WSEL: EEG feature selection with weighted self-expression learning for incomplete multi-dimensional emotion recognition
Abstract: Due to the small size of valid samples, multi-source EEG features with high dimensionality can easily cause problems such as overfitting and poor real-time performance of the emotion recognition classifier. Feature selection has been demonstrated as an effective means to solve these problems. Current EEG feature selection research assumes that all dimensions of emotional labels are complete. However, owing to the open acquisition environment, subjective variability, and border ambiguity of individual perceptions of emotion, the training data in the practical application often includes missing information, i.e., multi-dimensional emotional labels of several instances are incomplete. The aforementioned incomplete information directly restricts the accurate construction of the EEG feature selection model for multi-dimensional emotion recognition. To wrestle with the aforementioned problem, we propose a novel EEG feature selection model with weighted self-expression learning (WSEL). The model utilizes self-representation learning and least squares regression to reconstruct the label space through the second-order correlation and higher-order correlation within the multi-dimensional emotional labels and simultaneously realize the EEG feature subset selection under the incomplete information. We have utilized two multimedia-induced emotion datasets with EEG recordings, DREAMER and DEAP, to confirm the effectiveness of WSEL in the partial multi-dimensional emotional feature selection challenge. Compared to nine state-of-the-art feature selection approaches, the experimental results demonstrate that the EEG feature subsets chosen by WSEL can achieve optimal performance in terms of six performance metrics.
Primary Subject Area: [Engagement] Emotional and Social Signals
Relevance To Conference: Accurate identification of human affective states induced by multimedia plays an important role in applications such as multimedia assessment, grading, and clip optimization. Electroencephalogram (EEG) is a portable, non-traumatic technology for measuring brain activity that can react quickly to a range of affective states and has received extensive attention from the multimedia field and the brain-computer interface field. EEG-based affective computing applications, on the other hand, face the problems of feature dimension catastrophe and incomplete multi-dimensional labeling information, which greatly limit the field's development. To solve the problem, we conduct multi-dimension emotion recognition research under incomplete labels and propose a novel EEG feature selection method with missing multi-dimension affective labels. This research will help advance the use of brain-computer interfaces for multimedia content analysis. We hope that experts in the multimedia field will evaluate this research, leading to its eventual publication in ACM MM 2024.
Submission Number: 4786
Loading