Sparse Logistic Regression With L1/2 Penalty for Emotion Recognition in Electroencephalography Classification

Abstract

Emotion recognition based on electroencephalography (EEG) signals is a current focus in brain-computer interface research. However, the classification of EEG is difficult owing to large amounts of data and high levels of noise. Therefore, it is important to determine how to effectively extract features that include important information. Regularization, one of the effective methods for EEG signal processing, can effectively extract important features from the signal and has potential applications in EEG emotion recognition. Currently, the most popular regularization technique is Lasso (L 1) and Ridge Regression (L 2). In recent years, researchers have proposed many other regularization terms. In theory, L q-type regularization has a lower q value, which means that it can be used to find solutions with better sparsity. L 1/2 regularization is of L q type (0 < q < 1) and has been shown to have many attractive properties. In this work, we studied the L 1/2 penalty in sparse logistic regression for three-classification EEG emotion recognition, and used a coordinate descent algorithm and a univariate semi-threshold operator to implement L 1/2 penalty logistic regression. The experimental results on simulation and real data demonstrate that our proposed method is better than other existing regularization methods. Sparse logistic regression with L 1/2 penalty achieves higher classification accuracy than the conventional L 1 , Ridge Regression, and Elastic Net regularization methods, using fewer but more informative EEG signals. This is very important for high-dimensional small-sample EEG data and can help researchers to reduce computational complexity and improve computational accuracy. Therefore, we propose that sparse logistic regression with the L 1/2 penalty is an effective technique for emotion recognition in practical classification problems.

Machine Learning-Based Three-Month Outcome Prediction in Acute Ischemic Stroke: A Single Cerebrovascular-Specialty Hospital Study in South Korea

“…Among the ML algorithms we applied, RLR showed the best performance. Regularization lowers the weight of the parameter to reduce the complexity of the dataset and prevent overfitting [23,24]. Thus, a linear model sometimes outperforms ensemble algorithms, such as RF and XGB [25,26].…”

Sparse Granger Causality Analysis Model Based on Sensors Correlation for Emotion Recognition Classification in Electroencephalography

“…On the basis of this idea, we proposed the model described in this article, using the known sensor correlations as prior knowledge to enhance the causality construction ability of the existing sparse Granger model. Based on the existing literature, we selected 16 emotion-related sensor channels and used the L 1/2 norm to remove artifacts in the data while retaining emotion-related information (Zheng and Lu, 2015;Zheng et al, 2017;Chen et al, 2020). Next, we calculated the similarity between sensors.…”

“…This means that the final feature extraction result is only related to the value of the EEG signal, and does not necessarily correspond to the emotional state. If we can quantify the correlation between each EEG sensor and emotion (Chen et al, 2020), and use this as a weight in the sparse Granger analysis model, the model's feature selection ability would be improved, further improving the model's classification ability. Under this idea, based on existing research, we propose a sparse Granger analysis model based on sensor correlation and the L 1/2 norm.…”

Sparse Logistic Regression-Based EEG Channel Optimization Algorithm for Improved Universality across Participants

“…Sparse logistic regression (SLR) [ 40 ] is a sparse classification model that can realize classifier training and feature selection simultaneously. Due to its parameter-free property and robustness against over-fitting, SLR has been widely applied for brain activity analysis, including EEG [ 41 , 42 , 43 , 44 ], fMRI [ 40 , 45 , 46 , 47 ], and cortical current source [ 48 , 49 ]. Inspired by the generalization performance of the effective classification method SLR [ 50 ], this study proposes an SLR-based EEG channel optimization algorithm.…”