← Back to Publications List

BrainXAI-Net: An Interpretable Neural Framework for Spectro-Temporal EEG Emotion Recognition

Students & Supervisors

Student Authors
Hasin Almas Sifat
Bachelor of Science in Computer Science & Engineering, FST
Koushik Biswas Arko
Bachelor of Science in Computer Science & Engineering, FST
Md Anjir Jaman
Bachelor of Science in Computer Science & Engineering, FST
Supervisors
Md. Mortuza Ahmmed
Associate Professor, Faculty, FST

Abstract

Recognizing emotions via EEG waves is vital for affective computing and neuroadaptive systems. In this paper, we propose BrainXAI-Net, which is an interpretable neural model employing spectro-temporal EEG data and Local Interpretable Model-Agnostic Explanations (LIME) for post-hoc interpretation. We trained the model using 2,548 descriptors that were based on FFT, statistical, entropy, and quantile features for negative, neutral, and positive states. BrainXAI-Net attained an accuracy of 94% using a lightweight design. Using LIME with BrainXAINet, providers may read EEG markers in a geographically relevant fashion, establishing trust and transparency. BrainXAINet revealed increased interpretability and accuracy (+1.4%) than a GDESN-inspired model and offers a robust approach to ethically and openly detect emotions in brain-computer interface experiments.

Keywords

EEG Emotion Recognition Explainable AI Deep Learning Brain–Computer Interface LIME Spectrotemporal Features. EEG Emotion Recognition Explainable AI Deep Learning Brain–Computer Interface LIME Spectro-temporal Features.

Publication Details

  • Type of Publication:
  • Conference Name: IEEE International Conference on Biomedical Engineering, Computer and Information Technology for Health 2025 (BECITHCON 2025)
  • Date of Conference: 29/11/2025 - 29/11/2025
  • Venue: Eastern University, Dhaka, Bangladesh
  • Organizer: IEEE Bangladesh section and IEEE Engineering in Medicine and Biology Society Bangladesh
View on Publisher