M3D: Manifold-based Domain Adaptation with Dynamic Distribution for Non-Deep Transfer Learning in Cross-subject and Cross-session EEG-based Emotion Recognition

2024-04-24

AI Summary

To address severe domain shift, scarce labeled data, and high computational overhead of deep models in cross-subject and cross-session EEG-based emotion recognition, this paper proposes M3D—a lightweight, non-deep transfer learning framework. Methodologically, M3D introduces (1) a novel dynamic joint distribution alignment mechanism on the Grassmann manifold, simultaneously calibrating marginal and conditional distributions; and (2) an integrated pipeline combining manifold feature transformation, structural risk minimization-based classifier learning, and multi-stage ensemble—entirely without deep neural networks. Evaluated on three-way emotion classification, M3D achieves an average 4.47% accuracy gain over conventional non-deep methods, matching state-of-the-art deep models while drastically reducing data dependency and computational cost. Its efficacy is further validated on a real-world clinical dataset of major depressive disorder (MDD).

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Computer Vision: Multi-modal Vision

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

Abstract

Emotion decoding using Electroencephalography (EEG)-based affective brain-computer interfaces (aBCIs) plays a crucial role in affective computing but is limited by challenges such as EEG's non-stationarity, individual variability, and the high cost of large labeled datasets. While deep learning methods are effective, they require extensive computational resources and large data volumes, limiting their practical application. To overcome these issues, we propose Manifold-based Domain Adaptation with Dynamic Distribution (M3D), a lightweight, non-deep transfer learning framework. M3D consists of four key modules: manifold feature transformation, dynamic distribution alignment, classifier learning, and ensemble learning. The data is mapped to an optimal Grassmann manifold space, enabling dynamic alignment of source and target domains. This alignment is designed to prioritize both marginal and conditional distributions, improving adaptation efficiency across diverse datasets. In classifier learning, the principle of structural risk minimization is applied to build robust classification models. Additionally, dynamic distribution alignment iteratively refines the classifier. The ensemble learning module aggregates classifiers from different optimization stages to leverage diversity and enhance prediction accuracy. M3D is evaluated on two EEG emotion recognition datasets using two validation protocols (cross-subject single-session and cross-subject cross-session) and a clinical EEG dataset for Major Depressive Disorder (MDD). Experimental results show that M3D outperforms traditional non-deep learning methods with a 4.47% average improvement and achieves deep learning-level performance with reduced data and computational requirements, demonstrating its potential for real-world aBCI applications.

Problem

• EEG-based emotion recognition
• resource-efficient deep learning
• affective brain-computer interface (aBCI)

Innovation

• M3D Framework
• EEG Emotional Recognition
• Lightweight Learning