Pub Date : 2011-10-03DOI: 10.1109/IJCNN.2011.6033571
Michael R. Smith, T. Martinez
Appropriately handling noise and outliers is an important issue in data mining. In this paper we examine how noise and outliers are handled by learning algorithms. We introduce a filtering method called PRISM that identifies and removes instances that should be misclassified. We refer to the set of removed instances as ISMs (instances that should be misclassified). We examine PRISM and compare it against 3 existing outlier detection methods and 1 noise reduction technique on 48 data sets using 9 learning algorithms. Using PRISM, the classification accuracy increases from 78.5% to 79.8% on a set of 53 data sets and is statistically significant. In addition, the accuracy on the non-outlier instances increases from 82.8% to 84.7%. PRISM achieves a higher classification accuracy than the outlier detection methods and compares favorably with the noise reduction method.
{"title":"Improving classification accuracy by identifying and removing instances that should be misclassified","authors":"Michael R. Smith, T. Martinez","doi":"10.1109/IJCNN.2011.6033571","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033571","url":null,"abstract":"Appropriately handling noise and outliers is an important issue in data mining. In this paper we examine how noise and outliers are handled by learning algorithms. We introduce a filtering method called PRISM that identifies and removes instances that should be misclassified. We refer to the set of removed instances as ISMs (instances that should be misclassified). We examine PRISM and compare it against 3 existing outlier detection methods and 1 noise reduction technique on 48 data sets using 9 learning algorithms. Using PRISM, the classification accuracy increases from 78.5% to 79.8% on a set of 53 data sets and is statistically significant. In addition, the accuracy on the non-outlier instances increases from 82.8% to 84.7%. PRISM achieves a higher classification accuracy than the outlier detection methods and compares favorably with the noise reduction method.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128530441","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033587
Xiaoying Song, Wenqiang Zhang, J. Weng
The biologically-inspired developmental Where-What Networks (WWN) are general purpose visuomotor networks for detecting and recognizing objects from complex backgrounds, modeling the dorsal and ventral streams of the biological visual cortex. The networks are designed for the attention and recognition problem. The architecture in previous versions were meant for a single scale of foreground. This paper focuses on Where-What Network-5 (WWN-5), the extension for multiple scales. WWN-5 can learn three concepts of an object: type, location and scale.
{"title":"Where-What Network 5: Dealing with scales for objects in complex backgrounds","authors":"Xiaoying Song, Wenqiang Zhang, J. Weng","doi":"10.1109/IJCNN.2011.6033587","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033587","url":null,"abstract":"The biologically-inspired developmental Where-What Networks (WWN) are general purpose visuomotor networks for detecting and recognizing objects from complex backgrounds, modeling the dorsal and ventral streams of the biological visual cortex. The networks are designed for the attention and recognition problem. The architecture in previous versions were meant for a single scale of foreground. This paper focuses on Where-What Network-5 (WWN-5), the extension for multiple scales. WWN-5 can learn three concepts of an object: type, location and scale.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116199754","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033466
Alexander D. Rast, F. Galluppi, Sergio Davies, L. Plana, T. Sharp, S. Furber
Neural networks present a fundamentally different model of computation from conventional sequential hardware, making it inefficient for very-large-scale models. Current neuromorphic devices do not yet offer a fully satisfactory solution even though they have improved simulation performance, in part because of fixed hardware, in part because of poor software support. SpiNNaker introduces a different approach, the “neuromimetic” architecture, that maintains the neural optimisation of dedicated chips while offering FPGA-like universal configurability. Central to this parallel multiprocessor is an asynchronous event-driven model that uses interrupt-generating dedicated hardware on the chip to support real-time neural simulation. In turn this requires an event-driven software model: a rethink as fundamental as that of the hardware. We examine this event-driven software model for an important hardware subsystem, the previously-introduced virtual synaptic channel. Using a scheduler-based system service architecture, the software can “hide” low-level processes and events from models so that the only event the model sees is “spike received”. Results from simulation on-chip demonstrate the robustness of the system even in the presence of extremely bursty, unpredictable traffic, but also expose important model-evel tradeoffs that are a consequence of the physical nature of the SpiNNaker chip. This event-driven subsystem is the first component of a library-based development system that allows the user to describe a model in a high-level neural description environment and be able to rely on a lower layer of system services to execute the model efficiently on SpiNNaker. Such a system realises a general-purpose platform that can generate an arbitrary neural network and run it with hardware speed and scale.
{"title":"An event-driven model for the SpiNNaker virtual synaptic channel","authors":"Alexander D. Rast, F. Galluppi, Sergio Davies, L. Plana, T. Sharp, S. Furber","doi":"10.1109/IJCNN.2011.6033466","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033466","url":null,"abstract":"Neural networks present a fundamentally different model of computation from conventional sequential hardware, making it inefficient for very-large-scale models. Current neuromorphic devices do not yet offer a fully satisfactory solution even though they have improved simulation performance, in part because of fixed hardware, in part because of poor software support. SpiNNaker introduces a different approach, the “neuromimetic” architecture, that maintains the neural optimisation of dedicated chips while offering FPGA-like universal configurability. Central to this parallel multiprocessor is an asynchronous event-driven model that uses interrupt-generating dedicated hardware on the chip to support real-time neural simulation. In turn this requires an event-driven software model: a rethink as fundamental as that of the hardware. We examine this event-driven software model for an important hardware subsystem, the previously-introduced virtual synaptic channel. Using a scheduler-based system service architecture, the software can “hide” low-level processes and events from models so that the only event the model sees is “spike received”. Results from simulation on-chip demonstrate the robustness of the system even in the presence of extremely bursty, unpredictable traffic, but also expose important model-evel tradeoffs that are a consequence of the physical nature of the SpiNNaker chip. This event-driven subsystem is the first component of a library-based development system that allows the user to describe a model in a high-level neural description environment and be able to rely on a lower layer of system services to execute the model efficiently on SpiNNaker. Such a system realises a general-purpose platform that can generate an arbitrary neural network and run it with hardware speed and scale.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117001208","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033327
N. Reyhani, E. Oja
High dimensional data are often modeled by signal plus noise where the signal belongs to a low dimensional manifold contaminated with high dimensional noise. Estimating the signal subspace when the noise is Gaussian and the signal is non-Gaussian is the main focus of this paper. We assume that the Gaussian noise variance can be high, so standard denoising approaches like Principal Component Analysis fail. The approach also differs from standard Independent Component Analysis in that no independent signal factors are assumed. This model is called non-Gaussian subspace/component analysis (NGCA). The previous approaches proposed for this subspace analysis use the fourth cumulant matrix or the Hessian of the logarithm of characteristic functions, which both have some practical and theoretical issues. We propose to use sample Density Gradient Covariances, which are similar to the Fisher information matrix for estimating the non-Gaussian subspace. Here, we use nonparametric kernel density estimator to estimate the gradients of density functions. Moreover, we extend the notion of non-Gaussian subspace analysis to a supervised version where the label or response information is present. For the supervised non-Gaussian subspace analysis, we propose to use conditional density gradient covariances which are computed by conditioning on the discretized response variable. A non-asymptotic analysis of density gradient covariance is also provided which relates the error of estimating the population DGC matrix using sample DGC to the number of dimensions and the number of samples.
{"title":"Non-Gaussian component analysis using Density Gradient Covariance matrix","authors":"N. Reyhani, E. Oja","doi":"10.1109/IJCNN.2011.6033327","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033327","url":null,"abstract":"High dimensional data are often modeled by signal plus noise where the signal belongs to a low dimensional manifold contaminated with high dimensional noise. Estimating the signal subspace when the noise is Gaussian and the signal is non-Gaussian is the main focus of this paper. We assume that the Gaussian noise variance can be high, so standard denoising approaches like Principal Component Analysis fail. The approach also differs from standard Independent Component Analysis in that no independent signal factors are assumed. This model is called non-Gaussian subspace/component analysis (NGCA). The previous approaches proposed for this subspace analysis use the fourth cumulant matrix or the Hessian of the logarithm of characteristic functions, which both have some practical and theoretical issues. We propose to use sample Density Gradient Covariances, which are similar to the Fisher information matrix for estimating the non-Gaussian subspace. Here, we use nonparametric kernel density estimator to estimate the gradients of density functions. Moreover, we extend the notion of non-Gaussian subspace analysis to a supervised version where the label or response information is present. For the supervised non-Gaussian subspace analysis, we propose to use conditional density gradient covariances which are computed by conditioning on the discretized response variable. A non-asymptotic analysis of density gradient covariance is also provided which relates the error of estimating the population DGC matrix using sample DGC to the number of dimensions and the number of samples.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117295256","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033196
X. Hong, Yu Gong, Sheng Chen
In this paper a new nonlinear digital baseband predistorter design is introduced based on direct learning, together with a new Wiener system modeling approach for the high power amplifiers (HPA) based on the B-spline neural network. The contribution is twofold. Firstly, by assuming that the nonlinearity in the HPA is mainly dependent on the input signal amplitude the complex valued nonlinear static function is represented by two real valued B-spline neural networks, one for the amplitude distortion and another for the phase shift. The Gauss-Newton algorithm is applied for the parameter estimation, in which the De Boor recursion is employed to calculate both the B-spline curve and the first order derivatives. Secondly, we derive the predistorter algorithm calculating the inverse of the complex valued nonlinear static function according to B-spline neural network based Wiener models. The inverse of the amplitude and phase shift distortion are then computed and compensated using the identified phase shift model. Numerical examples have been employed to demonstrate the efficacy of the proposed approaches.
{"title":"B-spline neural network based digital baseband predistorter solution using the inverse of De Boor algorithm","authors":"X. Hong, Yu Gong, Sheng Chen","doi":"10.1109/IJCNN.2011.6033196","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033196","url":null,"abstract":"In this paper a new nonlinear digital baseband predistorter design is introduced based on direct learning, together with a new Wiener system modeling approach for the high power amplifiers (HPA) based on the B-spline neural network. The contribution is twofold. Firstly, by assuming that the nonlinearity in the HPA is mainly dependent on the input signal amplitude the complex valued nonlinear static function is represented by two real valued B-spline neural networks, one for the amplitude distortion and another for the phase shift. The Gauss-Newton algorithm is applied for the parameter estimation, in which the De Boor recursion is employed to calculate both the B-spline curve and the first order derivatives. Secondly, we derive the predistorter algorithm calculating the inverse of the complex valued nonlinear static function according to B-spline neural network based Wiener models. The inverse of the amplitude and phase shift distortion are then computed and compensated using the identified phase shift model. Numerical examples have been employed to demonstrate the efficacy of the proposed approaches.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114531322","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033192
D. Wilson
Probabilistic record linkage has been used for many years in a variety of industries, including medical, government, private sector and research groups. The formulas used for probabilistic record linkage have been recognized by some as being equivalent to the naïve Bayes classifier. While this method can produce useful results, it is not difficult to improve accuracy by using one of a host of other machine learning or neural network algorithms. Even a simple single-layer perceptron tends to outperform the naïve Bayes classifier—and thus traditional probabilistic record linkage methods—by a substantial margin. Furthermore, many record linkage system use simple field comparisons rather than more complex features, partially due to the limits of the probabilistic formulas they use. This paper presents an overview of probabilistic record linkage, shows how to cast it in machine learning terms, and then shows that it is equivalent to a naïve Bayes classifier. It then discusses how to use more complex features than simple field comparisons, and shows how probabilistic record linkage formulas can be modified to handle this. Finally, it demonstrates a huge improvement in accuracy through the use of neural networks and higher-level matching features, compared to traditional probabilistic record linkage on a large (80,000 pair) set of labeled pairs of genealogical records used by FamilySearch.org.
{"title":"Beyond probabilistic record linkage: Using neural networks and complex features to improve genealogical record linkage","authors":"D. Wilson","doi":"10.1109/IJCNN.2011.6033192","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033192","url":null,"abstract":"Probabilistic record linkage has been used for many years in a variety of industries, including medical, government, private sector and research groups. The formulas used for probabilistic record linkage have been recognized by some as being equivalent to the naïve Bayes classifier. While this method can produce useful results, it is not difficult to improve accuracy by using one of a host of other machine learning or neural network algorithms. Even a simple single-layer perceptron tends to outperform the naïve Bayes classifier—and thus traditional probabilistic record linkage methods—by a substantial margin. Furthermore, many record linkage system use simple field comparisons rather than more complex features, partially due to the limits of the probabilistic formulas they use. This paper presents an overview of probabilistic record linkage, shows how to cast it in machine learning terms, and then shows that it is equivalent to a naïve Bayes classifier. It then discusses how to use more complex features than simple field comparisons, and shows how probabilistic record linkage formulas can be modified to handle this. Finally, it demonstrates a huge improvement in accuracy through the use of neural networks and higher-level matching features, compared to traditional probabilistic record linkage on a large (80,000 pair) set of labeled pairs of genealogical records used by FamilySearch.org.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115146046","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033655
K. Harrington, Megan M. Olsen, H. Siegelmann
We use emotional communication within a predator-prey game to evaluate the tradeoff between socio-emotional behavior at individual- and species- scales. In this predator-prey game, individual predators and prey use emotion in their decision making, and communicate their emotional state with neighboring conspecifics. The model of emotion is based upon the somatic marker hypothesis. In comparing individual utility and population dynamics we find emotion is capable of both supporting species and individual gain. We suggest this type of dynamic may provide a mechanism for the emergence of altruistic behavior within a species under individual and/or group selection.
{"title":"Communicated somatic markers benefit both the individual and the species","authors":"K. Harrington, Megan M. Olsen, H. Siegelmann","doi":"10.1109/IJCNN.2011.6033655","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033655","url":null,"abstract":"We use emotional communication within a predator-prey game to evaluate the tradeoff between socio-emotional behavior at individual- and species- scales. In this predator-prey game, individual predators and prey use emotion in their decision making, and communicate their emotional state with neighboring conspecifics. The model of emotion is based upon the somatic marker hypothesis. In comparing individual utility and population dynamics we find emotion is capable of both supporting species and individual gain. We suggest this type of dynamic may provide a mechanism for the emergence of altruistic behavior within a species under individual and/or group selection.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115154802","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033473
Songlin Zhao, Badong Chen, J. Príncipe
Kernel adaptive filters have drawn increasing attention due to their advantages such as universal nonlinear approximation with universal kernels, linearity and convexity in Reproducing Kernel Hilbert Space (RKHS). Among them, the kernel least mean square (KLMS) algorithm deserves particular attention because of its simplicity and sequential learning approach. Similar to most conventional adaptive filtering algorithms, the KLMS adopts the mean square error (MSE) as the adaptation cost. However, the mere second-order statistics is often not suitable for nonlinear and non-Gaussian situations. Therefore, various non-MSE criteria, which involve higher-order statistics, have received an increasing interest. Recently, the correntropy, as an alternative of MSE, has been successfully used in nonlinear and non-Gaussian signal processing and machine learning domains. This fact motivates us in this paper to develop a new kernel adaptive algorithm, called the kernel maximum correntropy (KMC), which combines the advantages of the KLMS and maximum correntropy criterion (MCC). We also study its convergence and self-regularization properties by using the energy conservation relation. The superior performance of the new algorithm has been demonstrated by simulation experiments in the noisy frequency doubling problem.
{"title":"Kernel adaptive filtering with maximum correntropy criterion","authors":"Songlin Zhao, Badong Chen, J. Príncipe","doi":"10.1109/IJCNN.2011.6033473","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033473","url":null,"abstract":"Kernel adaptive filters have drawn increasing attention due to their advantages such as universal nonlinear approximation with universal kernels, linearity and convexity in Reproducing Kernel Hilbert Space (RKHS). Among them, the kernel least mean square (KLMS) algorithm deserves particular attention because of its simplicity and sequential learning approach. Similar to most conventional adaptive filtering algorithms, the KLMS adopts the mean square error (MSE) as the adaptation cost. However, the mere second-order statistics is often not suitable for nonlinear and non-Gaussian situations. Therefore, various non-MSE criteria, which involve higher-order statistics, have received an increasing interest. Recently, the correntropy, as an alternative of MSE, has been successfully used in nonlinear and non-Gaussian signal processing and machine learning domains. This fact motivates us in this paper to develop a new kernel adaptive algorithm, called the kernel maximum correntropy (KMC), which combines the advantages of the KLMS and maximum correntropy criterion (MCC). We also study its convergence and self-regularization properties by using the energy conservation relation. The superior performance of the new algorithm has been demonstrated by simulation experiments in the noisy frequency doubling problem.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"359 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115200658","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033585
Mingxuan Wang, C. C. Took, D. Mandic
We introduce a class of gradient adaptive stepsize algorithms for quaternion valued adaptive filtering based on three- and four-dimensional vector sensors. This equips the recently introduced quaternion least mean square (QLMS) algorithm with enhanced tracking ability and enables it to be more responsive to dynamically changing environments, while maintaining its desired characteristics of catering for large dynamical differences and coupling between signal components. For generality, the analysis is performed for the widely linear signal model, which by virtue of accounting for signal noncircularity, is optimal in the mean squared error (MSE) sense for both second order circular (proper) and noncircular (improper) processes. The widely linear QLMS (WL-QLMS) employing the proposed adaptive stepsize modifications is shown to provide enhanced performance for both synthetic and real world quaternion valued signals. Simulations include signals with drastically different component dynamics, such as four dimensional quaternion comprising three dimensional turbulent wind and air temperature for renewable energy applications.
{"title":"A class of fast quaternion valued variable stepsize stochastic gradient learning algorithms for vector sensor processes","authors":"Mingxuan Wang, C. C. Took, D. Mandic","doi":"10.1109/IJCNN.2011.6033585","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033585","url":null,"abstract":"We introduce a class of gradient adaptive stepsize algorithms for quaternion valued adaptive filtering based on three- and four-dimensional vector sensors. This equips the recently introduced quaternion least mean square (QLMS) algorithm with enhanced tracking ability and enables it to be more responsive to dynamically changing environments, while maintaining its desired characteristics of catering for large dynamical differences and coupling between signal components. For generality, the analysis is performed for the widely linear signal model, which by virtue of accounting for signal noncircularity, is optimal in the mean squared error (MSE) sense for both second order circular (proper) and noncircular (improper) processes. The widely linear QLMS (WL-QLMS) employing the proposed adaptive stepsize modifications is shown to provide enhanced performance for both synthetic and real world quaternion valued signals. Simulations include signals with drastically different component dynamics, such as four dimensional quaternion comprising three dimensional turbulent wind and air temperature for renewable energy applications.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114100017","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 : 2011-10-03DOI: 10.1109/IJCNN.2011.6033547
Shuo Chen, Chengjun Liu
For complicated classification problems, the standard Support Vector Machine (SVM) is likely to be complex and thus the classification efficiency is low. In this paper, we propose a new efficient SVM (eSVM), which is based on the idea of minimizing the margin of misclassified samples. Compared with the conventional SVM, the eSVM is defined on fewer support vectors and thus can achieve much faster classification speed and comparable or even higher classification accuracy. We then present a real-time accurate eye localization system using the eSVM together with color information and 2D Haar wavelet features. Experiments on some public data sets show that (i) the eSVM significantly improves the efficiency of the standard SVM without sacrificing its accuracy and (ii) the eye localization system has real-time speed and higher detection accuracy than some state-of-the-art approaches.
{"title":"A new efficient SVM and its application to real-time accurate eye localization","authors":"Shuo Chen, Chengjun Liu","doi":"10.1109/IJCNN.2011.6033547","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033547","url":null,"abstract":"For complicated classification problems, the standard Support Vector Machine (SVM) is likely to be complex and thus the classification efficiency is low. In this paper, we propose a new efficient SVM (eSVM), which is based on the idea of minimizing the margin of misclassified samples. Compared with the conventional SVM, the eSVM is defined on fewer support vectors and thus can achieve much faster classification speed and comparable or even higher classification accuracy. We then present a real-time accurate eye localization system using the eSVM together with color information and 2D Haar wavelet features. Experiments on some public data sets show that (i) the eSVM significantly improves the efficiency of the standard SVM without sacrificing its accuracy and (ii) the eye localization system has real-time speed and higher detection accuracy than some state-of-the-art approaches.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127397424","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：