Learning with covariate shift-detection and adaptation in non-stationary environments : application to brain-computer interface

Raza, H; Cecotti, H; Li, Y; Prasad, G

Abstract

Learning in the presence of dataset shifts in non-stationary environments is a major challenge. Dataset shifts in the form of covariate shifts commonly occur in a broad range of real-world systems such as, electroencephalogram (EEG) based brain-computer interfaces (BCIs). Under covariate shifts, the properties of the input data distribution may shift over time from training to test/operating phase. In such systems, there is a need for continuous monitoring of the process behavior and tracking the state of the shifts to decide about initiating adaptation in a timely manner. This paper presents a covariate shift-detection and adaptation methodology, and its application to motor-imagery based BCIs. An exponential weighted moving average (EWMA) model based test is used for the covariate shift-detection in the features of EEG signals. The proposed algorithm initiates the adaptation by reconfiguring the knowledge-base of the classifier. Its performance is evaluated through experiments using a real-world dataset i.e. BCI Competition IV dataset 2A. Results show that the proposed method effectively performs covariate-shift-detection and adaptation and it can help to realize adaptive BCI systems.

Citation

Raza, H., Cecotti, H., Li, Y., & Prasad, G. (2015). Learning with covariate shift-detection and adaptation in non-stationary environments : application to brain-computer interface. In Proceedings of the International Joint Conference on Neural Networks (Article number 7280742). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IJCNN.2015.7280742

• Start Date: Jul 12, 2015
• End Date: Jul 17, 2015
• Publication Date: Jul 13, 2015
• Deposit Date: Jul 27, 2015
• Publisher: Institute of Electrical and Electronics Engineers
• Pages: Article number 7280742
• Book Title: Proceedings of the International Joint Conference on Neural Networks
• ISBN: 978147991964
• DOI: https://doi.org/10.1109/IJCNN.2015.7280742
• Publisher URL: http://dx.doi.org/10.1109/IJCNN.2015.7280742
• Related Public URLs: http://www.ijcnn.org/
• Additional Information: Additional Information : International Joint Conference on Neural Networks, IJCNN 2015; Killarney; Ireland; 12 July 2015 through 17 July 2015; Event Type : Conference