KochCollaborative Signal and Information Processing: AnInformation-Directed Approach Feng Zhao, Jie Liu, Juan Liu, Leonidas Guibas, and James ReichEnvironmental Effects, David C. SwansonDetecting and Counteracting Atmospheric Effects Lynne L. GreweSignal Processing and Propagation for Aeroacoustic Sensor Networks, Richard J. Kozick, Brian M. Sadler, and D. Keith WilsonDistributed Multi-Target Detection in Sensor Networks Xiaoling Wang, Hairong Qi, and Steve BeckFoundations of Data Fusion f...

Simultaneous allocation of distributed resources using improved teaching learning based optimization

International Nuclear Information System (INIS)

Kanwar, Neeraj; Gupta, Nikhil; Niazi, K.R.; Swarnkar, Anil

2015-01-01

Highlights: • Simultaneous allocation of distributed energy resources in distribution networks. • Annual energy loss reduction is optimized using a multi-level load profile. • A new penalty factor approach is suggested to check node voltage deviations. • An improved TLBO is proposed by suggesting several modifications in standard TLBO. • An intelligent search is proposed to enhance the performance of solution technique. - Abstract: Active and reactive power flow in distribution networks can be effectively controlled by optimally placing distributed resources like shunt capacitors and distributed generators. This paper presents improved variant of Teaching Learning Based Optimization (TLBO) to efficiently and effectively deal with the problem of simultaneous allocation of these distributed resources in radial distribution networks while considering multi-level load scenario. Several algorithm specific modifications are suggested in the standard form of TLBO to cope against the intrinsic flaws of this technique. In addition, an intelligent search approach is proposed to restrict the problem search space without loss of diversity. This enhances the overall performance of the proposed method. The proposed method is investigated on IEEE 33-bus, 69-bus and 83-bus test distribution systems showing promising results

IMPLEMENTATION OF MULTIAGENT REINFORCEMENT LEARNING MECHANISM FOR OPTIMAL ISLANDING OPERATION OF DISTRIBUTION NETWORK

DEFF Research Database (Denmark)

Saleem, Arshad; Lind, Morten

2008-01-01

among electric power utilities to utilize modern information and communication technologies (ICT) in order to improve the automation of the distribution system. In this paper we present our work for the implementation of a dynamic multi-agent based distributed reinforcement learning mechanism...

Wealth distribution on complex networks

Science.gov (United States)

Ichinomiya, Takashi

2012-12-01

We study the wealth distribution of the Bouchaud-Mézard model on complex networks. It is known from numerical simulations that this distribution depends on the topology of the network; however, no one has succeeded in explaining it. Using “adiabatic” and “independent” assumptions along with the central-limit theorem, we derive equations that determine the probability distribution function. The results are compared to those of simulations for various networks. We find good agreement between our theory and the simulations, except for the case of Watts-Strogatz networks with a low rewiring rate due to the breakdown of independent assumption.

Adaptive competitive learning neural networks

Directory of Open Access Journals (Sweden)

Ahmed R. Abas

2013-11-01

Full Text Available In this paper, the adaptive competitive learning (ACL neural network algorithm is proposed. This neural network not only groups similar input feature vectors together but also determines the appropriate number of groups of these vectors. This algorithm uses a new proposed criterion referred to as the ACL criterion. This criterion evaluates different clustering structures produced by the ACL neural network for an input data set. Then, it selects the best clustering structure and the corresponding network architecture for this data set. The selected structure is composed of the minimum number of clusters that are compact and balanced in their sizes. The selected network architecture is efficient, in terms of its complexity, as it contains the minimum number of neurons. Synaptic weight vectors of these neurons represent well-separated, compact and balanced clusters in the input data set. The performance of the ACL algorithm is evaluated and compared with the performance of a recently proposed algorithm in the literature in clustering an input data set and determining its number of clusters. Results show that the ACL algorithm is more accurate and robust in both determining the number of clusters and allocating input feature vectors into these clusters than the other algorithm especially with data sets that are sparsely distributed.

Bayesian network learning for natural hazard assessments

Science.gov (United States)

Vogel, Kristin

2016-04-01

Even though quite different in occurrence and consequences, from a modelling perspective many natural hazards share similar properties and challenges. Their complex nature as well as lacking knowledge about their driving forces and potential effects make their analysis demanding. On top of the uncertainty about the modelling framework, inaccurate or incomplete event observations and the intrinsic randomness of the natural phenomenon add up to different interacting layers of uncertainty, which require a careful handling. Thus, for reliable natural hazard assessments it is crucial not only to capture and quantify involved uncertainties, but also to express and communicate uncertainties in an intuitive way. Decision-makers, who often find it difficult to deal with uncertainties, might otherwise return to familiar (mostly deterministic) proceedings. In the scope of the DFG research training group „NatRiskChange" we apply the probabilistic framework of Bayesian networks for diverse natural hazard and vulnerability studies. The great potential of Bayesian networks was already shown in previous natural hazard assessments. Treating each model component as random variable, Bayesian networks aim at capturing the joint distribution of all considered variables. Hence, each conditional distribution of interest (e.g. the effect of precautionary measures on damage reduction) can be inferred. The (in-)dependencies between the considered variables can be learned purely data driven or be given by experts. Even a combination of both is possible. By translating the (in-)dependences into a graph structure, Bayesian networks provide direct insights into the workings of the system and allow to learn about the underlying processes. Besides numerous studies on the topic, learning Bayesian networks from real-world data remains challenging. In previous studies, e.g. on earthquake induced ground motion and flood damage assessments, we tackled the problems arising with continuous variables

Fastest learning in small-world neural networks

International Nuclear Information System (INIS)

Simard, D.; Nadeau, L.; Kroeger, H.

2005-01-01

We investigate supervised learning in neural networks. We consider a multi-layered feed-forward network with back propagation. We find that the network of small-world connectivity reduces the learning error and learning time when compared to the networks of regular or random connectivity. Our study has potential applications in the domain of data-mining, image processing, speech recognition, and pattern recognition

The Integration of Personal Learning Environments & Open Network Learning Environments

Science.gov (United States)

Tu, Chih-Hsiung; Sujo-Montes, Laura; Yen, Cherng-Jyh; Chan, Junn-Yih; Blocher, Michael

2012-01-01

Learning management systems traditionally provide structures to guide online learners to achieve their learning goals. Web 2.0 technology empowers learners to create, share, and organize their personal learning environments in open network environments; and allows learners to engage in social networking and collaborating activities. Advanced…

Aggregated Representation of Distribution Networks for Large-Scale Transmission Network Simulations

DEFF Research Database (Denmark)

Göksu, Ömer; Altin, Müfit; Sørensen, Poul Ejnar

2014-01-01

As a common practice of large-scale transmission network analysis the distribution networks have been represented as aggregated loads. However, with increasing share of distributed generation, especially wind and solar power, in the distribution networks, it became necessary to include...... the distributed generation within those analysis. In this paper a practical methodology to obtain aggregated behaviour of the distributed generation is proposed. The methodology, which is based on the use of the IEC standard wind turbine models, is applied on a benchmark distribution network via simulations....

Mirrored STDP Implements Autoencoder Learning in a Network of Spiking Neurons.

Science.gov (United States)

Burbank, Kendra S

2015-12-01

The autoencoder algorithm is a simple but powerful unsupervised method for training neural networks. Autoencoder networks can learn sparse distributed codes similar to those seen in cortical sensory areas such as visual area V1, but they can also be stacked to learn increasingly abstract representations. Several computational neuroscience models of sensory areas, including Olshausen & Field's Sparse Coding algorithm, can be seen as autoencoder variants, and autoencoders have seen extensive use in the machine learning community. Despite their power and versatility, autoencoders have been difficult to implement in a biologically realistic fashion. The challenges include their need to calculate differences between two neuronal activities and their requirement for learning rules which lead to identical changes at feedforward and feedback connections. Here, we study a biologically realistic network of integrate-and-fire neurons with anatomical connectivity and synaptic plasticity that closely matches that observed in cortical sensory areas. Our choice of synaptic plasticity rules is inspired by recent experimental and theoretical results suggesting that learning at feedback connections may have a different form from learning at feedforward connections, and our results depend critically on this novel choice of plasticity rules. Specifically, we propose that plasticity rules at feedforward versus feedback connections are temporally opposed versions of spike-timing dependent plasticity (STDP), leading to a symmetric combined rule we call Mirrored STDP (mSTDP). We show that with mSTDP, our network follows a learning rule that approximately minimizes an autoencoder loss function. When trained with whitened natural image patches, the learned synaptic weights resemble the receptive fields seen in V1. Our results use realistic synaptic plasticity rules to show that the powerful autoencoder learning algorithm could be within the reach of real biological networks.

Making Improvements to The Army Distributed Learning Program

Science.gov (United States)

2012-01-01

ing focuses on leadership and management as well as technical skills, and involves the creation of global virtual teams. e training often deals...develop and distribute knowledge via a dynamic, global knowledge network called the Battle Command Knowledge System with a purpose of providing...Levels of Interactivity,” paper presented at 2006 dL Workshop, March 14, 2006. Wexler, S., et al., E-Learning 2.0., Santa Rosa, Calif.: e ELearning

Learning to read aloud: A neural network approach using sparse distributed memory

Science.gov (United States)

Joglekar, Umesh Dwarkanath

1989-01-01

An attempt to solve a problem of text-to-phoneme mapping is described which does not appear amenable to solution by use of standard algorithmic procedures. Experiments based on a model of distributed processing are also described. This model (sparse distributed memory (SDM)) can be used in an iterative supervised learning mode to solve the problem. Additional improvements aimed at obtaining better performance are suggested.

Learning Networks for Professional Development & Lifelong Learning

NARCIS (Netherlands)

Sloep, Peter

2009-01-01

Sloep, P. B. (2009). Learning Networks for Professional Development & Lifelong Learning. Presentation at a NeLLL seminar with Etienne Wenger held at the Open Universiteit Nederland. September, 10, 2009, Heerlen, The Netherlands.

Edmodo social learning network for elementary school mathematics learning

Science.gov (United States)

Ariani, Y.; Helsa, Y.; Ahmad, S.; Prahmana, RCI

2017-12-01

A developed instructional media can be as printed media, visual media, audio media, and multimedia. The development of instructional media can also take advantage of technological development by utilizing Edmodo social network. This research aims to develop a digital classroom learning model using Edmodo social learning network for elementary school mathematics learning which is practical, valid and effective in order to improve the quality of learning activities. The result of this research showed that the prototype of mathematics learning device for elementary school students using Edmodo was in good category. There were 72% of students passed the assessment as a result of Edmodo learning. Edmodo has become a promising way to engage students in a collaborative learning process.

Entropy Learning in Neural Network

Directory of Open Access Journals (Sweden)

Geok See Ng

2017-12-01

Full Text Available In this paper, entropy term is used in the learning phase of a neural network.  As learning progresses, more hidden nodes get into saturation.  The early creation of such hidden nodes may impair generalisation.  Hence entropy approach is proposed to dampen the early creation of such nodes.  The entropy learning also helps to increase the importance of relevant nodes while dampening the less important nodes.  At the end of learning, the less important nodes can then be eliminated to reduce the memory requirements of the neural network.

Monitoring of Students' Interaction in Online Learning Settings by Structural Network Analysis and Indicators.

Science.gov (United States)

Ammenwerth, Elske; Hackl, Werner O

2017-01-01

Learning as a constructive process works best in interaction with other learners. Support of social interaction processes is a particular challenge within online learning settings due to the spatial and temporal distribution of participants. It should thus be carefully monitored. We present structural network analysis and related indicators to analyse and visualize interaction patterns of participants in online learning settings. We validate this approach in two online courses and show how the visualization helps to monitor interaction and to identify activity profiles of learners. Structural network analysis is a feasible approach for an analysis of the intensity and direction of interaction in online learning settings.

A distribution network review

International Nuclear Information System (INIS)

Fairbairn, R.J.; Maunder, D.; Kenyon, P.

1999-01-01

This report summarises the findings of a study reviewing the distribution network in England, Scotland and Wales to evaluate its ability to accommodate more embedded generation from both fossil fuel and renewable energy sources. The background to the study is traced, and descriptions of the existing electricity supply system, the licence conditions relating to embedded generation, and the effects of the Review of Electricity Trading Arrangements are given. The ability of the UK distribution networks to accept embedded generation is examined, and technical benefits/drawbacks arising from embedded generation, and the potential for uptake of embedded generation technologies are considered. The distribution network capacity and the potential uptake of embedded generation are compared, and possible solutions to overcome obstacles are suggested. (UK)

A distribution network review

Energy Technology Data Exchange (ETDEWEB)

Fairbairn, R.J.; Maunder, D.; Kenyon, P.

1999-07-01

This report summarises the findings of a study reviewing the distribution network in England, Scotland and Wales to evaluate its ability to accommodate more embedded generation from both fossil fuel and renewable energy sources. The background to the study is traced, and descriptions of the existing electricity supply system, the licence conditions relating to embedded generation, and the effects of the Review of Electricity Trading Arrangements are given. The ability of the UK distribution networks to accept embedded generation is examined, and technical benefits/drawbacks arising from embedded generation, and the potential for uptake of embedded generation technologies are considered. The distribution network capacity and the potential uptake of embedded generation are compared, and possible solutions to overcome obstacles are suggested. (UK)

Learning multivariate distributions by competitive assembly of marginals.

Science.gov (United States)

Sánchez-Vega, Francisco; Younes, Laurent; Geman, Donald

2013-02-01

We present a new framework for learning high-dimensional multivariate probability distributions from estimated marginals. The approach is motivated by compositional models and Bayesian networks, and designed to adapt to small sample sizes. We start with a large, overlapping set of elementary statistical building blocks, or "primitives," which are low-dimensional marginal distributions learned from data. Each variable may appear in many primitives. Subsets of primitives are combined in a Lego-like fashion to construct a probabilistic graphical model; only a small fraction of the primitives will participate in any valid construction. Since primitives can be precomputed, parameter estimation and structure search are separated. Model complexity is controlled by strong biases; we adapt the primitives to the amount of training data and impose rules which restrict the merging of them into allowable compositions. The likelihood of the data decomposes into a sum of local gains, one for each primitive in the final structure. We focus on a specific subclass of networks which are binary forests. Structure optimization corresponds to an integer linear program and the maximizing composition can be computed for reasonably large numbers of variables. Performance is evaluated using both synthetic data and real datasets from natural language processing and computational biology.

Advanced Distribution Network Modelling with Distributed Energy Resources

Science.gov (United States)

O'Connell, Alison

The addition of new distributed energy resources, such as electric vehicles, photovoltaics, and storage, to low voltage distribution networks means that these networks will undergo major changes in the future. Traditionally, distribution systems would have been a passive part of the wider power system, delivering electricity to the customer and not needing much control or management. However, the introduction of these new technologies may cause unforeseen issues for distribution networks, due to the fact that they were not considered when the networks were originally designed. This thesis examines different types of technologies that may begin to emerge on distribution systems, as well as the resulting challenges that they may impose. Three-phase models of distribution networks are developed and subsequently utilised as test cases. Various management strategies are devised for the purposes of controlling distributed resources from a distribution network perspective. The aim of the management strategies is to mitigate those issues that distributed resources may cause, while also keeping customers' preferences in mind. A rolling optimisation formulation is proposed as an operational tool which can manage distributed resources, while also accounting for the uncertainties that these resources may present. Network sensitivities for a particular feeder are extracted from a three-phase load flow methodology and incorporated into an optimisation. Electric vehicles are the focus of the work, although the method could be applied to other types of resources. The aim is to minimise the cost of electric vehicle charging over a 24-hour time horizon by controlling the charge rates and timings of the vehicles. The results demonstrate the advantage that controlled EV charging can have over an uncontrolled case, as well as the benefits provided by the rolling formulation and updated inputs in terms of cost and energy delivered to customers. Building upon the rolling optimisation, a

Large scale network-centric distributed systems

CERN Document Server

Sarbazi-Azad, Hamid

2014-01-01

A highly accessible reference offering a broad range of topics and insights on large scale network-centric distributed systems Evolving from the fields of high-performance computing and networking, large scale network-centric distributed systems continues to grow as one of the most important topics in computing and communication and many interdisciplinary areas. Dealing with both wired and wireless networks, this book focuses on the design and performance issues of such systems. Large Scale Network-Centric Distributed Systems provides in-depth coverage ranging from ground-level hardware issu

Learning Based Approach for Optimal Clustering of Distributed Program's Call Flow Graph

Science.gov (United States)

Abofathi, Yousef; Zarei, Bager; Parsa, Saeed

Optimal clustering of call flow graph for reaching maximum concurrency in execution of distributable components is one of the NP-Complete problems. Learning automatas (LAs) are search tools which are used for solving many NP-Complete problems. In this paper a learning based algorithm is proposed to optimal clustering of call flow graph and appropriate distributing of programs in network level. The algorithm uses learning feature of LAs to search in state space. It has been shown that the speed of reaching to solution increases remarkably using LA in search process, and it also prevents algorithm from being trapped in local minimums. Experimental results show the superiority of proposed algorithm over others.

Protection of electricity distribution networks

CERN Document Server

Gers, Juan M

2004-01-01

Written by two practicing electrical engineers, this second edition of the bestselling Protection of Electricity Distribution Networks offers both practical and theoretical coverage of the technologies, from the classical electromechanical relays to the new numerical types, which protect equipment on networks and in electrical plants. A properly coordinated protection system is vital to ensure that an electricity distribution network can operate within preset requirements for safety for individual items of equipment, staff and public, and the network overall. Suitable and reliable equipment sh

Reconstructing Causal Biological Networks through Active Learning.

Directory of Open Access Journals (Sweden)

Hyunghoon Cho

Full Text Available Reverse-engineering of biological networks is a central problem in systems biology. The use of intervention data, such as gene knockouts or knockdowns, is typically used for teasing apart causal relationships among genes. Under time or resource constraints, one needs to carefully choose which intervention experiments to carry out. Previous approaches for selecting most informative interventions have largely been focused on discrete Bayesian networks. However, continuous Bayesian networks are of great practical interest, especially in the study of complex biological systems and their quantitative properties. In this work, we present an efficient, information-theoretic active learning algorithm for Gaussian Bayesian networks (GBNs, which serve as important models for gene regulatory networks. In addition to providing linear-algebraic insights unique to GBNs, leading to significant runtime improvements, we demonstrate the effectiveness of our method on data simulated with GBNs and the DREAM4 network inference challenge data sets. Our method generally leads to faster recovery of underlying network structure and faster convergence to final distribution of confidence scores over candidate graph structures using the full data, in comparison to random selection of intervention experiments.

Quantitative learning strategies based on word networks

Science.gov (United States)

Zhao, Yue-Tian-Yi; Jia, Zi-Yang; Tang, Yong; Xiong, Jason Jie; Zhang, Yi-Cheng

2018-02-01

Learning English requires a considerable effort, but the way that vocabulary is introduced in textbooks is not optimized for learning efficiency. With the increasing population of English learners, learning process optimization will have significant impact and improvement towards English learning and teaching. The recent developments of big data analysis and complex network science provide additional opportunities to design and further investigate the strategies in English learning. In this paper, quantitative English learning strategies based on word network and word usage information are proposed. The strategies integrate the words frequency with topological structural information. By analyzing the influence of connected learned words, the learning weights for the unlearned words and dynamically updating of the network are studied and analyzed. The results suggest that quantitative strategies significantly improve learning efficiency while maintaining effectiveness. Especially, the optimized-weight-first strategy and segmented strategies outperform other strategies. The results provide opportunities for researchers and practitioners to reconsider the way of English teaching and designing vocabularies quantitatively by balancing the efficiency and learning costs based on the word network.

Language Choice & Global Learning Networks

Directory of Open Access Journals (Sweden)

Dennis Sayers

1995-05-01

Full Text Available How can other languages be used in conjunction with English to further intercultural and multilingual learning when teachers and students participate in computer-based global learning networks? Two portraits are presented of multilingual activities in the Orillas and I*EARN learning networks, and are discussed as examples of the principal modalities of communication employed in networking projects between distant classes. Next, an important historical precedent --the social controversy which accompanied the introduction of telephone technology at the end of the last century-- is examined in terms of its implications for language choice in contemporary classroom telecomputing projects. Finally, recommendations are offered to guide decision making concerning the role of language choice in promoting collaborative critical inquiry.

Photovoltaic production and distribution network

International Nuclear Information System (INIS)

Fraisse, J.L.

2010-01-01

The rapid development of photovoltaics boosted by attractive feed-in tariffs caused a sharp increase in requests for connection to public distribution grids, which were originally designed to serve consumers. ERDF, main distribution network operator in France, is facing a challenge in terms of capacity for handling requests for connection and in terms of public distribution network operation and management. (author)

Intelligent sensor networks the integration of sensor networks, signal processing and machine learning

CERN Document Server

Hu, Fei

2012-01-01

Although governments worldwide have invested significantly in intelligent sensor network research and applications, few books cover intelligent sensor networks from a machine learning and signal processing perspective. Filling this void, Intelligent Sensor Networks: The Integration of Sensor Networks, Signal Processing and Machine Learning focuses on the close integration of sensing, networking, and smart signal processing via machine learning. Based on the world-class research of award-winning authors, the book provides a firm grounding in the fundamentals of intelligent sensor networks, incl

Deep Learning Neural Networks and Bayesian Neural Networks in Data Analysis

Directory of Open Access Journals (Sweden)

Chernoded Andrey

2017-01-01

Full Text Available Most of the modern analyses in high energy physics use signal-versus-background classification techniques of machine learning methods and neural networks in particular. Deep learning neural network is the most promising modern technique to separate signal and background and now days can be widely and successfully implemented as a part of physical analysis. In this article we compare Deep learning and Bayesian neural networks application as a classifiers in an instance of top quark analysis.

Learning and coding in biological neural networks

Science.gov (United States)

Fiete, Ila Rani

How can large groups of neurons that locally modify their activities learn to collectively perform a desired task? Do studies of learning in small networks tell us anything about learning in the fantastically large collection of neurons that make up a vertebrate brain? What factors do neurons optimize by encoding sensory inputs or motor commands in the way they do? In this thesis I present a collection of four theoretical works: each of the projects was motivated by specific constraints and complexities of biological neural networks, as revealed by experimental studies; together, they aim to partially address some of the central questions of neuroscience posed above. We first study the role of sparse neural activity, as seen in the coding of sequential commands in a premotor area responsible for birdsong. We show that the sparse coding of temporal sequences in the songbird brain can, in a network where the feedforward plastic weights must translate the sparse sequential code into a time-varying muscle code, facilitate learning by minimizing synaptic interference. Next, we propose a biologically plausible synaptic plasticity rule that can perform goal-directed learning in recurrent networks of voltage-based spiking neurons that interact through conductances. Learning is based on the correlation of noisy local activity with a global reward signal; we prove that this rule performs stochastic gradient ascent on the reward. Thus, if the reward signal quantifies network performance on some desired task, the plasticity rule provably drives goal-directed learning in the network. To assess the convergence properties of the learning rule, we compare it with a known example of learning in the brain. Song-learning in finches is a clear example of a learned behavior, with detailed available neurophysiological data. With our learning rule, we train an anatomically accurate model birdsong network that drives a sound source to mimic an actual zebrafinch song. Simulation and

Collective Learning in Games through Social Networks

NARCIS (Netherlands)

Kosterman, S.; Gierasimczuk, N.; Armentano, M.G.; Monteserin, A.; Tang, J.; Yannibelli, V.

2015-01-01

This paper argues that combining social networks communication and games can positively influence the learning behavior of players. We propose a computational model that combines features of social network learning (communication) and game-based learning (strategy reinforcement). The focus is on

MACHINE LEARNING FOR THE SELF-ORGANIZATION OF DISTRIBUTED SYSTEMS IN ECONOMIC APPLICATIONS

Directory of Open Access Journals (Sweden)

Jerzy Balicki

2017-03-01

Full Text Available In this paper, an application of machine learning to the problem of self-organization of distributed systems has been discussed with regard to economic applications, with particular emphasis on supervised neural network learning to predict stock investments and some ratings of companies. In addition, genetic programming can play an important role in the preparation and testing of several financial information systems. For this reason, machine learning applications have been discussed because some software applications can be automatically constructed by genetic programming. To obtain a competitive advantage, machine learning can be used for the management of self-organizing cloud computing systems performing calculations for business. Also the use of selected economic self-organizing distributed systems has been described, including some testing methods of predicting borrower reliability. Finally, some conclusions and directions for further research have been proposed.

Islanded operation of distributed networks

Energy Technology Data Exchange (ETDEWEB)

NONE

2005-07-01

This report summarises the findings of a study to investigate the regulatory, commercial and technical risks and benefits associated with the operation of distributed generation to power an islanded section of distributed network. A review of published literature was carried out, and UK generators were identified who could operate as part of an island network under the existing technical, regulatory, and safety framework. Agreement on case studies for consideration with distributed network operators (DNOs) is discussed as well as the quantification of the risks, benefits and costs of islanding, and the production of a case implementation plan for each case study. Technical issues associated with operating sections of network in islanded mode are described, and impacts of islanding on trading and settlement, and technical and commercial modelling are explored.

Islanded operation of distributed networks

International Nuclear Information System (INIS)

2005-01-01

This report summarises the findings of a study to investigate the regulatory, commercial and technical risks and benefits associated with the operation of distributed generation to power an islanded section of distributed network. A review of published literature was carried out, and UK generators were identified who could operate as part of an island network under the existing technical, regulatory, and safety framework. Agreement on case studies for consideration with distributed network operators (DNOs) is discussed as well as the quantification of the risks, benefits and costs of islanding, and the production of a case implementation plan for each case study. Technical issues associated with operating sections of network in islanded mode are described, and impacts of islanding on trading and settlement, and technical and commercial modelling are explored

Supervised Learning with Complex-valued Neural Networks

CERN Document Server

Suresh, Sundaram; Savitha, Ramasamy

2013-01-01

Recent advancements in the field of telecommunications, medical imaging and signal processing deal with signals that are inherently time varying, nonlinear and complex-valued. The time varying, nonlinear characteristics of these signals can be effectively analyzed using artificial neural networks.  Furthermore, to efficiently preserve the physical characteristics of these complex-valued signals, it is important to develop complex-valued neural networks and derive their learning algorithms to represent these signals at every step of the learning process. This monograph comprises a collection of new supervised learning algorithms along with novel architectures for complex-valued neural networks. The concepts of meta-cognition equipped with a self-regulated learning have been known to be the best human learning strategy. In this monograph, the principles of meta-cognition have been introduced for complex-valued neural networks in both the batch and sequential learning modes. For applications where the computati...

Loss optimization in distribution networks with distributed generation

DEFF Research Database (Denmark)

Pokhrel, Basanta Raj; Nainar, Karthikeyan; Bak-Jensen, Birgitte

2017-01-01

This paper presents a novel power loss minimization approach in distribution grids considering network reconfiguration, distributed generation and storage installation. Identification of optimum configuration in such scenario is one of the main challenges faced by distribution system operators...... in highly active distribution grids. This issue is tackled by formulating a hybrid loss optimization problem and solved using the Interior Point Method. Sensitivity analysis is used to identify the optimum location of storage units. Different scenarios of reconfiguration, storage and distributed generation...... penetration are created to test the proposed algorithm. It is tested in a benchmark medium voltage network to show the effectiveness and performance of the algorithm. Results obtained are found to be encouraging for radial distribution system. It shows that we can reduce the power loss by more than 30% using...

Changing Conditions for Networked Learning?

DEFF Research Database (Denmark)

Ryberg, Thomas

2011-01-01

in describing the novel pedagogical potentials of these new technologies and practices (e.g. in debates around virtual learning environments versus personal learning environment). Likewise, I shall briefly discuss the notions of ‘digital natives’ or ‘the net generation’ from a critical perspective...... of social technologies. I argue that we are seeing the emergence of new architectures and scales of participation, collaboration and networking e.g. through interesting formations of learning networks at different levels of scale, for different purposes and often bridging boundaries such as formal...

Learning-parameter adjustment in neural networks

Science.gov (United States)

Heskes, Tom M.; Kappen, Bert

1992-06-01

We present a learning-parameter adjustment algorithm, valid for a large class of learning rules in neural-network literature. The algorithm follows directly from a consideration of the statistics of the weights in the network. The characteristic behavior of the algorithm is calculated, both in a fixed and a changing environment. A simple example, Widrow-Hoff learning for statistical classification, serves as an illustration.

Researching Design, Experience and Practice of Networked Learning

DEFF Research Database (Denmark)

Hodgson, Vivien; de Laat, Maarten; McConnell, David

2014-01-01

and final section draws attention to a growing topic of interest within networked learning: that of networked learning in informal practices. In addition, we provide a reflection on the theories, methods and settings featured in the networked learning research of the chapters. We conclude the introduction...

Distribution network planning method considering distributed generation for peak cutting

International Nuclear Information System (INIS)

Ouyang Wu; Cheng Haozhong; Zhang Xiubin; Yao Liangzhong

2010-01-01

Conventional distribution planning method based on peak load brings about large investment, high risk and low utilization efficiency. A distribution network planning method considering distributed generation (DG) for peak cutting is proposed in this paper. The new integrated distribution network planning method with DG implementation aims to minimize the sum of feeder investments, DG investments, energy loss cost and the additional cost of DG for peak cutting. Using the solution techniques combining genetic algorithm (GA) with the heuristic approach, the proposed model determines the optimal planning scheme including the feeder network and the siting and sizing of DG. The strategy for the site and size of DG, which is based on the radial structure characteristics of distribution network, reduces the complexity degree of solving the optimization model and eases the computational burden substantially. Furthermore, the operation schedule of DG at the different load level is also provided.

Learning Bayesian networks for discrete data

KAUST Repository

Liang, Faming

2009-02-01

Bayesian networks have received much attention in the recent literature. In this article, we propose an approach to learn Bayesian networks using the stochastic approximation Monte Carlo (SAMC) algorithm. Our approach has two nice features. Firstly, it possesses the self-adjusting mechanism and thus avoids essentially the local-trap problem suffered by conventional MCMC simulation-based approaches in learning Bayesian networks. Secondly, it falls into the class of dynamic importance sampling algorithms; the network features can be inferred by dynamically weighted averaging the samples generated in the learning process, and the resulting estimates can have much lower variation than the single model-based estimates. The numerical results indicate that our approach can mix much faster over the space of Bayesian networks than the conventional MCMC simulation-based approaches. © 2008 Elsevier B.V. All rights reserved.

Distributed Bayesian Computation and Self-Organized Learning in Sheets of Spiking Neurons with Local Lateral Inhibition.

Directory of Open Access Journals (Sweden)

Johannes Bill

Full Text Available During the last decade, Bayesian probability theory has emerged as a framework in cognitive science and neuroscience for describing perception, reasoning and learning of mammals. However, our understanding of how probabilistic computations could be organized in the brain, and how the observed connectivity structure of cortical microcircuits supports these calculations, is rudimentary at best. In this study, we investigate statistical inference and self-organized learning in a spatially extended spiking network model, that accommodates both local competitive and large-scale associative aspects of neural information processing, under a unified Bayesian account. Specifically, we show how the spiking dynamics of a recurrent network with lateral excitation and local inhibition in response to distributed spiking input, can be understood as sampling from a variational posterior distribution of a well-defined implicit probabilistic model. This interpretation further permits a rigorous analytical treatment of experience-dependent plasticity on the network level. Using machine learning theory, we derive update rules for neuron and synapse parameters which equate with Hebbian synaptic and homeostatic intrinsic plasticity rules in a neural implementation. In computer simulations, we demonstrate that the interplay of these plasticity rules leads to the emergence of probabilistic local experts that form distributed assemblies of similarly tuned cells communicating through lateral excitatory connections. The resulting sparse distributed spike code of a well-adapted network carries compressed information on salient input features combined with prior experience on correlations among them. Our theory predicts that the emergence of such efficient representations benefits from network architectures in which the range of local inhibition matches the spatial extent of pyramidal cells that share common afferent input.

Distributed Bayesian Computation and Self-Organized Learning in Sheets of Spiking Neurons with Local Lateral Inhibition

Science.gov (United States)

Bill, Johannes; Buesing, Lars; Habenschuss, Stefan; Nessler, Bernhard; Maass, Wolfgang; Legenstein, Robert

2015-01-01

During the last decade, Bayesian probability theory has emerged as a framework in cognitive science and neuroscience for describing perception, reasoning and learning of mammals. However, our understanding of how probabilistic computations could be organized in the brain, and how the observed connectivity structure of cortical microcircuits supports these calculations, is rudimentary at best. In this study, we investigate statistical inference and self-organized learning in a spatially extended spiking network model, that accommodates both local competitive and large-scale associative aspects of neural information processing, under a unified Bayesian account. Specifically, we show how the spiking dynamics of a recurrent network with lateral excitation and local inhibition in response to distributed spiking input, can be understood as sampling from a variational posterior distribution of a well-defined implicit probabilistic model. This interpretation further permits a rigorous analytical treatment of experience-dependent plasticity on the network level. Using machine learning theory, we derive update rules for neuron and synapse parameters which equate with Hebbian synaptic and homeostatic intrinsic plasticity rules in a neural implementation. In computer simulations, we demonstrate that the interplay of these plasticity rules leads to the emergence of probabilistic local experts that form distributed assemblies of similarly tuned cells communicating through lateral excitatory connections. The resulting sparse distributed spike code of a well-adapted network carries compressed information on salient input features combined with prior experience on correlations among them. Our theory predicts that the emergence of such efficient representations benefits from network architectures in which the range of local inhibition matches the spatial extent of pyramidal cells that share common afferent input. PMID:26284370

Learning network theory : its contribution to our understanding of work-based learning projects and learning climate

NARCIS (Netherlands)

Poell, R.F.; Moorsel, M.A.A.H. van

1996-01-01

This paper discusses the relevance of Van der Krogt's learning network theory (1995) for our understanding of the concepts of work-related learning projects and learning climate in organisations. The main assumptions of the learning network theory are presented and transferred to the level of

DeepSpark: A Spark-Based Distributed Deep Learning Framework for Commodity Clusters

OpenAIRE

Kim, Hanjoo; Park, Jaehong; Jang, Jaehee; Yoon, Sungroh

2016-01-01

The increasing complexity of deep neural networks (DNNs) has made it challenging to exploit existing large-scale data processing pipelines for handling massive data and parameters involved in DNN training. Distributed computing platforms and GPGPU-based acceleration provide a mainstream solution to this computational challenge. In this paper, we propose DeepSpark, a distributed and parallel deep learning framework that exploits Apache Spark on commodity clusters. To support parallel operation...

Distance learning, problem based learning and dynamic knowledge networks.

Science.gov (United States)

Giani, U; Martone, P

1998-06-01

This paper is an attempt to develop a distance learning model grounded upon a strict integration of problem based learning (PBL), dynamic knowledge networks (DKN) and web tools, such as hypermedia documents, synchronous and asynchronous communication facilities, etc. The main objective is to develop a theory of distance learning based upon the idea that learning is a highly dynamic cognitive process aimed at connecting different concepts in a network of mutually supporting concepts. Moreover, this process is supposed to be the result of a social interaction that has to be facilitated by the web. The model was tested by creating a virtual classroom of medical and nursing students and activating a learning session on the concept of knowledge representation in health sciences.

Exploring the Role of Distributed Learning in Distance Education at Allama Iqbal Open University: Academic Challenges at Postgraduate Level

Directory of Open Access Journals (Sweden)

Qadir BUKHSH

2015-01-01

Full Text Available Distributed learning is derived from the concept of distributed resources. Different institutions around the globe connected through network and the learners are diverse, located in the different cultures and communities. Distributed learning provides global standards of quality to all learners through synchronous and asynchronous communications and provides the opportunity of flexible and independent learning with equity, low cost educational services and has become the first choice of the dispersed learners around the globe. The present study was undertaken to investigate the challenges faced by the Faculty Members of Department of Business Administration and Computer Science at Allama Iqbal Open University Islamabad Pakistan. 25 Faculty Members were taken as sample of the study from both Departments (100% Sampling. The study was qualitative in nature and interview was the data collection tool. Data was analyzed by thematic analysis technique. The major challenges faced by the Faculty Members were as: bandwidth, synchronous learning activities, irregularity of the learners, feedback on individual work, designing and managing the learning activities, quality issues and training to use the network for teaching learning activities

A Team Formation and Project-based Learning Support Service for Social Learning Networks

NARCIS (Netherlands)

Spoelstra, Howard; Van Rosmalen, Peter; Van de Vrie, Evert; Obreza, Matija; Sloep, Peter

2014-01-01

The Internet affords new approaches to learning. Geographically dispersed self-directed learners can learn in computer-supported communities, forming social learning networks. However, self-directed learners can suffer from a lack of continuous motivation. And surprisingly, social learning networks

Planning of Distribution Networks in Baghdad City

Directory of Open Access Journals (Sweden)

Thamir M. Abdul-Wahhab

2015-02-01

Full Text Available Planning of electrical distribution networks is considered of highest priority at the present time in Iraq, due to the huge increase in electrical demand and expansions imposed on distribution networks as a result of the great and rapid urban development. Distribution system planning simulates and studies the behavior of electrical distribution networks under different operating conditions. The study provide understanding of the existing system and to prepare a short term development plan or a long term plan used to guide system expansion and future investments needed for improved network performance. The objective of this research is the planning of Al_Bayaa 11 kV distribution network in Baghdad city based on the powerful and efficient CYMDist software as a tool for the simulation and analysis of the network. The planning method proposed in this thesis is to reach the optimum operating conditions of the network by combining the network reconfiguration in sequence with the insertion of capacitors with optimal sizing and locations. The optimum performance of the network is achieved by reducing losses, improving voltage profile and alleviating overload for transformers and cables.

Mathematical theories of distributed sensor networks

CERN Document Server

Iyengar, Sitharama S; Balakrishnan, N

2014-01-01

Mathematical Theory of Distributed Sensor Networks demonstrates how mathematical theories can be used to provide distributed sensor modeling and to solve important problems such as coverage hole detection and repair. The book introduces the mathematical and computational structure by discussing what they are, their applications and how they differ from traditional systems. The text also explains how mathematics are utilized to provide efficient techniques implementing effective coverage, deployment, transmission, data processing, signal processing, and data protection within distributed sensor networks. Finally, the authors discuss some important challenges facing mathematics to get more incite to the multidisciplinary area of distributed sensor networks.

Cost allocation model for distribution networks considering high penetration of distributed energy resources

DEFF Research Database (Denmark)

Soares, Tiago; Pereira, Fábio; Morais, Hugo

2015-01-01

The high penetration of distributed energy resources (DER) in distribution networks and the competitive environment of electricity markets impose the use of new approaches in several domains. The network cost allocation, traditionally used in transmission networks, should be adapted and used...... in the distribution networks considering the specifications of the connected resources. The main goal is to develop a fairer methodology trying to distribute the distribution network use costs to all players which are using the network in each period. In this paper, a model considering different type of costs (fixed......, losses, and congestion costs) is proposed comprising the use of a large set of DER, namely distributed generation (DG), demand response (DR) of direct load control type, energy storage systems (ESS), and electric vehicles with capability of discharging energy to the network, which is known as vehicle...

Contingent factors affecting network learning

OpenAIRE

Peters, Linda D.; Pressey, Andrew D.; Johnston, Wesley J.

2016-01-01

To increase understanding of the impact of individuals on organizational learning processes, this paper explores the impact of individual cognition and action on the absorptive capacity process of the wider network. In particular this study shows how contingent factors such as social integration mechanisms and power relationships influence how network members engage in, and benefit from, learning. The use of cognitive consistency and sensemaking theory enables examination of how these conting...

Machine learning based Intelligent cognitive network using fog computing

Science.gov (United States)

Lu, Jingyang; Li, Lun; Chen, Genshe; Shen, Dan; Pham, Khanh; Blasch, Erik

2017-05-01

In this paper, a Cognitive Radio Network (CRN) based on artificial intelligence is proposed to distribute the limited radio spectrum resources more efficiently. The CRN framework can analyze the time-sensitive signal data close to the signal source using fog computing with different types of machine learning techniques. Depending on the computational capabilities of the fog nodes, different features and machine learning techniques are chosen to optimize spectrum allocation. Also, the computing nodes send the periodic signal summary which is much smaller than the original signal to the cloud so that the overall system spectrum source allocation strategies are dynamically updated. Applying fog computing, the system is more adaptive to the local environment and robust to spectrum changes. As most of the signal data is processed at the fog level, it further strengthens the system security by reducing the communication burden of the communications network.

Comprehensive evaluation of impacts of distributed generation integration in distribution network

Science.gov (United States)

Peng, Sujiang; Zhou, Erbiao; Ji, Fengkun; Cao, Xinhui; Liu, Lingshuang; Liu, Zifa; Wang, Xuyang; Cai, Xiaoyu

2018-04-01

All Distributed generation (DG) as the supplement to renewable energy centralized utilization, is becoming the focus of development direction of renewable energy utilization. With the increasing proportion of DG in distribution network, the network power structure, power flow distribution, operation plans and protection are affected to some extent. According to the main impacts of DG, a comprehensive evaluation model of distributed network with DG is proposed in this paper. A comprehensive evaluation index system including 7 aspects, along with their corresponding index calculation method is established for quantitative analysis. The indices under different access capacity of DG in distribution network are calculated based on the IEEE RBTS-Bus 6 system and the evaluation result is calculated by analytic hierarchy process (AHP). The proposed model and method are verified effective and validity through case study.

Learning network theory : its contribution to our understanding of work-based learning projects and learning climate

OpenAIRE

Poell, R.F.; Moorsel, M.A.A.H. van

1996-01-01

This paper discusses the relevance of Van der Krogt's learning network theory (1995) for our understanding of the concepts of work-related learning projects and learning climate in organisations. The main assumptions of the learning network theory are presented and transferred to the level of learning groups in organisations. Four theoretical types of learning projects are distinguished. Four different approaches to the learning climate of work groups are compared to the approach offered by t...

Learning and structure of neuronal networks

Indian Academy of Sciences (India)

We study the effect of learning dynamics on network topology. Firstly, a network of discrete dynamical systems is considered for this purpose and the coupling strengths are made to evolve according to a temporal learning rule that is based on the paradigm of spike-time-dependent plasticity (STDP). This incorporates ...

Stochastic Variational Learning in Recurrent Spiking Networks

Directory of Open Access Journals (Sweden)

Danilo eJimenez Rezende

2014-04-01

Full Text Available The ability to learn and perform statistical inference with biologically plausible recurrent network of spiking neurons is an important step towards understanding perception and reasoning. Here we derive and investigate a new learning rule for recurrent spiking networks with hidden neurons, combining principles from variational learning and reinforcement learning. Our network defines a generative model over spike train histories and the derived learning rule has the form of a local Spike Timing Dependent Plasticity rule modulated by global factors (neuromodulators conveying information about ``novelty on a statistically rigorous ground.Simulations show that our model is able to learn bothstationary and non-stationary patterns of spike trains.We also propose one experiment that could potentially be performed with animals in order to test the dynamics of the predicted novelty signal.

Stochastic variational learning in recurrent spiking networks.

Science.gov (United States)

Jimenez Rezende, Danilo; Gerstner, Wulfram

2014-01-01

The ability to learn and perform statistical inference with biologically plausible recurrent networks of spiking neurons is an important step toward understanding perception and reasoning. Here we derive and investigate a new learning rule for recurrent spiking networks with hidden neurons, combining principles from variational learning and reinforcement learning. Our network defines a generative model over spike train histories and the derived learning rule has the form of a local Spike Timing Dependent Plasticity rule modulated by global factors (neuromodulators) conveying information about "novelty" on a statistically rigorous ground. Simulations show that our model is able to learn both stationary and non-stationary patterns of spike trains. We also propose one experiment that could potentially be performed with animals in order to test the dynamics of the predicted novelty signal.

Marginal Contribution-Based Distributed Subchannel Allocation in Small Cell Networks.

Science.gov (United States)

Shah, Shashi; Kittipiyakul, Somsak; Lim, Yuto; Tan, Yasuo

2018-05-10

The paper presents a game theoretic solution for distributed subchannel allocation problem in small cell networks (SCNs) analyzed under the physical interference model. The objective is to find a distributed solution that maximizes the welfare of the SCNs, defined as the total system capacity. Although the problem can be addressed through best-response (BR) dynamics, the existence of a steady-state solution, i.e., a pure strategy Nash equilibrium (NE), cannot be guaranteed. Potential games (PGs) ensure convergence to a pure strategy NE when players rationally play according to some specified learning rules. However, such a performance guarantee comes at the expense of complete knowledge of the SCNs. To overcome such requirements, properties of PGs are exploited for scalable implementations, where we utilize the concept of marginal contribution (MC) as a tool to design learning rules of players’ utility and propose the marginal contribution-based best-response (MCBR) algorithm of low computational complexity for the distributed subchannel allocation problem. Finally, we validate and evaluate the proposed scheme through simulations for various performance metrics.

Marginal Contribution-Based Distributed Subchannel Allocation in Small Cell Networks

Directory of Open Access Journals (Sweden)

Shashi Shah

2018-05-01

Full Text Available The paper presents a game theoretic solution for distributed subchannel allocation problem in small cell networks (SCNs analyzed under the physical interference model. The objective is to find a distributed solution that maximizes the welfare of the SCNs, defined as the total system capacity. Although the problem can be addressed through best-response (BR dynamics, the existence of a steady-state solution, i.e., a pure strategy Nash equilibrium (NE, cannot be guaranteed. Potential games (PGs ensure convergence to a pure strategy NE when players rationally play according to some specified learning rules. However, such a performance guarantee comes at the expense of complete knowledge of the SCNs. To overcome such requirements, properties of PGs are exploited for scalable implementations, where we utilize the concept of marginal contribution (MC as a tool to design learning rules of players’ utility and propose the marginal contribution-based best-response (MCBR algorithm of low computational complexity for the distributed subchannel allocation problem. Finally, we validate and evaluate the proposed scheme through simulations for various performance metrics.

Distributed state estimation for multi-agent based active distribution networks

NARCIS (Netherlands)

Nguyen, H.P.; Kling, W.L.

2010-01-01

Along with the large-scale implementation of distributed generators, the current distribution networks have changed gradually from passive to active operation. State estimation plays a vital role to facilitate this transition. In this paper, a suitable state estimation method for the active network

Current distribution in conducting nanowire networks

Science.gov (United States)

Kumar, Ankush; Vidhyadhiraja, N. S.; Kulkarni, Giridhar U.

2017-07-01

Conducting nanowire networks find diverse applications in solar cells, touch-screens, transparent heaters, sensors, and various related transparent conducting electrode (TCE) devices. The performances of these devices depend on effective resistance, transmittance, and local current distribution in these networks. Although, there have been rigorous studies addressing resistance and transmittance in TCE, not much attention is paid on studying the distribution of current. Present work addresses this compelling issue of understanding current distribution in TCE networks using analytical as well as Monte-Carlo approaches. We quantified the current carrying backbone region against isolated and dangling regions as a function of wire density (ranging from percolation threshold to many multiples of threshold) and compared the wired connectivity with those obtained from template-based methods. Further, the current distribution in the obtained backbone is studied using Kirchhoff's law, which reveals that a significant fraction of the backbone (which is believed to be an active current component) may not be active for end-to-end current transport due to the formation of intervening circular loops. The study shows that conducting wire based networks possess hot spots (extremely high current carrying regions) which can be potential sources of failure. The fraction of these hot spots is found to decrease with increase in wire density, while they are completely absent in template based networks. Thus, the present work discusses unexplored issues related to current distribution in conducting networks, which are necessary to choose the optimum network for best TCE applications.

Effective Loss Minimization and Allocation of Unbalanced Distribution Network

Directory of Open Access Journals (Sweden)

Manvir Kaur

2017-11-01

Full Text Available An efficient distribution network must be able to supply power with good voltage profile. The main objective of the proposed work is to allocate losses of the unbalanced distribution network by the firefly algorithm in regulated and deregulated environments before and after loss minimization. Reconfiguration is one of the methods for loss reduction of unbalanced distribution network. Further, optimal placement of distributed generation and capacitor in the reconfigured unbalanced distribution network can further reduce the loss. The results of reconfigured unbalanced distribution network in regulated environment have already been reported. In this paper reconfiguration of an unbalanced distribution network in a deregulated environment is also carried out using an established Fuzzy Firefly algorithm. Loss sensitivity factor of unbalanced distribution networks is used to get the appropriate location of distributed generation and capacitor to be placed in the unbalanced distribution network. Their ratings have been found out by using bacteria foraging optimization algorithm (BFOA. The suggested loss allocation method using Firefly algorithm is implemented at first on 13 node unbalanced distribution network to check the performance of the proposed loss allocation method when compared to other available method. Finally the proposed method has been implemented on 25 node unbalanced distribution network. Both of the implementations are carried out under MATLAB environment.

THE IMPACTS OF SOCIAL NETWORKING SITES IN HIGHER LEARNING

Directory of Open Access Journals (Sweden)

Mohd Ishak Bin Ismail

2016-02-01

Full Text Available Social networking sites, a web-based application have permeated the boundary between personal lives and student lives. Nowadays, students in higher learning used social networking site such as Facebook to facilitate their learning through the academic collaboration which it further enhances students’ social capital. Social networking site has many advantages to improve students’ learning. To date, Facebook is the leading social networking sites at this time which it being widely used by students in higher learning to communicate to each other, to carry out academic collaboration and sharing resources. Learning through social networking sites is based on the social interaction which learning are emphasizing on students, real world resources, active students` participation, diversity of learning resources and the use of digital tools to deliver meaningful learning. Many studies found the positive, neutral and negative impact of social networking sites on academic performance. Thus, this study will determine the relationship between Facebook usage and academic achievement. Also, it will investigate the association of social capital and academic collaboration to Facebook usage.

Regulatory Improvements for Effective Integration of Distributed Generation into Electricity Distribution Networks

International Nuclear Information System (INIS)

Scheepers, M.J.J.; Jansen, J.C.; De Joode, J.; Bauknecht, D.; Gomez, T.; Pudjianto, D.; Strbac, G.; Ropenus, S.

2007-11-01

The growth of distributed electricity supply of renewable energy sources (RES-E) and combined heat and power (CHP) - so called distributed generation (DG) - can cause technical problems for electricity distribution networks. These integration problems can be overcome by reinforcing the network. Many European Member States apply network regulation that does not account for the impact of DG growth on the network costs. Passing on network integration costs to the DG-operator who is responsible for these extra costs may result in discrimination between different DG plants and between DG and large power generation. Therefore, in many regulatory systems distribution system operators (DSOs) are not being compensated for the DG integration costs. The DG-GRID project analysed technical and economical barriers for integration of distributed generation into electricity distribution networks. The project looked into the impact of a high DG deployment on the electricity distribution system costs and the impact on the financial position of the DSO. Several ways for improving network regulation in order to compensate DSOs for the increasing DG penetration were identified and tested. The DG-GRID project looked also into stimulating network innovations through economic regulation. The project was co-financed by the European Commission and carried out by nine European universities and research institutes. This report summarises the project results and is based on a number of DG-GRID reports that describe the conducted analyses and their results

Intelligent distribution network design

NARCIS (Netherlands)

Provoost, F.

2009-01-01

Distribution networks (medium voltage and low voltage) are subject to changes caused by re-regulation of the energy supply, economical and environmental constraints more sensitive equipment, power quality requirements and the increasing penetration of distributed generation. The latter is seen as

The Use Of Social Networking Sites For Learning In Institutions Of Higher Learning

Directory of Open Access Journals (Sweden)

Mange Gladys Nkatha

2015-08-01

Full Text Available Abstract Institutions of higher learning are facing greater challenges to change and subjected to various transformations in the surrounding environment including technology. These challenge and motivate them to explore new ways to improve their teaching approaches. This study sought to investigate the use of social networking site in institutions of higher learning. To this end two objectives were formulated 1 to investigate the current state of the use of social networking sites by the students 2 investigate how social networking sites can be used to promote authentic learning in institutions of higher learning. The study adopted exploratory approach using descriptive survey design where a sample of 10 67 students were picked from Jomo Kenyatta University of Agriculture and Technology JKUAT main campus. The findings indicate the use of social networking sites is a viable option as the students are not only members of social networking sites but also that majority have access to the requisite technological devices. Additionally recommendations for ensuring authentic learning were presented. The researcher recommends the exploration of the leveraging of the existing social networking sites for learning in conjunction with key stakeholders.

Impact of distributed generation units with power electronic converters on distribution network protection

NARCIS (Netherlands)

Morren, J.; Haan, de S.W.H.

2008-01-01

An increasing number of distributed generation units (DG units) are connected to the distribution network. These generators affect the operation and coordination of the distribution network protection. The influence from DG units that are coupled to the network with a power electronic converter

Distributed Constrained Stochastic Subgradient Algorithms Based on Random Projection and Asynchronous Broadcast over Networks

Directory of Open Access Journals (Sweden)

Junlong Zhu

2017-01-01

Full Text Available We consider a distributed constrained optimization problem over a time-varying network, where each agent only knows its own cost functions and its constraint set. However, the local constraint set may not be known in advance or consists of huge number of components in some applications. To deal with such cases, we propose a distributed stochastic subgradient algorithm over time-varying networks, where the estimate of each agent projects onto its constraint set by using random projection technique and the implement of information exchange between agents by employing asynchronous broadcast communication protocol. We show that our proposed algorithm is convergent with probability 1 by choosing suitable learning rate. For constant learning rate, we obtain an error bound, which is defined as the expected distance between the estimates of agent and the optimal solution. We also establish an asymptotic upper bound between the global objective function value at the average of the estimates and the optimal value.

A Complex Network Approach to Distributional Semantic Models.

Directory of Open Access Journals (Sweden)

Akira Utsumi

Full Text Available A number of studies on network analysis have focused on language networks based on free word association, which reflects human lexical knowledge, and have demonstrated the small-world and scale-free properties in the word association network. Nevertheless, there have been very few attempts at applying network analysis to distributional semantic models, despite the fact that these models have been studied extensively as computational or cognitive models of human lexical knowledge. In this paper, we analyze three network properties, namely, small-world, scale-free, and hierarchical properties, of semantic networks created by distributional semantic models. We demonstrate that the created networks generally exhibit the same properties as word association networks. In particular, we show that the distribution of the number of connections in these networks follows the truncated power law, which is also observed in an association network. This indicates that distributional semantic models can provide a plausible model of lexical knowledge. Additionally, the observed differences in the network properties of various implementations of distributional semantic models are consistently explained or predicted by considering the intrinsic semantic features of a word-context matrix and the functions of matrix weighting and smoothing. Furthermore, to simulate a semantic network with the observed network properties, we propose a new growing network model based on the model of Steyvers and Tenenbaum. The idea underlying the proposed model is that both preferential and random attachments are required to reflect different types of semantic relations in network growth process. We demonstrate that this model provides a better explanation of network behaviors generated by distributional semantic models.

Collaborative Distributed Scheduling Approaches for Wireless Sensor Network

Science.gov (United States)

Niu, Jianjun; Deng, Zhidong

2009-01-01

Energy constraints restrict the lifetime of wireless sensor networks (WSNs) with battery-powered nodes, which poses great challenges for their large scale application. In this paper, we propose a family of collaborative distributed scheduling approaches (CDSAs) based on the Markov process to reduce the energy consumption of a WSN. The family of CDSAs comprises of two approaches: a one-step collaborative distributed approach and a two-step collaborative distributed approach. The approaches enable nodes to learn the behavior information of its environment collaboratively and integrate sleep scheduling with transmission scheduling to reduce the energy consumption. We analyze the adaptability and practicality features of the CDSAs. The simulation results show that the two proposed approaches can effectively reduce nodes' energy consumption. Some other characteristics of the CDSAs like buffer occupation and packet delay are also analyzed in this paper. We evaluate CDSAs extensively on a 15-node WSN testbed. The test results show that the CDSAs conserve the energy effectively and are feasible for real WSNs. PMID:22408491

Detecting Distributed Network Traffic Anomaly with Network-Wide Correlation Analysis

Directory of Open Access Journals (Sweden)

Yang Dan

2008-12-01

Full Text Available Distributed network traffic anomaly refers to a traffic abnormal behavior involving many links of a network and caused by the same source (e.g., DDoS attack, worm propagation. The anomaly transiting in a single link might be unnoticeable and hard to detect, while the anomalous aggregation from many links can be prevailing, and does more harm to the networks. Aiming at the similar features of distributed traffic anomaly on many links, this paper proposes a network-wide detection method by performing anomalous correlation analysis of traffic signals' instantaneous parameters. In our method, traffic signals' instantaneous parameters are firstly computed, and their network-wide anomalous space is then extracted via traffic prediction. Finally, an anomaly is detected by a global correlation coefficient of anomalous space. Our evaluation using Abilene traffic traces demonstrates the excellent performance of this approach for distributed traffic anomaly detection.

Routing strategy in a distribution network when the driver learning effect is considered

DEFF Research Database (Denmark)

Battini, Daria; Faccio, Maurizio; Persona, Alessandro

2015-01-01

This paper faces one critical short term decision: the construction of routes for daily goods' deliveries in a distribution network. It investigates the possibility of applying a fixed routing strategy instead of a daily routing optimisation strategy, analysing the benefits derived from the drive...

Reduction Method for Active Distribution Networks

DEFF Research Database (Denmark)

Raboni, Pietro; Chen, Zhe

2013-01-01

On-line security assessment is traditionally performed by Transmission System Operators at the transmission level, ignoring the effective response of distributed generators and small loads. On the other hand the required computation time and amount of real time data for including Distribution...... Networks also would be too large. In this paper an adaptive aggregation method for subsystems with power electronic interfaced generators and voltage dependant loads is proposed. With this tool may be relatively easier including distribution networks into security assessment. The method is validated...... by comparing the results obtained in PSCAD® with the detailed network model and with the reduced one. Moreover the control schemes of a wind turbine and a photovoltaic plant included in the detailed network model are described....

Definition of Distribution Network Tariffs Considering Distribution Generation and Demand Response

DEFF Research Database (Denmark)

Soares, Tiago; Faria, Pedro; Vale, Zita

2014-01-01

The use of distribution networks in the current scenario of high penetration of Distributed Generation (DG) is a problem of great importance. In the competitive environment of electricity markets and smart grids, Demand Response (DR) is also gaining notable impact with several benefits for the wh......The use of distribution networks in the current scenario of high penetration of Distributed Generation (DG) is a problem of great importance. In the competitive environment of electricity markets and smart grids, Demand Response (DR) is also gaining notable impact with several benefits...... the determination of topological distribution factors, and consequent application of the MW-mile method. The application of the proposed tariffs definition methodology is illustrated in a distribution network with 33 buses, 66 DG units, and 32 consumers with DR capacity...

Distributed controller clustering in software defined networks.

Directory of Open Access Journals (Sweden)

Ahmed Abdelaziz

Full Text Available Software Defined Networking (SDN is an emerging promising paradigm for network management because of its centralized network intelligence. However, the centralized control architecture of the software-defined networks (SDNs brings novel challenges of reliability, scalability, fault tolerance and interoperability. In this paper, we proposed a novel clustered distributed controller architecture in the real setting of SDNs. The distributed cluster implementation comprises of multiple popular SDN controllers. The proposed mechanism is evaluated using a real world network topology running on top of an emulated SDN environment. The result shows that the proposed distributed controller clustering mechanism is able to significantly reduce the average latency from 8.1% to 1.6%, the packet loss from 5.22% to 4.15%, compared to distributed controller without clustering running on HP Virtual Application Network (VAN SDN and Open Network Operating System (ONOS controllers respectively. Moreover, proposed method also shows reasonable CPU utilization results. Furthermore, the proposed mechanism makes possible to handle unexpected load fluctuations while maintaining a continuous network operation, even when there is a controller failure. The paper is a potential contribution stepping towards addressing the issues of reliability, scalability, fault tolerance, and inter-operability.

Distributed controller clustering in software defined networks.

Science.gov (United States)

Abdelaziz, Ahmed; Fong, Ang Tan; Gani, Abdullah; Garba, Usman; Khan, Suleman; Akhunzada, Adnan; Talebian, Hamid; Choo, Kim-Kwang Raymond

2017-01-01

Software Defined Networking (SDN) is an emerging promising paradigm for network management because of its centralized network intelligence. However, the centralized control architecture of the software-defined networks (SDNs) brings novel challenges of reliability, scalability, fault tolerance and interoperability. In this paper, we proposed a novel clustered distributed controller architecture in the real setting of SDNs. The distributed cluster implementation comprises of multiple popular SDN controllers. The proposed mechanism is evaluated using a real world network topology running on top of an emulated SDN environment. The result shows that the proposed distributed controller clustering mechanism is able to significantly reduce the average latency from 8.1% to 1.6%, the packet loss from 5.22% to 4.15%, compared to distributed controller without clustering running on HP Virtual Application Network (VAN) SDN and Open Network Operating System (ONOS) controllers respectively. Moreover, proposed method also shows reasonable CPU utilization results. Furthermore, the proposed mechanism makes possible to handle unexpected load fluctuations while maintaining a continuous network operation, even when there is a controller failure. The paper is a potential contribution stepping towards addressing the issues of reliability, scalability, fault tolerance, and inter-operability.

Learning and Model-checking Networks of I/O Automata

DEFF Research Database (Denmark)

Mao, Hua; Jaeger, Manfred

2012-01-01

We introduce a new statistical relational learning (SRL) approach in which models for structured data, especially network data, are constructed as networks of communicating nite probabilistic automata. Leveraging existing automata learning methods from the area of grammatical inference, we can...... learn generic models for network entities in the form of automata templates. As is characteristic for SRL techniques, the abstraction level aorded by learning generic templates enables one to apply the learned model to new domains. A main benet of learning models based on nite automata lies in the fact...

Optimal Channel Selection Based on Online Decision and Offline Learning in Multichannel Wireless Sensor Networks

Directory of Open Access Journals (Sweden)

Mu Qiao

2017-01-01

Full Text Available We propose a channel selection strategy with hybrid architecture, which combines the centralized method and the distributed method to alleviate the overhead of access point and at the same time provide more flexibility in network deployment. By this architecture, we make use of game theory and reinforcement learning to fulfill the optimal channel selection under different communication scenarios. Particularly, when the network can satisfy the requirements of energy and computational costs, the online decision algorithm based on noncooperative game can help each individual sensor node immediately select the optimal channel. Alternatively, when the network cannot satisfy the requirements of energy and computational costs, the offline learning algorithm based on reinforcement learning can help each individual sensor node to learn from its experience and iteratively adjust its behavior toward the expected target. Extensive simulation results validate the effectiveness of our proposal and also prove that higher system throughput can be achieved by our channel selection strategy over the conventional off-policy channel selection approaches.

A Network Neuroscience of Human Learning: Potential to Inform Quantitative Theories of Brain and Behavior.

Science.gov (United States)

Bassett, Danielle S; Mattar, Marcelo G

2017-04-01

Humans adapt their behavior to their external environment in a process often facilitated by learning. Efforts to describe learning empirically can be complemented by quantitative theories that map changes in neurophysiology to changes in behavior. In this review we highlight recent advances in network science that offer a sets of tools and a general perspective that may be particularly useful in understanding types of learning that are supported by distributed neural circuits. We describe recent applications of these tools to neuroimaging data that provide unique insights into adaptive neural processes, the attainment of knowledge, and the acquisition of new skills, forming a network neuroscience of human learning. While promising, the tools have yet to be linked to the well-formulated models of behavior that are commonly utilized in cognitive psychology. We argue that continued progress will require the explicit marriage of network approaches to neuroimaging data and quantitative models of behavior. Copyright © 2017 Elsevier Ltd. All rights reserved.

Optimizing Cellular Networks Enabled with Renewal Energy via Strategic Learning.

Science.gov (United States)

Sohn, Insoo; Liu, Huaping; Ansari, Nirwan

2015-01-01

An important issue in the cellular industry is the rising energy cost and carbon footprint due to the rapid expansion of the cellular infrastructure. Greening cellular networks has thus attracted attention. Among the promising green cellular network techniques, the renewable energy-powered cellular network has drawn increasing attention as a critical element towards reducing carbon emissions due to massive energy consumption in the base stations deployed in cellular networks. Game theory is a branch of mathematics that is used to evaluate and optimize systems with multiple players with conflicting objectives and has been successfully used to solve various problems in cellular networks. In this paper, we model the green energy utilization and power consumption optimization problem of a green cellular network as a pilot power selection strategic game and propose a novel distributed algorithm based on a strategic learning method. The simulation results indicate that the proposed algorithm achieves correlated equilibrium of the pilot power selection game, resulting in optimum green energy utilization and power consumption reduction.

Fast, Distributed Algorithms in Deep Networks

Science.gov (United States)

2016-05-11

shallow networks, additional work will need to be done in order to allow for the application of ADMM to deep nets. The ADMM method allows for quick...Quock V Le, et al. Large scale distributed deep networks. In Advances in Neural Information Processing Systems, pages 1223–1231, 2012. [11] Ken-Ichi...A TRIDENT SCHOLAR PROJECT REPORT NO. 446 Fast, Distributed Algorithms in Deep Networks by Midshipman 1/C Ryan J. Burmeister, USN

Interconnecting Networks of Practice for Professional Learning

Directory of Open Access Journals (Sweden)

Julie Mackey

2011-03-01

Full Text Available The article explores the complementary connections between communities of practice and the ways in which individuals orchestrate their engagement with others to further their professional learning. It does so by reporting on part of a research project conducted in New Zealand on teachers’ online professional learning in a university graduate diploma program on ICT education. Evolving from social constructivist pedagogy for online professional development, the research describes how teachers create their own networks of practice as they blend online and offline interactions with fellow learners and workplace colleagues. Teachers’ perspectives of their professional learning activities challenge the way universities design formal online learning communities and highlight the potential for networked learning in the zones and intersections between professional practice and study.The article extends the concepts of Lave and Wenger’s (1991 communities of practice social theory of learning by considering the role participants play in determining their engagement and connections in and across boundaries between online learning communities and professional practice. It provides insights into the applicability of connectivist concepts for developing online pedagogies to promote socially networked learning and for emphasising the role of the learner in defining their learning pathways.

Social Learning Network Analysis Model to Identify Learning Patterns Using Ontology Clustering Techniques and Meaningful Learning

Science.gov (United States)

Firdausiah Mansur, Andi Besse; Yusof, Norazah

2013-01-01

Clustering on Social Learning Network still not explored widely, especially when the network focuses on e-learning system. Any conventional methods are not really suitable for the e-learning data. SNA requires content analysis, which involves human intervention and need to be carried out manually. Some of the previous clustering techniques need…

Co-Operative Learning and Development Networks.

Science.gov (United States)

Hodgson, V.; McConnell, D.

1995-01-01

Discusses the theory, nature, and benefits of cooperative learning. Considers the Cooperative Learning and Development Network (CLDN) trial in the JITOL (Just in Time Open Learning) project and examines the relationship between theories about cooperative learning and the reality of a group of professionals participating in a virtual cooperative…

Networks and learning in game theory

NARCIS (Netherlands)

Kets, W.

2008-01-01

This work concentrates on two topics, networks and game theory, and learning in games. The first part of this thesis looks at network games and the role of incomplete information in such games. It is assumed that players are located on a network and interact with their neighbors in the network.

Learning as Issue Framing in Agricultural Innovation Networks

Science.gov (United States)

Tisenkopfs, Talis; Kunda, Ilona; Šumane, Sandra

2014-01-01

Purpose: Networks are increasingly viewed as entities of learning and innovation in agriculture. In this article we explore learning as issue framing in two agricultural innovation networks. Design/methodology/approach: We combine frame analysis and social learning theories to analyse the processes and factors contributing to frame convergence and…

A Decomposition Algorithm for Learning Bayesian Network Structures from Data

DEFF Research Database (Denmark)

Zeng, Yifeng; Cordero Hernandez, Jorge

2008-01-01

It is a challenging task of learning a large Bayesian network from a small data set. Most conventional structural learning approaches run into the computational as well as the statistical problems. We propose a decomposition algorithm for the structure construction without having to learn...... the complete network. The new learning algorithm firstly finds local components from the data, and then recover the complete network by joining the learned components. We show the empirical performance of the decomposition algorithm in several benchmark networks....

Distributed Optimization based Dynamic Tariff for Congestion Management in Distribution Networks

DEFF Research Database (Denmark)

Huang, Shaojun; Wu, Qiuwei; Zhao, Haoran

2017-01-01

This paper proposes a distributed optimization based dynamic tariff (DDT) method for congestion management in distribution networks with high penetration of electric vehicles (EVs) and heat pumps (HPs). The DDT method employs a decomposition based optimization method to have aggregators explicitly...... is able to minimize the overall energy consumption cost and line loss cost, which is different from previous decomposition-based methods such as multiagent system methods. In addition, a reconditioning method and an integral controller are introduced to improve convergence of the distributed optimization...... where challenges arise due to multiple congestion points, multiple types of flexible demands and network constraints. The case studies demonstrate the efficacy of the DDT method for congestion management in distribution networks....

Pareto Optimal Solutions for Network Defense Strategy Selection Simulator in Multi-Objective Reinforcement Learning

Directory of Open Access Journals (Sweden)

Yang Sun

2018-01-01

Full Text Available Using Pareto optimization in Multi-Objective Reinforcement Learning (MORL leads to better learning results for network defense games. This is particularly useful for network security agents, who must often balance several goals when choosing what action to take in defense of a network. If the defender knows his preferred reward distribution, the advantages of Pareto optimization can be retained by using a scalarization algorithm prior to the implementation of the MORL. In this paper, we simulate a network defense scenario by creating a multi-objective zero-sum game and using Pareto optimization and MORL to determine optimal solutions and compare those solutions to different scalarization approaches. We build a Pareto Defense Strategy Selection Simulator (PDSSS system for assisting network administrators on decision-making, specifically, on defense strategy selection, and the experiment results show that the Satisficing Trade-Off Method (STOM scalarization approach performs better than linear scalarization or GUESS method. The results of this paper can aid network security agents attempting to find an optimal defense policy for network security games.

Learning Bayesian Networks with Incomplete Data by Augmentation

OpenAIRE

Adel, Tameem; de Campos, Cassio P.

2016-01-01

We present new algorithms for learning Bayesian networks from data with missing values using a data augmentation approach. An exact Bayesian network learning algorithm is obtained by recasting the problem into a standard Bayesian network learning problem without missing data. To the best of our knowledge, this is the first exact algorithm for this problem. As expected, the exact algorithm does not scale to large domains. We build on the exact method to create an approximate algorithm using a ...

Parallelization of learning problems by artificial neural networks. Application in external radiotherapy

International Nuclear Information System (INIS)

Sauget, M.

2007-12-01

This research is about the application of neural networks used in the external radiotherapy domain. The goal is to elaborate a new evaluating system for the radiation dose distributions in heterogeneous environments. The al objective of this work is to build a complete tool kit to evaluate the optimal treatment planning. My st research point is about the conception of an incremental learning algorithm. The interest of my work is to combine different optimizations specialized in the function interpolation and to propose a new algorithm allowing to change the neural network architecture during the learning phase. This algorithm allows to minimise the al size of the neural network while keeping a good accuracy. The second part of my research is to parallelize the previous incremental learning algorithm. The goal of that work is to increase the speed of the learning step as well as the size of the learned dataset needed in a clinical case. For that, our incremental learning algorithm presents an original data decomposition with overlapping, together with a fault tolerance mechanism. My last research point is about a fast and accurate algorithm computing the radiation dose deposit in any heterogeneous environment. At the present time, the existing solutions used are not optimal. The fast solution are not accurate and do not give an optimal treatment planning. On the other hand, the accurate solutions are far too slow to be used in a clinical context. Our algorithm answers to this problem by bringing rapidity and accuracy. The concept is to use a neural network adequately learned together with a mechanism taking into account the environment changes. The advantages of this algorithm is to avoid the use of a complex physical code while keeping a good accuracy and reasonable computation times. (author)

THE IMPACTS OF SOCIAL NETWORKING SITES IN HIGHER LEARNING

OpenAIRE

Mohd Ishak Bin Ismail; Ruzaini Bin Abdullah Arshah

2016-01-01

Social networking sites, a web-based application have permeated the boundary between personal lives and student lives. Nowadays, students in higher learning used social networking site such as Facebook to facilitate their learning through the academic collaboration which it further enhances students’ social capital. Social networking site has many advantages to improve students’ learning. To date, Facebook is the leading social networking sites at this time which it being widely used by stude...

System analysis and planning of a gas distribution network

Energy Technology Data Exchange (ETDEWEB)

Salas, Edwin F.M.; Farias, Helio Monteiro [AUTOMIND, Rio de Janeiro, RJ (Brazil); Costa, Carla V.R. [Universidade Salvador (UNIFACS), BA (Brazil)

2009-07-01

The increase in demand by gas consumers require that projects or improvements in gas distribution networks be made carefully and safely to ensure a continuous, efficient and economical supply. Gas distribution companies must ensure that the networks and equipment involved are defined and designed at the appropriate time to attend to the demands of the market. To do that a gas distribution network analysis and planning tool should use distribution networks and transmission models for the current situation and the future changes to be implemented. These models are used to evaluate project options and help in making appropriate decisions in order to minimize the capital investment in new components or simple changes in operational procedures. Gas demands are increasing and it is important that gas distribute design new distribution systems to ensure this growth, considering financial constraints of the company, as well as local legislation and regulation. In this study some steps of developing a flexible system that attends to those needs will be described. The analysis of distribution requires geographically referenced data for the models as well as an accurate connectivity and the attributes of the equipment. GIS systems are often used as a deposit center that holds the majority of this information. GIS systems are constantly updated as distribution network equipment is modified. The distribution network modeling gathered from this system ensures that the model represents the current network condition. The benefits of this architecture drastically reduce the creation and maintenance cost of the network models, because network components data are conveniently made available to populate the distribution network. This architecture ensures that the models are continually reflecting the reality of the distribution network. (author)

Deep learning in neural networks: an overview.

Science.gov (United States)

Schmidhuber, Jürgen

2015-01-01

In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarizes relevant work, much of it from the previous millennium. Shallow and Deep Learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.

Reversal Learning in Humans and Gerbils: Dynamic Control Network Facilitates Learning.

Science.gov (United States)

Jarvers, Christian; Brosch, Tobias; Brechmann, André; Woldeit, Marie L; Schulz, Andreas L; Ohl, Frank W; Lommerzheim, Marcel; Neumann, Heiko

2016-01-01

Biologically plausible modeling of behavioral reinforcement learning tasks has seen great improvements over the past decades. Less work has been dedicated to tasks involving contingency reversals, i.e., tasks in which the original behavioral goal is reversed one or multiple times. The ability to adjust to such reversals is a key element of behavioral flexibility. Here, we investigate the neural mechanisms underlying contingency-reversal tasks. We first conduct experiments with humans and gerbils to demonstrate memory effects, including multiple reversals in which subjects (humans and animals) show a faster learning rate when a previously learned contingency re-appears. Motivated by recurrent mechanisms of learning and memory for object categories, we propose a network architecture which involves reinforcement learning to steer an orienting system that monitors the success in reward acquisition. We suggest that a model sensory system provides feature representations which are further processed by category-related subnetworks which constitute a neural analog of expert networks. Categories are selected dynamically in a competitive field and predict the expected reward. Learning occurs in sequentialized phases to selectively focus the weight adaptation to synapses in the hierarchical network and modulate their weight changes by a global modulator signal. The orienting subsystem itself learns to bias the competition in the presence of continuous monotonic reward accumulation. In case of sudden changes in the discrepancy of predicted and acquired reward the activated motor category can be switched. We suggest that this subsystem is composed of a hierarchically organized network of dis-inhibitory mechanisms, dubbed a dynamic control network (DCN), which resembles components of the basal ganglia. The DCN selectively activates an expert network, corresponding to the current behavioral strategy. The trace of the accumulated reward is monitored such that large sudden

Identifying Gatekeepers in Online Learning Networks

Science.gov (United States)

Gursakal, Necmi; Bozkurt, Aras

2017-01-01

The rise of the networked society has not only changed our perceptions but also the definitions, roles, processes and dynamics of online learning networks. From offline to online worlds, networks are everywhere and gatekeepers are an important entity in these networks. In this context, the purpose of this paper is to explore gatekeeping and…

Robust Learning of Fixed-Structure Bayesian Networks

OpenAIRE

Diakonikolas, Ilias; Kane, Daniel; Stewart, Alistair

2016-01-01

We investigate the problem of learning Bayesian networks in an agnostic model where an $\\epsilon$-fraction of the samples are adversarially corrupted. Our agnostic learning model is similar to -- in fact, stronger than -- Huber's contamination model in robust statistics. In this work, we study the fully observable Bernoulli case where the structure of the network is given. Even in this basic setting, previous learning algorithms either run in exponential time or lose dimension-dependent facto...

Statistical and machine learning approaches for network analysis

CERN Document Server

Dehmer, Matthias

2012-01-01

Explore the multidisciplinary nature of complex networks through machine learning techniques Statistical and Machine Learning Approaches for Network Analysis provides an accessible framework for structurally analyzing graphs by bringing together known and novel approaches on graph classes and graph measures for classification. By providing different approaches based on experimental data, the book uniquely sets itself apart from the current literature by exploring the application of machine learning techniques to various types of complex networks. Comprised of chapters written by internation

Design of a Networked Learning Master Environment for Professionals

DEFF Research Database (Denmark)

Dirckinck-Holmfeld, Lone

2010-01-01

The paper is presenting the overall learning design of MIL (Master in ICT and Learning). The learning design is integrating a number of principles: 1. Principles of problem and project based learning 2. Networked learning / learning in communities of practice. The paper will discuss how these pri......The paper is presenting the overall learning design of MIL (Master in ICT and Learning). The learning design is integrating a number of principles: 1. Principles of problem and project based learning 2. Networked learning / learning in communities of practice. The paper will discuss how...

Status of Utilizing Social Media Networks in the Teaching-Learning Process at Public Jordanian Universities

Directory of Open Access Journals (Sweden)

Muneera Abdalkareem Alshdefait

2018-03-01

Full Text Available This study aimed at finding out the status of utilizing social media networks in the teaching-learning process at public Jordanian Universities. To achieve the goal of the study, the descriptive developmental method was used and a questionnaire was developed, consisting of (35 statements. The questionnaire was checked for its validity and reliability. Then it was distributed to a sample of (382 male and female students from the undergraduate and graduate levels. The study results showed that the participants gave a low score to the status of utilizing social media networks in the teaching-learning process at public Jordanian universities. The results also showed that there were statistically significant differences between the participants of the study according to the academic rank attributed to the graduate students, and according to gender attributed to male students at the instrument macro level and on all dimensions of the two variables. In light of these results, the study recommended that public universities should utilize modern technology in the educational process, urge and encourage the teaching staff members to use the social media networks in the teaching-learning process and raise the students' awareness about the benefits of using social media networks. Keywords: Social media networks, Teaching-learning process, Public Jordanian Universities

A fusion networking model for smart grid power distribution backbone communication network based on PTN

Directory of Open Access Journals (Sweden)

Wang Hao

2016-01-01

Full Text Available In current communication network for distribution in Chinese power grid systems, the fiber communication backbone network for distribution and TD-LTE power private wireless backhaul network of power grid are both bearing by the SDH optical transmission network, which also carries the communication network of transformer substation and main electric. As the data traffic of the distribution communication and TD-LTE power private wireless network grow rapidly in recent years, it will have a big impact with the SDH network’s bearing capacity which is mainly used for main electric communication in high security level. This paper presents a fusion networking model which use a multiple-layer PTN network as the unified bearing of the TD-LTE power private wireless backhaul network and fiber communication backbone network for distribution. Network dataflow analysis shows that this model can greatly reduce the capacity pressure of the traditional SDH network as well as ensure the reliability of the transmission of the communication network for distribution and TD-LTE power private wireless network.

Thermodynamic efficiency of learning a rule in neural networks

Science.gov (United States)

Goldt, Sebastian; Seifert, Udo

2017-11-01

Biological systems have to build models from their sensory input data that allow them to efficiently process previously unseen inputs. Here, we study a neural network learning a binary classification rule for these inputs from examples provided by a teacher. We analyse the ability of the network to apply the rule to new inputs, that is to generalise from past experience. Using stochastic thermodynamics, we show that the thermodynamic costs of the learning process provide an upper bound on the amount of information that the network is able to learn from its teacher for both batch and online learning. This allows us to introduce a thermodynamic efficiency of learning. We analytically compute the dynamics and the efficiency of a noisy neural network performing online learning in the thermodynamic limit. In particular, we analyse three popular learning algorithms, namely Hebbian, Perceptron and AdaTron learning. Our work extends the methods of stochastic thermodynamics to a new type of learning problem and might form a suitable basis for investigating the thermodynamics of decision-making.

U.S. stock market interaction network as learned by the Boltzmann machine

Science.gov (United States)

Borysov, Stanislav S.; Roudi, Yasser; Balatsky, Alexander V.

2015-12-01

We study historical dynamics of joint equilibrium distribution of stock returns in the U.S. stock market using the Boltzmann distribution model being parametrized by external fields and pairwise couplings. Within Boltzmann learning framework for statistical inference, we analyze historical behavior of the parameters inferred using exact and approximate learning algorithms. Since the model and inference methods require use of binary variables, effect of this mapping of continuous returns to the discrete domain is studied. The presented results show that binarization preserves the correlation structure of the market. Properties of distributions of external fields and couplings as well as the market interaction network and industry sector clustering structure are studied for different historical dates and moving window sizes. We demonstrate that the observed positive heavy tail in distribution of couplings is related to the sparse clustering structure of the market. We also show that discrepancies between the model's parameters might be used as a precursor of financial instabilities.

The Impact of Distributed Generation on Distribution Networks ...

African Journals Online (AJOL)

Their advantages are the ability to reduce or postpone the need for investment in the transmission and distribution infrastructure when optimally located; the ability to reduce technical losses within the transmission and distribution networks as well as general improvement in power quality and system reliability. This paper ...

Collaborative Distributed Scheduling Approaches for Wireless Sensor Network

Directory of Open Access Journals (Sweden)

Zhidong Deng

2009-10-01

Full Text Available Energy constraints restrict the lifetime of wireless sensor networks (WSNs with battery-powered nodes, which poses great challenges for their large scale application. In this paper, we propose a family of collaborative distributed scheduling approaches (CDSAs based on the Markov process to reduce the energy consumption of a WSN. The family of CDSAs comprises of two approaches: a one-step collaborative distributed approach and a two-step collaborative distributed approach. The approaches enable nodes to learn the behavior information of its environment collaboratively and integrate sleep scheduling with transmission scheduling to reduce the energy consumption. We analyze the adaptability and practicality features of the CDSAs. The simulation results show that the two proposed approaches can effectively reduce nodes’ energy consumption. Some other characteristics of the CDSAs like buffer occupation and packet delay are also analyzed in this paper. We evaluate CDSAs extensively on a 15-node WSN testbed. The test results show that the CDSAs conserve the energy effectively and are feasible for real WSNs.

Learning modulation of odor representations: new findings from Arc-indexed networks

Directory of Open Access Journals (Sweden)

Qi eYuan

2014-12-01

Full Text Available We first review our understanding of odor representations in rodent olfactory bulb and anterior piriform cortex. We then consider learning-induced representation changes. Finally we describe the perspective on network representations gained from examining Arc-indexed odor networks of awake rats. Arc-indexed networks are sparse and distributed, consistent with current views. However Arc provides representations of repeated odors. Arc-indexed repeated odor representations are quite variable. Sparse representations are assumed to be compact and reliable memory codes. Arc suggests this is not necessarily the case. The variability seen is consistent with electrophysiology in awake animals and may reflect top down-cortical modulation of context. Arc-indexing shows that distinct odors share larger than predicted neuron pools. These may be low-threshold neuronal subsets.Learning’s effect on Arc-indexed representations is to increase the stable or overlapping component of rewarded odor representations. This component can decrease for similar odors when their discrimination is rewarded. The learning effects seen are supported by electrophysiology, but mechanisms remain to be elucidated.

Teachers’ motives for learning in networks : costs, rewards and community interest

NARCIS (Netherlands)

van den Beemt, A.A.J.; Ketelaar, E.; Diepstraten, I.; de Laat, M.

2018-01-01

Background: This paper discusses teachers’ perspectives on learning networks and their motives for participating in these networks. Although it is widely held that teachers’ learning may be developed through learning networks, not all teachers participate in such networks. Purpose: The theme of

Hydraulic Network Modelling of Small Community Water Distribution ...

African Journals Online (AJOL)

Prof Anyata

... design of a small community (Sakwa) water distribution network in North Eastern geopolitical region of Nigeria using ..... self cleansing drinking water distribution system is set at 0.4m/s, .... distribution network offers advantages over manual ...

Learning Local Components to Understand Large Bayesian Networks

DEFF Research Database (Denmark)

Zeng, Yifeng; Xiang, Yanping; Cordero, Jorge

2009-01-01

(domain experts) to extract accurate information from a large Bayesian network due to dimensional difficulty. We define a formulation of local components and propose a clustering algorithm to learn such local components given complete data. The algorithm groups together most inter-relevant attributes......Bayesian networks are known for providing an intuitive and compact representation of probabilistic information and allowing the creation of models over a large and complex domain. Bayesian learning and reasoning are nontrivial for a large Bayesian network. In parallel, it is a tough job for users...... in a domain. We evaluate its performance on three benchmark Bayesian networks and provide results in support. We further show that the learned components may represent local knowledge more precisely in comparison to the full Bayesian networks when working with a small amount of data....

Evolving autonomous learning in cognitive networks.

Science.gov (United States)

Sheneman, Leigh; Hintze, Arend

2017-12-01

There are two common approaches for optimizing the performance of a machine: genetic algorithms and machine learning. A genetic algorithm is applied over many generations whereas machine learning works by applying feedback until the system meets a performance threshold. These methods have been previously combined, particularly in artificial neural networks using an external objective feedback mechanism. We adapt this approach to Markov Brains, which are evolvable networks of probabilistic and deterministic logic gates. Prior to this work MB could only adapt from one generation to the other, so we introduce feedback gates which augment their ability to learn during their lifetime. We show that Markov Brains can incorporate these feedback gates in such a way that they do not rely on an external objective feedback signal, but instead can generate internal feedback that is then used to learn. This results in a more biologically accurate model of the evolution of learning, which will enable us to study the interplay between evolution and learning and could be another step towards autonomously learning machines.

Effects of network topology on wealth distributions

International Nuclear Information System (INIS)

Garlaschelli, Diego; Loffredo, Maria I

2008-01-01

We focus on the problem of how the wealth is distributed among the units of a networked economic system. We first review the empirical results documenting that in many economies the wealth distribution is described by a combination of the log-normal and power-law behaviours. We then focus on the Bouchaud-Mezard model of wealth exchange, describing an economy of interacting agents connected through an exchange network. We report analytical and numerical results showing that the system self-organizes towards a stationary state whose associated wealth distribution depends crucially on the underlying interaction network. In particular, we show that if the network displays a homogeneous density of links, the wealth distribution displays either the log-normal or the power-law form. This means that the first-order topological properties alone (such as the scale-free property) are not enough to explain the emergence of the empirically observed mixed form of the wealth distribution. In order to reproduce this nontrivial pattern, the network has to be heterogeneously divided into regions with a variable density of links. We show new results detailing how this effect is related to the higher-order correlation properties of the underlying network. In particular, we analyse assortativity by degree and the pairwise wealth correlations, and discuss the effects that these properties have on each other

Delivering Sustainability Through Supply Chain Distribution Network Redesign

Directory of Open Access Journals (Sweden)

Denise Ravet

2013-09-01

Full Text Available Purpose - Companies could gain (cost, service, green/sustainable competitive advantage through the supply chain network. The goal of this article is to study how to deliver sustainability through the supply chain distribution network redesign.Design/methodology/approach - A literature review is conducted to examine research relating to sustainable supply chain strategies and supply chain distribution network redesign.Findings - A study of the supply chain literature reveals the importance to rethink the supply chain distribution network design and to treat sustainability as integral to operations.

Learning Bayesian networks for discrete data

KAUST Repository

Liang, Faming; Zhang, Jian

2009-01-01

Bayesian networks have received much attention in the recent literature. In this article, we propose an approach to learn Bayesian networks using the stochastic approximation Monte Carlo (SAMC) algorithm. Our approach has two nice features. Firstly

Short term and medium term power distribution load forecasting by neural networks

International Nuclear Information System (INIS)

Yalcinoz, T.; Eminoglu, U.

2005-01-01

Load forecasting is an important subject for power distribution systems and has been studied from different points of view. In general, load forecasts should be performed over a broad spectrum of time intervals, which could be classified into short term, medium term and long term forecasts. Several research groups have proposed various techniques for either short term load forecasting or medium term load forecasting or long term load forecasting. This paper presents a neural network (NN) model for short term peak load forecasting, short term total load forecasting and medium term monthly load forecasting in power distribution systems. The NN is used to learn the relationships among past, current and future temperatures and loads. The neural network was trained to recognize the peak load of the day, total load of the day and monthly electricity consumption. The suitability of the proposed approach is illustrated through an application to real load shapes from the Turkish Electricity Distribution Corporation (TEDAS) in Nigde. The data represents the daily and monthly electricity consumption in Nigde, Turkey

Visionary network 2030. Technology vision for future distribution network

International Nuclear Information System (INIS)

Kumpulainen, L.; Laaksonen, H.; Komulainen, R.

2006-11-01

Objective of this research was to create the long term vision of a distribution network technology to be used for the near future rebuild and necessary R and D efforts. Present status of the grid was briefly handled and created scenarios for the operational environment changes and available technology International view was used for getting familiar with the present solutions and future expectations in other countries. Centralised power generation is supposed to form the majority, but also the distributed generation will play more and more important role, which is hard to predict due to the uncertainty of the development of the regulation. Higher reliability and safety in major faults are expected from the future network with the reasonable costs. Impact of the climate change and impregnant using restrictions cause difficulties especially for the overhead lines in the forests. In the rural network also the ageing is the problem. For the urban networks the land usage and environmental issues get more challenging and the network reinforcement is necessary due to the increased use of electricity. As a result several technical solutions are available. Additions to the technology today, several new solutions were introduced. Important solutions in the future network are supposed to be the wide range of underground cable, high degree utilisation of the communication and network automation solutions, considerable shorter protection zones and new layout solution. In a long run the islanding enabled by the distributed energy systems and totally new network structures and solutions based on power electronics are supposed to improve the power quality and profitability. Separate quality classes in network design principally are also supposed to be approved. Getting into the vision needs also the Roadmap project, which coordinates and focuses the development of the industry. So the limited national development resources can be effectively utilised. A coordinated national

Topology Counts: Force Distributions in Circular Spring Networks

Science.gov (United States)

Heidemann, Knut M.; Sageman-Furnas, Andrew O.; Sharma, Abhinav; Rehfeldt, Florian; Schmidt, Christoph F.; Wardetzky, Max

2018-02-01

Filamentous polymer networks govern the mechanical properties of many biological materials. Force distributions within these networks are typically highly inhomogeneous, and, although the importance of force distributions for structural properties is well recognized, they are far from being understood quantitatively. Using a combination of probabilistic and graph-theoretical techniques, we derive force distributions in a model system consisting of ensembles of random linear spring networks on a circle. We show that characteristic quantities, such as the mean and variance of the force supported by individual springs, can be derived explicitly in terms of only two parameters: (i) average connectivity and (ii) number of nodes. Our analysis shows that a classical mean-field approach fails to capture these characteristic quantities correctly. In contrast, we demonstrate that network topology is a crucial determinant of force distributions in an elastic spring network. Our results for 1D linear spring networks readily generalize to arbitrary dimensions.

Topology Counts: Force Distributions in Circular Spring Networks.

Science.gov (United States)

Heidemann, Knut M; Sageman-Furnas, Andrew O; Sharma, Abhinav; Rehfeldt, Florian; Schmidt, Christoph F; Wardetzky, Max

2018-02-09

Filamentous polymer networks govern the mechanical properties of many biological materials. Force distributions within these networks are typically highly inhomogeneous, and, although the importance of force distributions for structural properties is well recognized, they are far from being understood quantitatively. Using a combination of probabilistic and graph-theoretical techniques, we derive force distributions in a model system consisting of ensembles of random linear spring networks on a circle. We show that characteristic quantities, such as the mean and variance of the force supported by individual springs, can be derived explicitly in terms of only two parameters: (i) average connectivity and (ii) number of nodes. Our analysis shows that a classical mean-field approach fails to capture these characteristic quantities correctly. In contrast, we demonstrate that network topology is a crucial determinant of force distributions in an elastic spring network. Our results for 1D linear spring networks readily generalize to arbitrary dimensions.

A Capacity Dimensioning Method for Broadband Distribution Networks

DEFF Research Database (Denmark)

Shawky, Ahmed; Pedersen, Jens Myrup; Bergheim, Hans

2010-01-01

This paper presents capacity dimensioning for a hypothetical distribution network in the Danish municipality of Aalborg. The number of customers in need for a better service level and the continuous increase in network traffic makes it harder for ISPs to deliver high levels of service to their cu......This paper presents capacity dimensioning for a hypothetical distribution network in the Danish municipality of Aalborg. The number of customers in need for a better service level and the continuous increase in network traffic makes it harder for ISPs to deliver high levels of service...... to their customers. This paper starts by defining three levels of services, together with traffic demands based on research of traffic distribution and generation in networks. Calculations for network dimension are then calculated. The results from the dimensioning are used to compare different network topologies...

Distributed learning process: principles of design and implementation

Directory of Open Access Journals (Sweden)

G. N. Boychenko

2016-01-01

Full Text Available At the present stage, broad information and communication technologies (ICT usage in educational practices is one of the leading trends of global education system development. This trend has led to the instructional interaction models transformation. Scientists have developed the theory of distributed cognition (Salomon, G., Hutchins, E., and distributed education and training (Fiore, S. M., Salas, E., Oblinger, D. G., Barone, C. A., Hawkins, B. L.. Educational process is based on two separated in time and space sub-processes of learning and teaching which are aimed at the organization of fl exible interactions between learners, teachers and educational content located in different non-centralized places.The purpose of this design research is to fi nd a solution for the problem of formalizing distributed learning process design and realization that is signifi cant in instructional design. The solution to this problem should take into account specifi cs of distributed interactions between team members, which becomes collective subject of distributed cognition in distributed learning process. This makes it necessary to design roles and functions of the individual team members performing distributed educational activities. Personal educational objectives should be determined by decomposition of team objectives into functional roles of its members with considering personal and learning needs and interests of students.Theoretical and empirical methods used in the study: theoretical analysis of philosophical, psychological, and pedagogical literature on the issue, analysis of international standards in the e-learning domain; exploration on practical usage of distributed learning in academic and corporate sectors; generalization, abstraction, cognitive modelling, ontology engineering methods.Result of the research is methodology for design and implementation of distributed learning process based on the competency approach. Methodology proposed by

QSAR modelling using combined simple competitive learning networks and RBF neural networks.

Science.gov (United States)

Sheikhpour, R; Sarram, M A; Rezaeian, M; Sheikhpour, E

2018-04-01

The aim of this study was to propose a QSAR modelling approach based on the combination of simple competitive learning (SCL) networks with radial basis function (RBF) neural networks for predicting the biological activity of chemical compounds. The proposed QSAR method consisted of two phases. In the first phase, an SCL network was applied to determine the centres of an RBF neural network. In the second phase, the RBF neural network was used to predict the biological activity of various phenols and Rho kinase (ROCK) inhibitors. The predictive ability of the proposed QSAR models was evaluated and compared with other QSAR models using external validation. The results of this study showed that the proposed QSAR modelling approach leads to better performances than other models in predicting the biological activity of chemical compounds. This indicated the efficiency of simple competitive learning networks in determining the centres of RBF neural networks.

A Hierarchical Dispatch Structure for Distribution Network Pricing

OpenAIRE

Yuan, Zhao; Hesamzadeh, Mohammad Reza

2015-01-01

This paper presents a hierarchical dispatch structure for efficient distribution network pricing. The dispatch coordination problem in the context of hierarchical network operators are addressed. We formulate decentralized generation dispatch into a bilevel optimization problem in which main network operator and the connected distribution network operator optimize their costs in two levels. By using Karush-Kuhn-Tucker conditions and Fortuny-Amat McCarl linearization, the bilevel optimization ...

Multi-modal Social Networks: A MRF Learning Approach

Science.gov (United States)

2016-06-20

Network forensics: random infection vs spreading epidemic , Proceedings of ACM Sigmetrics. 11-JUN-12, London, UK. : , TOTAL: 4 06/09/2016 Received Paper...Multi-modal Social Networks A MRF Learning Approach The work primarily focused on two lines of research. 1. We propose new greedy algorithms...Box 12211 Research Triangle Park, NC 27709-2211 social networks , learning and inference REPORT DOCUMENTATION PAGE 11. SPONSOR/MONITOR’S REPORT

Network Capacity Assessment of CHP-based Distributed Generation on Urban Energy Distribution Networks

Science.gov (United States)

Zhang, Xianjun

The combined heat and power (CHP)-based distributed generation (DG) or dis-tributed energy resources (DERs) are mature options available in the present energy market, considered to be an effective solution to promote energy efficiency. In the urban environment, the electricity, water and natural gas distribution networks are becoming increasingly interconnected with the growing penetration of the CHP-based DG. Subsequently, this emerging interdependence leads to new topics meriting serious consideration: how much of the CHP-based DG can be accommodated and where to locate these DERs, and given preexisting constraints, how to quantify the mutual impacts on operation performances between these urban energy distribution networks and the CHP-based DG. The early research work was conducted to investigate the feasibility and design methods for one residential microgrid system based on existing electricity, water and gas infrastructures of a residential community, mainly focusing on the economic planning. However, this proposed design method cannot determine the optimal DG sizing and siting for a larger test bed with the given information of energy infrastructures. In this context, a more systematic as well as generalized approach should be developed to solve these problems. In the later study, the model architecture that integrates urban electricity, water and gas distribution networks, and the CHP-based DG system was developed. The proposed approach addressed the challenge of identifying the optimal sizing and siting of the CHP-based DG on these urban energy networks and the mutual impacts on operation performances were also quantified. For this study, the overall objective is to maximize the electrical output and recovered thermal output of the CHP-based DG units. The electricity, gas, and water system models were developed individually and coupled by the developed CHP-based DG system model. The resultant integrated system model is used to constrain the DG's electrical

Machine Learning Topological Invariants with Neural Networks

Science.gov (United States)

Zhang, Pengfei; Shen, Huitao; Zhai, Hui

2018-02-01

In this Letter we supervisedly train neural networks to distinguish different topological phases in the context of topological band insulators. After training with Hamiltonians of one-dimensional insulators with chiral symmetry, the neural network can predict their topological winding numbers with nearly 100% accuracy, even for Hamiltonians with larger winding numbers that are not included in the training data. These results show a remarkable success that the neural network can capture the global and nonlinear topological features of quantum phases from local inputs. By opening up the neural network, we confirm that the network does learn the discrete version of the winding number formula. We also make a couple of remarks regarding the role of the symmetry and the opposite effect of regularization techniques when applying machine learning to physical systems.

Distribution Network Design--literature study based

OpenAIRE

LI, ANG

2012-01-01

The focus of this research is companies' outbound distribution network design in supply chain management. Within the present competitive market, it is a fundamental importance for companies to achieve high level business performance with an effective supply chain. Outbound distribution network design as an important part in supply chain management, to a large extent decides whether companies can fulfill customers' requirement or not. Therefore, such a study is important for manufacturers and ...

Accelerated Monte Carlo system reliability analysis through machine-learning-based surrogate models of network connectivity

International Nuclear Information System (INIS)

Stern, R.E.; Song, J.; Work, D.B.

2017-01-01

The two-terminal reliability problem in system reliability analysis is known to be computationally intractable for large infrastructure graphs. Monte Carlo techniques can estimate the probability of a disconnection between two points in a network by selecting a representative sample of network component failure realizations and determining the source-terminal connectivity of each realization. To reduce the runtime required for the Monte Carlo approximation, this article proposes an approximate framework in which the connectivity check of each sample is estimated using a machine-learning-based classifier. The framework is implemented using both a support vector machine (SVM) and a logistic regression based surrogate model. Numerical experiments are performed on the California gas distribution network using the epicenter and magnitude of the 1989 Loma Prieta earthquake as well as randomly-generated earthquakes. It is shown that the SVM and logistic regression surrogate models are able to predict network connectivity with accuracies of 99% for both methods, and are 1–2 orders of magnitude faster than using a Monte Carlo method with an exact connectivity check. - Highlights: • Surrogate models of network connectivity are developed by machine-learning algorithms. • Developed surrogate models can reduce the runtime required for Monte Carlo simulations. • Support vector machine and logistic regressions are employed to develop surrogate models. • Numerical example of California gas distribution network demonstrate the proposed approach. • The developed models have accuracies 99%, and are 1–2 orders of magnitude faster than MCS.

Hybrid e-learning tool TransLearning

NARCIS (Netherlands)

Meij, van der Marjoleine G.; Kupper, Frank; Beers, P.J.; Broerse, Jacqueline E.W.

2016-01-01

E-learning and storytelling approaches can support informal vicarious learning within geographically widely distributed multi-stakeholder collaboration networks. This case study evaluates hybrid e-learning and video-storytelling approach ‘TransLearning’ by investigation into how its storytelling

The Role of Architectural and Learning Constraints in Neural Network Models: A Case Study on Visual Space Coding.

Science.gov (United States)

Testolin, Alberto; De Filippo De Grazia, Michele; Zorzi, Marco

2017-01-01

The recent "deep learning revolution" in artificial neural networks had strong impact and widespread deployment for engineering applications, but the use of deep learning for neurocomputational modeling has been so far limited. In this article we argue that unsupervised deep learning represents an important step forward for improving neurocomputational models of perception and cognition, because it emphasizes the role of generative learning as opposed to discriminative (supervised) learning. As a case study, we present a series of simulations investigating the emergence of neural coding of visual space for sensorimotor transformations. We compare different network architectures commonly used as building blocks for unsupervised deep learning by systematically testing the type of receptive fields and gain modulation developed by the hidden neurons. In particular, we compare Restricted Boltzmann Machines (RBMs), which are stochastic, generative networks with bidirectional connections trained using contrastive divergence, with autoencoders, which are deterministic networks trained using error backpropagation. For both learning architectures we also explore the role of sparse coding, which has been identified as a fundamental principle of neural computation. The unsupervised models are then compared with supervised, feed-forward networks that learn an explicit mapping between different spatial reference frames. Our simulations show that both architectural and learning constraints strongly influenced the emergent coding of visual space in terms of distribution of tuning functions at the level of single neurons. Unsupervised models, and particularly RBMs, were found to more closely adhere to neurophysiological data from single-cell recordings in the primate parietal cortex. These results provide new insights into how basic properties of artificial neural networks might be relevant for modeling neural information processing in biological systems.

Functionality for learning networks: lessons learned from social web applications

NARCIS (Netherlands)

Berlanga, Adriana; Sloep, Peter; Brouns, Francis; Van Rosmalen, Peter; Bitter-Rijpkema, Marlies; Koper, Rob

2007-01-01

Berlanga, A. J., Sloep, P., Brouns, F., Van Rosmalen, P., Bitter-Rijpkema, M., & Koper, R. (2007). Functionality for learning networks: lessons learned from social web applications. Proceedings of the ePortfolio 2007 Conference. October, 18-19, 2007, Maastricht, The Netherlands. [See also

On-line learning in radial basis functions networks

OpenAIRE

Freeman, Jason; Saad, David

1997-01-01

An analytic investigation of the average case learning and generalization properties of Radial Basis Function Networks (RBFs) is presented, utilising on-line gradient descent as the learning rule. The analytic method employed allows both the calculation of generalization error and the examination of the internal dynamics of the network. The generalization error and internal dynamics are then used to examine the role of the learning rate and the specialization of the hidden units, which gives ...

Approximation methods for efficient learning of Bayesian networks

CERN Document Server

Riggelsen, C

2008-01-01

This publication offers and investigates efficient Monte Carlo simulation methods in order to realize a Bayesian approach to approximate learning of Bayesian networks from both complete and incomplete data. For large amounts of incomplete data when Monte Carlo methods are inefficient, approximations are implemented, such that learning remains feasible, albeit non-Bayesian. The topics discussed are: basic concepts about probabilities, graph theory and conditional independence; Bayesian network learning from data; Monte Carlo simulation techniques; and, the concept of incomplete data. In order to provide a coherent treatment of matters, thereby helping the reader to gain a thorough understanding of the whole concept of learning Bayesian networks from (in)complete data, this publication combines in a clarifying way all the issues presented in the papers with previously unpublished work.

Adaptive Learning in Weighted Network Games

NARCIS (Netherlands)

Bayer, Péter; Herings, P. Jean-Jacques; Peeters, Ronald; Thuijsman, Frank

2017-01-01

This paper studies adaptive learning in the class of weighted network games. This class of games includes applications like research and development within interlinked firms, crime within social networks, the economics of pollution, and defense expenditures within allied nations. We show that for

Personalizing Access to Learning Networks

DEFF Research Database (Denmark)

Dolog, Peter; Simon, Bernd; Nejdl, Wolfgang

2008-01-01

In this article, we describe a Smart Space for Learning™ (SS4L) framework and infrastructure that enables personalized access to distributed heterogeneous knowledge repositories. Helping a learner to choose an appropriate learning resource or activity is a key problem which we address in this fra......In this article, we describe a Smart Space for Learning™ (SS4L) framework and infrastructure that enables personalized access to distributed heterogeneous knowledge repositories. Helping a learner to choose an appropriate learning resource or activity is a key problem which we address...... in this framework, enabling personalized access to federated learning repositories with a vast number of learning offers. Our infrastructure includes personalization strategies both at the query and the query results level. Query rewriting is based on learning and language preferences; rule-based and ranking...

Learning by stimulation avoidance: A principle to control spiking neural networks dynamics.

Science.gov (United States)

Sinapayen, Lana; Masumori, Atsushi; Ikegami, Takashi

2017-01-01

Learning based on networks of real neurons, and learning based on biologically inspired models of neural networks, have yet to find general learning rules leading to widespread applications. In this paper, we argue for the existence of a principle allowing to steer the dynamics of a biologically inspired neural network. Using carefully timed external stimulation, the network can be driven towards a desired dynamical state. We term this principle "Learning by Stimulation Avoidance" (LSA). We demonstrate through simulation that the minimal sufficient conditions leading to LSA in artificial networks are also sufficient to reproduce learning results similar to those obtained in biological neurons by Shahaf and Marom, and in addition explains synaptic pruning. We examined the underlying mechanism by simulating a small network of 3 neurons, then scaled it up to a hundred neurons. We show that LSA has a higher explanatory power than existing hypotheses about the response of biological neural networks to external simulation, and can be used as a learning rule for an embodied application: learning of wall avoidance by a simulated robot. In other works, reinforcement learning with spiking networks can be obtained through global reward signals akin simulating the dopamine system; we believe that this is the first project demonstrating sensory-motor learning with random spiking networks through Hebbian learning relying on environmental conditions without a separate reward system.

Extensible router for a quantum key distribution network

International Nuclear Information System (INIS)

Zhang Tao; Mo Xiaofan; Han Zhengfu; Guo Guangcan

2008-01-01

Building a quantum key distribution network is crucial for practical quantum cryptography. We present a scheme to build a star topology quantum key distribution network based on wavelength division multiplexing which, with current technology, can connect at least a hundred users. With the scheme, a 4-user demonstration network was built up and key exchanges were performed

Evolution of individual versus social learning on social networks.

Science.gov (United States)

Tamura, Kohei; Kobayashi, Yutaka; Ihara, Yasuo

2015-03-06

A number of studies have investigated the roles played by individual and social learning in cultural phenomena and the relative advantages of the two learning strategies in variable environments. Because social learning involves the acquisition of behaviours from others, its utility depends on the availability of 'cultural models' exhibiting adaptive behaviours. This indicates that social networks play an essential role in the evolution of learning. However, possible effects of social structure on the evolution of learning have not been fully explored. Here, we develop a mathematical model to explore the evolutionary dynamics of learning strategies on social networks. We first derive the condition under which social learners (SLs) are selectively favoured over individual learners in a broad range of social network. We then obtain an analytical approximation of the long-term average frequency of SLs in homogeneous networks, from which we specify the condition, in terms of three relatedness measures, for social structure to facilitate the long-term evolution of social learning. Finally, we evaluate our approximation by Monte Carlo simulations in complete graphs, regular random graphs and scale-free networks. We formally show that whether social structure favours the evolution of social learning is determined by the relative magnitudes of two effects of social structure: localization in competition, by which competition between learning strategies is evaded, and localization in cultural transmission, which slows down the spread of adaptive traits. In addition, our estimates of the relatedness measures suggest that social structure disfavours the evolution of social learning when selection is weak. © 2015 The Author(s) Published by the Royal Society. All rights reserved.

Biologically-inspired Learning in Pulsed Neural Networks

DEFF Research Database (Denmark)

Lehmann, Torsten; Woodburn, Robin

1999-01-01

Self-learning chips to implement many popular ANN (artificial neural network) algorithms are very difficult to design. We explain why this is so and say what lessons previous work teaches us in the design of self-learning systems. We offer a contribution to the `biologically-inspired' approach......, explaining what we mean by this term and providing an example of a robust, self-learning design that can solve simple classical-conditioning tasks. We give details of the design of individual circuits to perform component functions, which can then be combined into a network to solve the task. We argue...

Learning oncogenetic networks by reducing to mixed integer linear programming.

Science.gov (United States)

Shahrabi Farahani, Hossein; Lagergren, Jens

2013-01-01

Cancer can be a result of accumulation of different types of genetic mutations such as copy number aberrations. The data from tumors are cross-sectional and do not contain the temporal order of the genetic events. Finding the order in which the genetic events have occurred and progression pathways are of vital importance in understanding the disease. In order to model cancer progression, we propose Progression Networks, a special case of Bayesian networks, that are tailored to model disease progression. Progression networks have similarities with Conjunctive Bayesian Networks (CBNs) [1],a variation of Bayesian networks also proposed for modeling disease progression. We also describe a learning algorithm for learning Bayesian networks in general and progression networks in particular. We reduce the hard problem of learning the Bayesian and progression networks to Mixed Integer Linear Programming (MILP). MILP is a Non-deterministic Polynomial-time complete (NP-complete) problem for which very good heuristics exists. We tested our algorithm on synthetic and real cytogenetic data from renal cell carcinoma. We also compared our learned progression networks with the networks proposed in earlier publications. The software is available on the website https://bitbucket.org/farahani/diprog.

Mocapy++ - A toolkit for inference and learning in dynamic Bayesian networks

Directory of Open Access Journals (Sweden)

Hamelryck Thomas

2010-03-01

Full Text Available Abstract Background Mocapy++ is a toolkit for parameter learning and inference in dynamic Bayesian networks (DBNs. It supports a wide range of DBN architectures and probability distributions, including distributions from directional statistics (the statistics of angles, directions and orientations. Results The program package is freely available under the GNU General Public Licence (GPL from SourceForge http://sourceforge.net/projects/mocapy. The package contains the source for building the Mocapy++ library, several usage examples and the user manual. Conclusions Mocapy++ is especially suitable for constructing probabilistic models of biomolecular structure, due to its support for directional statistics. In particular, it supports the Kent distribution on the sphere and the bivariate von Mises distribution on the torus. These distributions have proven useful to formulate probabilistic models of protein and RNA structure in atomic detail.

Transient stability analysis of a distribution network with distributed generators

NARCIS (Netherlands)

Xyngi, I.; Ishchenko, A.; Popov, M.; Sluis, van der L.

2009-01-01

This letter describes the transient stability analysis of a 10-kV distribution network with wind generators, microturbines, and CHP plants. The network being modeled in Matlab/Simulink takes into account detailed dynamic models of the generators. Fault simulations at various locations are

Robust quantum network architectures and topologies for entanglement distribution

Science.gov (United States)

Das, Siddhartha; Khatri, Sumeet; Dowling, Jonathan P.

2018-01-01

Entanglement distribution is a prerequisite for several important quantum information processing and computing tasks, such as quantum teleportation, quantum key distribution, and distributed quantum computing. In this work, we focus on two-dimensional quantum networks based on optical quantum technologies using dual-rail photonic qubits for the building of a fail-safe quantum internet. We lay out a quantum network architecture for entanglement distribution between distant parties using a Bravais lattice topology, with the technological constraint that quantum repeaters equipped with quantum memories are not easily accessible. We provide a robust protocol for simultaneous entanglement distribution between two distant groups of parties on this network. We also discuss a memory-based quantum network architecture that can be implemented on networks with an arbitrary topology. We examine networks with bow-tie lattice and Archimedean lattice topologies and use percolation theory to quantify the robustness of the networks. In particular, we provide figures of merit on the loss parameter of the optical medium that depend only on the topology of the network and quantify the robustness of the network against intermittent photon loss and intermittent failure of nodes. These figures of merit can be used to compare the robustness of different network topologies in order to determine the best topology in a given real-world scenario, which is critical in the realization of the quantum internet.

Adaptive intelligent power systems: Active distribution networks

International Nuclear Information System (INIS)

McDonald, Jim

2008-01-01

Electricity networks are extensive and well established. They form a key part of the infrastructure that supports industrialised society. These networks are moving from a period of stability to a time of potentially major transition, driven by a need for old equipment to be replaced, by government policy commitments to cleaner and renewable sources of electricity generation, and by change in the power industry. This paper looks at moves towards active distribution networks. The novel transmission and distribution systems of the future will challenge today's system designs. They will cope with variable voltages and frequencies, and will offer more flexible, sustainable options. Intelligent power networks will need innovation in several key areas of information technology. Active control of flexible, large-scale electrical power systems is required. Protection and control systems will have to react to faults and unusual transient behaviour and ensure recovery after such events. Real-time network simulation and performance analysis will be needed to provide decision support for system operators, and the inputs to energy and distribution management systems. Advanced sensors and measurement will be used to achieve higher degrees of network automation and better system control, while pervasive communications will allow networks to be reconfigured by intelligent systems

Incentive-Based Voltage Regulation in Distribution Networks

Energy Technology Data Exchange (ETDEWEB)

Dall-Anese, Emiliano [National Renewable Energy Laboratory (NREL), Golden, CO (United States); Baker, Kyri A [National Renewable Energy Laboratory (NREL), Golden, CO (United States); Zhou, Xinyang [University of Colorado; Chen, Lijun [University of Colorado

2017-07-03

This paper considers distribution networks fea- turing distributed energy resources, and designs incentive-based mechanisms that allow the network operator and end-customers to pursue given operational and economic objectives, while concurrently ensuring that voltages are within prescribed limits. Two different network-customer coordination mechanisms that require different amounts of information shared between the network operator and end-customers are developed to identify a solution of a well-defined social-welfare maximization prob- lem. Notably, the signals broadcast by the network operator assume the connotation of prices/incentives that induce the end- customers to adjust the generated/consumed powers in order to avoid the violation of the voltage constraints. Stability of the proposed schemes is analytically established and numerically corroborated.

Scalable and practical multi-objective distribution network expansion planning

NARCIS (Netherlands)

Luong, N.H.; Grond, M.O.W.; Poutré, La J.A.; Bosman, P.A.N.

2015-01-01

We formulate the distribution network expansion planning (DNEP) problem as a multi-objective optimization (MOO) problem with different objectives that distribution network operators (DNOs) would typically like to consider during decision making processes for expanding their networks. Objectives are

The Mobile Learning Network: Getting Serious about Games Technologies for Learning

Science.gov (United States)

Petley, Rebecca; Parker, Guy; Attewell, Jill

2011-01-01

The Mobile Learning Network currently in its third year, is a unique collaborative initiative encouraging and enabling the introduction of mobile learning in English post-14 education. The programme, funded jointly by the Learning and Skills Council and participating colleges and schools and supported by LSN has involved nearly 40,000 learners and…

Photovoltaic production and distribution network; La production photovoltaique et les reseaux de distribution

Energy Technology Data Exchange (ETDEWEB)

Fraisse, J.L. [ERDF, 75 - Paris (France)

2010-04-15

The rapid development of photovoltaics boosted by attractive feed-in tariffs caused a sharp increase in requests for connection to public distribution grids, which were originally designed to serve consumers. ERDF, main distribution network operator in France, is facing a challenge in terms of capacity for handling requests for connection and in terms of public distribution network operation and management. (author)

Learning drifting concepts with neural networks

NARCIS (Netherlands)

Biehl, Michael; Schwarze, Holm

1993-01-01

The learning of time-dependent concepts with a neural network is studied analytically and numerically. The linearly separable target rule is represented by an N-vector, whose time dependence is modelled by a random or deterministic drift process. A single-layer network is trained online using

Distributional learning has immediate and long-lasting effects.

Science.gov (United States)

Escudero, Paola; Williams, Daniel

2014-11-01

Evidence of distributional learning, a statistical learning mechanism centered on relative frequency of exposure to different tokens, has mainly come from short-term learning and therefore does not ostensibly address the development of important learning processes. The present longitudinal study examines both short- and long-term effects of distributional learning of phonetic categories on non-native sound discrimination over a 12-month period. Two groups of listeners were exposed to a two-minute distribution of auditory stimuli in which the most frequently presented tokens either approximated or exaggerated the natural production of the speech sounds, whereas a control group listened to a piece of classical music for the same length of time. Discrimination by listeners in the two distribution groups improved immediately after the short exposure, replicating previous results. Crucially, this improvement was maintained after six and 12 months, demonstrating that distributional learning has long-lasting effects. Copyright © 2014 Elsevier B.V. All rights reserved.

Resilience-based optimal design of water distribution network

Science.gov (United States)

Suribabu, C. R.

2017-11-01

Optimal design of water distribution network is generally aimed to minimize the capital cost of the investments on tanks, pipes, pumps, and other appurtenances. Minimizing the cost of pipes is usually considered as a prime objective as its proportion in capital cost of the water distribution system project is very high. However, minimizing the capital cost of the pipeline alone may result in economical network configuration, but it may not be a promising solution in terms of resilience point of view. Resilience of the water distribution network has been considered as one of the popular surrogate measures to address ability of network to withstand failure scenarios. To improve the resiliency of the network, the pipe network optimization can be performed with two objectives, namely minimizing the capital cost as first objective and maximizing resilience measure of the configuration as secondary objective. In the present work, these two objectives are combined as single objective and optimization problem is solved by differential evolution technique. The paper illustrates the procedure for normalizing the objective functions having distinct metrics. Two of the existing resilience indices and power efficiency are considered for optimal design of water distribution network. The proposed normalized objective function is found to be efficient under weighted method of handling multi-objective water distribution design problem. The numerical results of the design indicate the importance of sizing pipe telescopically along shortest path of flow to have enhanced resiliency indices.

Fuzzy comprehensive evaluation model of interuniversity collaborative learning based on network

Science.gov (United States)

Wenhui, Ma; Yu, Wang

2017-06-01

Learning evaluation is an effective method, which plays an important role in the network education evaluation system. But most of the current network learning evaluation methods still use traditional university education evaluation system, which do not take into account of web-based learning characteristics, and they are difficult to fit the rapid development of interuniversity collaborative learning based on network. Fuzzy comprehensive evaluation method is used to evaluate interuniversity collaborative learning based on the combination of fuzzy theory and analytic hierarchy process. Analytic hierarchy process is used to determine the weight of evaluation factors of each layer and to carry out the consistency check. According to the fuzzy comprehensive evaluation method, we establish interuniversity collaborative learning evaluation mathematical model. The proposed scheme provides a new thought for interuniversity collaborative learning evaluation based on network.

Integrated Power Flow and Short Circuit Calculation Method for Distribution Network with Inverter Based Distributed Generation

OpenAIRE

Yang, Shan; Tong, Xiangqian

2016-01-01

Power flow calculation and short circuit calculation are the basis of theoretical research for distribution network with inverter based distributed generation. The similarity of equivalent model for inverter based distributed generation during normal and fault conditions of distribution network and the differences between power flow and short circuit calculation are analyzed in this paper. Then an integrated power flow and short circuit calculation method for distribution network with inverte...

An integrated control for overvoltage mitigation in the distribution network

NARCIS (Netherlands)

Viyathukattuva Mohamed Ali, M.M.; Nguyen, P.H.; Kling, W.L.

2014-01-01

Increasing share of distributed renewable energy sources (DRES) in the distribution network raises new operational and power quality challenges like overvoltage in the network feeders. Such power quality challenge limits the penetration of DRES in the distribution network. This paper addresses a

How to Trigger Emergence and Self-Organisation in Learning Networks

Science.gov (United States)

Brouns, Francis; Fetter, Sibren; van Rosmalen, Peter

The previous chapters of this section discussed why the social structure of Learning Networks is important and present guidelines on how to maintain and allow the emergence of communities in Learning Networks. Chapter 2 explains how Learning Networks rely on social interaction and active participations of the participants. Chapter 3 then continues by presenting guidelines and policies that should be incorporated into Learning Network Services in order to maintain existing communities by creating conditions that promote social interaction and knowledge sharing. Chapter 4 discusses the necessary conditions required for knowledge sharing to occur and to trigger communities to self-organise and emerge. As pointed out in Chap. 4, ad-hoc transient communities facilitate the emergence of social interaction in Learning Networks, self-organising them into communities, taking into account personal characteristics, community characteristics and general guidelines. As explained in Chap. 4 community members would benefit from a service that brings suitable people together for a specific purpose, because it will allow the participant to focus on the knowledge sharing process by reducing the effort or costs. In the current chapter, we describe an example of a peer support Learning Network Service based on the mechanism of peer tutoring in ad-hoc transient communities.

A compound memristive synapse model for statistical learning through STDP in spiking neural networks.

Science.gov (United States)

Bill, Johannes; Legenstein, Robert

2014-01-01

Memristors have recently emerged as promising circuit elements to mimic the function of biological synapses in neuromorphic computing. The fabrication of reliable nanoscale memristive synapses, that feature continuous conductance changes based on the timing of pre- and postsynaptic spikes, has however turned out to be challenging. In this article, we propose an alternative approach, the compound memristive synapse, that circumvents this problem by the use of memristors with binary memristive states. A compound memristive synapse employs multiple bistable memristors in parallel to jointly form one synapse, thereby providing a spectrum of synaptic efficacies. We investigate the computational implications of synaptic plasticity in the compound synapse by integrating the recently observed phenomenon of stochastic filament formation into an abstract model of stochastic switching. Using this abstract model, we first show how standard pulsing schemes give rise to spike-timing dependent plasticity (STDP) with a stabilizing weight dependence in compound synapses. In a next step, we study unsupervised learning with compound synapses in networks of spiking neurons organized in a winner-take-all architecture. Our theoretical analysis reveals that compound-synapse STDP implements generalized Expectation-Maximization in the spiking network. Specifically, the emergent synapse configuration represents the most salient features of the input distribution in a Mixture-of-Gaussians generative model. Furthermore, the network's spike response to spiking input streams approximates a well-defined Bayesian posterior distribution. We show in computer simulations how such networks learn to represent high-dimensional distributions over images of handwritten digits with high fidelity even in presence of substantial device variations and under severe noise conditions. Therefore, the compound memristive synapse may provide a synaptic design principle for future neuromorphic architectures.

Hybrid Collaborative Learning for Classification and Clustering in Sensor Networks

Science.gov (United States)

Wagstaff, Kiri L.; Sosnowski, Scott; Lane, Terran

2012-01-01

Traditionally, nodes in a sensor network simply collect data and then pass it on to a centralized node that archives, distributes, and possibly analyzes the data. However, analysis at the individual nodes could enable faster detection of anomalies or other interesting events as well as faster responses, such as sending out alerts or increasing the data collection rate. There is an additional opportunity for increased performance if learners at individual nodes can communicate with their neighbors. In previous work, methods were developed by which classification algorithms deployed at sensor nodes can communicate information about event labels to each other, building on prior work with co-training, self-training, and active learning. The idea of collaborative learning was extended to function for clustering algorithms as well, similar to ideas from penta-training and consensus clustering. However, collaboration between these learner types had not been explored. A new protocol was developed by which classifiers and clusterers can share key information about their observations and conclusions as they learn. This is an active collaboration in which learners of either type can query their neighbors for information that they then use to re-train or re-learn the concept they are studying. The protocol also supports broadcasts from the classifiers and clusterers to the rest of the network to announce new discoveries. Classifiers observe an event and assign it a label (type). Clusterers instead group observations into clusters without assigning them a label, and they collaborate in terms of pairwise constraints between two events [same-cluster (mustlink) or different-cluster (cannot-link)]. Fundamentally, these two learner types speak different languages. To bridge this gap, the new communication protocol provides four types of exchanges: hybrid queries for information, hybrid "broadcasts" of learned information, each specified for classifiers-to-clusterers, and clusterers

Teachers' Motives for Learning in Networks: Costs, Rewards and Community Interest

Science.gov (United States)

van den Beemt, Antoine; Ketelaar, Evelien; Diepstraten, Isabelle; de Laat, Maarten

2018-01-01

Background: This paper discusses teachers' perspectives on learning networks and their motives for participating in these networks. Although it is widely held that teachers' learning may be developed through learning networks, not all teachers participate in such networks. Purpose: The theme of reciprocity, central to studies in the area of…

Network connection of distributed electricity production - a preliminary study

International Nuclear Information System (INIS)

Pleym, Anngjerd; Mogstad, Olve

2002-01-01

It will be necessary to lower the barriers for utilisation of distributed energy sources in order to increase the use of such sources in Norway. A relatively extensive R and D activity would be required for reaching this goal. Available Norwegian and international guidelines and technical requirements with respect to network connection of the distributed energy sources are studied with the aim of exposing needs for further R and D initiatives. A limited monitor is also carried out among the Norwegian network businesses with distributed units in their networks. The results show that the main focus in the R and D activities has drifted away from establishing guidelines for technical requirements for network coupling. Some verification work remains in investigating the usefulness of the existing international and the specific commercial network guidelines. For the network industry the main focus must be on the two following areas: 1) How will large concentrations of distributed production units connected to the same network influence the voltage quality and the delivery reliability in the networks. 2) How can the network businesses employ the distributed production units in their networks. A Nordic project (Finland, Sweden, Norway) which will study these problems is being established. Large national scientific institutions will be involved. The executive committee will consist of representatives from Finenergy, Elforsk and EBL Kompetanse and other financing institutions and industries. A Finnish business Merinova, is to be appointed to the project leadership

Distributed routing algorithms to manage power flow in agent-based active distribution network

NARCIS (Netherlands)

Nguyen, H.P.; Kling, W.L.; Georgiadis, G.; Papatriantafilou, M.; Anh-Tuan, L.; Bertling, L.

2010-01-01

The current transition from passive to active electric distribution networks comes with problems and challenges on bi-directional power flow in the network and the uncertainty in the forecast of power generation from grid-connected renewable and distributed energy sources. The power flow management

Evaluation of Voltage Control Approaches for Future Smart Distribution Networks

Directory of Open Access Journals (Sweden)

Pengfei Wang

2017-08-01

Full Text Available This paper evaluates meta-heuristic and deterministic approaches for distribution network voltage control. As part of this evaluation, a novel meta-heuristic algorithm, Cuckoo Search, is applied for distribution network voltage control and compared with a deterministic voltage control algorithm, the oriented discrete coordinate decent method (ODCDM. ODCDM has been adopted in a state-of-the-art industrial product and applied in real distribution networks. These two algorithms have been evaluated under a set of test cases, which were generated to represent the voltage control problems in current and future distribution networks. Sampled test results have been presented, and findings have been discussed regarding the adoption of different optimization algorithms for current and future distribution networks.

Comprehensive evaluation index system of total supply capability in distribution network

Science.gov (United States)

Zhang, Linyao; Wu, Guilian; Yang, Jingyuan; Jia, Shuangrui; Zhang, Wei; Sun, Weiqing

2018-01-01

Aiming at the lack of a comprehensive evaluation of the distribution network, based on the existing distribution network evaluation index system, combined with the basic principles of constructing the evaluation index, put forward a new evaluation index system of distribution network capacity. This paper is mainly based on the total supply capability of the distribution network, combining single index and various factors, into a multi-evaluation index of the distribution network, thus forming a reasonable index system, and various indicators of rational quantification make the evaluation results more intuitive. In order to have a comprehensive judgment of distribution network, this paper uses weights to analyse the importance of each index, verify the rationality of the index system through the example, it is proved that the rationality of the index system, so as to guide the direction of distribution network planning.

Applicability of line outage distribution factors to evaluate distribution network expansion options

NARCIS (Netherlands)

Grond, M.O.W.; Pouw, J.I.P.; Morren, J.; Slootweg, J.G.

2014-01-01

Distribution network operators require more advanced planning tools to deal with the challenges of future network planning. An appropriate planning and optimization tool can identify which option for network extension should be selected from available alternatives. However, the evaluation part in

Assessment of energy supply and continuity of service in distribution network with renewable distributed generation

International Nuclear Information System (INIS)

Abdullah, M.A.; Agalgaonkar, A.P.; Muttaqi, K.M.

2014-01-01

Highlights: • Difficulties in assessing distribution network adequacy with DG are addressed. • Indices are proposed to assess adequacy of energy supply and service continuity. • Analytical methodology is developed to assess the proposed indices. • Concept of joint probability distribution of demand and generation is applied. - Abstract: Continuity of electricity supply with renewable distributed generation (DG) is a topical issue for distribution system planning and operation, especially due to the stochastic nature of power generation and time varying load demand. The conventional adequacy and reliability analysis methods related to bulk generation systems cannot be applied directly for the evaluation of adequacy criteria such as ‘energy supply’ and ‘continuity of service’ for distribution networks embedded with renewable DG. In this paper, new indices highlighting ‘available supply capacity’ and ‘continuity of service’ are proposed for ‘energy supply’ and ‘continuation of service’ evaluation of generation-rich distribution networks, and analytical techniques are developed for their quantification. A probability based analytical method has been developed using the joint probability of the demand and generation, and probability distributions of the proposed indices have been used to evaluate the network adequacy in energy supply and service continuation. A data clustering technique has been used to evaluate the joint probability between coincidental demand and renewable generation. Time sequential Monte Carlo simulation has been used to compare the results obtained using the proposed analytical method. A standard distribution network derived from Roy Billinton test system and a practical radial distribution network have been used to test the proposed method and demonstrate the estimation of the well-being of a system for hosting renewable DG units. It is found that renewable DG systems improve the ‘energy supply’ and �

Distribution network topology identification based on synchrophasor

Directory of Open Access Journals (Sweden)

Stefania Conti

2018-03-01

Full Text Available A distribution system upgrade moving towards Smart Grid implementation is necessary to face the proliferation of distributed generators and electric vehicles, in order to satisfy the increasing demand for high quality, efficient, secure, reliable energy supply. This perspective requires taking into account system vulnerability to cyber attacks. An effective attack could destroy stored information about network structure, historical data and so on. Countermeasures and network applications could be made impracticable since most of them are based on the knowledge of network topology. Usually, the location of each link between nodes in a network is known. Therefore, the methods used for topology identification determine if a link is open or closed. When no information on the location of the network links is available, these methods become totally unfeasible. This paper presents a method to identify the network topology using only nodal measures obtained by means of phasor measurement units.

Quantum key distribution network for multiple applications

Science.gov (United States)

Tajima, A.; Kondoh, T.; Ochi, T.; Fujiwara, M.; Yoshino, K.; Iizuka, H.; Sakamoto, T.; Tomita, A.; Shimamura, E.; Asami, S.; Sasaki, M.

2017-09-01

The fundamental architecture and functions of secure key management in a quantum key distribution (QKD) network with enhanced universal interfaces for smooth key sharing between arbitrary two nodes and enabling multiple secure communication applications are proposed. The proposed architecture consists of three layers: a quantum layer, key management layer and key supply layer. We explain the functions of each layer, the key formats in each layer and the key lifecycle for enabling a practical QKD network. A quantum key distribution-advanced encryption standard (QKD-AES) hybrid system and an encrypted smartphone system were developed as secure communication applications on our QKD network. The validity and usefulness of these systems were demonstrated on the Tokyo QKD Network testbed.

Fuzzy comprehensive evaluation model of interuniversity collaborative learning based on network

Directory of Open Access Journals (Sweden)

Wenhui Ma

2017-06-01

Full Text Available Learning evaluation is an effective method, which plays an important role in the network education evaluation system. But most of the current network learning evaluation methods still use traditional university education evaluation system, which do not take into account of web-based learning characteristics, and they are difficult to fit the rapid development of interuniversity collaborative learning based on network. Fuzzy comprehensive evaluation method is used to evaluate interuniversity collaborative learning based on the combination of fuzzy theory and analytic hierarchy process. Analytic hierarchy process is used to determine the weight of evaluation factors of each layer and to carry out the consistency check. According to the fuzzy comprehensive evaluation method, we establish interuniversity collaborative learning evaluation mathematical model. The proposed scheme provides a new thought for interuniversity collaborative learning evaluation based on network.

Integrated Power Flow and Short Circuit Calculation Method for Distribution Network with Inverter Based Distributed Generation

Directory of Open Access Journals (Sweden)

Shan Yang

2016-01-01

Full Text Available Power flow calculation and short circuit calculation are the basis of theoretical research for distribution network with inverter based distributed generation. The similarity of equivalent model for inverter based distributed generation during normal and fault conditions of distribution network and the differences between power flow and short circuit calculation are analyzed in this paper. Then an integrated power flow and short circuit calculation method for distribution network with inverter based distributed generation is proposed. The proposed method let the inverter based distributed generation be equivalent to Iθ bus, which makes it suitable to calculate the power flow of distribution network with a current limited inverter based distributed generation. And the low voltage ride through capability of inverter based distributed generation can be considered as well in this paper. Finally, some tests of power flow and short circuit current calculation are performed on a 33-bus distribution network. The calculated results from the proposed method in this paper are contrasted with those by the traditional method and the simulation method, whose results have verified the effectiveness of the integrated method suggested in this paper.

Business opportunities and dynamic competition through distributed generation in primary electricity distribution networks

International Nuclear Information System (INIS)

Raineri, R.; Rios, S.; Vasquez, R.

2005-01-01

In this paper, for a real electricity distribution network, an assessment of business opportunities to invest in distributed generation (DG) is performed through a simulation based on a full representation of three medium voltage (12 kV) feeders. The three feeders representation includes 1062 sections of conductors with 13 different sizes. The economic assessment focuses on both, the incentives of the incumbent distribution company and those of a new entrant. The technical and economic impact on losses, reliability and voltage regulation in the network area are verified. The DG solution analyzed determines a business opportunity for new investors where end users are also benefited. This work calls in the debate on the need to reformulate the current regulation model on electricity distribution, by defining clear rules to incorporate DG to the existing network, and to enable any agent to develop the proposed business. DG success depends on the location of adequate sites to strategically establish few DG units being a substitute to network expansion

Social networks as ICT collaborative and supportive learning media ...

African Journals Online (AJOL)

... ICT collaborative and supportive learning media utilisation within the Nigerian educational system. The concept of ICT was concisely explained vis-à-vis the social network concept, theory and collaborative and supportive learning media utilisation. Different types of social network are highlighted among which Facebook, ...

Criticality meets learning: Criticality signatures in a self-organizing recurrent neural network.

Science.gov (United States)

Del Papa, Bruno; Priesemann, Viola; Triesch, Jochen

2017-01-01

Many experiments have suggested that the brain operates close to a critical state, based on signatures of criticality such as power-law distributed neuronal avalanches. In neural network models, criticality is a dynamical state that maximizes information processing capacities, e.g. sensitivity to input, dynamical range and storage capacity, which makes it a favorable candidate state for brain function. Although models that self-organize towards a critical state have been proposed, the relation between criticality signatures and learning is still unclear. Here, we investigate signatures of criticality in a self-organizing recurrent neural network (SORN). Investigating criticality in the SORN is of particular interest because it has not been developed to show criticality. Instead, the SORN has been shown to exhibit spatio-temporal pattern learning through a combination of neural plasticity mechanisms and it reproduces a number of biological findings on neural variability and the statistics and fluctuations of synaptic efficacies. We show that, after a transient, the SORN spontaneously self-organizes into a dynamical state that shows criticality signatures comparable to those found in experiments. The plasticity mechanisms are necessary to attain that dynamical state, but not to maintain it. Furthermore, onset of external input transiently changes the slope of the avalanche distributions - matching recent experimental findings. Interestingly, the membrane noise level necessary for the occurrence of the criticality signatures reduces the model's performance in simple learning tasks. Overall, our work shows that the biologically inspired plasticity and homeostasis mechanisms responsible for the SORN's spatio-temporal learning abilities can give rise to criticality signatures in its activity when driven by random input, but these break down under the structured input of short repeating sequences.

The Value of Information in Distributed Decision Networks

Science.gov (United States)

2016-03-04

formulation, and then we describe the various results at- tained. 1 Mathematical description of Distributed Decision Network un- der Information...Constraints We now define a mathematical framework for networks. Let G = (V,E) be an undirected random network (graph) drawn from a known distribution pG, 1...to any linear, combinatorial problem like shortest path optimization, and, further, so long as the original combinatorial problem can be solved in

Modelling aspects of distributed processing in telecommunication networks

NARCIS (Netherlands)

Tomasgard, A; Audestad, JA; Dye, S; Stougie, L; van der Vlerk, MH; Wallace, SW

1998-01-01

The purpose of this paper is to formally describe new optimization models for telecommunication networks with distributed processing. Modem distributed networks put more focus on the processing of information and less on the actual transportation of data than we are traditionally used to in

Conflict free network coding for distributed storage networks

KAUST Repository

Al-Habob, Ahmed A.; Sorour, Sameh; Aboutorab, Neda; Sadeghi, Parastoo

2015-01-01

© 2015 IEEE. In this paper, we design a conflict free instantly decodable network coding (IDNC) solution for file download from distributed storage servers. Considering previously downloaded files at the clients from these servers as side

Consensus-based distributed cooperative learning from closed-loop neural control systems.

Science.gov (United States)

Chen, Weisheng; Hua, Shaoyong; Zhang, Huaguang

2015-02-01

In this paper, the neural tracking problem is addressed for a group of uncertain nonlinear systems where the system structures are identical but the reference signals are different. This paper focuses on studying the learning capability of neural networks (NNs) during the control process. First, we propose a novel control scheme called distributed cooperative learning (DCL) control scheme, by establishing the communication topology among adaptive laws of NN weights to share their learned knowledge online. It is further proved that if the communication topology is undirected and connected, all estimated weights of NNs can converge to small neighborhoods around their optimal values over a domain consisting of the union of all state orbits. Second, as a corollary it is shown that the conclusion on the deterministic learning still holds in the decentralized adaptive neural control scheme where, however, the estimated weights of NNs just converge to small neighborhoods of the optimal values along their own state orbits. Thus, the learned controllers obtained by DCL scheme have the better generalization capability than ones obtained by decentralized learning method. A simulation example is provided to verify the effectiveness and advantages of the control schemes proposed in this paper.

Constructing a Watts-Strogatz network from a small-world network with symmetric degree distribution.

Directory of Open Access Journals (Sweden)

Mozart B C Menezes

Full Text Available Though the small-world phenomenon is widespread in many real networks, it is still challenging to replicate a large network at the full scale for further study on its structure and dynamics when sufficient data are not readily available. We propose a method to construct a Watts-Strogatz network using a sample from a small-world network with symmetric degree distribution. Our method yields an estimated degree distribution which fits closely with that of a Watts-Strogatz network and leads into accurate estimates of network metrics such as clustering coefficient and degree of separation. We observe that the accuracy of our method increases as network size increases.

Constructing a Watts-Strogatz network from a small-world network with symmetric degree distribution.

Science.gov (United States)

Menezes, Mozart B C; Kim, Seokjin; Huang, Rongbing

2017-01-01

Though the small-world phenomenon is widespread in many real networks, it is still challenging to replicate a large network at the full scale for further study on its structure and dynamics when sufficient data are not readily available. We propose a method to construct a Watts-Strogatz network using a sample from a small-world network with symmetric degree distribution. Our method yields an estimated degree distribution which fits closely with that of a Watts-Strogatz network and leads into accurate estimates of network metrics such as clustering coefficient and degree of separation. We observe that the accuracy of our method increases as network size increases.

Exploring Practice-Research Networks for Critical Professional Learning

Science.gov (United States)

Appleby, Yvon; Hillier, Yvonne

2012-01-01

This paper discusses the contribution that practice-research networks can make to support critical professional development in the Learning and Skills sector in England. By practice-research networks we mean groups or networks which maintain a connection between research and professional practice. These networks stem from the philosophy of…

Developing equivalent circuits for radial distribution networks

Energy Technology Data Exchange (ETDEWEB)

Prada, Ricardo; Coelho, Agnelo; Rodrigues, Anselmo [Catholic University of Rio de Janeiro (PUC-Rio), RJ (Brazil). Dept. of Electrical Engineering], Emails: prada@ele.puc-rio.br, agnelo@ele.puc-rio.br, nebulok_99@yahoo.com; Silva, Maria da Guia da [Federal University of Maranhao, Sao Luiz, MA (Brazil). Dept. of Electrical Engineering

2009-07-01

This paper presents a method for evaluating External Equivalent in Electric Distribution Networks (EDN).The proposed method has as its main objectives the reduction of the computational costs in distribution network reconfiguration, investigation of the optimal allocation of banks of capacitors, investigation of the allocation of distributed generation, etc. In these sorts of problems a large number of alternative projects must be assessed in order to identify the optimal solution. The optimal solution comes up with the voltage level in the load points within specified limits. Consequently, the EDN must retain the external network load points but without major increasing in the dimension of the equivalent circuit. The proposed method has been tested and validated in a substation of the Electricity Utility of Maranhao - CEMAR, in Brazil. (author)

Theoretical framework on selected core issues on conditions for productive learning in networked learning environments

DEFF Research Database (Denmark)

Dirckinck-Holmfeld, Lone; Svendsen, Brian Møller; Ponti, Marisa

The report documents and summarises the elements and dimensions that have been identified to describe and analyse the case studies collected in the Kaleidoscope Jointly Executed Integrating Research Project (JEIRP) on Conditions for productive learning in network learning environments.......The report documents and summarises the elements and dimensions that have been identified to describe and analyse the case studies collected in the Kaleidoscope Jointly Executed Integrating Research Project (JEIRP) on Conditions for productive learning in network learning environments....

Architectural transformations in network services and distributed systems

CERN Document Server

Luntovskyy, Andriy

2017-01-01

With the given work we decided to help not only the readers but ourselves, as the professionals who actively involved in the networking branch, with understanding the trends that have developed in recent two decades in distributed systems and networks. Important architecture transformations of distributed systems have been examined. The examples of new architectural solutions are discussed. Content Periodization of service development Energy efficiency Architectural transformations in Distributed Systems Clustering and Parallel Computing, performance models Cloud Computing, RAICs, Virtualization, SDN Smart Grid, Internet of Things, Fog Computing Mobile Communication from LTE to 5G, DIDO, SAT-based systems Data Security Guaranteeing Distributed Systems Target Groups Students in EE and IT of universities and (dual) technical high schools Graduated engineers as well as teaching staff About the Authors Andriy Luntovskyy provides classes on networks, mobile communication, software technology, distributed systems, ...

Efficient Reactive Power Compensation Algorithm for Distribution Network

Directory of Open Access Journals (Sweden)

J. Jerome

2017-12-01

Full Text Available The use of automation and energy efficient equipment with electronic control would greatly improve industrial production.  These new devices are more sensitive to supply voltage deviation and the characteristics of the power system that was previously ignored are now very important. Hence the benefits of distribution automation have been widely acknowledged in recent years. This paper proposes an efficient load flow solution technique extended to find optimum location for reactive power compensation and network reconfiguration for planning and day-to-day operation of distribution networks.  This is required as a part of the distribution automation system (DAS for taking various control and operation decisions.  The method exploits the radial nature of the network and uses forward and backward propagation technique to calculate branch currents and node voltages.  The proposed method has been tested to analyze several practical distribution networks of various voltage levels and also having high R/X ratio.

Logarithmic learning for generalized classifier neural network.

Science.gov (United States)

Ozyildirim, Buse Melis; Avci, Mutlu

2014-12-01

Generalized classifier neural network is introduced as an efficient classifier among the others. Unless the initial smoothing parameter value is close to the optimal one, generalized classifier neural network suffers from convergence problem and requires quite a long time to converge. In this work, to overcome this problem, a logarithmic learning approach is proposed. The proposed method uses logarithmic cost function instead of squared error. Minimization of this cost function reduces the number of iterations used for reaching the minima. The proposed method is tested on 15 different data sets and performance of logarithmic learning generalized classifier neural network is compared with that of standard one. Thanks to operation range of radial basis function included by generalized classifier neural network, proposed logarithmic approach and its derivative has continuous values. This makes it possible to adopt the advantage of logarithmic fast convergence by the proposed learning method. Due to fast convergence ability of logarithmic cost function, training time is maximally decreased to 99.2%. In addition to decrease in training time, classification performance may also be improved till 60%. According to the test results, while the proposed method provides a solution for time requirement problem of generalized classifier neural network, it may also improve the classification accuracy. The proposed method can be considered as an efficient way for reducing the time requirement problem of generalized classifier neural network. Copyright © 2014 Elsevier Ltd. All rights reserved.

Analysis of critical operating conditions for LV distribution networks with microgrids

Science.gov (United States)

Zehir, M. A.; Batman, A.; Sonmez, M. A.; Font, A.; Tsiamitros, D.; Stimoniaris, D.; Kollatou, T.; Bagriyanik, M.; Ozdemir, A.; Dialynas, E.

2016-11-01

Increase in the penetration of Distributed Generation (DG) in distribution networks, raises the risk of voltage limit violations while contributing to line losses. Especially in low voltage (LV) distribution networks (secondary distribution networks), impacts of active power flows on the bus voltages and on the network losses are more dominant. As network operators must meet regulatory limitations, they have to take into account the most critical operating conditions in their systems. In this study, it is aimed to present the impact of the worst operation cases of LV distribution networks comprising microgrids. Simulation studies are performed on a field data-based virtual test-bed. The simulations are repeated for several cases consisting different microgrid points of connection with different network loading and microgrid supply/demand conditions.

Distributional Language Learning: Mechanisms and Models of ategory Formation.

Science.gov (United States)

Aslin, Richard N; Newport, Elissa L

2014-09-01

In the past 15 years, a substantial body of evidence has confirmed that a powerful distributional learning mechanism is present in infants, children, adults and (at least to some degree) in nonhuman animals as well. The present article briefly reviews this literature and then examines some of the fundamental questions that must be addressed for any distributional learning mechanism to operate effectively within the linguistic domain. In particular, how does a naive learner determine the number of categories that are present in a corpus of linguistic input and what distributional cues enable the learner to assign individual lexical items to those categories? Contrary to the hypothesis that distributional learning and category (or rule) learning are separate mechanisms, the present article argues that these two seemingly different processes---acquiring specific structure from linguistic input and generalizing beyond that input to novel exemplars---actually represent a single mechanism. Evidence in support of this single-mechanism hypothesis comes from a series of artificial grammar-learning studies that not only demonstrate that adults can learn grammatical categories from distributional information alone, but that the specific patterning of distributional information among attested utterances in the learning corpus enables adults to generalize to novel utterances or to restrict generalization when unattested utterances are consistently absent from the learning corpus. Finally, a computational model of distributional learning that accounts for the presence or absence of generalization is reviewed and the implications of this model for linguistic-category learning are summarized.

Towards a Social Networks Model for Online Learning & Performance

Science.gov (United States)

Chung, Kon Shing Kenneth; Paredes, Walter Christian

2015-01-01

In this study, we develop a theoretical model to investigate the association between social network properties, "content richness" (CR) in academic learning discourse, and performance. CR is the extent to which one contributes content that is meaningful, insightful and constructive to aid learning and by social network properties we…

Evaluating Maximum Wind Energy Exploitation in Active Distribution Networks

DEFF Research Database (Denmark)

Siano, Pierluigi; Chen, Peiyuan; Chen, Zhe

2010-01-01

The increased spreading of distributed and renewable generation requires moving towards active management of distribution networks. In this paper, in order to evaluate maximum wind energy exploitation in active distribution networks, a method based on a multi-period optimal power flow (OPF......) analysis is proposed. Active network management schemes such as coordinated voltage control, energy curtailment and power factor control are integrated in the method in order to investigate their impacts on the maximization of wind energy exploitation. Some case studies, using real data from a Danish...... distribution system, confirmed the effectiveness of the proposed method in evaluating the optimal applications of active management schemes to increase wind energy harvesting without costly network reinforcement for the connection of wind generation....

Improved Quantum Artificial Fish Algorithm Application to Distributed Network Considering Distributed Generation.

Science.gov (United States)

Du, Tingsong; Hu, Yang; Ke, Xianting

2015-01-01

An improved quantum artificial fish swarm algorithm (IQAFSA) for solving distributed network programming considering distributed generation is proposed in this work. The IQAFSA based on quantum computing which has exponential acceleration for heuristic algorithm uses quantum bits to code artificial fish and quantum revolving gate, preying behavior, and following behavior and variation of quantum artificial fish to update the artificial fish for searching for optimal value. Then, we apply the proposed new algorithm, the quantum artificial fish swarm algorithm (QAFSA), the basic artificial fish swarm algorithm (BAFSA), and the global edition artificial fish swarm algorithm (GAFSA) to the simulation experiments for some typical test functions, respectively. The simulation results demonstrate that the proposed algorithm can escape from the local extremum effectively and has higher convergence speed and better accuracy. Finally, applying IQAFSA to distributed network problems and the simulation results for 33-bus radial distribution network system show that IQAFSA can get the minimum power loss after comparing with BAFSA, GAFSA, and QAFSA.

Improved Quantum Artificial Fish Algorithm Application to Distributed Network Considering Distributed Generation

Directory of Open Access Journals (Sweden)

Tingsong Du

2015-01-01

Full Text Available An improved quantum artificial fish swarm algorithm (IQAFSA for solving distributed network programming considering distributed generation is proposed in this work. The IQAFSA based on quantum computing which has exponential acceleration for heuristic algorithm uses quantum bits to code artificial fish and quantum revolving gate, preying behavior, and following behavior and variation of quantum artificial fish to update the artificial fish for searching for optimal value. Then, we apply the proposed new algorithm, the quantum artificial fish swarm algorithm (QAFSA, the basic artificial fish swarm algorithm (BAFSA, and the global edition artificial fish swarm algorithm (GAFSA to the simulation experiments for some typical test functions, respectively. The simulation results demonstrate that the proposed algorithm can escape from the local extremum effectively and has higher convergence speed and better accuracy. Finally, applying IQAFSA to distributed network problems and the simulation results for 33-bus radial distribution network system show that IQAFSA can get the minimum power loss after comparing with BAFSA, GAFSA, and QAFSA.

Semantic Coherence Facilitates Distributional Learning.

Science.gov (United States)

Ouyang, Long; Boroditsky, Lera; Frank, Michael C

2017-04-01

Computational models have shown that purely statistical knowledge about words' linguistic contexts is sufficient to learn many properties of words, including syntactic and semantic category. For example, models can infer that "postman" and "mailman" are semantically similar because they have quantitatively similar patterns of association with other words (e.g., they both tend to occur with words like "deliver," "truck," "package"). In contrast to these computational results, artificial language learning experiments suggest that distributional statistics alone do not facilitate learning of linguistic categories. However, experiments in this paradigm expose participants to entirely novel words, whereas real language learners encounter input that contains some known words that are semantically organized. In three experiments, we show that (a) the presence of familiar semantic reference points facilitates distributional learning and (b) this effect crucially depends both on the presence of known words and the adherence of these known words to some semantic organization. Copyright © 2016 Cognitive Science Society, Inc.

Distributed learning: Developing a predictive model based on data from multiple hospitals without data leaving the hospital - A real life proof of concept.

Science.gov (United States)

Jochems, Arthur; Deist, Timo M; van Soest, Johan; Eble, Michael; Bulens, Paul; Coucke, Philippe; Dries, Wim; Lambin, Philippe; Dekker, Andre

2016-12-01

One of the major hurdles in enabling personalized medicine is obtaining sufficient patient data to feed into predictive models. Combining data originating from multiple hospitals is difficult because of ethical, legal, political, and administrative barriers associated with data sharing. In order to avoid these issues, a distributed learning approach can be used. Distributed learning is defined as learning from data without the data leaving the hospital. Clinical data from 287 lung cancer patients, treated with curative intent with chemoradiation (CRT) or radiotherapy (RT) alone were collected from and stored in 5 different medical institutes (123 patients at MAASTRO (Netherlands, Dutch), 24 at Jessa (Belgium, Dutch), 34 at Liege (Belgium, Dutch and French), 48 at Aachen (Germany, German) and 58 at Eindhoven (Netherlands, Dutch)). A Bayesian network model is adapted for distributed learning (watch the animation: http://youtu.be/nQpqMIuHyOk). The model predicts dyspnea, which is a common side effect after radiotherapy treatment of lung cancer. We show that it is possible to use the distributed learning approach to train a Bayesian network model on patient data originating from multiple hospitals without these data leaving the individual hospital. The AUC of the model is 0.61 (95%CI, 0.51-0.70) on a 5-fold cross-validation and ranges from 0.59 to 0.71 on external validation sets. Distributed learning can allow the learning of predictive models on data originating from multiple hospitals while avoiding many of the data sharing barriers. Furthermore, the distributed learning approach can be used to extract and employ knowledge from routine patient data from multiple hospitals while being compliant to the various national and European privacy laws. Copyright © 2016 The Author(s). Published by Elsevier Ireland Ltd.. All rights reserved.

Networked Learning and Network Science: Potential Applications to Health Professionals' Continuing Education and Development.

Science.gov (United States)

Margolis, Alvaro; Parboosingh, John

2015-01-01

Prior interpersonal relationships and interactivity among members of professional associations may impact the learning process in continuing medical education (CME). On the other hand, CME programs that encourage interactivity between participants may impact structures and behaviors in these professional associations. With the advent of information and communication technologies, new communication spaces have emerged that have the potential to enhance networked learning in national and international professional associations and increase the effectiveness of CME for health professionals. In this article, network science, based on the application of network theory and other theories, is proposed as an approach to better understand the contribution networking and interactivity between health professionals in professional communities make to their learning and adoption of new practices over time. © 2015 The Alliance for Continuing Education in the Health Professions, the Society for Academic Continuing Medical Education, and the Council on Continuing Medical Education, Association for Hospital Medical Education.

Research on Harmonic Characteristics Influence for Distribution Network with Renewable Energy

Directory of Open Access Journals (Sweden)

Huang Wei

2016-01-01

Full Text Available In order to study the influence on harmonic characteristics of distribution network with renewable energy, a simplified model of distribution network is established to analyse theory while considering the influence of cable on the system capacitive current. Establishing an actual distribution network model by Digsilent to research the harmonic characteristics impact when photovoltaic power with PV incorporated the distribution network in a variety of different access , while using constant current source model as harmonic source model which often been used in engineering practices. The simulation results show that: optimizing the access location and dispersion of PV can decrease the waveform distortion levels in distribution network and a certain number of high-order harmonic will magnify by a specific grid structure, deteriorating the distribution network power quality.

Network anomaly detection a machine learning perspective

CERN Document Server

Bhattacharyya, Dhruba Kumar

2013-01-01

With the rapid rise in the ubiquity and sophistication of Internet technology and the accompanying growth in the number of network attacks, network intrusion detection has become increasingly important. Anomaly-based network intrusion detection refers to finding exceptional or nonconforming patterns in network traffic data compared to normal behavior. Finding these anomalies has extensive applications in areas such as cyber security, credit card and insurance fraud detection, and military surveillance for enemy activities. Network Anomaly Detection: A Machine Learning Perspective presents mach

SuperSpike: Supervised Learning in Multilayer Spiking Neural Networks.

Science.gov (United States)

Zenke, Friedemann; Ganguli, Surya

2018-04-13

A vast majority of computation in the brain is performed by spiking neural networks. Despite the ubiquity of such spiking, we currently lack an understanding of how biological spiking neural circuits learn and compute in vivo, as well as how we can instantiate such capabilities in artificial spiking circuits in silico. Here we revisit the problem of supervised learning in temporally coding multilayer spiking neural networks. First, by using a surrogate gradient approach, we derive SuperSpike, a nonlinear voltage-based three-factor learning rule capable of training multilayer networks of deterministic integrate-and-fire neurons to perform nonlinear computations on spatiotemporal spike patterns. Second, inspired by recent results on feedback alignment, we compare the performance of our learning rule under different credit assignment strategies for propagating output errors to hidden units. Specifically, we test uniform, symmetric, and random feedback, finding that simpler tasks can be solved with any type of feedback, while more complex tasks require symmetric feedback. In summary, our results open the door to obtaining a better scientific understanding of learning and computation in spiking neural networks by advancing our ability to train them to solve nonlinear problems involving transformations between different spatiotemporal spike time patterns.

Social Networking Sites and Language Learning

Science.gov (United States)

Brick, Billy

2011-01-01

This article examines a study of seven learners who logged their experiences on the language leaning social networking site Livemocha over a period of three months. The features of the site are described and the likelihood of their future success is considered. The learners were introduced to the Social Networking Site (SNS) and asked to learn a…

Recruitment and Consolidation of Cell Assemblies for Words by Way of Hebbian Learning and Competition in a Multi-Layer Neural Network.

Science.gov (United States)

Garagnani, Max; Wennekers, Thomas; Pulvermüller, Friedemann

2009-06-01

Current cognitive theories postulate either localist representations of knowledge or fully overlapping, distributed ones. We use a connectionist model that closely replicates known anatomical properties of the cerebral cortex and neurophysiological principles to show that Hebbian learning in a multi-layer neural network leads to memory traces (cell assemblies) that are both distributed and anatomically distinct. Taking the example of word learning based on action-perception correlation, we document mechanisms underlying the emergence of these assemblies, especially (i) the recruitment of neurons and consolidation of connections defining the kernel of the assembly along with (ii) the pruning of the cell assembly's halo (consisting of very weakly connected cells). We found that, whereas a learning rule mapping covariance led to significant overlap and merging of assemblies, a neurobiologically grounded synaptic plasticity rule with fixed LTP/LTD thresholds produced minimal overlap and prevented merging, exhibiting competitive learning behaviour. Our results are discussed in light of current theories of language and memory. As simulations with neurobiologically realistic neural networks demonstrate here spontaneous emergence of lexical representations that are both cortically dispersed and anatomically distinct, both localist and distributed cognitive accounts receive partial support.

Software defined networking applications in distributed datacenters

CERN Document Server

Qi, Heng

2016-01-01

This SpringerBrief provides essential insights on the SDN application designing and deployment in distributed datacenters. In this book, three key problems are discussed: SDN application designing, SDN deployment and SDN management. This book demonstrates how to design the SDN-based request allocation application in distributed datacenters. It also presents solutions for SDN controller placement to deploy SDN in distributed datacenters. Finally, an SDN management system is proposed to guarantee the performance of datacenter networks which are covered and controlled by many heterogeneous controllers. Researchers and practitioners alike will find this book a valuable resource for further study on Software Defined Networking. .

Learning and forgetting on asymmetric, diluted neural networks

International Nuclear Information System (INIS)

Derrida, B.; Nadal, J.P.

1987-01-01

It is possible to construct diluted asymmetric models of neural networks for which the dynamics can be calculated exactly. The authors test several learning schemes, in particular, models for which the values of the synapses remain bounded and depend on the history. Our analytical results on the relative efficiencies of the various learning schemes are qualitatively similar to the corresponding ones obtained numerically on fully connected symmetric networks

A distributed lumped active all-pass network configuration.

Science.gov (United States)

Huelsman, L. P.; Raghunath, S.

1972-01-01

In this correspondence a new and interesting distributed lumped active network configuration that realizes an all-pass network function is described. A design chart for determining the values of the network elements is included.

Learning Networks: connecting people, organizations, autonomous agents and learning resources to establish the emergence of effective lifelong learning

NARCIS (Netherlands)

Koper, Rob; Sloep, Peter

2003-01-01

Koper, E.J.R., Sloep, P.B. (2002) Learning Networks connecting people, organizations, autonomous agents and learning resources to establish the emergence of effective lifelong learning. RTD Programma into Learning Technologies 2003-2008. More is different… Heerlen, Nederland: Open Universiteit

MANAGING WITHIN DISTRIBUTED INNOVATION NETWORKS

OpenAIRE

LAWRENCE DOOLEY; DAVID O'SULLIVAN

2007-01-01

Business competitiveness and sustainability depends on the effective management of innovation. To be effective, innovation needs to take place within every area of an organisation and by association within organisational networks that include key suppliers, customers and other strategic partners. Distributed innovation management is the process of managing innovation both within and across networks of organisations that have come together to co-design, co-produce and co-service the needs of c...

Disseminating Innovations in Teaching Value-Based Care Through an Online Learning Network.

Science.gov (United States)

Gupta, Reshma; Shah, Neel T; Moriates, Christopher; Wallingford, September; Arora, Vineet M

2017-08-01

A national imperative to provide value-based care requires new strategies to teach clinicians about high-value care. We developed a virtual online learning network aimed at disseminating emerging strategies in teaching value-based care. The online Teaching Value in Health Care Learning Network includes monthly webinars that feature selected innovators, online discussion forums, and a repository for sharing tools. The learning network comprises clinician-educators and health system leaders across North America. We conducted a cross-sectional online survey of all webinar presenters and the active members of the network, and we assessed program feasibility. Six months after the program launched, there were 277 learning community members in 22 US states. Of the 74 active members, 50 (68%) completed the evaluation. Active members represented independently practicing physicians and trainees in 7 specialties, nurses, educators, and health system leaders. Nearly all speakers reported that the learning network provided them with a unique opportunity to connect with a different audience and achieve greater recognition for their work. Of the members who were active in the learning network, most reported that strategies gleaned from the network were helpful, and some adopted or adapted these innovations at their home institutions. One year after the program launched, the learning network had grown to 364 total members. The learning network helped participants share and implement innovations to promote high-value care. The model can help disseminate innovations in emerging areas of health care transformation, and is sustainable without ongoing support after a period of start-up funding.

A Contextualised Multi-Platform Framework to Support Blended Learning Scenarios in Learning Networks

NARCIS (Netherlands)

De Jong, Tim; Fuertes, Alba; Schmeits, Tally; Specht, Marcus; Koper, Rob

2008-01-01

De Jong, T., Fuertes, A., Schmeits, T., Specht, M., & Koper, R. (2009). A Contextualised Multi-Platform Framework to Support Blended Learning Scenarios in Learning Networks. In D. Goh (Ed.), Multiplatform E-Learning Systems and Technologies: Mobile Devices for Ubiquitous ICT-Based Education (pp.

Novel Machine Learning-Based Techniques for Efficient Resource Allocation in Next Generation Wireless Networks

KAUST Repository

AlQuerm, Ismail A.

2018-02-21

resources management in diverse wireless networks. The core operation of the proposed architecture is decision-making for resource allocation and system’s parameters adaptation. Thus, we develop the decision-making mechanism using different artificial intelligence techniques, evaluate the performance achieved and determine the tradeoff of using one technique over the others. The techniques include decision-trees, genetic algorithm, hybrid engine based on decision-trees and case based reasoning, and supervised engine with machine learning contribution to determine the ultimate technique that suits the current environment conditions. All the proposed techniques are evaluated using testbed implementation in different topologies and scenarios. LTE networks have been considered as a potential environment for demonstration of our proposed cognitive based resource allocation techniques as they lack of radio resource management. In addition, we explore the use of enhanced online learning to perform efficient resource allocation in the upcoming 5G networks to maximize energy efficiency and data rate. The considered 5G structures are heterogeneous multi-tier networks with device to device communication and heterogeneous cloud radio access networks. We propose power and resource blocks allocation schemes to maximize energy efficiency and data rate in heterogeneous 5G networks. Moreover, traffic offloading from large cells to small cells in 5G heterogeneous networks is investigated and an online learning based traffic offloading strategy is developed to enhance energy efficiency. Energy efficiency problem in heterogeneous cloud radio access networks is tackled using online learning in centralized and distributed fashions. The proposed online learning comprises improvement features that reduce the algorithms complexities and enhance the performance achieved.

Feedback control stabilization of critical dynamics via resource transport on multilayer networks: How glia enable learning dynamics in the brain

Science.gov (United States)

Virkar, Yogesh S.; Shew, Woodrow L.; Restrepo, Juan G.; Ott, Edward

2016-10-01

Learning and memory are acquired through long-lasting changes in synapses. In the simplest models, such synaptic potentiation typically leads to runaway excitation, but in reality there must exist processes that robustly preserve overall stability of the neural system dynamics. How is this accomplished? Various approaches to this basic question have been considered. Here we propose a particularly compelling and natural mechanism for preserving stability of learning neural systems. This mechanism is based on the global processes by which metabolic resources are distributed to the neurons by glial cells. Specifically, we introduce and study a model composed of two interacting networks: a model neural network interconnected by synapses that undergo spike-timing-dependent plasticity; and a model glial network interconnected by gap junctions that diffusively transport metabolic resources among the glia and, ultimately, to neural synapses where they are consumed. Our main result is that the biophysical constraints imposed by diffusive transport of metabolic resources through the glial network can prevent runaway growth of synaptic strength, both during ongoing activity and during learning. Our findings suggest a previously unappreciated role for glial transport of metabolites in the feedback control stabilization of neural network dynamics during learning.

Stochastic sensitivity analysis and Langevin simulation for neural network learning

International Nuclear Information System (INIS)

Koda, Masato

1997-01-01

A comprehensive theoretical framework is proposed for the learning of a class of gradient-type neural networks with an additive Gaussian white noise process. The study is based on stochastic sensitivity analysis techniques, and formal expressions are obtained for stochastic learning laws in terms of functional derivative sensitivity coefficients. The present method, based on Langevin simulation techniques, uses only the internal states of the network and ubiquitous noise to compute the learning information inherent in the stochastic correlation between noise signals and the performance functional. In particular, the method does not require the solution of adjoint equations of the back-propagation type. Thus, the present algorithm has the potential for efficiently learning network weights with significantly fewer computations. Application to an unfolded multi-layered network is described, and the results are compared with those obtained by using a back-propagation method

Reinforcement learning account of network reciprocity.

Science.gov (United States)

Ezaki, Takahiro; Masuda, Naoki

2017-01-01

Evolutionary game theory predicts that cooperation in social dilemma games is promoted when agents are connected as a network. However, when networks are fixed over time, humans do not necessarily show enhanced mutual cooperation. Here we show that reinforcement learning (specifically, the so-called Bush-Mosteller model) approximately explains the experimentally observed network reciprocity and the lack thereof in a parameter region spanned by the benefit-to-cost ratio and the node's degree. Thus, we significantly extend previously obtained numerical results.

Boltzmann learning of parameters in cellular neural networks

DEFF Research Database (Denmark)

Hansen, Lars Kai

1992-01-01

The use of Bayesian methods to design cellular neural networks for signal processing tasks and the Boltzmann machine learning rule for parameter estimation is discussed. The learning rule can be used for models with hidden units, or for completely unsupervised learning. The latter is exemplified...

A Probability-based Evolutionary Algorithm with Mutations to Learn Bayesian Networks

Directory of Open Access Journals (Sweden)

Sho Fukuda

2014-12-01

Full Text Available Bayesian networks are regarded as one of the essential tools to analyze causal relationship between events from data. To learn the structure of highly-reliable Bayesian networks from data as quickly as possible is one of the important problems that several studies have been tried to achieve. In recent years, probability-based evolutionary algorithms have been proposed as a new efficient approach to learn Bayesian networks. In this paper, we target on one of the probability-based evolutionary algorithms called PBIL (Probability-Based Incremental Learning, and propose a new mutation operator. Through performance evaluation, we found that the proposed mutation operator has a good performance in learning Bayesian networks

Solutions to operate transmission and distribution gas networks

Directory of Open Access Journals (Sweden)

Neacsu Sorin

2017-01-01

Full Text Available In order to respect the actual and future regulations, besides SCADA, there is a need for further modern operating solutions for the transmission and distribution gas network. The paper presents the newest operating principles and modern software solutions that represent a considerable help to operate the transmission and distribution gas networks.

Review of Congestion Management Methods for Distribution Networks with High Penetration of Distributed Energy Resources

DEFF Research Database (Denmark)

Huang, Shaojun; Wu, Qiuwei; Liu, Zhaoxi

2014-01-01

This paper reviews the existing congestion management methods for distribution networks with high penetration of DERs documented in the recent research literatures. The congestion management methods for distribution networks reviewed can be grouped into two categories – market methods and direct...... control methods. The market methods consist of dynamic tariff, distribution capacity market, shadow price and flexible service market. The direct control methods are comprised of network reconfiguration, reactive power control and active power control. Based on the review of the existing methods...

Optimal residential smart appliances scheduling considering distribution network constraints

Directory of Open Access Journals (Sweden)

Yu-Ree Kim

2016-01-01

Full Text Available As smart appliances (SAs are more widely adopted within distribution networks, residential consumers can contribute to electricity market operations with demand response resources and reduce their electricity bill. However, if the schedules of demand response resources are determined only by the economic electricity rate signal, the schedule can be unfeasible due to the distribution network constraints. Furthermore, it is impossible for consumers to understand the complex physical characteristics and reflect them in their everyday behaviors. This paper introduces the concept of load coordinating retailer (LCR that deals with demand responsive appliances to reduce electrical consumption for the given distribution network constraints. The LCR can play the role of both conventional retailer and aggregated demand response provider for residential customers. It determines the optimal schedules for the aggregated neighboring SAs according to their types within each distribution feeder. The optimization algorithms are developed using Mixed Integer Linear Programming, and the distribution network is solved by the Newton–Raphson AC power flow.

A Large-Scale Multi-Hop Localization Algorithm Based on Regularized Extreme Learning for Wireless Networks.

Science.gov (United States)

Zheng, Wei; Yan, Xiaoyong; Zhao, Wei; Qian, Chengshan

2017-12-20

A novel large-scale multi-hop localization algorithm based on regularized extreme learning is proposed in this paper. The large-scale multi-hop localization problem is formulated as a learning problem. Unlike other similar localization algorithms, the proposed algorithm overcomes the shortcoming of the traditional algorithms which are only applicable to an isotropic network, therefore has a strong adaptability to the complex deployment environment. The proposed algorithm is composed of three stages: data acquisition, modeling and location estimation. In data acquisition stage, the training information between nodes of the given network is collected. In modeling stage, the model among the hop-counts and the physical distances between nodes is constructed using regularized extreme learning. In location estimation stage, each node finds its specific location in a distributed manner. Theoretical analysis and several experiments show that the proposed algorithm can adapt to the different topological environments with low computational cost. Furthermore, high accuracy can be achieved by this method without setting complex parameters.

Learning theory of distributed spectral algorithms

International Nuclear Information System (INIS)

Guo, Zheng-Chu; Lin, Shao-Bo; Zhou, Ding-Xuan

2017-01-01

Spectral algorithms have been widely used and studied in learning theory and inverse problems. This paper is concerned with distributed spectral algorithms, for handling big data, based on a divide-and-conquer approach. We present a learning theory for these distributed kernel-based learning algorithms in a regression framework including nice error bounds and optimal minimax learning rates achieved by means of a novel integral operator approach and a second order decomposition of inverse operators. Our quantitative estimates are given in terms of regularity of the regression function, effective dimension of the reproducing kernel Hilbert space, and qualification of the filter function of the spectral algorithm. They do not need any eigenfunction or noise conditions and are better than the existing results even for the classical family of spectral algorithms. (paper)

Learning Errors by Radial Basis Function Neural Networks and Regularization Networks

Czech Academy of Sciences Publication Activity Database

Neruda, Roman; Vidnerová, Petra

2009-01-01

Roč. 1, č. 2 (2009), s. 49-57 ISSN 2005-4262 R&D Projects: GA MŠk(CZ) 1M0567 Institutional research plan: CEZ:AV0Z10300504 Keywords : neural network * RBF networks * regularization * learning Subject RIV: IN - Informatics, Computer Science http://www.sersc.org/journals/IJGDC/vol2_no1/5.pdf

Incentive-Based Voltage Regulation in Distribution Networks: Preprint

Energy Technology Data Exchange (ETDEWEB)

Zhou, Xinyang; Chen, Lijun; Dall' Anese, Emiliano; Baker, Kyri

2017-03-03

This paper considers distribution networks fea- turing distributed energy resources, and designs incentive-based mechanisms that allow the network operator and end-customers to pursue given operational and economic objectives, while concurrently ensuring that voltages are within prescribed limits. Two different network-customer coordination mechanisms that require different amounts of information shared between the network operator and end-customers are developed to identify a solution of a well-defined social-welfare maximization prob- lem. Notably, the signals broadcast by the network operator assume the connotation of prices/incentives that induce the end- customers to adjust the generated/consumed powers in order to avoid the violation of the voltage constraints. Stability of the proposed schemes is analytically established and numerically corroborated.

Learning State Space Dynamics in Recurrent Networks

Science.gov (United States)

Simard, Patrice Yvon

Fully recurrent (asymmetrical) networks can be used to learn temporal trajectories. The network is unfolded in time, and backpropagation is used to train the weights. The presence of recurrent connections creates internal states in the system which vary as a function of time. The resulting dynamics can provide interesting additional computing power but learning is made more difficult by the existence of internal memories. This study first exhibits the properties of recurrent networks in terms of convergence when the internal states of the system are unknown. A new energy functional is provided to change the weights of the units in order to the control the stability of the fixed points of the network's dynamics. The power of the resultant algorithm is illustrated with the simulation of a content addressable memory. Next, the more general case of time trajectories on a recurrent network is studied. An application is proposed in which trajectories are generated to draw letters as a function of an input. In another application of recurrent systems, a neural network certain temporal properties observed in human callosally sectioned brains. Finally the proposed algorithm for stabilizing dynamics around fixed points is extended to one for stabilizing dynamics around time trajectories. Its effects are illustrated on a network which generates Lisajous curves.

Flow distributions and spatial correlations in human brain capillary networks

Science.gov (United States)

Lorthois, Sylvie; Peyrounette, Myriam; Larue, Anne; Le Borgne, Tanguy

2015-11-01

The vascular system of the human brain cortex is composed of a space filling mesh-like capillary network connected upstream and downstream to branched quasi-fractal arterioles and venules. The distribution of blood flow rates in these networks may affect the efficiency of oxygen transfer processes. Here, we investigate the distribution and correlation properties of blood flow velocities from numerical simulations in large 3D human intra-cortical vascular network (10000 segments) obtained from an anatomical database. In each segment, flow is solved from a 1D non-linear model taking account of the complex rheological properties of blood flow in microcirculation to deduce blood pressure, blood flow and red blood cell volume fraction distributions throughout the network. The network structural complexity is found to impart broad and spatially correlated Lagrangian velocity distributions, leading to power law transit time distributions. The origins of this behavior (existence of velocity correlations in capillary networks, influence of the coupling with the feeding arterioles and draining veins, topological disorder, complex blood rheology) are studied by comparison with results obtained in various model capillary networks of controlled disorder. ERC BrainMicroFlow GA615102, ERC ReactiveFronts GA648377.

A distributed database view of network tracking systems

Science.gov (United States)

Yosinski, Jason; Paffenroth, Randy

2008-04-01

In distributed tracking systems, multiple non-collocated trackers cooperate to fuse local sensor data into a global track picture. Generating this global track picture at a central location is fairly straightforward, but the single point of failure and excessive bandwidth requirements introduced by centralized processing motivate the development of decentralized methods. In many decentralized tracking systems, trackers communicate with their peers via a lossy, bandwidth-limited network in which dropped, delayed, and out of order packets are typical. Oftentimes the decentralized tracking problem is viewed as a local tracking problem with a networking twist; we believe this view can underestimate the network complexities to be overcome. Indeed, a subsequent 'oversight' layer is often introduced to detect and handle track inconsistencies arising from a lack of robustness to network conditions. We instead pose the decentralized tracking problem as a distributed database problem, enabling us to draw inspiration from the vast extant literature on distributed databases. Using the two-phase commit algorithm, a well known technique for resolving transactions across a lossy network, we describe several ways in which one may build a distributed multiple hypothesis tracking system from the ground up to be robust to typical network intricacies. We pay particular attention to the dissimilar challenges presented by network track initiation vs. maintenance and suggest a hybrid system that balances speed and robustness by utilizing two-phase commit for only track initiation transactions. Finally, we present simulation results contrasting the performance of such a system with that of more traditional decentralized tracking implementations.

Spiking neural networks for handwritten digit recognition-Supervised learning and network optimization.

Science.gov (United States)

Kulkarni, Shruti R; Rajendran, Bipin

2018-07-01

We demonstrate supervised learning in Spiking Neural Networks (SNNs) for the problem of handwritten digit recognition using the spike triggered Normalized Approximate Descent (NormAD) algorithm. Our network that employs neurons operating at sparse biological spike rates below 300Hz achieves a classification accuracy of 98.17% on the MNIST test database with four times fewer parameters compared to the state-of-the-art. We present several insights from extensive numerical experiments regarding optimization of learning parameters and network configuration to improve its accuracy. We also describe a number of strategies to optimize the SNN for implementation in memory and energy constrained hardware, including approximations in computing the neuronal dynamics and reduced precision in storing the synaptic weights. Experiments reveal that even with 3-bit synaptic weights, the classification accuracy of the designed SNN does not degrade beyond 1% as compared to the floating-point baseline. Further, the proposed SNN, which is trained based on the precise spike timing information outperforms an equivalent non-spiking artificial neural network (ANN) trained using back propagation, especially at low bit precision. Thus, our study shows the potential for realizing efficient neuromorphic systems that use spike based information encoding and learning for real-world applications. Copyright © 2018 Elsevier Ltd. All rights reserved.

Minimizing communication cost among distributed controllers in software defined networks

Science.gov (United States)

Arlimatti, Shivaleela; Elbreiki, Walid; Hassan, Suhaidi; Habbal, Adib; Elshaikh, Mohamed

2016-08-01

Software Defined Networking (SDN) is a new paradigm to increase the flexibility of today's network by promising for a programmable network. The fundamental idea behind this new architecture is to simplify network complexity by decoupling control plane and data plane of the network devices, and by making the control plane centralized. Recently controllers have distributed to solve the problem of single point of failure, and to increase scalability and flexibility during workload distribution. Even though, controllers are flexible and scalable to accommodate more number of network switches, yet the problem of intercommunication cost between distributed controllers is still challenging issue in the Software Defined Network environment. This paper, aims to fill the gap by proposing a new mechanism, which minimizes intercommunication cost with graph partitioning algorithm, an NP hard problem. The methodology proposed in this paper is, swapping of network elements between controller domains to minimize communication cost by calculating communication gain. The swapping of elements minimizes inter and intra communication cost among network domains. We validate our work with the OMNeT++ simulation environment tool. Simulation results show that the proposed mechanism minimizes the inter domain communication cost among controllers compared to traditional distributed controllers.

Software-Enabled Distributed Network Governance: The PopMedNet Experience.

Science.gov (United States)

Davies, Melanie; Erickson, Kyle; Wyner, Zachary; Malenfant, Jessica; Rosen, Rob; Brown, Jeffrey

2016-01-01

The expanded availability of electronic health information has led to increased interest in distributed health data research networks. The distributed research network model leaves data with and under the control of the data holder. Data holders, network coordinating centers, and researchers have distinct needs and challenges within this model. The concerns of network stakeholders are addressed in the design and governance models of the PopMedNet software platform. PopMedNet features include distributed querying, customizable workflows, and auditing and search capabilities. Its flexible role-based access control system enables the enforcement of varying governance policies. Four case studies describe how PopMedNet is used to enforce network governance models. Trust is an essential component of a distributed research network and must be built before data partners may be willing to participate further. The complexity of the PopMedNet system must be managed as networks grow and new data, analytic methods, and querying approaches are developed. The PopMedNet software platform supports a variety of network structures, governance models, and research activities through customizable features designed to meet the needs of network stakeholders.

Congestion management in Smart Distribution Network

NARCIS (Netherlands)

Haque, A.N.M.M.; Nguyen, P.H.; Kling, W.L.; Bliek, F.W.

2014-01-01

The accelerating use of Distributed Energy Resources (DERs) and new forms of loads connected in the Medium Voltage (MV) and Low Voltage (LV) networks are posing a great challenge for the Distribution System Operators (DSOs) in the near future. The bidirectional and uncertain flow of power may result

Energy flow models for the estimation of technical losses in distribution network

International Nuclear Information System (INIS)

Au, Mau Teng; Tan, Chin Hooi

2013-01-01

This paper presents energy flow models developed to estimate technical losses in distribution network. Energy flow models applied in this paper is based on input energy and peak demand of distribution network, feeder length and peak demand, transformer loading capacity, and load factor. Two case studies, an urban distribution network and a rural distribution network are used to illustrate application of the energy flow models. Results on technical losses obtained for the two distribution networks are consistent and comparable to network of similar types and characteristics. Hence, the energy flow models are suitable for practical application.

An improved algorithm for connectivity analysis of distribution networks

International Nuclear Information System (INIS)

Kansal, M.L.; Devi, Sunita

2007-01-01

In the present paper, an efficient algorithm for connectivity analysis of moderately sized distribution networks has been suggested. Algorithm is based on generation of all possible minimal system cutsets. The algorithm is efficient as it identifies only the necessary and sufficient conditions of system failure conditions in n-out-of-n type of distribution networks. The proposed algorithm is demonstrated with the help of saturated and unsaturated distribution networks. The computational efficiency of the algorithm is justified by comparing the computational efforts with the previously suggested appended spanning tree (AST) algorithm. The proposed technique has the added advantage as it can be utilized for generation of system inequalities which is useful in reliability estimation of capacitated networks

Directed networks' different link formation mechanisms causing degree distribution distinction

Science.gov (United States)

Behfar, Stefan Kambiz; Turkina, Ekaterina; Cohendet, Patrick; Burger-Helmchen, Thierry

2016-11-01

Within undirected networks, scientists have shown much interest in presenting power-law features. For instance, Barabási and Albert (1999) claimed that a common property of many large networks is that vertex connectivity follows scale-free power-law distribution, and in another study Barabási et al. (2002) showed power law evolution in the social network of scientific collaboration. At the same time, Jiang et al. (2011) discussed deviation from power-law distribution; others indicated that size effect (Bagrow et al., 2008), information filtering mechanism (Mossa et al., 2002), and birth and death process (Shi et al., 2005) could account for this deviation. Within directed networks, many authors have considered that outlinks follow a similar mechanism of creation as inlinks' (Faloutsos et al., 1999; Krapivsky et al., 2001; Tanimoto, 2009) with link creation rate being the linear function of node degree, resulting in a power-law shape for both indegree and outdegree distribution. Some other authors have made an assumption that directed networks, such as scientific collaboration or citation, behave as undirected, resulting in a power-law degree distribution accordingly (Barabási et al., 2002). At the same time, we claim (1) Outlinks feature different degree distributions than inlinks; where different link formation mechanisms cause the distribution distinctions, (2) in/outdegree distribution distinction holds for different levels of system decomposition; therefore this distribution distinction is a property of directed networks. First, we emphasize in/outlink formation mechanisms as causal factors for distinction between indegree and outdegree distributions (where this distinction has already been noticed in Barker et al. (2010) and Baxter et al. (2006)) within a sample network of OSS projects as well as Java software corpus as a network. Second, we analyze whether this distribution distinction holds for different levels of system decomposition: open

Distributed Collaborative Learning Communities Enabled by Information Communication Technology

NARCIS (Netherlands)

H.L. Alvarez (Heidi Lee)

2006-01-01

textabstractHow and why can Information Communication Technology (ICT) contribute to enhancing learning in distributed Collaborative Learning Communities (CLCs)? Drawing from relevant theories concerned with phenomenon of ICT enabled distributed collaborative learning, this book identifies gaps in

Problems in the Deployment of Learning Networks In Small Organizations

NARCIS (Netherlands)

Shankle, Dean E.; Shankle, Jeremy P.

2006-01-01

Please, cite this publication as: Shankle, D.E., & Shankle, J.P. (2006). Problems in the Deployment of Learning Networks In Small Organizations. Proceedings of International Workshop in Learning Networks for Lifelong Competence Development, TENCompetence Conference. March 30th-31st, Sofia, Bulgaria:

Parameter diagnostics of phases and phase transition learning by neural networks

Science.gov (United States)

Suchsland, Philippe; Wessel, Stefan

2018-05-01

We present an analysis of neural network-based machine learning schemes for phases and phase transitions in theoretical condensed matter research, focusing on neural networks with a single hidden layer. Such shallow neural networks were previously found to be efficient in classifying phases and locating phase transitions of various basic model systems. In order to rationalize the emergence of the classification process and for identifying any underlying physical quantities, it is feasible to examine the weight matrices and the convolutional filter kernels that result from the learning process of such shallow networks. Furthermore, we demonstrate how the learning-by-confusing scheme can be used, in combination with a simple threshold-value classification method, to diagnose the learning parameters of neural networks. In particular, we study the classification process of both fully-connected and convolutional neural networks for the two-dimensional Ising model with extended domain wall configurations included in the low-temperature regime. Moreover, we consider the two-dimensional XY model and contrast the performance of the learning-by-confusing scheme and convolutional neural networks trained on bare spin configurations to the case of preprocessed samples with respect to vortex configurations. We discuss these findings in relation to similar recent investigations and possible further applications.

Coordinated Voltage Control of Active Distribution Network

Directory of Open Access Journals (Sweden)

Xie Jiang

2016-01-01

Full Text Available This paper presents a centralized coordinated voltage control method for active distribution network to solve off-limit problem of voltage after incorporation of distributed generation (DG. The proposed method consists of two parts, it coordinated primal-dual interior point method-based voltage regulation schemes of DG reactive powers and capacitors with centralized on-load tap changer (OLTC controlling method which utilizes system’s maximum and minimum voltages, to improve the qualified rate of voltage and reduce the operation numbers of OLTC. The proposed coordination has considered the cost of capacitors. The method is tested using a radial edited IEEE-33 nodes distribution network which is modelled using MATLAB.

Reinforcement learning account of network reciprocity.

Directory of Open Access Journals (Sweden)

Takahiro Ezaki

Full Text Available Evolutionary game theory predicts that cooperation in social dilemma games is promoted when agents are connected as a network. However, when networks are fixed over time, humans do not necessarily show enhanced mutual cooperation. Here we show that reinforcement learning (specifically, the so-called Bush-Mosteller model approximately explains the experimentally observed network reciprocity and the lack thereof in a parameter region spanned by the benefit-to-cost ratio and the node's degree. Thus, we significantly extend previously obtained numerical results.

Wireless sensor networks distributed consensus estimation

CERN Document Server

Chen, Cailian; Guan, Xinping

2014-01-01

This SpringerBrief evaluates the cooperative effort of sensor nodes to accomplish high-level tasks with sensing, data processing and communication. The metrics of network-wide convergence, unbiasedness, consistency and optimality are discussed through network topology, distributed estimation algorithms and consensus strategy. Systematic analysis reveals that proper deployment of sensor nodes and a small number of low-cost relays (without sensing function) can speed up the information fusion and thus improve the estimation capability of wireless sensor networks (WSNs). This brief also investiga

Degree and wealth distribution in a network induced by wealth

Science.gov (United States)

Lee, Gyemin; Kim, Gwang Il

2007-09-01

A network induced by wealth is a social network model in which wealth induces individuals to participate as nodes, and every node in the network produces and accumulates wealth utilizing its links. More specifically, at every time step a new node is added to the network, and a link is created between one of the existing nodes and the new node. Innate wealth-producing ability is randomly assigned to every new node, and the node to be connected to the new node is chosen randomly, with odds proportional to the accumulated wealth of each existing node. Analyzing this network using the mean value and continuous flow approaches, we derive a relation between the conditional expectations of the degree and the accumulated wealth of each node. From this relation, we show that the degree distribution of the network induced by wealth is scale-free. We also show that the wealth distribution has a power-law tail and satisfies the 80/20 rule. We also show that, over the whole range, the cumulative wealth distribution exhibits the same topological characteristics as the wealth distributions of several networks based on the Bouchaud-Mèzard model, even though the mechanism for producing wealth is quite different in our model. Further, we show that the cumulative wealth distribution for the poor and middle class seems likely to follow by a log-normal distribution, while for the richest, the cumulative wealth distribution has a power-law behavior.

TF.Learn: TensorFlow's High-level Module for Distributed Machine Learning

OpenAIRE

Tang, Yuan

2016-01-01

TF.Learn is a high-level Python module for distributed machine learning inside TensorFlow. It provides an easy-to-use Scikit-learn style interface to simplify the process of creating, configuring, training, evaluating, and experimenting a machine learning model. TF.Learn integrates a wide range of state-of-art machine learning algorithms built on top of TensorFlow's low level APIs for small to large-scale supervised and unsupervised problems. This module focuses on bringing machine learning t...

The Relationships Between Policy, Boundaries and Research in Networked Learning

DEFF Research Database (Denmark)

Ryberg, Thomas; Sinclair, Christine

2016-01-01

the books that include a selection of reworked and peer-reviewed papers from the conference. The 2014 Networked Learning Conference which was held in Edinburgh was characterised by animated dialogue on emergent influences affecting networked teaching and learning building on work established in earlier...

The Impacts of Network Centrality and Self-Regulation on an E-Learning Environment with the Support of Social Network Awareness

Science.gov (United States)

Lin, Jian-Wei; Huang, Hsieh-Hong; Chuang, Yuh-Shy

2015-01-01

An e-learning environment that supports social network awareness (SNA) is a highly effective means of increasing peer interaction and assisting student learning by raising awareness of social and learning contexts of peers. Network centrality profoundly impacts student learning in an SNA-related e-learning environment. Additionally,…

Continuous Online Sequence Learning with an Unsupervised Neural Network Model.

Science.gov (United States)

Cui, Yuwei; Ahmad, Subutar; Hawkins, Jeff

2016-09-14

The ability to recognize and predict temporal sequences of sensory inputs is vital for survival in natural environments. Based on many known properties of cortical neurons, hierarchical temporal memory (HTM) sequence memory recently has been proposed as a theoretical framework for sequence learning in the cortex. In this letter, we analyze properties of HTM sequence memory and apply it to sequence learning and prediction problems with streaming data. We show the model is able to continuously learn a large number of variableorder temporal sequences using an unsupervised Hebbian-like learning rule. The sparse temporal codes formed by the model can robustly handle branching temporal sequences by maintaining multiple predictions until there is sufficient disambiguating evidence. We compare the HTM sequence memory with other sequence learning algorithms, including statistical methods: autoregressive integrated moving average; feedforward neural networks-time delay neural network and online sequential extreme learning machine; and recurrent neural networks-long short-term memory and echo-state networks on sequence prediction problems with both artificial and real-world data. The HTM model achieves comparable accuracy to other state-of-the-art algorithms. The model also exhibits properties that are critical for sequence learning, including continuous online learning, the ability to handle multiple predictions and branching sequences with high-order statistics, robustness to sensor noise and fault tolerance, and good performance without task-specific hyperparameter tuning. Therefore, the HTM sequence memory not only advances our understanding of how the brain may solve the sequence learning problem but is also applicable to real-world sequence learning problems from continuous data streams.

Islanded operation of distribution networks

Energy Technology Data Exchange (ETDEWEB)

NONE

2005-07-01

This report summarises the results of a study assessing the benefits and risks to distribution network of generator islanding and examining the technical, commercial and regulatory changes required to facilitate the operation of islanding. The background to the study is traced, and details are given of a literature review, the technical criteria for operating sections of the network in islanding mode, and the impact of islanding on trading. Case studies and a detailed implementation plan, data acquisition, and commercial incentives are discussed.

Islanded operation of distribution networks

International Nuclear Information System (INIS)

2005-01-01

This report summarises the results of a study assessing the benefits and risks to distribution network of generator islanding and examining the technical, commercial and regulatory changes required to facilitate the operation of islanding. The background to the study is traced, and details are given of a literature review, the technical criteria for operating sections of the network in islanding mode, and the impact of islanding on trading. Case studies and a detailed implementation plan, data acquisition, and commercial incentives are discussed

The TENCompetence Infrastructure: A Learning Network Implementation

Science.gov (United States)

Vogten, Hubert; Martens, Harrie; Lemmers, Ruud

The TENCompetence project developed a first release of a Learning Network infrastructure to support individuals, groups and organisations in professional competence development. This infrastructure Learning Network infrastructure was released as open source to the community thereby allowing users and organisations to use and contribute to this development as they see fit. The infrastructure consists of client applications providing the user experience and server components that provide the services to these clients. These services implement the domain model (Koper 2006) by provisioning the entities of the domain model (see also Sect. 18.4) and henceforth will be referenced as domain entity services.

Optimal power flow for distribution networks with distributed generation

Directory of Open Access Journals (Sweden)

Radosavljević Jordan

2015-01-01

Full Text Available This paper presents a genetic algorithm (GA based approach for the solution of the optimal power flow (OPF in distribution networks with distributed generation (DG units, including fuel cells, micro turbines, diesel generators, photovoltaic systems and wind turbines. The OPF is formulated as a nonlinear multi-objective optimization problem with equality and inequality constraints. Due to the stochastic nature of energy produced from renewable sources, i.e. wind turbines and photovoltaic systems, as well as load uncertainties, a probabilisticalgorithm is introduced in the OPF analysis. The Weibull and normal distributions are employed to model the input random variables, namely the wind speed, solar irradiance and load power. The 2m+1 point estimate method and the Gram Charlier expansion theory are used to obtain the statistical moments and the probability density functions (PDFs of the OPF results. The proposed approach is examined and tested on a modified IEEE 34 node test feeder with integrated five different DG units. The obtained results prove the efficiency of the proposed approach to solve both deterministic and probabilistic OPF problems for different forms of the multi-objective function. As such, it can serve as a useful decision-making supporting tool for distribution network operators. [Projekat Ministarstva nauke Republike Srbije, br. TR33046

Small Distributed Renewable Energy Generation for Low Voltage Distribution Networks

Directory of Open Access Journals (Sweden)

Chindris M.

2016-08-01

Full Text Available Driven by the existing energy policies, the use of renewable energy has increased considerably all over the world in order to respond to the increasing energy consumption and to reduce the environmental impact of the electricity generation. Although most policy makers and companies are focusing on large applications, the use of cheap small generation units, based on local renewable resources, has become increasingly attractive for the general public, small farms and remote communities. The paper presents several results of a research project aiming to identify the power quality issues and the impact of RES based distributed generation (DG or other non-linear loads on low voltage (LV distribution networks in Romania; the final goal is to develop a Universal Power Quality Conditioner (UPQC able to diminish the existing disturbances. Basically, the work analyses the existing DG technologies and identifies possible solutions for their integration in Romania; taking into account the existent state of the art, the attention was paid on small systems, using wind and solar energy, and on possibility to integrate them into suburban and rural LV distribution networks. The presence of DG units at distribution voltage level means the transition from traditional passive to active distribution networks. In general, the relatively low penetration levels of DG does not produce problems; however, the nowadays massive increase of local power generation have led to new integration challenges in order to ensure the reliability and quality of the power supply. Power quality issues are identified and their assessment is the key element in the design of measures aiming to diminish all existing disturbances.

Distributed medium access control in wireless networks

CERN Document Server

Wang, Ping

2013-01-01

This brief investigates distributed medium access control (MAC) with QoS provisioning for both single- and multi-hop wireless networks including wireless local area networks (WLANs), wireless ad hoc networks, and wireless mesh networks. For WLANs, an efficient MAC scheme and a call admission control algorithm are presented to provide guaranteed QoS for voice traffic and, at the same time, increase the voice capacity significantly compared with the current WLAN standard. In addition, a novel token-based scheduling scheme is proposed to provide great flexibility and facility to the network servi

A theoretical design for learning model addressing the networked society

DEFF Research Database (Denmark)

Levinsen, Karin; Nielsen, Janni; Sørensen, Birgitte Holm

2010-01-01

The transition from the industrial to the networked society produces contradictions that challenges the educational system and force it to adapt to new conditions. In a Danish virtual Master in Information and Communication Technologies and Learning (MIL) these contradictions appear as a field of...... which enables students to develop Networked Society competencies and maintain progression in the learning process also during the online periods. Additionally we suggest that our model contributes to the innovation of a networked society's design for learning....... is continuously decreasing. We teach for deep learning but are confronted by students' cost-benefit strategies when they navigate through the study programme under time pressure. To meet these challenges a Design for Learning Model has been developed. The aim is to provide a scaffold that ensures students......' acquisition of the subject matter within a time limit and at a learning quality that support their deep learning process during a subsequent period of on-line study work. In the process of moving from theory to application the model passes through three stages: 1) Conceptual modelling; 2) Orchestration, and 3...

Packets Distributing Evolutionary Algorithm Based on PSO for Ad Hoc Network

Science.gov (United States)

Xu, Xiao-Feng

2018-03-01

Wireless communication network has such features as limited bandwidth, changeful channel and dynamic topology, etc. Ad hoc network has lots of difficulties in accessing control, bandwidth distribution, resource assign and congestion control. Therefore, a wireless packets distributing Evolutionary algorithm based on PSO (DPSO)for Ad Hoc Network is proposed. Firstly, parameters impact on performance of network are analyzed and researched to obtain network performance effective function. Secondly, the improved PSO Evolutionary Algorithm is used to solve the optimization problem from local to global in the process of network packets distributing. The simulation results show that the algorithm can ensure fairness and timeliness of network transmission, as well as improve ad hoc network resource integrated utilization efficiency.

Optimal placement of distributed generation in distribution networks ...

African Journals Online (AJOL)

This paper proposes the application of Particle Swarm Optimization (PSO) technique to find the optimal size and optimum location for the placement of DG in the radial distribution networks for active power compensation by reduction in real power losses and enhancement in voltage profile. In the first segment, the optimal ...

Comparison between extreme learning machine and wavelet neural networks in data classification

Science.gov (United States)

Yahia, Siwar; Said, Salwa; Jemai, Olfa; Zaied, Mourad; Ben Amar, Chokri

2017-03-01

Extreme learning Machine is a well known learning algorithm in the field of machine learning. It's about a feed forward neural network with a single-hidden layer. It is an extremely fast learning algorithm with good generalization performance. In this paper, we aim to compare the Extreme learning Machine with wavelet neural networks, which is a very used algorithm. We have used six benchmark data sets to evaluate each technique. These datasets Including Wisconsin Breast Cancer, Glass Identification, Ionosphere, Pima Indians Diabetes, Wine Recognition and Iris Plant. Experimental results have shown that both extreme learning machine and wavelet neural networks have reached good results.

Mobile Agents in Networking and Distributed Computing

CERN Document Server

Cao, Jiannong

2012-01-01

The book focuses on mobile agents, which are computer programs that can autonomously migrate between network sites. This text introduces the concepts and principles of mobile agents, provides an overview of mobile agent technology, and focuses on applications in networking and distributed computing.

Validating module network learning algorithms using simulated data.

Science.gov (United States)

Michoel, Tom; Maere, Steven; Bonnet, Eric; Joshi, Anagha; Saeys, Yvan; Van den Bulcke, Tim; Van Leemput, Koenraad; van Remortel, Piet; Kuiper, Martin; Marchal, Kathleen; Van de Peer, Yves

2007-05-03

In recent years, several authors have used probabilistic graphical models to learn expression modules and their regulatory programs from gene expression data. Despite the demonstrated success of such algorithms in uncovering biologically relevant regulatory relations, further developments in the area are hampered by a lack of tools to compare the performance of alternative module network learning strategies. Here, we demonstrate the use of the synthetic data generator SynTReN for the purpose of testing and comparing module network learning algorithms. We introduce a software package for learning module networks, called LeMoNe, which incorporates a novel strategy for learning regulatory programs. Novelties include the use of a bottom-up Bayesian hierarchical clustering to construct the regulatory programs, and the use of a conditional entropy measure to assign regulators to the regulation program nodes. Using SynTReN data, we test the performance of LeMoNe in a completely controlled situation and assess the effect of the methodological changes we made with respect to an existing software package, namely Genomica. Additionally, we assess the effect of various parameters, such as the size of the data set and the amount of noise, on the inference performance. Overall, application of Genomica and LeMoNe to simulated data sets gave comparable results. However, LeMoNe offers some advantages, one of them being that the learning process is considerably faster for larger data sets. Additionally, we show that the location of the regulators in the LeMoNe regulation programs and their conditional entropy may be used to prioritize regulators for functional validation, and that the combination of the bottom-up clustering strategy with the conditional entropy-based assignment of regulators improves the handling of missing or hidden regulators. We show that data simulators such as SynTReN are very well suited for the purpose of developing, testing and improving module network

Gamification of learning deactivates the Default Mode Network

Directory of Open Access Journals (Sweden)

Paul Alexander Howard-Jones

2016-01-01

Full Text Available We hypothesised that embedding educational learning in a game would improve learning outcomes, with increased engagement and recruitment of cognitive resources evidenced by increased activation of working memory network (WMN and deactivation of Default Mode Network (DMN regions. In an fMRI study, we compared activity during periods of learning in three conditions that were increasingly game-like: Study-only (when periods of learning were followed by an exemplar question together with its correct answer, Self-quizzing (when periods of learning were followed by a multiple choice question in return for a fixed number of points and Game-based (when, following each period of learning, participants competed with a peer to answer the question for escalating, uncertain rewards. DMN hubs deactivated as conditions became more game-like, alongside greater self-reported engagement and, in the Game-based condition, higher learning scores. These changes did not occur with any detectable increase in WMN activity. Additionally, ventral striatal activation was associated with responding to questions and receiving positive question feedback. Results support the significance of DMN deactivation for educational learning, and are aligned with recent evidence suggesting DMN and WMN activity may not always be anti-correlated.

Gamification of Learning Deactivates the Default Mode Network.

Science.gov (United States)

Howard-Jones, Paul A; Jay, Tim; Mason, Alice; Jones, Harvey

2015-01-01

We hypothesized that embedding educational learning in a game would improve learning outcomes, with increased engagement and recruitment of cognitive resources evidenced by increased activation of working memory network (WMN) and deactivation of default mode network (DMN) regions. In an fMRI study, we compared activity during periods of learning in three conditions that were increasingly game-like: Study-only (when periods of learning were followed by an exemplar question together with its correct answer), Self-quizzing (when periods of learning were followed by a multiple choice question in return for a fixed number of points) and Game-based (when, following each period of learning, participants competed with a peer to answer the question for escalating, uncertain rewards). DMN hubs deactivated as conditions became more game-like, alongside greater self-reported engagement and, in the Game-based condition, higher learning scores. These changes did not occur with any detectable increase in WMN activity. Additionally, ventral striatal activation was associated with responding to questions and receiving positive question feedback. Results support the significance of DMN deactivation for educational learning, and are aligned with recent evidence suggesting DMN and WMN activity may not always be anti-correlated.

Distributed Processing System for Restoration of Electric Power Distribution Network Using Two-Layered Contract Net Protocol

Science.gov (United States)

Kodama, Yu; Hamagami, Tomoki

Distributed processing system for restoration of electric power distribution network using two-layered CNP is proposed. The goal of this study is to develop the restoration system which adjusts to the future power network with distributed generators. The state of the art of this study is that the two-layered CNP is applied for the distributed computing environment in practical use. The two-layered CNP has two classes of agents, named field agent and operating agent in the network. In order to avoid conflicts of tasks, operating agent controls privilege for managers to send the task announcement messages in CNP. This technique realizes the coordination between agents which work asynchronously in parallel with others. Moreover, this study implements the distributed processing system using a de-fact standard multi-agent framework, JADE(Java Agent DEvelopment framework). This study conducts the simulation experiments of power distribution network restoration and compares the proposed system with the previous system. We confirmed the results show effectiveness of the proposed system.

Hazard tolerance of spatially distributed complex networks

International Nuclear Information System (INIS)

Dunn, Sarah; Wilkinson, Sean

2017-01-01

In this paper, we present a new methodology for quantifying the reliability of complex systems, using techniques from network graph theory. In recent years, network theory has been applied to many areas of research and has allowed us to gain insight into the behaviour of real systems that would otherwise be difficult or impossible to analyse, for example increasingly complex infrastructure systems. Although this work has made great advances in understanding complex systems, the vast majority of these studies only consider a systems topological reliability and largely ignore their spatial component. It has been shown that the omission of this spatial component can have potentially devastating consequences. In this paper, we propose a number of algorithms for generating a range of synthetic spatial networks with different topological and spatial characteristics and identify real-world networks that share the same characteristics. We assess the influence of nodal location and the spatial distribution of highly connected nodes on hazard tolerance by comparing our generic networks to benchmark networks. We discuss the relevance of these findings for real world networks and show that the combination of topological and spatial configurations renders many real world networks vulnerable to certain spatial hazards. - Highlights: • We develop a method for quantifying the reliability of real-world systems. • We assess the spatial resilience of synthetic spatially distributed networks. • We form algorithms to generate spatial scale-free and exponential networks. • We show how these “synthetic” networks are proxies for real world systems. • Conclude that many real world systems are vulnerable to spatially coherent hazard.

Smart curtailment for congestion management in LV distribution network

NARCIS (Netherlands)

Haque, A. N.M.M.; Rahman, M. T.; Nguyen, P. H.; Bliek, F. W.

2016-01-01

The rapid proliferation of distributed energy resources (DERs) leads to capacity challenges, i.e. network congestions, in the low-voltage (LV) distribution networks. A number of strategies are being widely studied to tackle the challenges with direct switching actions such as load shedding or power

Control of Networked Traffic Flow Distribution - A Stochastic Distribution System Perspective

Energy Technology Data Exchange (ETDEWEB)

Wang, Hong [Pacific Northwest National Laboratory (PNNL); Aziz, H M Abdul [ORNL; Young, Stan [National Renewable Energy Laboratory (NREL); Patil, Sagar [Pacific Northwest National Laboratory (PNNL)

2017-10-01

Networked traffic flow is a common scenario for urban transportation, where the distribution of vehicle queues either at controlled intersections or highway segments reflect the smoothness of the traffic flow in the network. At signalized intersections, the traffic queues are controlled by traffic signal control settings and effective traffic lights control would realize both smooth traffic flow and minimize fuel consumption. Funded by the Energy Efficient Mobility Systems (EEMS) program of the Vehicle Technologies Office of the US Department of Energy, we performed a preliminary investigation on the modelling and control framework in context of urban network of signalized intersections. In specific, we developed a recursive input-output traffic queueing models. The queue formation can be modeled as a stochastic process where the number of vehicles entering each intersection is a random number. Further, we proposed a preliminary B-Spline stochastic model for a one-way single-lane corridor traffic system based on theory of stochastic distribution control.. It has been shown that the developed stochastic model would provide the optimal probability density function (PDF) of the traffic queueing length as a dynamic function of the traffic signal setting parameters. Based upon such a stochastic distribution model, we have proposed a preliminary closed loop framework on stochastic distribution control for the traffic queueing system to make the traffic queueing length PDF follow a target PDF that potentially realizes the smooth traffic flow distribution in a concerned corridor.

Learning, memory, and the role of neural network architecture.

Directory of Open Access Journals (Sweden)

Ann M Hermundstad

2011-06-01

Full Text Available The performance of information processing systems, from artificial neural networks to natural neuronal ensembles, depends heavily on the underlying system architecture. In this study, we compare the performance of parallel and layered network architectures during sequential tasks that require both acquisition and retention of information, thereby identifying tradeoffs between learning and memory processes. During the task of supervised, sequential function approximation, networks produce and adapt representations of external information. Performance is evaluated by statistically analyzing the error in these representations while varying the initial network state, the structure of the external information, and the time given to learn the information. We link performance to complexity in network architecture by characterizing local error landscape curvature. We find that variations in error landscape structure give rise to tradeoffs in performance; these include the ability of the network to maximize accuracy versus minimize inaccuracy and produce specific versus generalizable representations of information. Parallel networks generate smooth error landscapes with deep, narrow minima, enabling them to find highly specific representations given sufficient time. While accurate, however, these representations are difficult to generalize. In contrast, layered networks generate rough error landscapes with a variety of local minima, allowing them to quickly find coarse representations. Although less accurate, these representations are easily adaptable. The presence of measurable performance tradeoffs in both layered and parallel networks has implications for understanding the behavior of a wide variety of natural and artificial learning systems.

A compound memristive synapse model for statistical learning through STDP in spiking neural networks

Directory of Open Access Journals (Sweden)

Johannes eBill

2014-12-01

Full Text Available Memristors have recently emerged as promising circuit elements to mimic the function of biological synapses in neuromorphic computing. The fabrication of reliable nanoscale memristive synapses, that feature continuous conductance changes based on the timing of pre- and postsynaptic spikes, has however turned out to be challenging. In this article, we propose an alternative approach, the compound memristive synapse, that circumvents this problem by the use of memristors with binary memristive states. A compound memristive synapse employs multiple bistable memristors in parallel to jointly form one synapse, thereby providing a spectrum of synaptic efficacies. We investigate the computational implications of synaptic plasticity in the compound synapse by integrating the recently observed phenomenon of stochastic filament formation into an abstract model of stochastic switching. Using this abstract model, we first show how standard pulsing schemes give rise to spike-timing dependent plasticity (STDP with a stabilizing weight dependence in compound synapses. In a next step, we study unsupervised learning with compound synapses in networks of spiking neurons organized in a winner-take-all architecture. Our theoretical analysis reveals that compound-synapse STDP implements generalized Expectation-Maximization in the spiking network. Specifically, the emergent synapse configuration represents the most salient features of the input distribution in a Mixture-of-Gaussians generative model. Furthermore, the network’s spike response to spiking input streams approximates a well-defined Bayesian posterior distribution. We show in computer simulations how such networks learn to represent high-dimensional distributions over images of handwritten digits with high fidelity even in presence of substantial device variations and under severe noise conditions. Therefore, the compound memristive synapse may provide a synaptic design principle for future neuromorphic

Controlling Voltage Levels of Distribution Network-Radial Feeder after Connecting Wind Turbines to the Network

Directory of Open Access Journals (Sweden)

Muhammad Al Badri

2017-11-01

Full Text Available Several factors in power generation and supply need to be taken into account such as shortages of energy supply, system stability, and energy quality and system disruption due to network losses, industrial development and population expansion. The addition of wind turbines to the distribution network is of great benefit in providing additional power and solving these problems, but this addition is accompanied by the problem of low voltage network. This research found optimal solutions to the problem of low voltage distribution network after connecting wind turbines. The main idea of this paper is to optimize the low-voltage problem as a result of connecting the wind turbines to the "far end" of the radial feeder for a distribution network and to obtain a voltage level within an acceptable and stable range. The problem of low voltage solved by using the load-drop compensation, capacitor-bank and “doubly-fed” induction generators. The results of this study were based on the operation of the entire design of the simulation system which would be compatible with the reality of the energy flow of all network components by using the PSCAD program. The present analysis program revealed an optimum solution for the low voltage profile of the distribution network after connecting the wind turbine.

A Network Reconfiguration Method Considering Data Uncertainties in Smart Distribution Networks

Directory of Open Access Journals (Sweden)

Ke-yan Liu

2017-05-01

Full Text Available This work presents a method for distribution network reconfiguration with the simultaneous consideration of distributed generation (DG allocation. The uncertainties of load fluctuation before the network reconfiguration are also considered. Three optimal objectives, including minimal line loss cost, minimum Expected Energy Not Supplied, and minimum switch operation cost, are investigated. The multi-objective optimization problem is further transformed into a single-objective optimization problem by utilizing weighting factors. The proposed network reconfiguration method includes two periods. The first period is to create a feasible topology network by using binary particle swarm optimization (BPSO. Then the DG allocation problem is solved by utilizing sensitivity analysis and a Harmony Search algorithm (HSA. In the meanwhile, interval analysis is applied to deal with the uncertainties of load and devices parameters. Test cases are studied using the standard IEEE 33-bus and PG&E 69-bus systems. Different scenarios and comparisons are analyzed in the experiments. The results show the applicability of the proposed method. The performance analysis of the proposed method is also investigated. The computational results indicate that the proposed network reconfiguration algorithm is feasible.

Topology determines force distributions in one-dimensional random spring networks

Science.gov (United States)

Heidemann, Knut M.; Sageman-Furnas, Andrew O.; Sharma, Abhinav; Rehfeldt, Florian; Schmidt, Christoph F.; Wardetzky, Max

2018-02-01

Networks of elastic fibers are ubiquitous in biological systems and often provide mechanical stability to cells and tissues. Fiber-reinforced materials are also common in technology. An important characteristic of such materials is their resistance to failure under load. Rupture occurs when fibers break under excessive force and when that failure propagates. Therefore, it is crucial to understand force distributions. Force distributions within such networks are typically highly inhomogeneous and are not well understood. Here we construct a simple one-dimensional model system with periodic boundary conditions by randomly placing linear springs on a circle. We consider ensembles of such networks that consist of N nodes and have an average degree of connectivity z but vary in topology. Using a graph-theoretical approach that accounts for the full topology of each network in the ensemble, we show that, surprisingly, the force distributions can be fully characterized in terms of the parameters (N ,z ) . Despite the universal properties of such (N ,z ) ensembles, our analysis further reveals that a classical mean-field approach fails to capture force distributions correctly. We demonstrate that network topology is a crucial determinant of force distributions in elastic spring networks.

Reinforcement Learning for Routing in Cognitive Radio Ad Hoc Networks

Directory of Open Access Journals (Sweden)

Hasan A. A. Al-Rawi

2014-01-01

Full Text Available Cognitive radio (CR enables unlicensed users (or secondary users, SUs to sense for and exploit underutilized licensed spectrum owned by the licensed users (or primary users, PUs. Reinforcement learning (RL is an artificial intelligence approach that enables a node to observe, learn, and make appropriate decisions on action selection in order to maximize network performance. Routing enables a source node to search for a least-cost route to its destination node. While there have been increasing efforts to enhance the traditional RL approach for routing in wireless networks, this research area remains largely unexplored in the domain of routing in CR networks. This paper applies RL in routing and investigates the effects of various features of RL (i.e., reward function, exploitation, and exploration, as well as learning rate through simulation. New approaches and recommendations are proposed to enhance the features in order to improve the network performance brought about by RL to routing. Simulation results show that the RL parameters of the reward function, exploitation, and exploration, as well as learning rate, must be well regulated, and the new approaches proposed in this paper improves SUs’ network performance without significantly jeopardizing PUs’ network performance, specifically SUs’ interference to PUs.

A Newton-type neural network learning algorithm

International Nuclear Information System (INIS)

Ivanov, V.V.; Puzynin, I.V.; Purehvdorzh, B.

1993-01-01

First- and second-order learning methods for feed-forward multilayer networks are considered. A Newton-type algorithm is proposed and compared with the common back-propagation algorithm. It is shown that the proposed algorithm provides better learning quality. Some recommendations for their usage are given. 11 refs.; 1 fig.; 1 tab

Learning in innovation networks: Some simulation experiments

Science.gov (United States)

Gilbert, Nigel; Ahrweiler, Petra; Pyka, Andreas

2007-05-01

According to the organizational learning literature, the greatest competitive advantage a firm has is its ability to learn. In this paper, a framework for modeling learning competence in firms is presented to improve the understanding of managing innovation. Firms with different knowledge stocks attempt to improve their economic performance by engaging in radical or incremental innovation activities and through partnerships and networking with other firms. In trying to vary and/or to stabilize their knowledge stocks by organizational learning, they attempt to adapt to environmental requirements while the market strongly selects on the results. The simulation experiments show the impact of different learning activities, underlining the importance of innovation and learning.

Impact of censoring on learning Bayesian networks in survival modelling.

Science.gov (United States)

Stajduhar, Ivan; Dalbelo-Basić, Bojana; Bogunović, Nikola

2009-11-01

Bayesian networks are commonly used for presenting uncertainty and covariate interactions in an easily interpretable way. Because of their efficient inference and ability to represent causal relationships, they are an excellent choice for medical decision support systems in diagnosis, treatment, and prognosis. Although good procedures for learning Bayesian networks from data have been defined, their performance in learning from censored survival data has not been widely studied. In this paper, we explore how to use these procedures to learn about possible interactions between prognostic factors and their influence on the variate of interest. We study how censoring affects the probability of learning correct Bayesian network structures. Additionally, we analyse the potential usefulness of the learnt models for predicting the time-independent probability of an event of interest. We analysed the influence of censoring with a simulation on synthetic data sampled from randomly generated Bayesian networks. We used two well-known methods for learning Bayesian networks from data: a constraint-based method and a score-based method. We compared the performance of each method under different levels of censoring to those of the naive Bayes classifier and the proportional hazards model. We did additional experiments on several datasets from real-world medical domains. The machine-learning methods treated censored cases in the data as event-free. We report and compare results for several commonly used model evaluation metrics. On average, the proportional hazards method outperformed other methods in most censoring setups. As part of the simulation study, we also analysed structural similarities of the learnt networks. Heavy censoring, as opposed to no censoring, produces up to a 5% surplus and up to 10% missing total arcs. It also produces up to 50% missing arcs that should originally be connected to the variate of interest. Presented methods for learning Bayesian networks from

Anti-correlations in the degree distribution increase stimulus detection performance in noisy spiking neural networks.

Science.gov (United States)

Martens, Marijn B; Houweling, Arthur R; E Tiesinga, Paul H

2017-02-01

Neuronal circuits in the rodent barrel cortex are characterized by stable low firing rates. However, recent experiments show that short spike trains elicited by electrical stimulation in single neurons can induce behavioral responses. Hence, the underlying neural networks provide stability against internal fluctuations in the firing rate, while simultaneously making the circuits sensitive to small external perturbations. Here we studied whether stability and sensitivity are affected by the connectivity structure in recurrently connected spiking networks. We found that anti-correlation between the number of afferent (in-degree) and efferent (out-degree) synaptic connections of neurons increases stability against pathological bursting, relative to networks where the degrees were either positively correlated or uncorrelated. In the stable network state, stimulation of a few cells could lead to a detectable change in the firing rate. To quantify the ability of networks to detect the stimulation, we used a receiver operating characteristic (ROC) analysis. For a given level of background noise, networks with anti-correlated degrees displayed the lowest false positive rates, and consequently had the highest stimulus detection performance. We propose that anti-correlation in the degree distribution may be a computational strategy employed by sensory cortices to increase the detectability of external stimuli. We show that networks with anti-correlated degrees can in principle be formed by applying learning rules comprised of a combination of spike-timing dependent plasticity, homeostatic plasticity and pruning to networks with uncorrelated degrees. To test our prediction we suggest a novel experimental method to estimate correlations in the degree distribution.

Network characteristics emerging from agent interactions in balanced distributed system.

Science.gov (United States)

Salman, Mahdi Abed; Bertelle, Cyrille; Sanlaville, Eric

2015-01-01

A distributed computing system behaves like a complex network, the interactions between nodes being essential information exchanges and migrations of jobs or services to execute. These actions are performed by software agents, which behave like the members of social networks, cooperating and competing to obtain knowledge and services. The load balancing consists in distributing the load evenly between system nodes. It aims at enhancing the resource usage. A load balancing strategy specifies scenarios for the cooperation. Its efficiency depends on quantity, accuracy, and distribution of available information. Nevertheless, the distribution of information on the nodes, together with the initial network structure, may create different logical network structures. In this paper, different load balancing strategies are tested on different network structures using a simulation. The four tested strategies are able to distribute evenly the load so that the system reaches a steady state (the mean response time of the jobs is constant), but it is shown that a given strategy indeed behaves differently according to structural parameters and information spreading. Such a study, devoted to distributed computing systems (DCSs), can be useful to understand and drive the behavior of other complex systems.

Multi-level Control Framework for Enhanced Flexibility of Active Distribution Network

DEFF Research Database (Denmark)

Nainar, Karthikeyan; Pokhrel, Basanta Raj; Pillai, Jayakrishnan Radhakrishna

2017-01-01

In this paper, the control objectives of future active distribution networks with high penetration of renewables and flexible loads are analyzed and reviewed. From a state of the art review, the important control objectives seen from the perspective of a distribution system operator are identifie......-ordination and management of the network assets at different voltage levels and geographical locations. The paper finally shows the applicability of the multi-level control architecture to some of the key challenges in the distribution system operation by relevant scenarios....... to be hosting capacity improvement, high reliable operation and cost effective network management. Based on this review and a state of the art review concerning future distribution network control methods, a multi-level control architecture is constructed for an active distribution network, which satisfies...... the selected control objectives and provides enhanced flexibility. The control architecture is supported by generation/load forecasting and distribution state estimation techniques to improve the controllability of the network. The multi-level control architecture consists of three levels of hierarchical...

Real-world experimentation of distributed DSA network algorithms

DEFF Research Database (Denmark)

Tonelli, Oscar; Berardinelli, Gilberto; Tavares, Fernando Menezes Leitão

2013-01-01

such as a dynamic propagation environment, human presence impact and terminals mobility. This chapter focuses on the practical aspects related to the real world-experimentation with distributed DSA network algorithms over a testbed network. Challenges and solutions are extensively discussed, from the testbed design......The problem of spectrum scarcity in uncoordinated and/or heterogeneous wireless networks is the key aspect driving the research in the field of flexible management of frequency resources. In particular, distributed dynamic spectrum access (DSA) algorithms enable an efficient sharing...... to the setup of experiments. A practical example of experimentation process with a DSA algorithm is also provided....

Networking for Learning The role of Networking in a Lifelong Learner's Professional Development

NARCIS (Netherlands)

Rajagopal, Kamakshi

2016-01-01

This dissertation discusses the role the social activity of networking plays in lifelong learners’ professional and personal continuous development. The main hypothesis of this thesis is that networking is a learning strategy for lifelong learners, in which conversations are key activities through

Using Epistemic Network Analysis to understand core topics as planned learning objectives

DEFF Research Database (Denmark)

Allsopp, Benjamin Brink; Dreyøe, Jonas; Misfeldt, Morten

Epistemic Network Analysis is a tool developed by the epistemic games group at the University of Wisconsin Madison for tracking the relations between concepts in students discourse (Shaffer 2017). In our current work we are applying this tool to learning objectives in teachers digital preparation....... The danish mathematics curriculum is organised in six competencies and three topics. In the recently implemented learning platforms teacher choose which of the mathematical competencies that serves as objective for a specific lesson or teaching sequence. Hence learning objectives for lessons and teaching...... sequences are defining a network of competencies, where two competencies are closely related of they often are part of the same learning objective or teaching sequence. We are currently using Epistemic Network Analysis to study these networks. In the poster we will include examples of different networks...

Learning-induced pattern classification in a chaotic neural network

International Nuclear Information System (INIS)

Li, Yang; Zhu, Ping; Xie, Xiaoping; He, Guoguang; Aihara, Kazuyuki

2012-01-01

In this Letter, we propose a Hebbian learning rule with passive forgetting (HLRPF) for use in a chaotic neural network (CNN). We then define the indices based on the Euclidean distance to investigate the evolution of the weights in a simplified way. Numerical simulations demonstrate that, under suitable external stimulations, the CNN with the proposed HLRPF acts as a fuzzy-like pattern classifier that performs much better than an ordinary CNN. The results imply relationship between learning and recognition. -- Highlights: ► Proposing a Hebbian learning rule with passive forgetting (HLRPF). ► Defining indices to investigate the evolution of the weights simply. ► The chaotic neural network with HLRPF acts as a fuzzy-like pattern classifier. ► The pattern classifier ability of the network is improved much.

A Three-Threshold Learning Rule Approaches the Maximal Capacity of Recurrent Neural Networks.

Directory of Open Access Journals (Sweden)

Alireza Alemi

2015-08-01

Full Text Available Understanding the theoretical foundations of how memories are encoded and retrieved in neural populations is a central challenge in neuroscience. A popular theoretical scenario for modeling memory function is the attractor neural network scenario, whose prototype is the Hopfield model. The model simplicity and the locality of the synaptic update rules come at the cost of a poor storage capacity, compared with the capacity achieved with perceptron learning algorithms. Here, by transforming the perceptron learning rule, we present an online learning rule for a recurrent neural network that achieves near-maximal storage capacity without an explicit supervisory error signal, relying only upon locally accessible information. The fully-connected network consists of excitatory binary neurons with plastic recurrent connections and non-plastic inhibitory feedback stabilizing the network dynamics; the memory patterns to be memorized are presented online as strong afferent currents, producing a bimodal distribution for the neuron synaptic inputs. Synapses corresponding to active inputs are modified as a function of the value of the local fields with respect to three thresholds. Above the highest threshold, and below the lowest threshold, no plasticity occurs. In between these two thresholds, potentiation/depression occurs when the local field is above/below an intermediate threshold. We simulated and analyzed a network of binary neurons implementing this rule and measured its storage capacity for different sizes of the basins of attraction. The storage capacity obtained through numerical simulations is shown to be close to the value predicted by analytical calculations. We also measured the dependence of capacity on the strength of external inputs. Finally, we quantified the statistics of the resulting synaptic connectivity matrix, and found that both the fraction of zero weight synapses and the degree of symmetry of the weight matrix increase with the

Robust Power Supply Restoration for Self-Healing Active Distribution Networks Considering the Availability of Distributed Generation

Directory of Open Access Journals (Sweden)

Qiang Yang

2018-01-01

Full Text Available The increasing penetration of distributed generations (DGs with intermittent and stochastic characteristics into current power distribution networks can lead to increased fault levels and degradation in network protection. As one of the key requirements of active network management (ANM, efficient power supply restoration solution to guarantee network self-healing capability with full consideration of DG uncertainties is demanded. This paper presents a joint power supply restoration through combining the DG local restoration and switcher operation-based restoration to enhance the self-healing capability in active distribution networks considering the availability of distributed generation. The restoration algorithmic solution is designed to be able to carry out power restoration in parallel upon multiple simultaneous faults to maximize the load restoration while additionally minimizing power loss, topology variation and power flow changes due to switcher operations. The performance of the proposed solution is validated based on a 53-bus distribution network with wind power generators through extensive simulation experiments for a range of fault cases and DG scenarios generated based on Heuristic Moment Matching (HMM method to fully consider the DG randomness. The numerical result in comparison with the existing solutions demonstrates the effectiveness of the proposed power supply restoration solution.

Learning of N-layers neural network

Directory of Open Access Journals (Sweden)

Vladimír Konečný

2005-01-01

Full Text Available In the last decade we can observe increasing number of applications based on the Artificial Intelligence that are designed to solve problems from different areas of human activity. The reason why there is so much interest in these technologies is that the classical way of solutions does not exist or these technologies are not suitable because of their robustness. They are often used in applications like Business Intelligence that enable to obtain useful information for high-quality decision-making and to increase competitive advantage.One of the most widespread tools for the Artificial Intelligence are the artificial neural networks. Their high advantage is relative simplicity and the possibility of self-learning based on set of pattern situations.For the learning phase is the most commonly used algorithm back-propagation error (BPE. The base of BPE is the method minima of error function representing the sum of squared errors on outputs of neural net, for all patterns of the learning set. However, while performing BPE and in the first usage, we can find out that it is necessary to complete the handling of the learning factor by suitable method. The stability of the learning process and the rate of convergence depend on the selected method. In the article there are derived two functions: one function for the learning process management by the relative great error function value and the second function when the value of error function approximates to global minimum.The aim of the article is to introduce the BPE algorithm in compact matrix form for multilayer neural networks, the derivation of the learning factor handling method and the presentation of the results.

The integration of elastic wave properties and machine learning for the distribution of petrophysical properties in reservoir modeling

Science.gov (United States)

Ratnam, T. C.; Ghosh, D. P.; Negash, B. M.

2018-05-01

Conventional reservoir modeling employs variograms to predict the spatial distribution of petrophysical properties. This study aims to improve property distribution by incorporating elastic wave properties. In this study, elastic wave properties obtained from seismic inversion are used as input for an artificial neural network to predict neutron porosity in between well locations. The method employed in this study is supervised learning based on available well logs. This method converts every seismic trace into a pseudo-well log, hence reducing the uncertainty between well locations. By incorporating the seismic response, the reliance on geostatistical methods such as variograms for the distribution of petrophysical properties is reduced drastically. The results of the artificial neural network show good correlation with the neutron porosity log which gives confidence for spatial prediction in areas where well logs are not available.

Game-Theoretic Learning in Distributed Control

KAUST Repository

Marden, Jason R.

2018-01-05

In distributed architecture control problems, there is a collection of interconnected decision-making components that seek to realize desirable collective behaviors through local interactions and by processing local information. Applications range from autonomous vehicles to energy to transportation. One approach to control of such distributed architectures is to view the components as players in a game. In this approach, two design considerations are the components’ incentives and the rules that dictate how components react to the decisions of other components. In game-theoretic language, the incentives are defined through utility functions, and the reaction rules are online learning dynamics. This chapter presents an overview of this approach, covering basic concepts in game theory, special game classes, measures of distributed efficiency, utility design, and online learning rules, all with the interpretation of using game theory as a prescriptive paradigm for distributed control design.

Distributed Multi-Commodity Network Flow Algorithm for Energy Optimal Routing in Wireless Sensor Networks.

Directory of Open Access Journals (Sweden)

J. Trdlicka

2010-12-01

Full Text Available This work proposes a distributed algorithm for energy optimal routing in a wireless sensor network. The routing problem is described as a mathematical problem by the minimum-cost multi-commodity network flow problem. Due to the separability of the problem, we use the duality theorem to derive the distributed algorithm. The algorithm computes the energy optimal routing in the network without any central node or knowledge of the whole network structure. Each node only needs to know the flow which is supposed to send or receive and the costs and capacities of the neighboring links. An evaluation of the presented algorithm on benchmarks for the energy optimal data flow routing in sensor networks with up to 100 nodes is presented.

Learning Spatiotemporally Encoded Pattern Transformations in Structured Spiking Neural Networks.

Science.gov (United States)

Gardner, Brian; Sporea, Ioana; Grüning, André

2015-12-01

Information encoding in the nervous system is supported through the precise spike timings of neurons; however, an understanding of the underlying processes by which such representations are formed in the first place remains an open question. Here we examine how multilayered networks of spiking neurons can learn to encode for input patterns using a fully temporal coding scheme. To this end, we introduce a new supervised learning rule, MultilayerSpiker, that can train spiking networks containing hidden layer neurons to perform transformations between spatiotemporal input and output spike patterns. The performance of the proposed learning rule is demonstrated in terms of the number of pattern mappings it can learn, the complexity of network structures it can be used on, and its classification accuracy when using multispike-based encodings. In particular, the learning rule displays robustness against input noise and can generalize well on an example data set. Our approach contributes to both a systematic understanding of how computations might take place in the nervous system and a learning rule that displays strong technical capability.

Learning the Structure of Bayesian Network from Small Amount of Data

Directory of Open Access Journals (Sweden)

Bogdan COCU

2009-12-01

Full Text Available Many areas of artificial intelligence must handling with imperfection ofinformation. One of the ways to do this is using representation and reasoning withBayesian networks. Creation of a Bayesian network consists in two stages. First stage isto design the node structure and directed links between them. Choosing of a structurefor network can be done either through empirical developing by human experts orthrough machine learning algorithm. The second stage is completion of probabilitytables for each node. Using a machine learning method is useful, especially when wehave a big amount of leaning data. But in many fields the amount of data is small,incomplete and inconsistent. In this paper, we make a case study for choosing the bestlearning method for small amount of learning data. Means more experiments we dropconclusion of using existent methods for learning a network structure.

Multi-agent based controller for islanding operation of active distribution networks with distributed generation

DEFF Research Database (Denmark)

Cha, Seung-Tae; Wu, Qiuwei; Østergaard, Jacob

2011-01-01

-bus system was used to investigate the dynamic and steady state performance of the active distribution system during islanding operation. Case studies have been carried out using the Real-Time Digital Simulator (RTDS) based simulation platform. Case study results show that the proposed multi......The increasing amount of distributed generation (DG) in today’s highly complex restructured power networks gives more options for distribution system operators (DSOs) under contingency conditions. A low voltage distribution network with a large amount of DG can be operated as an islanded system...... if the distribution system is disconnected from the main grid due to the contingency. In order to successfully operate distribution systems under islanding mode, the possibility of small power islands within the distribution system needs to be considered. The control and management of these small power islands...

The Practices of Student Network as Cooperative Learning in Ethiopia

Science.gov (United States)

Reda, Weldemariam Nigusse; Hagos, Girmay Tsegay

2015-01-01

Student network is a teaching strategy introduced as cooperative learning to all educational levels above the upper primary schools (grade 5 and above) in Ethiopia. The study was, therefore, aimed at investigating to what extent the student network in Ethiopia is actually practiced in line with the principles of cooperative learning. Consequently,…

"Getting Practical" and the National Network of Science Learning Centres

Science.gov (United States)

Chapman, Georgina; Langley, Mark; Skilling, Gus; Walker, John

2011-01-01

The national network of Science Learning Centres is a co-ordinating partner in the Getting Practical--Improving Practical Work in Science programme. The principle of training provision for the "Getting Practical" programme is a cascade model. Regional trainers employed by the national network of Science Learning Centres trained the cohort of local…

Mimicking Nature´s way of organizing in industry: a network learning perspective

DEFF Research Database (Denmark)

Ulhøi, John Parm; Madsen, Henning

to reconsider organisational learning as being both an internal as well as an external phenomenon. By bringing network learning into an existing interorganisational setting (such as industrial ecology) new potentials for increased learning emerge for the participating companies. The concept of network learning...

Research for the Influence of Distribution Network Line Reclosing Current on Line Protection

Directory of Open Access Journals (Sweden)

Yu Kansheng

2016-01-01

Full Text Available According to the distribution network line structure and reclosing control strategy, the system simulation model of distribution network lines has established based on the real-time digital simulation RTDS. Based on this, distribution network switching impulse current characteristic has researched with different capacity, different distribution and different load power factor under the different voltage switching angles. The results of the study provide a scientific basis for distribution network line protection setting, in order to further lay the foundation for improvement the validity and reliability of distribution network line protection action.

Relationship between neuronal network architecture and naming performance in temporal lobe epilepsy: A connectome based approach using machine learning.

Science.gov (United States)

Munsell, B C; Wu, G; Fridriksson, J; Thayer, K; Mofrad, N; Desisto, N; Shen, D; Bonilha, L

2017-09-09

Impaired confrontation naming is a common symptom of temporal lobe epilepsy (TLE). The neurobiological mechanisms underlying this impairment are poorly understood but may indicate a structural disorganization of broadly distributed neuronal networks that support naming ability. Importantly, naming is frequently impaired in other neurological disorders and by contrasting the neuronal structures supporting naming in TLE with other diseases, it will become possible to elucidate the common systems supporting naming. We aimed to evaluate the neuronal networks that support naming in TLE by using a machine learning algorithm intended to predict naming performance in subjects with medication refractory TLE using only the structural brain connectome reconstructed from diffusion tensor imaging. A connectome-based prediction framework was developed using network properties from anatomically defined brain regions across the entire brain, which were used in a multi-task machine learning algorithm followed by support vector regression. Nodal eigenvector centrality, a measure of regional network integration, predicted approximately 60% of the variance in naming. The nodes with the highest regression weight were bilaterally distributed among perilimbic sub-networks involving mainly the medial and lateral temporal lobe regions. In the context of emerging evidence regarding the role of large structural networks that support language processing, our results suggest intact naming relies on the integration of sub-networks, as opposed to being dependent on isolated brain areas. In the case of TLE, these sub-networks may be disproportionately indicative naming processes that are dependent semantic integration from memory and lexical retrieval, as opposed to multi-modal perception or motor speech production. Copyright © 2017. Published by Elsevier Inc.

A distributed framework for inter-domain virtual network embedding

Science.gov (United States)

Wang, Zihua; Han, Yanni; Lin, Tao; Tang, Hui

2013-03-01

Network virtualization has been a promising technology for overcoming the Internet impasse. A main challenge in network virtualization is the efficient assignment of virtual resources. Existing work focused on intra-domain solutions whereas inter-domain situation is more practical in realistic setting. In this paper, we present a distributed inter-domain framework for mapping virtual networks to physical networks which can ameliorate the performance of the virtual network embedding. The distributed framework is based on a Multi-agent approach. A set of messages for information exchange is defined. We design different operations and IPTV use scenarios to validate the advantages of our framework. Use cases shows that our framework can solve the inter-domain problem efficiently.

Flood impacts on a water distribution network

Science.gov (United States)

Arrighi, Chiara; Tarani, Fabio; Vicario, Enrico; Castelli, Fabio

2017-12-01

Floods cause damage to people, buildings and infrastructures. Water distribution systems are particularly exposed, since water treatment plants are often located next to the rivers. Failure of the system leads to both direct losses, for instance damage to equipment and pipework contamination, and indirect impact, since it may lead to service disruption and thus affect populations far from the event through the functional dependencies of the network. In this work, we present an analysis of direct and indirect damages on a drinking water supply system, considering the hazard of riverine flooding as well as the exposure and vulnerability of active system components. The method is based on interweaving, through a semi-automated GIS procedure, a flood model and an EPANET-based pipe network model with a pressure-driven demand approach, which is needed when modelling water distribution networks in highly off-design conditions. Impact measures are defined and estimated so as to quantify service outage and potential pipe contamination. The method is applied to the water supply system of the city of Florence, Italy, serving approximately 380 000 inhabitants. The evaluation of flood impact on the water distribution network is carried out for different events with assigned recurrence intervals. Vulnerable elements exposed to the flood are identified and analysed in order to estimate their residual functionality and to simulate failure scenarios. Results show that in the worst failure scenario (no residual functionality of the lifting station and a 500-year flood), 420 km of pipework would require disinfection with an estimated cost of EUR 21 million, which is about 0.5 % of the direct flood losses evaluated for buildings and contents. Moreover, if flood impacts on the water distribution network are considered, the population affected by the flood is up to 3 times the population directly flooded.

Developing electricity distribution networks and their regulation to support sustainable energy

International Nuclear Information System (INIS)

Shaw, Rita; Attree, Mike; Jackson, Tim

2010-01-01

A more sustainable energy system will alter the current patterns of electricity demand and generation. This means technical, commercial and regulatory change for electricity network systems such as distribution networks. This paper traces the links in Great Britain between changes in energy policy since privatisation, changes in the objectives of the electricity regulator and changes in the objectives of the distribution networks and their owners, the distribution network operators (DNOs). The paper identifies tensions in regulatory policy and suggests reforms to the regulatory framework to support a lower-carbon future. DNOs are licensed regional infrastructure providers. In addition to their network services, the network companies can potentially deliver public policy objectives to facilitate heat infrastructure, energy-efficiency and distributed renewables. The paper identifies the potential benefits of a novel approach to facilitating renewable energy feed-in tariffs for electricity and heat, using DNOs.

Theses on Distributed Aesthetics. Or, What a Network is Not

Directory of Open Access Journals (Sweden)

Geert Lovink

2005-01-01

Full Text Available In this essay Lovink and Munster set forward a number of proposals for a distributed aesthetics. If new media artistic practice and aesthetic experience were most often characterised by recourse to computational culture, then distributed aesthetics is dominated by networks. Networked media and technologies help to disperse experience so that we never seem to be having our experiences in the one place anymore. However, the authors suggest, most of the images and rhetoric attempting to characterise this distributed experience are drawn from the cartographic traditions of geographic information systems and/or conceptions of biological networking and growth. These do not assist in coming to terms with the specifically social aspects of online networking. The authors speculate that a distributed aesthetics must take into account the collective and personal 'aesthesia' of online networks - the experience of labouring towards new forms of social collectivity that produces not only euphoria but also boredom and frustration.

An Improved Harmony Search Algorithm for Power Distribution Network Planning