What question did this study set out to answer?

To develop a framework for real-time emotion recognition from EEG signals using deep learning.

May 7, 2026Cognitive Computation2 citationsOpen Access

EmoDLNet: End-to-End Multi-Scale Spatio-Temporal Deep Learning for EEG-Based Emotion Recognition in Affective Human-Computer Interaction

MGM W GedaHong Kong Polytechnic University YTYuk Ming TangHong Kong Polytechnic University CLC.K.M. LeeHong Kong Polytechnic University

Key Points

To develop a framework for real-time emotion recognition from EEG signals using deep learning.
Proposed EmoDLNet framework combining CNNs and hierarchical GRUs
Evaluated on two datasets: DREAMER and SEED-V
DREAMER used for binary classification of arousal and valence
SEED-V used for multi-class emotion classification (happy, sad, fear, disgust, neutral)
Measured inference latency to ensure real-time capability.
Achieved 89.4% accuracy for arousal and 84.5% for valence on DREAMER
Outperformed state-of-the-art methods by 6.1% for arousal and 4.1% for valence
On SEED-V, average accuracy was 89.9%, with 96.1% for disgust and 93.6% for happy
Inferred with a latency of 67.10 ms per 1-second epoch for real-time applications.

Abstract

Abstract Real-time emotion recognition from EEG signals is crucial for enhancing user engagement in human-computer interaction (HCI) applications, yet extracting emotion-specific features remains a challenge. This paper proposes EmoDLNet, a deep learning framework combining convolutional neural networks (CNNs) and hierarchical gated recurrent units (GRUs) to automate feature extraction from raw EEG data for emotion classification. We evaluate EmoDLNet on two datasets: DREAMER for binary arousal/valence classification and SEED-V for multi-class (happy, sad, fear, disgust, and neutral) emotion classification. On DREAMER, EmoDLNet achieved 89.4% (arousal) and 84.5% (valence) classification accuracy, surpassing state-of-the-art methods by 6.1% and 4.1%, respectively. On SEED-V, the model demonstrated robust multi-class performance, with an average accuracy of 89.9%, including 96.1% for disgust and 93.6% for happy emotions, outperforming baseline methods. Furthermore, the model’s inference latency of 67.10 ms per 1-second epoch shows its capability to support real-time emotion classification, making it suitable for brain-computer interaction (BCI) and HCI applications.

AI से पूछें

Bookmark

View Full Paper