Progressive low-rank subspace alignment based on semi-supervised joint domain adaption for personalized emotion recognition

• Published in: Neurocomputing (Amsterdam) Vol. 456; pp. 312 - 326
• Main Authors: Luo, Junhai, Wu, Man, Wang, Zhiyan, Chen, Yanping, Yang, Yang
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 07.10.2021
• Subjects: Brain computer interface (BCI); EEG signals; Feature matching; Instance reweighting; Semi-supervised joint domain adaption (SSJDA); User-dependent emotion recognition; Semi-supervised joint domain adaption (SSJDA); Feature matching; Instance reweighting; EEG signals; User-dependent emotion recognition; Brain computer interface (BCI)
• ISSN: 0925-2312
• DOI: 10.1016/j.neucom.2021.05.064

•ER needs algorithms transfering knowledge of source subjects to a customized model.•User-dependent emotion recognition with PLRSA is a semi-supervised method.•PLRSA is the first to unify the instance reweighting and feature matching paradigm. Recently, many scenarios, such as affective disorders treatment, have sparked rising needs for establishment of personalized emotion recognition (PER) models. Unfortunately, the data sparsity issue violates the basic i.i.d. assumption of supervised learning (i.e., training data and test data are independently and identically distributed). In this paper, we present a semi-supervised joint domain adaption (SSJDA) solution, aiming to inject the hidden domain knowledge from ample labeled data of multiple source individuals into the target subject’s customized model. Specifically, we put forward a novel Progressive Low-Rank Subspace Alignment (PLRSA) approach, which unifies a semi-supervised instance-transfer paradigm and an unsupervised mapping-transfer learning paradigm in a single optimization framework. We leverage the boosting-based TrAdaBoost algorithm and the Transfer Component Analysis (TCA) algorithm for the implementation of instance reweighting and feature matching, respectively. Then we introduce the ℓ2,1- norm to pass feedback and make the joint learning feasible. The central idea is to progressively minimize the cross-domain distribution discrepancies to finally construct the optimal domain-invariant features. We systematically compare the PLRSA method with five state-of-the-art techniques using two public EEG datasets (DEAP and SEED). Both many-to-one and one-to-one evaluations are performed. The experimental results have confirmed the efficacy of the proposed method.