Driver Drowsiness Estimation from EEG Signals Using Online Weighted Adaptation Regularization for Regression (OwARR)

Abstract

One big challenge that hinders the transition of brain-computer interfaces (BCIs) from laboratory settings to real-life applications is the availability of high-performance and robust learning algorithms that can effectively handle individual differences, i.e., algorithms that can be applied to a new subject with zero or very little subject-specific calibration data. Transfer learning and domain adaptation have been extensively used for this purpose. However, most previous works focused on classification problems. This paper considers an important regression problem in BCI, namely, online driver drowsiness estimation from EEG signals. By integrating fuzzy sets with domain adaptation, we propose a novel online weighted adaptation regularization for regression (OwARR) algorithm to reduce the amount of subject-specific calibration data, and also a source domain selection (SDS) approach to save about half of the computational cost of OwARR. Using a simulated driving dataset with 15 subjects, we show that OwARR and OwARR-SDS can achieve significantly smaller estimation errors than several other approaches. We also provide comprehensive analyses on the robustness of OwARR and OwARR-SDS.

in press

References in corpus (4)

• Transfer Learning in Brain-Computer Interfaces
• Brain Computer Interface Technologies in the Coming Decades
• Transferring Subspaces Between Subjects in Brain-Computer Interfacing
• Switching EEG Headsets Made Easy: Reducing Offline Calibration Effort Using Active Weighted Adaptation Regularization

Cited by in corpus (23)

• Multi-channel EEG recordings during a sustained-attention driving task
• Transfer Learning for Motor Imagery Based Brain-Computer Interfaces: A Complete Pipeline
• Challenges of Driver Drowsiness Prediction: The Remaining Steps to Implementation
• A Fuzzy-set-based Joint Distribution Adaptation Method for Regression and its Application to Online Damage Quantification for Structural Digital Twin
• Adversarial Attacks and Defenses in Physiological Computing: A Systematic Review
• Alignment-Based Adversarial Training (ABAT) for Improving the Robustness and Accuracy of EEG-Based BCIs
• Transfer Learning for EEG-Based Brain-Computer Interfaces: A Review of Progress Made Since 2016
• Ultra Efficient Transfer Learning with Meta Update for Cross Subject EEG Classification
• Revisiting Euclidean Alignment for Transfer Learning in EEG-Based Brain-Computer Interfaces
• Transfer Learning for Brain-Computer Interfaces: A Euclidean Space Data Alignment Approach
• Adversarial Artifact Detection in EEG-Based Brain-Computer Interfaces
• Decoding Neural Activity to Assess Individual Latent State in Ecologically Valid Contexts
• Active Learning for Regression Using Greedy Sampling
• EEG-Based Driver Drowsiness Estimation Using Feature Weighted Episodic Training
• EEG-based Drowsiness Estimation for Driving Safety using Deep Q-Learning
• White-Box Target Attack for EEG-Based BCI Regression Problems
• Development of a Game with a Purpose for Acquisition of Brain-Computer Interface Data
• Multi-Tasking Genetic Algorithm (MTGA) for Fuzzy System Optimization
• Different Set Domain Adaptation for Brain-Computer Interfaces: A Label Alignment Approach
• Spatial Filtering for EEG-Based Regression Problems in Brain-Computer Interface (BCI)
• Manifold Embedded Knowledge Transfer for Brain-Computer Interfaces
• Active Semi-supervised Transfer Learning (ASTL) for Offline BCI Calibration
• On the Vulnerability of CNN Classifiers in EEG-Based BCIs