Switching EEG Headsets Made Easy: Reducing Offline Calibration Effort Using Active Weighted Adaptation Regularization

Abstract

Electroencephalography (EEG) headsets are the most commonly used sensing devices for Brain-Computer Interface. In real-world applications, there are advantages to extrapolating data from one user session to another. However, these advantages are limited if the data arise from different hardware systems, which often vary between application spaces. Currently, this creates a need to recalibrate classifiers, which negatively affects people's interest in using such systems. In this paper, we employ active weighted adaptation regularization (AwAR), which integrates weighted adaptation regularization (wAR) and active learning, to expedite the calibration process. wAR makes use of labeled data from the previous headset and handles class-imbalance, and active learning selects the most informative samples from the new headset to label. Experiments on single-trial event-related potential classification show that AwAR can significantly increase the classification accuracy, given the same number of labeled samples from the new headset. In other words, AwAR can effectively reduce the number of labeled samples required from the new headset, given a desired classification accuracy, suggesting value in collating data for use in wide scale transfer-learning applications.

References in corpus (2)

• Brain Computer Interface Technologies in the Coming Decades
• Transferring Subspaces Between Subjects in Brain-Computer Interfacing

Cited by in corpus (24)

• A Survey on Negative Transfer
• Progress in Brain Computer Interfaces: Challenges and Trends
• Driver Drowsiness Estimation from EEG Signals Using Online Weighted Adaptation Regularization for Regression (OwARR)
• Transfer Learning for Motor Imagery Based Brain-Computer Interfaces: A Complete Pipeline
• Online and Offline Domain Adaptation for Reducing BCI Calibration Effort
• Adversarial Attacks and Defenses in Physiological Computing: A Systematic Review
• Ultra Efficient Transfer Learning with Meta Update for Cross Subject EEG Classification
• Transfer Learning for EEG-Based Brain-Computer Interfaces: A Review of Progress Made Since 2016
• Transfer Learning for Brain-Computer Interfaces: A Euclidean Space Data Alignment Approach
• Discriminative Joint Probability Maximum Mean Discrepancy (DJP-MMD) for Domain Adaptation
• Active Learning for Regression Using Greedy Sampling
• Active Stacking for Heart Rate Estimation
• Different Set Domain Adaptation for Brain-Computer Interfaces: A Label Alignment Approach
• Universal Adversarial Perturbations for CNN Classifiers in EEG-Based BCIs
• A Many Objective Optimization Approach for Transfer Learning in EEG Classification
• Multi-Tasking Genetic Algorithm (MTGA) for Fuzzy System Optimization
• Offline EEG-Based Driver Drowsiness Estimation Using Enhanced Batch-Mode Active Learning (EBMAL) for Regression
• Affect Estimation in 3D Space Using Multi-Task Active Learning for Regression
• Spatial Distillation based Distribution Alignment (SDDA) for Cross-Headset EEG Classification
• Agreement Rate Initialized Maximum Likelihood Estimator for Ensemble Classifier Aggregation and Its Application in Brain-Computer Interface
• Active Semi-supervised Transfer Learning (ASTL) for Offline BCI Calibration
• On the Vulnerability of CNN Classifiers in EEG-Based BCIs
• Active Learning for Black-Box Adversarial Attacks in EEG-Based Brain-Computer Interfaces
• Manifold Embedded Knowledge Transfer for Brain-Computer Interfaces