Abstract
Affective computing is concerned with simulating people’s psychological cognitive processes, of which emotion classification is an important part. Electroencephalogram (EEG), as an electrophysiological indicator capable of recording brain activity, is portable and non-invasive. It has emerged as an essential measurement method in the study of emotion classification. EEG signals are typically split into different frequency bands based on rhythmic characteristics. Most of machine learning methods combine multiple frequency band features into a single feature vector. This strategy is incapable of utilizing the complementary and consistent information of each frequency band effectively. It does not always achieve the satisfactory results. To obtain the sparse and consistent representation of the multi-frequency band EEG signals for emotion classification, this paper propose a multi-frequent band collaborative classification method based on optimal projection and shared dictionary learning (called MBCC). The joint learning model of dictionary learning and subspace learning is introduced in this method. MBCC maps multi-frequent band data into the subspaces of the same dimension using projection matrices, which are composed of a common shared component and a band-specific component. This projection method can not only make full use of the relevant information across multiple frequency bands, but it can also maintain consistency across each frequency band. Based on dictionary learning, the subspace learns the correlation between frequency bands using Fisher criterion and principal component analysis (PCA)-like regularization term, resulting in a strong discriminative model. The objective function of MBCC is solved by an iterative optimization algorithm. Experiment results on public datasets SEED and DEAP verify the effectiveness of the proposed method.
Highlights
Affective computing focuses on how to actively learn, reason, and perceive the surrounding world, as well as realize a certain level of brain-inspired cognitive intelligence by simulating people’s psychological cognitive processes (Aranha et al, 2019; Samsonovich, 2020)
Our previous work named as optimized projection and Fisher discriminative dictionary learning (OPFDDL) (Gu et al, 2021a) extracted multi-frequent band EEG features in the optimal sparse representation subspace, and adopted the Fisher discrimination criterion to build a discriminative classifier
Considering the information available in the original domain should not be lost in the projection space, we provide a regularization term similar to principal component analysis (PCA) that can retain discriminative knowledge to improve the discrimination ability of the model
Summary
Affective computing focuses on how to actively learn, reason, and perceive the surrounding world, as well as realize a certain level of brain-inspired cognitive intelligence by simulating people’s psychological cognitive processes (Aranha et al, 2019; Samsonovich, 2020). Liu et al (2020) developed a multi-level features guided capsule network to describe the internal relationship of multiple EEG signal channels The advantage of this model is that different levels of feature mapping are integrated during the process of forming the primary capsule, which can improve feature representation ability. Zhong et al (2020) proposed a regularized graph neural network to mine both local and global relationships between various EEG channels This method can alleviate the problem of time dependence in emotional process. Li et al (2018) used the hierarchical deep learning model to train numerous classifiers on EEG signals They verified that high-frequency bands played the most important role in emotion classification. Despite extensive research on the use of different frequency bands of EEG signals for emotion recognition, one traditional strategy is to directly concatenate features from
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
