Cross-Subject Emotion Recognition Based on Domain Similarity of EEG Signal Transfer Learning

For solving the problem of the inevitable decline in the accuracy of cross-subject emotion recognition via Electroencephalograph (EEG) signal transfer learning due to the negative transfer of data in the source domain, this paper offers a new method to dynamically select the data suitable for transfer learning and eliminate the data that may lead to negative transfer. The method which is called cross-subject source domain selection (CSDS) consists of the next three parts. 1) First, a Frank-copula model is established according to Copula function theory to study the correlation between the source domain and the target domain, which is described by the Kendall correlation coefficient. 2) The calculation method for the Maximum Mean Discrepancy is improved to determine the distance between classes in a single source. After normalization, the Kendall correlation coefficient is superimposed, and the threshold is set to identify the source-domain data most suitable for transfer learning. 3) In the process of transfer learning, on the basis of Manifold Embedded Distribution Alignment, the Local Tangent Space Alignment method is used to provide a low-dimensional linear estimation of the local geometry of nonlinear manifolds, which maintains the local characteristics of the sample data after dimensionality reduction. Experimental results show that compared with the traditional methods, the CSDS increases the accuracy of emotion classification by approximately 2.8% and reduces the runtime by approximately 65%.

• Publication year

  2023

• Venue

  IEEE transactions on neural systems and rehabilitation engineering

• Publication date

  2023-01-16

• Fields of study

  Medicine, Computer Science

• Identifiers
  DOI 10.1109/TNSRE.2023.3236687PMID 37021906
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Statistical Learning Theory

  2021influential reference
• Multisource Transfer Learning for Cross-Subject EEG Emotion Recognition

  2020cited by this paper
• Domain Selection of Transfer Learning in Fuzzy Prediction Models

  2019cited by this paper
• An EEG-based robot arm control to express human emotions

  2018cited by this paper
• Visual Domain Adaptation with Manifold Embedded Distribution Alignment

  2018influential reference
• Parameter estimation of copula functions using an optimization-based method

  2017cited by this paper
• Stratified Transfer Learning for Cross-domain Activity Recognition

  2017cited by this paper
• Balanced Distribution Adaptation for Transfer Learning

  2017cited by this paper
• Identifying Stable Patterns over Time for Emotion Recognition from EEG

  2016cited by this paper
• Personalizing EEG-Based Affective Models with Transfer Learning

  2016cited by this paper
• Investigating Critical Frequency Bands and Channels for EEG-Based Emotion Recognition with Deep Neural Networks

  2015cited by this paper
• Return of Frustratingly Easy Domain Adaptation

  2015cited by this paper
• Mathematical Risk Analysis

  2013cited by this paper
• Transfer Feature Learning with Joint Distribution Adaptation

  2013cited by this paper
• Emotional Recognition from Facial Expression Analysis Using Bezier Curve Fitting

  2013cited by this paper
• Differential entropy feature for EEG-based emotion classification

  2013cited by this paper
• Geodesic flow kernel for unsupervised domain adaptation

  2012cited by this paper
• Equivalence of distance-based and RKHS-based statistics in hypothesis testing

  2012cited by this paper
• Biographies or Blenders: Which Resource Is Best for Cross-Domain Sentiment Analysis?

  2012cited by this paper
• Domain Adaptation Using Domain Similarity- and Domain Complexity-Based Instance Selection for Cross-Domain Sentiment Analysis

  2012cited by this paper
• Do Neighbours Help? An Exploration of Graph-based Algorithms for Cross-domain Sentiment Classification

  2012cited by this paper
• Domain Adaptation via Transfer Component Analysis

  2009cited by this paper
• Grassmann discriminant analysis: a unifying view on subspace-based learning

  2008cited by this paper
• Integrating structured biological data by Kernel Maximum Mean Discrepancy

  2006cited by this paper
• Analysis of Representations for Domain Adaptation

  2006cited by this paper
• 2005 Special Issue: Emotion recognition in human-computer interaction

  2005cited by this paper
• Principal Manifolds and Nonlinear Dimension Reduction via Local Tangent Space Alignment

  2004cited by this paper
• An Introduction to Copulas

  2000cited by this paper
• An overview of statistical learning theory

  1999cited by this paper
• Fast Dimensionality Reduction and Simple PCA

  1998cited by this paper
• Pleasure, arousal, and dominance: Exploring affective determinants of recreation satisfaction

  1997cited by this paper
• An Analytic Approximation to the Distribution of Lilliefors's Test Statistic for Normality

  1986cited by this paper
• Fonctions de repartition a n dimensions et leurs marges

  1959cited by this paper

• How EEG-based cross-subject driving emotion is recognized: A multi-source transfer manifold learning model

  2026cites this paper
• Affective computing–driven virtual rehabilitation: a systematic survey

  2026cites this paper
• Local-Global Feature Fusion for Subject-Independent EEG Emotion Recognition

  2026cites this paper
• A Novel Approach to Pulse Coupling Analysis: Frank Copula Transfer Entropy for Finger–Wrist PPG Signals

  2026cites this paper
• EEG-Infinity: A Mathematical Modeling-Inspired Architecture for Addressing Cross-Device Challenges in Motor Imagery

  2025cites this paper
• EffortNet: A Deep Learning Framework for Objective Assessment of Speech Enhancement Technologies Using EEG-Based Alpha Oscillations

  2025cites this paper
• Recent Advances in Portable Dry Electrode EEG: Architecture and Applications in Brain-Computer Interfaces

  2025cites this paper
• A Progressive Multi-Domain Adaptation Network With Reinforced Self-Constructed Graphs for Cross-Subject EEG-Based Emotion and Consciousness Recognition

  2025cites this paper
• An enhanced filtering-dynamic matching-coordinated interaction framework for open-set fault diagnosis of rolling bearings

  2025cites this paper
• A survey of neural signal decoding based on domain adaptation

  2025cites this paper
• A dual-branch self-supervised contrastive learning framework for emotion recognition based on time-frequency fusion

  2025cites this paper
• Fine-grained label propagation via density-based prototype matching for cross-subject EEG emotion recognition

  2025cites this paper
• DAMSDAN: Distribution-Aware Multi-Source Domain Adaptation Network for Cross-Domain EEG-based Emotion Recognition

  2025cites this paper
• Investigation of Fatigue Mechanisms and Detection Methods for Anesthesiologists Based on Multimodal Physiological Signals.

  2025cites this paper
• Foundation models for EEG decoding: current progress and prospective research

  2025cites this paper
• HEDN: A Hard-Easy Dual Network with Source Reliability Assessment for Cross-Subject EEG Emotion Recognition

  2025cites this paper
• P2CSL: cross-subject EEG classification by subspace class prototype-based progressive confident target sample labeling

  2025cites this paper
• EmoEEG: A transferable generalist framework for EEG emotion recognition via information bottleneck theory

  2025cites this paper
• C2DGCN: cross-connected distributive learning-enabled graph convolutional network for human emotion recognition using electroencephalography signal

  2025cites this paper
• HEDN: A Hard-Easy Dual Network with Task Difficulty Assessment for EEG Emotion Recognition

  2025cites this paper
• Weight-freezing: A motor imagery inspired regularization approach for EEG classification

  2025cites this paper
• Multi-view domain adaption based multi-scale convolutional conditional invertible discriminator for cross-subject electroencephalogram emotion recognition

  2025cites this paper
• A Resource-Efficient Multi-Entropy Fusion Method and Its Application for EEG-Based Emotion Recognition

  2025cites this paper
• DISD-Net: A Dynamic Interactive Network With Self-Distillation for Cross-Subject Multi-Modal Emotion Recognition

  2025cites this paper
• Application of transfer learning for biomedical signals: A comprehensive review of the last decade (2014-2024)

  2025cites this paper
• Commonality and individuality based graph learning network for EEG emotion recognition

  2025cites this paper
• Multi-Source Reinforced Selective Domain Adaptation for Cross-Subject and Cross-Session EEG-Based Emotion Recognition

  2025cites this paper
• SASD-MCL: Semi-supervised alignment self-distillation with mixed contrastive learning for cross-subject EEG emotion recognition

  2025cites this paper
• Hybrid Multi-Branch Attention–CNN–BiLSTM Forecast Model for Reservoir Capacities of Pumped Storage Hydropower Plant

  2025cites this paper
• Adaptive dual-graph learning joint feature selection for EEG emotion recognition

  2025cites this paper
• MVC-former adaptation: A multi-view convolution transformer-based domain adaptation framework for cross-subject motor imagery classification

  2025cites this paper
• Spatiotemporal isomorphic cross-brain region interaction network for cross-subject EEG emotion recognition

  2025cites this paper
• Multi-view multi-scale adapter squeeze excitation network with domain generalization for cross-subject emotion recognition

  2025cites this paper
• Cross-Session EEG Classification Based on Domain Selection

  2025cites this paper
• Comparison of Domain Selection Methods for Multi-Source Manifold Feature Transfer Learning in Electroencephalogram Classification

  2024cites this paper
• A Survey of Machine Learning for Estimating Workload: Considering Unknown Tasks

  2024cites this paper
• Evolutionary Ensemble Learning for EEG-Based Cross-Subject Emotion Recognition

  2024cites this paper
• Advancing cross-subject olfactory EEG recognition: A novel framework for collaborative multimodal learning between human-machine

  2024cites this paper
• EEG-eye movement based subject dependence, cross-subject, and cross-session emotion recognition with multidimensional homogeneous encoding space alignment

  2024cites this paper
• Dynamic Stream Selection Network for Subject-Independent EEG-Based Emotion Recognition

  2024cites this paper
• Modality- and Subject-Aware Emotion Recognition Using Knowledge Distillation

  2024cites this paper
• Cross-Subject EEG-Based Emotion Recognition Using Deep Metric Learning and Adversarial Training

  2024cites this paper
• A study on the combination of functional connection features and Riemannian manifold in EEG emotion recognition

  2024cites this paper
• Towards Personalized Brain-Computer Interface Application Based on Endogenous EEG Paradigms

  2024cites this paper
• Domain adversarial learning with multiple adversarial tasks for EEG emotion recognition

  2024cites this paper
• Online multi-hypergraph fusion learning for cross-subject emotion recognition

  2024cites this paper
• Dual selections based knowledge transfer learning for cross-subject motor imagery EEG classification

  2023cites this paper
• Global Adaptive Transformer for Cross-Subject Enhanced EEG Classification

  2023cites this paper
• Self-supervised group meiosis contrastive learning for EEG-based emotion recognition

  2022cites this paper