Pub Date : 2011-10-03DOI: 10.1109/IJCNN.2011.6033484
Derrik E. Asher, Andrew Zaldivar, B. Barton, A. Brewer, J. Krichmar
Game theory has been useful for understanding risk-taking, cooperation, and social behavior. However, in studies of the neural basis of decision-making during games of conflict, subjects typically play against an opponent with a predetermined strategy [1–3]. In the present study, human subjects played Hawk-Dove games against a neural agent, both simulated and robotic, with the ability to assess the potential costs and rewards of its actions and adapt its behavior accordingly. The neural agent's model was based on the assumption that the dopaminergic and serotonergic systems track expected rewards and costs, respectively [4]. The study consisted of two experimental days, one in which subjects' serotonin levels were lowered through acute tryptophan depletion (ATD), where human subjects played against neural agents whose simulated serotonin systems were altered as well. When the neural agent's serotonergic system was compromised, by turning off neural activity in its raphe nucleus, the neural agent tended towards aggressive behavior, due to its inability to assess the cost of its actions [4]. When subjects played against an aggressive neural agent, there was a significant shift in their strategy from Win-Stay-Lose-Shift (WSLS) to Tit-For-Tat (T4T). This shift to a T4T strategy may be similar to the rejection of unfair offers in the Ultimatum Game [2]. A T4T strategy, which is strategically less advantageous than WSLS, could send a message to another player that the subject believes he is being treated unfairly. In other studies, ATD led to increased defections in the Prisoner's Dilemma [3] and more rejections of offers in the Ultimatum Game [1]. In contrast, we did not observe a decrease of cooperativeness in our subjects due to ATD, but rather the emergence of a strongly significant shift in strategies based on opponent type. It may be that iterative interactions with a responsive, adaptive agent outweighed the effects of ATD in our human subjects. Additionally, the physical instantiation of the neural agent did not evoke stronger responses from subjects than did the simulated neural agent. We suggest that both the simulated and embodied versions of the neural agent evoked strong responses in subjects because of the neural agent's adaptive behavior. These results highlight the important interactions between human subjects and an agent that can adapt its behavior. Moreover, they reveal neuromodulatory mechanisms that give rise to cooperative and competitive behaviors.
{"title":"The effects of neuromodulation on human-robot interaction in games of conflict and cooperation","authors":"Derrik E. Asher, Andrew Zaldivar, B. Barton, A. Brewer, J. Krichmar","doi":"10.1109/IJCNN.2011.6033484","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033484","url":null,"abstract":"Game theory has been useful for understanding risk-taking, cooperation, and social behavior. However, in studies of the neural basis of decision-making during games of conflict, subjects typically play against an opponent with a predetermined strategy [1–3]. In the present study, human subjects played Hawk-Dove games against a neural agent, both simulated and robotic, with the ability to assess the potential costs and rewards of its actions and adapt its behavior accordingly. The neural agent's model was based on the assumption that the dopaminergic and serotonergic systems track expected rewards and costs, respectively [4]. The study consisted of two experimental days, one in which subjects' serotonin levels were lowered through acute tryptophan depletion (ATD), where human subjects played against neural agents whose simulated serotonin systems were altered as well. When the neural agent's serotonergic system was compromised, by turning off neural activity in its raphe nucleus, the neural agent tended towards aggressive behavior, due to its inability to assess the cost of its actions [4]. When subjects played against an aggressive neural agent, there was a significant shift in their strategy from Win-Stay-Lose-Shift (WSLS) to Tit-For-Tat (T4T). This shift to a T4T strategy may be similar to the rejection of unfair offers in the Ultimatum Game [2]. A T4T strategy, which is strategically less advantageous than WSLS, could send a message to another player that the subject believes he is being treated unfairly. In other studies, ATD led to increased defections in the Prisoner's Dilemma [3] and more rejections of offers in the Ultimatum Game [1]. In contrast, we did not observe a decrease of cooperativeness in our subjects due to ATD, but rather the emergence of a strongly significant shift in strategies based on opponent type. It may be that iterative interactions with a responsive, adaptive agent outweighed the effects of ATD in our human subjects. Additionally, the physical instantiation of the neural agent did not evoke stronger responses from subjects than did the simulated neural agent. We suggest that both the simulated and embodied versions of the neural agent evoked strong responses in subjects because of the neural agent's adaptive behavior. These results highlight the important interactions between human subjects and an agent that can adapt its behavior. Moreover, they reveal neuromodulatory mechanisms that give rise to cooperative and competitive behaviors.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"113 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":"115036780","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.2011.6033534
Shenglan Ben, Zhong Jin, Jing-yu Yang
A new fuzzy clustering algorithm using multi-prototype representation of clusters is proposed in this paper to discover clusters with arbitrary shapes and sizes. Intra-cluster non-consistency and inter-cluster overlap are proposed as two mistake measurements to guide the splitting and merging step of the algorithm. In the splitting step, clusters with the largest intra-cluster non-consistency are iteratively split such that the resulting subclusters only contain data from the same class. In the following merging step, subclusters with the largest inter-cluster overlap are iteratively merged until a pre-determined cluster number is achieved. A multi-prototy-pe representation of clusters is used in the merging step to handle the clusters with different size and shapes. Experimental results on synthetic and real datasets demonstrate the effectiveness and robustness of the proposed algorithm.
{"title":"Guided fuzzy clustering with multi-prototypes","authors":"Shenglan Ben, Zhong Jin, Jing-yu Yang","doi":"10.1109/IJCNN.2011.6033534","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033534","url":null,"abstract":"A new fuzzy clustering algorithm using multi-prototype representation of clusters is proposed in this paper to discover clusters with arbitrary shapes and sizes. Intra-cluster non-consistency and inter-cluster overlap are proposed as two mistake measurements to guide the splitting and merging step of the algorithm. In the splitting step, clusters with the largest intra-cluster non-consistency are iteratively split such that the resulting subclusters only contain data from the same class. In the following merging step, subclusters with the largest inter-cluster overlap are iteratively merged until a pre-determined cluster number is achieved. A multi-prototy-pe representation of clusters is used in the merging step to handle the clusters with different size and shapes. Experimental results on synthetic and real datasets demonstrate the effectiveness and robustness of the proposed algorithm.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"44 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":"122062333","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.2011.6033460
B. S. Mahanand, S. Sundaram, N. Sundararajan, M. A. Kumar
This paper presents a new approach using Voxel-Based Morphometry (VBM) detected features with a Self-adaptive Resource Allocation Network (SRAN) classifier for the detection of Alzheimer's Disease (AD) from Magnetic Resonance Imaging (MRI) scans. For feature reduction, Principal Component Analysis (PCA) has been performed on the morphometric features obtained from the VBM analysis and these reduced features are then used as input to the SRAN classifier. In our study, the MRI volumes of 30 ‘mild AD to moderate AD’ patients and 30 normal persons from the well-known Open Access Series of Imaging Studies (OASIS) data set have been used. The results indicate that the SRAN classifier produces a mean testing efficiency of 91.18% with only 20 PCA reduced features whereas, the Support Vector Machine (SVM) produces a mean testing efficiency of 90.57% using 45 PCA reduced features. Also, the results show that the SRAN classifier avoids over-training by minimizing the number of samples used for training and provides a better generalization performance compared to the SVM classifier. The study clearly indicates that our proposed approach of PCA-SRAN classifier performs accurate classification of AD subjects using reduced morphometric features.
{"title":"Alzheimer's disease detection using a Self-adaptive Resource Allocation Network classifier","authors":"B. S. Mahanand, S. Sundaram, N. Sundararajan, M. A. Kumar","doi":"10.1109/IJCNN.2011.6033460","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033460","url":null,"abstract":"This paper presents a new approach using Voxel-Based Morphometry (VBM) detected features with a Self-adaptive Resource Allocation Network (SRAN) classifier for the detection of Alzheimer's Disease (AD) from Magnetic Resonance Imaging (MRI) scans. For feature reduction, Principal Component Analysis (PCA) has been performed on the morphometric features obtained from the VBM analysis and these reduced features are then used as input to the SRAN classifier. In our study, the MRI volumes of 30 ‘mild AD to moderate AD’ patients and 30 normal persons from the well-known Open Access Series of Imaging Studies (OASIS) data set have been used. The results indicate that the SRAN classifier produces a mean testing efficiency of 91.18% with only 20 PCA reduced features whereas, the Support Vector Machine (SVM) produces a mean testing efficiency of 90.57% using 45 PCA reduced features. Also, the results show that the SRAN classifier avoids over-training by minimizing the number of samples used for training and provides a better generalization performance compared to the SVM classifier. The study clearly indicates that our proposed approach of PCA-SRAN classifier performs accurate classification of AD subjects using reduced morphometric features.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"25 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":"116908132","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.2011.6033605
Xianxue Fan, J. Igual, R. Llinares, A. Salazar, Gang Wu
One of the main advantages of cooperative communication systems is the use of information at the surrounding nodes in order to create spatial diversity and so far obtaining higher throughput and reliability. We propose in this paper a blind detector that involves the formulation of the system as a Blind Source Separation BSS problem. In the BSS framework, we do not have to estimate the channel using training data, removing the necessity of pilot symbols and the prior estimation of the channel. We analyze two kinds of distributed space-time codes for the single relay system, showing that they can be stated in terms of BSS as a linear instantaneous mixture of complex-valued sources. The BSS method applied is the complex version of the FastICA algorithm since it is very flexible, robust and the convergence is very fast so we can estimate the symbols accurately with a low-complexity algorithm that can adapt to changes in the channel with relative simplicity.
{"title":"Blind signal separation in distributed space-time coding systems using the FastICA algorithm","authors":"Xianxue Fan, J. Igual, R. Llinares, A. Salazar, Gang Wu","doi":"10.1109/IJCNN.2011.6033605","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033605","url":null,"abstract":"One of the main advantages of cooperative communication systems is the use of information at the surrounding nodes in order to create spatial diversity and so far obtaining higher throughput and reliability. We propose in this paper a blind detector that involves the formulation of the system as a Blind Source Separation BSS problem. In the BSS framework, we do not have to estimate the channel using training data, removing the necessity of pilot symbols and the prior estimation of the channel. We analyze two kinds of distributed space-time codes for the single relay system, showing that they can be stated in terms of BSS as a linear instantaneous mixture of complex-valued sources. The BSS method applied is the complex version of the FastICA algorithm since it is very flexible, robust and the convergence is very fast so we can estimate the symbols accurately with a low-complexity algorithm that can adapt to changes in the channel with relative simplicity.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"3 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":"126124598","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.2011.6033489
S. Nõmm, Ü. Kotta
A correlation-test-based validation procedure is applied in this study to compare neural networks based nonlinear autoregressive exogenous model class to its subclass of additive nonlinear autoregressive exogenous models.
{"title":"Comparison of neural networks-based ANARX and NARX models by application of correlation tests","authors":"S. Nõmm, Ü. Kotta","doi":"10.1109/IJCNN.2011.6033489","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033489","url":null,"abstract":"A correlation-test-based validation procedure is applied in this study to compare neural networks based nonlinear autoregressive exogenous model class to its subclass of additive nonlinear autoregressive exogenous models.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"37 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":"124740162","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.2011.6033252
Hui Wei, Xiaomei Wang
According to Biology there is a large disinhibitory area outside the classical receptive field (CRF), which is called as non-classical receptive field (nCRF). Combining CRF with nCRF could increase the sparseness, reliability and precision of the neuronal responses. This paper is aimed at the realization of the neural circuit and the dynamic adjustment mechanism of the receptive field (RF) with respect to nCRF. On the basis of anatomical and electrophysiological evidence, we constructed a neural computational model, which can represent natural images faithfully, simply and rapidly. And the representation can significantly improve the subsequent operation efficiency such as segmentation or integration. This study is of particular significance in the development of efficient image processing algorithms based on neurobiological mechanisms. The RF mechanism of ganglion cell (GC) is the result of a long term of evolution and optimization of self-adaptability and high representation efficiency. So its performance evaluation in natural image processing is worthy of further study.
{"title":"A neural circuit model for nCRF's dynamic adjustment and its application on image representation","authors":"Hui Wei, Xiaomei Wang","doi":"10.1109/IJCNN.2011.6033252","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033252","url":null,"abstract":"According to Biology there is a large disinhibitory area outside the classical receptive field (CRF), which is called as non-classical receptive field (nCRF). Combining CRF with nCRF could increase the sparseness, reliability and precision of the neuronal responses. This paper is aimed at the realization of the neural circuit and the dynamic adjustment mechanism of the receptive field (RF) with respect to nCRF. On the basis of anatomical and electrophysiological evidence, we constructed a neural computational model, which can represent natural images faithfully, simply and rapidly. And the representation can significantly improve the subsequent operation efficiency such as segmentation or integration. This study is of particular significance in the development of efficient image processing algorithms based on neurobiological mechanisms. The RF mechanism of ganglion cell (GC) is the result of a long term of evolution and optimization of self-adaptability and high representation efficiency. So its performance evaluation in natural image processing is worthy of further study.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"86 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":"124781493","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.2011.6033288
R. Kamimura
In this paper, we propose a new type of information-theoretic method called “information-theoretic cooperative learning.” In this method, two networks, namely, cooperative and uncooperative networks are prepared. The roles of these networks are controlled by the cooperation parameter α. As the parameter is increased, the role of cooperative networks becomes more important in learning. We applied the method to the automobile data from the machine learning database. Experimental results showed that cooperation control could be used to increase mutual information on input patterns and to produce clearer class structure in SOM.
{"title":"Cooperation control and enhanced class structure in self-organizing maps","authors":"R. Kamimura","doi":"10.1109/IJCNN.2011.6033288","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033288","url":null,"abstract":"In this paper, we propose a new type of information-theoretic method called “information-theoretic cooperative learning.” In this method, two networks, namely, cooperative and uncooperative networks are prepared. The roles of these networks are controlled by the cooperation parameter α. As the parameter is increased, the role of cooperative networks becomes more important in learning. We applied the method to the automobile data from the machine learning database. Experimental results showed that cooperation control could be used to increase mutual information on input patterns and to produce clearer class structure in SOM.","PeriodicalId":415833,"journal":{"name":"The 2011 International Joint Conference on Neural Networks","volume":"10 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":"124841994","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.2011.6033292
Yutaro Yamashita, H. Torikai
A novel analog spiking neuron model which has a piece-wise constant (ab. PWC) vector field and can be implemented by a simple electronic circuit is proposed. Using theories on discontinuous ODEs, the dynamics of the proposed model can be reduced into a one-dimensional return map analytically. Using the return map, it is shown that the proposed model can exhibit various neuron-like behaviors and bifurcations. It is also shown that the model can reproduce not only the individual neuron-like behaviors and bifurcations but also relations among them that are typically observed in biological and model neurons.
{"title":"A novel piece-wise constant analog spiking neuron model and its neuron-like excitabilities","authors":"Yutaro Yamashita, H. Torikai","doi":"10.1109/IJCNN.2011.6033292","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033292","url":null,"abstract":"A novel analog spiking neuron model which has a piece-wise constant (ab. PWC) vector field and can be implemented by a simple electronic circuit is proposed. Using theories on discontinuous ODEs, the dynamics of the proposed model can be reduced into a one-dimensional return map analytically. Using the return map, it is shown that the proposed model can exhibit various neuron-like behaviors and bifurcations. It is also shown that the model can reproduce not only the individual neuron-like behaviors and bifurcations but also relations among them that are typically observed in biological and model neurons.","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":"129386131","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.2011.6033567
Icamaan B. Viegas da Silva, P. Adeodato
Machine learning approaches have been successfully applied for automatic decision support in several domains. The quality of these systems, however, degrades severely in classification problems with small and unbalanced data sets for knowledge acquisition. Inherent to several real-world problems, data sets with these characteristics are the reality to be tackled by learning algorithms, but the small amount of data affects the classifiers' generalization power while the imbalance in class distribution makes the classifiers biased towards the larger classes. Previous work had addressed these data constraints with the addition of Gaussian noise to the input patterns' variables during the iterative training process of a MultiLayer perceptron (MLP) neural network (NN). This paper improves the quality of such classifier by decorrelating the input variables via a Principal Component Analysis (PCA) transformation of the original input space before applying additive Gaussian noise to each transformed variable for each input pattern. PCA transformation prevents the conflicting effect of adding decorrelated noise to correlated variables, an effect which increases with the noise level. Three public data sets from a well-known benchmark (Proben1) were used to validate the proposed approach. Experimental results indicate that the proposed methodology improves the performance of the previous approach being statistically better than the traditional training method (95% confidence) in further experimental set-ups.
{"title":"PCA and Gaussian noise in MLP neural network training improve generalization in problems with small and unbalanced data sets","authors":"Icamaan B. Viegas da Silva, P. Adeodato","doi":"10.1109/IJCNN.2011.6033567","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033567","url":null,"abstract":"Machine learning approaches have been successfully applied for automatic decision support in several domains. The quality of these systems, however, degrades severely in classification problems with small and unbalanced data sets for knowledge acquisition. Inherent to several real-world problems, data sets with these characteristics are the reality to be tackled by learning algorithms, but the small amount of data affects the classifiers' generalization power while the imbalance in class distribution makes the classifiers biased towards the larger classes. Previous work had addressed these data constraints with the addition of Gaussian noise to the input patterns' variables during the iterative training process of a MultiLayer perceptron (MLP) neural network (NN). This paper improves the quality of such classifier by decorrelating the input variables via a Principal Component Analysis (PCA) transformation of the original input space before applying additive Gaussian noise to each transformed variable for each input pattern. PCA transformation prevents the conflicting effect of adding decorrelated noise to correlated variables, an effect which increases with the noise level. Three public data sets from a well-known benchmark (Proben1) were used to validate the proposed approach. Experimental results indicate that the proposed methodology improves the performance of the previous approach being statistically better than the traditional training method (95% confidence) in further experimental set-ups.","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":"129416689","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.2011.6033413
Vaibhav Gandhi, Vipul Arora, L. Behera, G. Prasad, D. Coyle, T. McGinnity
Brain-computer interface (BCI) technology is a means of communication that allows individuals with severe movement disability to communicate with external assistive devices using the electroencephalogram (EEG) or other brain signals. This paper presents an alternative neural information processing architecture using the Schrödinger wave equation (SWE) for enhancement of the raw EEG signal. The raw EEG signal obtained during the motor imagery (MI) of a BCI user is intrinsically embedded with non-Gaussian noise while the actual signal is still a mystery. The proposed work in the field of recurrent quantum neural network (RQNN) is designed to filter such non-Gaussian noise using an unsupervised learning scheme without making any assumption about the signal type. The proposed learning architecture has been modified to do away with the Hebbian learning associated with the existing RQNN architecture as this learning scheme was found to be unstable for complex signals such as EEG. Besides, this the soliton behaviour of the non-linear SWE was not properly preserved in the existing scheme. The unsupervised learning algorithm proposed in this paper is able to efficiently capture the statistical behaviour of the input signal while making the algorithm robust to parametric sensitivity. This denoised EEG signal is then fed as an input to the feature extractor to obtain the Hjorth features. These features are then used to train a Linear Discriminant Analysis (LDA) classifier. It is shown that the accuracy of the classifier output over the training and the evaluation datasets using the filtered EEG is much higher compared to that using the raw EEG signal. The improvement in classification accuracy computed over nine subjects is found to be statistically significant.
{"title":"EEG denoising with a recurrent quantum neural network for a brain-computer interface","authors":"Vaibhav Gandhi, Vipul Arora, L. Behera, G. Prasad, D. Coyle, T. McGinnity","doi":"10.1109/IJCNN.2011.6033413","DOIUrl":"https://doi.org/10.1109/IJCNN.2011.6033413","url":null,"abstract":"Brain-computer interface (BCI) technology is a means of communication that allows individuals with severe movement disability to communicate with external assistive devices using the electroencephalogram (EEG) or other brain signals. This paper presents an alternative neural information processing architecture using the Schrödinger wave equation (SWE) for enhancement of the raw EEG signal. The raw EEG signal obtained during the motor imagery (MI) of a BCI user is intrinsically embedded with non-Gaussian noise while the actual signal is still a mystery. The proposed work in the field of recurrent quantum neural network (RQNN) is designed to filter such non-Gaussian noise using an unsupervised learning scheme without making any assumption about the signal type. The proposed learning architecture has been modified to do away with the Hebbian learning associated with the existing RQNN architecture as this learning scheme was found to be unstable for complex signals such as EEG. Besides, this the soliton behaviour of the non-linear SWE was not properly preserved in the existing scheme. The unsupervised learning algorithm proposed in this paper is able to efficiently capture the statistical behaviour of the input signal while making the algorithm robust to parametric sensitivity. This denoised EEG signal is then fed as an input to the feature extractor to obtain the Hjorth features. These features are then used to train a Linear Discriminant Analysis (LDA) classifier. It is shown that the accuracy of the classifier output over the training and the evaluation datasets using the filtered EEG is much higher compared to that using the raw EEG signal. The improvement in classification accuracy computed over nine subjects is found to be statistically significant.","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":"129858078","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：