A Hybrid Hand-Crafted and Deep Neural Spatio-Temporal EEG Features Clustering Framework for Precise Emotional Status Recognition

Abstract

Human emotions are variant with time, non-stationary, complex in nature, and are invoked as a result of human reactions during our daily lives. Continuously detecting human emotions from one-dimensional EEG signals is an arduous task. This paper proposes an advanced signal processing mechanism for emotion detection from EEG signals using continuous wavelet transform. The space and time components of the raw EEG signals are converted into 2D spectrograms followed by feature extraction. A hybrid spatio-temporal deep neural network is implemented to extract rich features. A differential-based entropy feature selection technique adaptively differentiates features based on entropy, based on low and high information regions. Bag of Deep Features (BoDF) is applied to create clusters of similar features and computes the features vocabularies for reduction of feature dimensionality. Extensive experiments are performed on the SEED dataset, which shows the significance of the proposed method compared to state-of-the-art methods. Specifically, the proposed model achieved 96.7%, 96.2%, 95.8%, and 95.3% accuracy with the SJTU SEED dataset, for SVM, ensemble, tree, and KNN classifiers, respectively.

Wavelet Set Theory Enhanced Wavelet Entropy Clustering for Pattern Recognition

“…Researchers call this strategy "extract and classify". Wavelet entropy clustering (WEC) [9][10][11][12][13][14][15] is a wellestablished technique for this approach. It is a versatile technique used in various fields.…”

“…It is a versatile technique used in various fields. These fields include biomedical research [9,10], monitoring strategies [11,12], imaging [13], and fault detection [14,15]. It utilizes wavelets and entropy mathematical functions to analyze TS data.…”

“…This versatility makes WEC a valuable tool across diverse disciplines. Researchers applied WEC for tasks like classifying fish feeding sounds to identify species [26], detecting pavement damage through smartphone sensors [27], and even analyzing human emotions using neural networks [28]. WEC is also applicable to study communityacquired pneumonia [29,30,31] and identify pavement quality [32].…”