A Two-Stage Efficient 3-D CNN Framework for EEG Based Emotion Recognition

TL;DR

This paper introduces a two-stage EEG-based emotion recognition framework using efficient and binarized CNN models, achieving high accuracy with minimal model size suitable for edge deployment.

Contribution

The paper presents a novel two-stage framework combining efficient EEGNet models and their binarized versions, significantly reducing model size while maintaining high accuracy.

Findings

EEGNet models achieve up to 99.5% accuracy with few parameters.

Binarized EEGNet models improve accuracy by 20% over baseline binary models.

Models enable precise emotion recognition on edge devices.

Abstract

This paper proposes a novel two-stage framework for emotion recognition using EEG data that outperforms state-of-the-art models while keeping the model size small and computationally efficient. The framework consists of two stages; the first stage involves constructing efficient models named EEGNet, which is inspired by the state-of-the-art efficient architecture and employs inverted-residual blocks that contain depthwise separable convolutional layers. The EEGNet models on both valence and arousal labels achieve the average classification accuracy of 90%, 96.6%, and 99.5% with only 6.4k, 14k, and 25k parameters, respectively. In terms of accuracy and storage cost, these models outperform the previous state-of-the-art result by up to 9%. In the second stage, we binarize these models to further compress them and deploy them easily on edge devices. Binary Neural Networks (BNNs) typically degrade model accuracy. We improve the EEGNet binarized models in this paper by introducing three novel methods and achieving a 20\% improvement over the baseline binary models. The proposed binarized EEGNet models achieve accuracies of 81%, 95%, and 99% with storage costs of 0.11Mbits, 0.28Mbits, and 0.46Mbits, respectively. Those models help deploy a precise human emotion recognition system on the edge environment.