Applied Computer Vision through Artificial Intelligence

8Synergizing Ensemble Learning Techniques for Robust Emotion Detection using EEG Signals

Pulkit Dwivedi¹*, Jasminder Kaur Sandhu² and Rakesh Sahu³

¹School of Computer Science Engineering & Technology, Bennett University, Greater Noida, India

²School of Computer Science and Engineering, IILM University, Greater Noida, India

³School of Computer Science Engineering and Technology (SCSET), Bennett University, Greater Noida, India

Abstract

Electroencephalography (EEG) serves as an essential method for capturing brain activity and is increasingly applied to detect and classify human emotions. Nevertheless, the inherent complexity and variability of EEG data pose considerable difficulties for conventional machine learning models. This chapter investigates the use of ensemble learning approaches, such as random forests, boosting, and extra trees, to enhance classification performance by improving accuracy, robustness, and generalization. The focus is on the rationale behind using ensemble learning techniques for EEG-based emotion detection. Ensemble methods, which aggregate multiple models to form a more precise and reliable classifier, are demonstrated to significantly surpass the performance of single models by reducing the impacts of noise and overfitting. Furthermore, the chapter delves into practical applications of these methods in fields such as mental health monitoring, adaptive human–computer interaction, and affective computing. By consolidating the latest advancements in ...