PlugSelect: Pruning Channels with Plug-and-Play Flexibility for Electroencephalography-based Brain Computer Interface

2025-04-11

AI Summary

To address hardware overhead and low inference efficiency caused by electrode channel redundancy in EEG-based brain–computer interfaces (BCIs), this paper proposes a zero-training-cost, plug-and-play channel pruning method. Leveraging global attribution analysis of input-path gradients, it enables unsupervised, cross-paradigm ranking of channel importance—identifying and retaining the most discriminative electrodes without model retraining. Channel contributions are quantified via backpropagated gradients to construct an optimal pruning sequence. Evaluated on three canonical BCI paradigms—auditory attention decoding, motor imagery, and affective computing—the method maintains original decoding accuracy while reducing channel count by over 50%, and significantly accelerates inference. To our knowledge, this is the first EEG channel optimization framework supporting immediate deployment without fine-tuning, offering an efficient, lightweight solution for practical BCI implementation.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Hardware-aware ML
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Automatic minimization and optimization of the number of the electrodes is essential for the practical application of electroencephalography (EEG)-based brain computer interface (BCI). Previous methods typically require additional training costs or rely on prior knowledge assumptions. This study proposed a novel channel pruning model, plug-and-select (PlugSelect), applicable across a broad range of BCI paradigms with no additional training cost and plug-and-play functionality. It integrates gradients along the input path to globally infer the causal relationships between input channels and outputs, and ranks the contribution sequences to identify the most highly attributed channels. The results showed that for three BCI paradigms, i.e., auditory attention decoding (AAD), motor imagery (MI), affective computation (AC), PlugSelect could reduce the number of channels by at least half while effectively maintaining decoding performance and improving efficiency. The outcome benefits the design of wearable EEG-based devices, facilitating the practical application of BCI technology.

Problem

• Minimizing EEG electrodes for practical BCI applications
• Eliminating training costs in channel pruning methods
• Maintaining performance while reducing channels in BCI

Innovation

• Plug-and-play channel pruning for EEG-BCI
• Gradient-based global causal channel ranking
• Halves channels while maintaining performance