A data partitioning method for increasing ensemble diversity of an eSVM-based P300 speller. (January 2018)

• Record Type: Journal Article
• Authors: Lee, Yu-Ri; Kim, Hyoung-Nam
• Is Part Of: Biomedical signal processing and control. Volume 39(2018)
• Page Start: 53
• Page End: 63
• Publication Date: 2018-01
• Subjects: Brain–computer interface -- EEG -- P300 speller -- Ensemble of SVMs -- Ensemble diversity; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2017.07.025
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: An ensemble method with increased diversity is applied to a P300 speller to achieve higher accuracy. We partition the training data into groups with the same distance to increase diversity. The proposed method improves the letter-typing speed in a P300 speller. Abstract: A P300 speller is a device for typing words by analysing the electroencephalogram (EEG) caused by visual stimuli. Among classifying methods used for the P300 speller, the ensemble of support vector machines (eSVM) is well known for achieving considerable classification accuracy. The eSVM is composed of linear support vector machines trained by each small part of the divided training data. To obtain an ensemble model with good accuracy, it is generally important that each classifier be as accurate and diverse as possible; diverse classifiers have different errors on a dataset. However, the conventional eSVM considers only an accuracy viewpoint of an individual classifier by clustering the homogeneous training data with similar noisy components. With such a viewpoint of diversity, we propose a dataset manipulation method to divide a training dataset into several groups with different characteristics for training each classifier. We reveal that the distance between a letter on which a subject is concentrating, and an intensified line on a visual keyboard, can generate EEG signals with different characteristics in a P300 speller. Based on this property, we partition the training data into groups with the same distance. If each individual SVM is trained using each of these groups, the trained classifiers have the increased diversity. The experimental results of a P300 speller show that the proposed eSVM with higher diversity improves the letter typing speed of the P300 speller. Specifically, the proposed method shows an average of 70% accuracy (verbal communication with the Language Support Program is possible at that level) by repeating the dataset for a single letter only four times.