Author:
Fujita Kosuke, ,Touyama Hideaki
Abstract
In this study, a new method to realize majority rule is presented by using noninvasive brain activities. With the majority rule based on an electroencephalogram (EEG), a technique to determine the attention of multiple users is proposed. In general, a single-shot EEG ensures short-time response, but it is inevitably deteriorated by artifacts. To enhance the accuracy of the majority rule, the collaborative signals of P300 evoked potentials are focused. The collaborative P300 signal is prepared by averaging individual single-shot P300 signals among subjects. In experiments, the EEG signals of twelve volunteers were collected by using auditory stimuli. The subjects paid attention to target stimuli and no attention to standard stimuli. The collaborative P300 signal was used to evaluate the performance of the majority rule. The proposed algorithm enables us to estimate the degree of attention of the group. The classification is based on supervised machine learning, and the accuracy approximately 80%. The applications of this novel technique in multimedia content evaluations as well as neuromarketing and computer-supported co-operative work are discussed.
Publisher
Fuji Technology Press Ltd.
Subject
Artificial Intelligence,Computer Vision and Pattern Recognition,Human-Computer Interaction
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献