SPARK: A High-Efficiency Black-Box Domain Adaptation Framework for Source Privacy-Preserving Drowsiness Detection

• Published in: IEEE journal of biomedical and health informatics Vol. 28; no. 6; pp. 3478 - 3488
• Main Authors: Yuan, Liqiang, Li, Ruilin, Cui, Jian, Siyal, Mohammed Yakoob
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.06.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation; Adaptation models; Adult; Algorithms; Availability; Biomedical monitoring; Black-box domain adaptation (BBDA); Brain modeling; Closed box; Data models; Datasets; Deep Learning; Distillation; driver drowsiness detection; Driver fatigue; Drowsiness; EEG; Electroencephalography; Electroencephalography - methods; ensemble deep random vector functional link (edRVFL); Ensemble learning; Humans; Labelling; Labels; Monitoring; Privacy; Risk reduction; Signal Processing, Computer-Assisted; Sleep Stages - physiology; Sleepiness; Traffic accidents & safety; Traffic safety; Training; unsupervised domain adaptation (UDA)
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2024.3377373

Developing an effective and efficient electroencephalography (EEG)-based drowsiness monitoring system is crucial for enhancing road safety and reducing the risk of accidents. For general usage, cross-subject evaluation is indispensable. Despite progress in unsupervised domain adaptation (UDA) and source-free domain adaptation (SFDA) methods, these often rely on the availability of labeled source data or white-box source models, posing potential privacy risks. This study explores a more challenging setting of UDA for EEG-based drowsiness detection, termed black-box domain adaptation (BBDA). In BBDA, adaptation in the target domain relies solely on a black-box source model, without access to the source data or parameters of the source model. Specifically, we propose a framework called Self-distillation and Pseudo-labelling for Ensemble Deep Random Vector Functional Link (edRVFL)-based Black-box Knowledge Adaptation (SPARK). SPARK employs entropy-based selection of high-confidence samples, which are then pseudo-labeled to train a student edRVFL network. Subsequently, ensemble self-distillation is performed to extract knowledge by training the edRVFL using refined labels introduced by ensemble learning. This process further improves the robustness of the student edRVFL network. The features of the edRVFL are beneficial for improving the computational efficiency of the framework, making it more suitable for tasks involving small datasets. The proposed SPARK framework is evaluated on two publicly available driver drowsiness datasets. Experimental results demonstrate its superior performance over strong baselines, while significantly reducing training time. These findings underscore the potential for practical integration of the proposed framework into drowsiness monitoring systems, thereby contributing substantially to the privacy preservation of source subjects.