TY - GEN
T1 - Adaptive Brain-Machine Interface of Brain-Controlled Vehicles Using Semi-MIM and TSVM
AU - Fei, Weijie
AU - Bi, Luzheng
AU - Zhang, Jingwei
N1 - Publisher Copyright:
© 2021 ACM.
PY - 2021/1/14
Y1 - 2021/1/14
N2 - Brain-machine interfaces (BMIs) have been developed for healthy individuals to control external devices. However, like all the existing BMIs, a time-consuming training process is required. To address this problem, a semi-supervised decoding framework is proposed to develop an adaptive BMI. The adaptive BMI is firstly initialized using a small labeled training set, and then increasingly adjusts itself by updating with newly collected unlabeled electroencephalogram (EEG) samples. The semi-supervised decoding framework starts with a semi-supervised mutual information maximization (semi-MIM) method to select optimal features and then uses the transductive support vector machine (TSVM) for classification. Experimental results show that the proposed semi-supervised framework performs better than other semi-supervised approaches and enables the adaptive BMI to catch up with the performance of the supervised learning-based BMI. Since the adaptive BMI uses a smaller training set, it can significantly reduce the training effort.
AB - Brain-machine interfaces (BMIs) have been developed for healthy individuals to control external devices. However, like all the existing BMIs, a time-consuming training process is required. To address this problem, a semi-supervised decoding framework is proposed to develop an adaptive BMI. The adaptive BMI is firstly initialized using a small labeled training set, and then increasingly adjusts itself by updating with newly collected unlabeled electroencephalogram (EEG) samples. The semi-supervised decoding framework starts with a semi-supervised mutual information maximization (semi-MIM) method to select optimal features and then uses the transductive support vector machine (TSVM) for classification. Experimental results show that the proposed semi-supervised framework performs better than other semi-supervised approaches and enables the adaptive BMI to catch up with the performance of the supervised learning-based BMI. Since the adaptive BMI uses a smaller training set, it can significantly reduce the training effort.
KW - Adaptive Brain Machine Interface
KW - Electroencephalogram
KW - Mutual Information Maximization
KW - Semi-Supervised Learning
KW - Surrogate Strategy
KW - Transductive support Vector Machine
UR - http://www.scopus.com/inward/record.url?scp=85101805237&partnerID=8YFLogxK
U2 - 10.1145/3448218.3448231
DO - 10.1145/3448218.3448231
M3 - Conference contribution
AN - SCOPUS:85101805237
T3 - ACM International Conference Proceeding Series
SP - 31
EP - 35
BT - Proceedings - 5th International Conference on Control Engineering and Artificial Intelligence, CCEAI 2021
A2 - Zhang, Dan
PB - Association for Computing Machinery
T2 - 5th International Conference on Control Engineering and Artificial Intelligence, CCEAI 2021
Y2 - 14 January 2021 through 16 January 2021
ER -