Yuanyuan Zhang1, Chienkai Wang2, Fangfang Wu3, Kun Huang4, Lijian Yang5, Linhong Ji6. 1. Center for Statistical Science and Department of Industrial Engineering, Tsinghua University, Beijing, 100084, China. Electronic address: yy-z17@mails.tsinghua.edu.cn. 2. Division of Intelligent and Biomechanical System, State Key Laboratory of Tribology, Department of Mechanical Engineering, Tsinghua University, Beijing, 100084, China. Electronic address: wjk17@mails.tsinghua.edu.cn. 3. Division of Intelligent and Biomechanical System, State Key Laboratory of Tribology, Department of Mechanical Engineering, Tsinghua University, Beijing, 100084, China. 4. Center for Statistical Science and Department of Industrial Engineering, Tsinghua University, Beijing, 100084, China. 5. Center for Statistical Science and Department of Industrial Engineering, Tsinghua University, Beijing, 100084, China. Electronic address: yanglijian@mail.tsinghua.edu.cn. 6. Division of Intelligent and Biomechanical System, State Key Laboratory of Tribology, Department of Mechanical Engineering, Tsinghua University, Beijing, 100084, China. Electronic address: jilh@tsinghua.edu.cn.
Abstract
BACKGROUND: There is always a demand for fast and accurate algorithms for EEG signal processing. Owing to the high sample rate, EEG signals usually come with a large number of sample points, making it difficult to predict the working memory ability in cognitive research with EEG. NEW METHOD: Following well-designed experiments, the functional linear model provides a simple framework for regressions involving EEG signal predictors. The use of a data-driven basis in a linear structure naturally extends the standard linear regression model. The proposed approach utilizes B-spline approximation of functional principal components that greatly facilitates implementation. RESULTS: Using LASSO feature selection, critical features have been extracted from eight frontal electrodes, and the R-square of 0.72 indicates rather strong linear association of actual observations and out-of-sample predictions. COMPARISON WITH EXISTING METHODS: There does not seem to be any existing methods of predicting working memory ability from N-back task tests via EEG signals; the data-driven functional linear regression method proposed in this work is, to the best of our knowledge, the first of its kind. CONCLUSIONS: The data analytics suggest that a multiple functional linear regression model for the predictive relationship between working memory ability and frontal activity of the brain is both feasible and accurate via EEG signal processing.
BACKGROUND: There is always a demand for fast and accurate algorithms for EEG signal processing. Owing to the high sample rate, EEG signals usually come with a large number of sample points, making it difficult to predict the working memory ability in cognitive research with EEG. NEW METHOD: Following well-designed experiments, the functional linear model provides a simple framework for regressions involving EEG signal predictors. The use of a data-driven basis in a linear structure naturally extends the standard linear regression model. The proposed approach utilizes B-spline approximation of functional principal components that greatly facilitates implementation. RESULTS: Using LASSO feature selection, critical features have been extracted from eight frontal electrodes, and the R-square of 0.72 indicates rather strong linear association of actual observations and out-of-sample predictions. COMPARISON WITH EXISTING METHODS: There does not seem to be any existing methods of predicting working memory ability from N-back task tests via EEG signals; the data-driven functional linear regression method proposed in this work is, to the best of our knowledge, the first of its kind. CONCLUSIONS: The data analytics suggest that a multiple functional linear regression model for the predictive relationship between working memory ability and frontal activity of the brain is both feasible and accurate via EEG signal processing.