2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB)最新文献

筛选

英文中文

Navigation in a virtual environment using multiclass motor imagery Brain-Computer Interface 基于多级运动图像脑机接口的虚拟环境导航

2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB) Pub Date : 2013-04-01 DOI: 10.1109/CCMB.2013.6609179

Z. Chin, K. Ang, C. Wang, Cuntai Guan

{"title":"Navigation in a virtual environment using multiclass motor imagery Brain-Computer Interface","authors":"Z. Chin, K. Ang, C. Wang, Cuntai Guan","doi":"10.1109/CCMB.2013.6609179","DOIUrl":"https://doi.org/10.1109/CCMB.2013.6609179","url":null,"abstract":"Virtual Reality is a useful platform for Brain-Computer Interface (BCI) users as it offers a relatively safe and cost-effective way for BCI users to train and familiarize themselves with using BCI in a virtual environment before using it in a real-world scenario. Hence this paper presents a pilot study of a virtual navigation task, where control signals from a synchronous multi-class motor imagery-based BCI (MI-BCI) is used by the subject to perform a navigation task in a 3D virtual environment, from a first-person perspective displayed on the computer screen. Preliminary results on one healthy subject showed that the MI-BCI was able to distinguish between 4 classes of motor imagery with an accuracy of about 67.5%, and the subject was able to navigate through the virtual environment in 87 trials in contrast to a theoretical minimum of 74 trials. Results from this study provide motivation to further investigate the potential of the MI-BCI in a larger-scale study, with the possibility of future clinical applications such as a training tool for users in BCI-based rehabilitation and other assistive technologies such as neural prosthetics or brain-controlled wheelchairs.","PeriodicalId":395025,"journal":{"name":"2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126614535","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}

引用次数: 7

Differential evolution with temporal difference Q-learning based feature selection for motor imagery EEG data 基于时间差分q学习的差分进化运动图像脑电特征选择

2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB) Pub Date : 2013-04-01 DOI: 10.1109/CCMB.2013.6609177

S. Bhattacharyya, P. Rakshit, A. Konar, D. Tibarewala, Swagatam Das, A. Nagar

{"title":"Differential evolution with temporal difference Q-learning based feature selection for motor imagery EEG data","authors":"S. Bhattacharyya, P. Rakshit, A. Konar, D. Tibarewala, Swagatam Das, A. Nagar","doi":"10.1109/CCMB.2013.6609177","DOIUrl":"https://doi.org/10.1109/CCMB.2013.6609177","url":null,"abstract":"Electroencephalograph (EEG) based Braincomputer Interface (BCI) research aims to decode the various movement related data generated from the motor areas of the brain. One of the issues in BCI research is the presence of redundant data in the features of a given dataset, which not only increases the dimensions but also reduces the accuracy of the classifiers. In this paper, we aim to reduce the redundant features of a dataset to improve the accuracy of classification. For this, we have employed Differential Evolution with Temporal Difference Q-Learning (DE-TDQL)-based clustering algorithm to reduce the features and have acquired their corresponding accuracy. Experiments with synthetic and real-world data provide evidence that such an approach leads to improved classification performance. Superiority of the new method is demonstrated by comparing it with three classification methods including Linear Discriminant Analysis, K-Nearest Neighbor and Support Vector Machine-Radial Basis Function. Self-Adaptive Differential Evolution, Differential Evolution/current-to-best/l, Particle Swarm Optimization and Genetic Algorithm-based clustering approaches have also been used here to study the relative performance of the proposed adaptive memetic algorithm-based clustering technique with respect to runtime and classification accuracy.","PeriodicalId":395025,"journal":{"name":"2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132372487","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}

引用次数: 5

Online feature selection for Brain Computer Interfaces 脑机接口的在线特征选择

2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB) Pub Date : 2013-04-01 DOI: 10.1109/CCMB.2013.6609175

G. Oliver, P. Sunehag, Tom Gedeon

{"title":"Online feature selection for Brain Computer Interfaces","authors":"G. Oliver, P. Sunehag, Tom Gedeon","doi":"10.1109/CCMB.2013.6609175","DOIUrl":"https://doi.org/10.1109/CCMB.2013.6609175","url":null,"abstract":"Online adaptation of Brain Computer Interfaces allows for arduous training periods to be circumvented. To do this we must adapt a classifier to a new session, or better yet, a new subject. We initially outline a procedure to perform online adaptation of both the classifier's weights and the feature selection and confirm its use in session to session transfer. We found that retraining both feature selection and the classifier resulted in an average improvement of 5% over simply retraining the classifier, and as high as 10%. To avoid a retraining phase the online adaptation must be performed without labeled data. We propose and compare several methods to adapt the feature selection on unlabeled data, making use of both semi-supervised learning and interactive error potentials. From this we determined that performing a weighted feature selection performed the best, and the proposed novel approach of combining semi-supervised learning and interactive error potentials outperformed performing each individually. To improve the subject to subject adaptation when a database of previous subjects is available, we investigated using Weighted Majority Voting to weight the classifier towards subjects in that database that are useful for the new subject. We found this approach to outperform pooling all data.","PeriodicalId":395025,"journal":{"name":"2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115842262","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}

引用次数: 2

首页上一页