https://scholars.lib.ntu.edu.tw/handle/123456789/611568
標題: | Development of a motor imagery based brain-computer interface for humanoid robot control applications | 作者: | Prakaksita N. Kuo C.-Y. Kuo C.-H. CHUNG-HSIEN KUO |
關鍵字: | Anthropomorphic robots;Artificial intelligence;Biomedical signal processing;Electroencephalography;Induction motors;Interfaces (computer);Learning systems;Neural networks;Particle swarm optimization (PSO);Signal processing;Spectrum analysis;Brain computer interfaces (BCIs);Healthy subjects;Humanoid robot controls;Motor imagery;Neural network (nn);Off-line analysis;Power spectral analysis;Recognition accuracy;Brain computer interface | 公開日期: | 2016 | 卷: | 2016-May | 起(迄)頁: | 1607-1637 | 來源出版物: | Proceedings of the IEEE International Conference on Industrial Technology | 摘要: | This paper focuses on the developments of asynchronous motor imagery (MI) based brain-computer interfaces (BCIs) applications, signal processing and machine learning to provide some basic capabilities for consumer grade products. For the proposed MI detection technique, two channels of FC5 and FC6 according to 10-20 system over primary motor area are used to recognize 3 mental tasks of tongue, left hand and right hand movements. The amplitude features of EEG signals are extracted from power spectral analysis especially in mu rhythm (8-12 Hz) and low beta wave (12-16 Hz) bands. MI features were obtained from offline analysis, and then applied to neural network (NN) with particle swarm optimization (PSO). The classification paradigm then applied to real-time BCI for humanoid robot control applications in terms of recognized MI classes from subjects. According to the experiments of 45 trials for a healthy subject, the NN-based MI recognition accuracy with PSO is 91%. ? 2016 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-84974603464&doi=10.1109%2fICIT.2016.7475001&partnerID=40&md5=e078f4c1e96a49028a581f9783b48f3b https://scholars.lib.ntu.edu.tw/handle/123456789/611568 |
DOI: | 10.1109/ICIT.2016.7475001 |
顯示於: | 機械工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。