An Advanced EEG based Human Emotion Detection with Giant Armadillo Optimization Algorithm

Emotion detection is the technique of determining the emotions for identifying the human mood or feelings. .In this Manuscript, Augmented Physics-Informed Neural Networks Optimized with Giant Armadillo Optimization Algorithm for Human Emotion Detection (APINN-GOA-HED) is proposed. First, data regarding human emotions is retrieved from the EEG dataset. Data-Adaptive Gaussian Average Filtering is used as a pre-processing technique to remove noise from collected data.Statistical characteristics such as RMS and variance are extracted using the High-Order synchro extracting transform (HSET) after pre-processed data has been exposed to feature extraction. The Augmented Physics-Informed Neural Network (APINN) is then fed the extracted features in order to efficiently categorize human emotions including happy, relaxed, disgusted, sad, and neutral. In general, the classifier of Augmented Physics-Informed Neural Networks does not exhibit the capability to modify optimization strategies in order to identify the ideal parameters for a system that accurately detects human emotions. Giant Armadillo Optimization is therefore suggested as a way to improve Augmented Physics-Informed Neural Networks, which correctly classify human emotions.The ROC analysis of the proposed APINN-GOA-HED approach is 0.87%, 0.88%, and 0.89% higher than that of the current methods, respectively.