Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280411
Haoqi Sun, Yan Yang, O. Sourina, G. Huang
Due to the precise spike timing in neural coding, spiking neural network (SNN) possesses richer spatiotemporal dynamics compared to neural networks with firing rate coding. One of the distinct features of SNN, polychronous neuronal group (PNG), receives much attention from both computational neuroscience and machine learning communities. However, all existing algorithms detect PNGs from the spike recording collected after simulation in an offline manner. There is currently no algorithm that detects PNGs actually being activated in runtime (online manner), which could be potentially used as inputs to higher level neural processing. We propose a runtime detection algorithm particularly for activated PNGs, using PNG readout neurons, to fill this gap. The proposed algorithm can reveal the spatiotemporal PNG patterns embedded in spike trains, which is higher level neuronal dynamics. We demonstrate through an example that for composed input patterns, new PNGs except the constituent PNGs can be easily found using the proposed algorithm. As an important interpretation, we give further insights on how to use PNG readout neurons to construct layered network structure.
{"title":"Runtime detection of activated polychronous neuronal group towards its spatiotemporal analysis","authors":"Haoqi Sun, Yan Yang, O. Sourina, G. Huang","doi":"10.1109/IJCNN.2015.7280411","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280411","url":null,"abstract":"Due to the precise spike timing in neural coding, spiking neural network (SNN) possesses richer spatiotemporal dynamics compared to neural networks with firing rate coding. One of the distinct features of SNN, polychronous neuronal group (PNG), receives much attention from both computational neuroscience and machine learning communities. However, all existing algorithms detect PNGs from the spike recording collected after simulation in an offline manner. There is currently no algorithm that detects PNGs actually being activated in runtime (online manner), which could be potentially used as inputs to higher level neural processing. We propose a runtime detection algorithm particularly for activated PNGs, using PNG readout neurons, to fill this gap. The proposed algorithm can reveal the spatiotemporal PNG patterns embedded in spike trains, which is higher level neuronal dynamics. We demonstrate through an example that for composed input patterns, new PNGs except the constituent PNGs can be easily found using the proposed algorithm. As an important interpretation, we give further insights on how to use PNG readout neurons to construct layered network structure.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"7 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80735976","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280823
Tatiana Escovedo, Adriano Soares Koshiyama, M. Vellasco, R. Melo, A. D. Cruz
Most drift detection mechanisms designed for classification problems works in a post-event manner: after receiving the data set completely (patterns and class labels of the train and test set), they apply a sequence of procedures to identify some change in the class-conditional distribution - a concept drift. However, detecting changes after its occurrence can be in some situations harmful for the process under supervision. This paper proposes a pre-event approach for abrupt drift detection, called by A2D2. Briefly, this method is composed of three steps: (i) label the patterns from the test set, using an unsupervised method; (ii) compute some statistics from the train and test set, conditioned on the given class labels; and (iii) compare the train and test statistics using a multivariate hypothesis test. Also, it has been proposed a procedure for creating datasets with abrupt drift. This procedure was used in the sensivity analysis of A2D2, in order to understand the influence degree of each parameter on its final performance.
{"title":"A2D2: A pre-event abrupt drift detection","authors":"Tatiana Escovedo, Adriano Soares Koshiyama, M. Vellasco, R. Melo, A. D. Cruz","doi":"10.1109/IJCNN.2015.7280823","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280823","url":null,"abstract":"Most drift detection mechanisms designed for classification problems works in a post-event manner: after receiving the data set completely (patterns and class labels of the train and test set), they apply a sequence of procedures to identify some change in the class-conditional distribution - a concept drift. However, detecting changes after its occurrence can be in some situations harmful for the process under supervision. This paper proposes a pre-event approach for abrupt drift detection, called by A2D2. Briefly, this method is composed of three steps: (i) label the patterns from the test set, using an unsupervised method; (ii) compute some statistics from the train and test set, conditioned on the given class labels; and (iii) compare the train and test statistics using a multivariate hypothesis test. Also, it has been proposed a procedure for creating datasets with abrupt drift. This procedure was used in the sensivity analysis of A2D2, in order to understand the influence degree of each parameter on its final performance.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"5 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81301855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280756
Enrico De Santis, A. Rizzi, A. Sadeghian, F. Mascioli
The analysis and recognition of fault status in the Smart Grid field is a challenging problem. Computational Intelligence techniques have already been shown to be a successful framework to face complex problems related to a Smart Grid. The availability of huge amounts of data coming from smart sensors allows the system to take a fine grained picture of the power grid status. This data can be processed in order to offer an instrument in aiding humans operators to better understand the power grid status and to take decisions on grid operations. This paper addresses the problem of fault recognitions in a real-world power grid (i. e. the power grid that feds the city of Rome, Italy) with the One-Class Classification paradigm by a combined approach of dissimilarity measure learning by means of an evolution strategy and clustering techniques for modeling the decision regions between fault status and the standard functioning of the power system. In this paper we present an in-depth study of the performance of two clustering algorithms in building up the model of faults, as the core procedure of the proposed recognition system.
{"title":"A learning intelligent system for fault detection in Smart Grid by a One-Class Classification approach","authors":"Enrico De Santis, A. Rizzi, A. Sadeghian, F. Mascioli","doi":"10.1109/IJCNN.2015.7280756","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280756","url":null,"abstract":"The analysis and recognition of fault status in the Smart Grid field is a challenging problem. Computational Intelligence techniques have already been shown to be a successful framework to face complex problems related to a Smart Grid. The availability of huge amounts of data coming from smart sensors allows the system to take a fine grained picture of the power grid status. This data can be processed in order to offer an instrument in aiding humans operators to better understand the power grid status and to take decisions on grid operations. This paper addresses the problem of fault recognitions in a real-world power grid (i. e. the power grid that feds the city of Rome, Italy) with the One-Class Classification paradigm by a combined approach of dissimilarity measure learning by means of an evolution strategy and clustering techniques for modeling the decision regions between fault status and the standard functioning of the power system. In this paper we present an in-depth study of the performance of two clustering algorithms in building up the model of faults, as the core procedure of the proposed recognition system.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"32 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81407275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280638
Chaitanya Medini, G. Naldi, B. Nair, E. D’Angelo, S. Sunitha Diwakar
Understanding the relationship between fMRI BOLD and underlying neuronal activity has been crucial to connect circuit behavior to cognitive functions. In this paper, we modeled fMRI BOLD reconstructions with general linear model and balloon modeling using biophysical models of rat cerebellum granular layer and stimuli spike trains of various response times. Linear convolution of the hemodynamic response function with the known spiking information reconstructed activity similar to experimental BOLD-like signals with the limitation of short stimuli trains. Balloon model through Volterra kernels gave seemingly similar results to that of general linear model. Our main goal in this study was to understand the activity role of densely populated clusters through BOLD-like reconstructions given neuronal responses and by varying response times for the whole stimulus duration.
{"title":"Reconstructing fMRI BOLD signals arising from cerebellar granule neurons - comparing GLM and balloon models","authors":"Chaitanya Medini, G. Naldi, B. Nair, E. D’Angelo, S. Sunitha Diwakar","doi":"10.1109/IJCNN.2015.7280638","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280638","url":null,"abstract":"Understanding the relationship between fMRI BOLD and underlying neuronal activity has been crucial to connect circuit behavior to cognitive functions. In this paper, we modeled fMRI BOLD reconstructions with general linear model and balloon modeling using biophysical models of rat cerebellum granular layer and stimuli spike trains of various response times. Linear convolution of the hemodynamic response function with the known spiking information reconstructed activity similar to experimental BOLD-like signals with the limitation of short stimuli trains. Balloon model through Volterra kernels gave seemingly similar results to that of general linear model. Our main goal in this study was to understand the activity role of densely populated clusters through BOLD-like reconstructions given neuronal responses and by varying response times for the whole stimulus duration.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"24 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82546481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280673
Giorgio Manganini, Matteo Pirotta, Marcello Restelli, L. Bascetta
This paper investigates the use of second-order methods to solve Markov Decision Processes (MDPs). Despite the popularity of second-order methods in optimization literature, so far little attention has been paid to the extension of such techniques to face sequential decision problems. Here we provide a model-free Reinforcement Learning method that estimates the Newton direction by sampling directly in the parameter space. In order to compute the Newton direction we provide the formulation of the Hessian of the expected return, a technique for variance reduction in the sample-based estimation and a finite sample analysis in the case of Normal distribution. Beside discussing the theoretical properties, we empirically evaluate the method on an instructional linear-quadratic regulator and on a complex dynamical quadrotor system.
{"title":"Following Newton direction in Policy Gradient with parameter exploration","authors":"Giorgio Manganini, Matteo Pirotta, Marcello Restelli, L. Bascetta","doi":"10.1109/IJCNN.2015.7280673","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280673","url":null,"abstract":"This paper investigates the use of second-order methods to solve Markov Decision Processes (MDPs). Despite the popularity of second-order methods in optimization literature, so far little attention has been paid to the extension of such techniques to face sequential decision problems. Here we provide a model-free Reinforcement Learning method that estimates the Newton direction by sampling directly in the parameter space. In order to compute the Newton direction we provide the formulation of the Hessian of the expected return, a technique for variance reduction in the sample-based estimation and a finite sample analysis in the case of Normal distribution. Beside discussing the theoretical properties, we empirically evaluate the method on an instructional linear-quadratic regulator and on a complex dynamical quadrotor system.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"44 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81039186","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280539
Dennis Hamester, Pablo V. A. Barros, S. Wermter
A new architecture based on the Multi-channel Convolutional Neural Network (MCCNN) is proposed for recognizing facial expressions. Two hard-coded feature extractors are replaced by a single channel which is partially trained in an unsupervised fashion as a Convolutional Autoencoder (CAE). One additional channel that contains a standard CNN is left unchanged. Information from both channels converges in a fully connected layer and is then used for classification. We perform two distinct experiments on the JAFFE dataset (leave-one-out and ten-fold cross validation) to evaluate our architecture. Our comparison with the previous model that uses hard-coded Sobel features shows that an additional channel of information with unsupervised learning can significantly boost accuracy and reduce the overall training time. Furthermore, experimental results are compared with benchmarks from the literature showing that our method provides state-of-the-art recognition rates for facial expressions. Our method outperforms previously published methods that used hand-crafted features by a large margin.
{"title":"Face expression recognition with a 2-channel Convolutional Neural Network","authors":"Dennis Hamester, Pablo V. A. Barros, S. Wermter","doi":"10.1109/IJCNN.2015.7280539","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280539","url":null,"abstract":"A new architecture based on the Multi-channel Convolutional Neural Network (MCCNN) is proposed for recognizing facial expressions. Two hard-coded feature extractors are replaced by a single channel which is partially trained in an unsupervised fashion as a Convolutional Autoencoder (CAE). One additional channel that contains a standard CNN is left unchanged. Information from both channels converges in a fully connected layer and is then used for classification. We perform two distinct experiments on the JAFFE dataset (leave-one-out and ten-fold cross validation) to evaluate our architecture. Our comparison with the previous model that uses hard-coded Sobel features shows that an additional channel of information with unsupervised learning can significantly boost accuracy and reduce the overall training time. Furthermore, experimental results are compared with benchmarks from the literature showing that our method provides state-of-the-art recognition rates for facial expressions. Our method outperforms previously published methods that used hand-crafted features by a large margin.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"51 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90960371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280627
Adam J. Wootton, C. Day, P. Haycock
Echo State Networks (ESNs) have been applied to time-series data arising from a structural health monitoring multi-sensor array placed onto a test footbridge which has been subjected to a number of potentially damaging interventions over a three year period. The time-series data, sampled approximately every five minutes from ten temperature sensors, have been used as inputs and the ESNs were tasked with predicting the expected output signal from eight tilt sensors that were also placed on the footbridge. The networks were trained using temperature and tilt sensor data up to the first intervention and subsequent discrepancies in the ESNs' prediction accuracy allowed inferences to be made about when further interventions occurred and also the level of damage caused. Comparing the error in signals with the location of each of the tilt sensors allowed damaged regions to be determined.
{"title":"An Echo State Network approach to structural health monitoring","authors":"Adam J. Wootton, C. Day, P. Haycock","doi":"10.1109/IJCNN.2015.7280627","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280627","url":null,"abstract":"Echo State Networks (ESNs) have been applied to time-series data arising from a structural health monitoring multi-sensor array placed onto a test footbridge which has been subjected to a number of potentially damaging interventions over a three year period. The time-series data, sampled approximately every five minutes from ten temperature sensors, have been used as inputs and the ESNs were tasked with predicting the expected output signal from eight tilt sensors that were also placed on the footbridge. The networks were trained using temperature and tilt sensor data up to the first intervention and subsequent discrepancies in the ESNs' prediction accuracy allowed inferences to be made about when further interventions occurred and also the level of damage caused. Comparing the error in signals with the location of each of the tilt sensors allowed damaged regions to be determined.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"39 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90191601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280621
M. Severini, S. Squartini, Marco Fagiani, F. Piazza
Although smart grids are regarded as the technology to overcome the limits of nowadays power distribution grids, the transition will require much time. Dynamic pricing, a straightforward implementation of demand response, may provide the means to manipulate the grid load thus extending the life expectancy of current technology. However, to integrate a dynamic pricing scheme in the crowded pool of technologies, available at demand side, a proper energy manager with the support of a pricing profile forecaster is mandatory. Although energy management and price forecasting are recurrent topics, in literature they have been addressed separately. On the other hand, in this work, the aim is to investigate how well an energy manager is able to perform in presence of data uncertainty originating from the forecasting process. On purpose, an energy and resource manager has been revised and extended in the current manuscript. Finally, it has been complemented with a price forecasting technique, based on the Extreme Learning Machine paradigm. The proposed forecaster has proven to be better performing and more robust, with respect to the most common forecasting approaches. The energy manager, as well, has proven that the energy efficiency of the residential environment can be improved significantly. Nonetheless, to achieve the theoretical optimum, forecasting techniques tailored for that purpose may be required.
{"title":"Energy management with the support of dynamic pricing strategies in real micro-grid scenarios","authors":"M. Severini, S. Squartini, Marco Fagiani, F. Piazza","doi":"10.1109/IJCNN.2015.7280621","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280621","url":null,"abstract":"Although smart grids are regarded as the technology to overcome the limits of nowadays power distribution grids, the transition will require much time. Dynamic pricing, a straightforward implementation of demand response, may provide the means to manipulate the grid load thus extending the life expectancy of current technology. However, to integrate a dynamic pricing scheme in the crowded pool of technologies, available at demand side, a proper energy manager with the support of a pricing profile forecaster is mandatory. Although energy management and price forecasting are recurrent topics, in literature they have been addressed separately. On the other hand, in this work, the aim is to investigate how well an energy manager is able to perform in presence of data uncertainty originating from the forecasting process. On purpose, an energy and resource manager has been revised and extended in the current manuscript. Finally, it has been complemented with a price forecasting technique, based on the Extreme Learning Machine paradigm. The proposed forecaster has proven to be better performing and more robust, with respect to the most common forecasting approaches. The energy manager, as well, has proven that the energy efficiency of the residential environment can be improved significantly. Nonetheless, to achieve the theoretical optimum, forecasting techniques tailored for that purpose may be required.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"35 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89326153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280505
Yan-Ping Wu, Yun Li
Min-Max Modular Support Vector Machine (M3-SVM) is a powerful supervised ensemble pattern classification method, and it can efficiently deal with large scale labeled data. However, it is very expensive, even infeasible, to label the large scale data set. In order to extend the M3-SVM to handle unlabeled data, a Semi-Supervised M3-SVM learning algorithm (SS-M3-SVM) is proposed in this paper. SS-M3-SVM completes the task decomposition for labeled and unlabeled data, then combines the unlabeled sample subset with labeled sample subset and explores some hidden concepts exist in this combined sample subset. After the hidden concepts explored, the posterior probability of each concept with respect to labeled samples are treated as new features for these labeled samples. Some discriminant information derived from unlabeled data is embedded in these new features. Then each base SVM classifier is trained on the labeled data subset with addition of new features. Finally, the base classifiers are combined using Min-Max rule to obtain the SS-M3-SVM. Experiments on different data sets indicate that the proposed semi-supervised learning strategy can enhance the classification performance of traditional M3-SVM.
{"title":"Semi-supervised Min-Max Modular SVM","authors":"Yan-Ping Wu, Yun Li","doi":"10.1109/IJCNN.2015.7280505","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280505","url":null,"abstract":"Min-Max Modular Support Vector Machine (M3-SVM) is a powerful supervised ensemble pattern classification method, and it can efficiently deal with large scale labeled data. However, it is very expensive, even infeasible, to label the large scale data set. In order to extend the M3-SVM to handle unlabeled data, a Semi-Supervised M3-SVM learning algorithm (SS-M3-SVM) is proposed in this paper. SS-M3-SVM completes the task decomposition for labeled and unlabeled data, then combines the unlabeled sample subset with labeled sample subset and explores some hidden concepts exist in this combined sample subset. After the hidden concepts explored, the posterior probability of each concept with respect to labeled samples are treated as new features for these labeled samples. Some discriminant information derived from unlabeled data is embedded in these new features. Then each base SVM classifier is trained on the labeled data subset with addition of new features. Finally, the base classifiers are combined using Min-Max rule to obtain the SS-M3-SVM. Experiments on different data sets indicate that the proposed semi-supervised learning strategy can enhance the classification performance of traditional M3-SVM.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"58 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89400854","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-07-12DOI: 10.1109/IJCNN.2015.7280849
Jose Augusto S. Lustosa Filho, A. Canuto, J. C. Xavier
Researches with ensemble Systems have emerged as an attempt to obtain a computational system that works with classification tasks in an efficient way. The main goal of using ensemble systems is to improve the performance of a pattern recognition system in terms of better generalization and/or of clearer design. One of the main challenges in the design of a ensemble system is the definition of the system components. The choice of the ensemble members can become a very difficult task and, in some cases, it can lead to ensembles with no performance improvement. In order to avoid this situation, the idea of DES (Dynamic Ensemble Selection)-based method has emerged, in which the classifiers to compose the ensemble systems are chosen in a dynamic way. In this paper, we present an analysis of different diversity measures in two dynamic ensemble election methods. These two methods use accuracy and diversity as the main criteria to select classifiers dynamically. The goal of this paper is to investigate the influence of different diversity measure in the dynamic selection of classifiers.
{"title":"An analysis of diversity measures for the dynamic design of ensemble of classifiers","authors":"Jose Augusto S. Lustosa Filho, A. Canuto, J. C. Xavier","doi":"10.1109/IJCNN.2015.7280849","DOIUrl":"https://doi.org/10.1109/IJCNN.2015.7280849","url":null,"abstract":"Researches with ensemble Systems have emerged as an attempt to obtain a computational system that works with classification tasks in an efficient way. The main goal of using ensemble systems is to improve the performance of a pattern recognition system in terms of better generalization and/or of clearer design. One of the main challenges in the design of a ensemble system is the definition of the system components. The choice of the ensemble members can become a very difficult task and, in some cases, it can lead to ensembles with no performance improvement. In order to avoid this situation, the idea of DES (Dynamic Ensemble Selection)-based method has emerged, in which the classifiers to compose the ensemble systems are chosen in a dynamic way. In this paper, we present an analysis of different diversity measures in two dynamic ensemble election methods. These two methods use accuracy and diversity as the main criteria to select classifiers dynamically. The goal of this paper is to investigate the influence of different diversity measure in the dynamic selection of classifiers.","PeriodicalId":6539,"journal":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","volume":"30 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2015-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89427178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：