An intelligent emotion prediction system using improved sand cat optimization technique based on EEG signals.

Area of Science:

• Neuroscience
• Computer Science
• Artificial Intelligence

Background:

• Emotion recognition is crucial for advancing human-computer interaction (HCI).
• Electroencephalogram (EEG) signals offer a reliable measure of brain activity for emotion detection.
• Existing methods require improvement in prediction accuracy and efficiency.

Purpose of the Study:

• To develop an efficient and accurate emotion prediction method using EEG signals.
• To enhance the Sand Cat Optimization algorithm for improved performance in emotion recognition.
• To validate the proposed technique against established bio-inspired optimization algorithms.

Main Methods:

• An Improved Sand Cat Optimization (ISCO) technique was developed, incorporating a convex lens opposition-based learning strategy.
• The ISCO algorithm was applied to a dataset of 2132 labeled EEG signals across three emotional states.
• Performance was benchmarked against Practical Swarm Optimization (PSO), Artificial Rabbit Optimization (ARO), Artificial Bee Colony Optimization (ABCO), and Cat Optimization (CO).

Main Results:

• The proposed ISCO technique achieved a high prediction accuracy of 97.5%.
• ISCO demonstrated significant improvements over existing bio-inspired optimization algorithms in emotion prediction.
• The enhanced algorithm showed faster convergence towards target identification.

Conclusions:

• The ISCO technique presents a highly effective approach for emotion prediction from EEG signals.
• This advancement holds significant potential for applications in mental health monitoring, HCI, gaming, and affective computing.
• The study validates the superiority of the proposed ISCO method in enhancing emotion recognition systems.