BRIDGE-EEG：桥接自监督预训练与高效部署用于跨数据集脑电图分类
BRIDGE-EEG: Bridging Self-Supervised Pretraining and Efficient Deployment for Cross-Dataset EEG Classification
浏览论文内容
中文总结 AI 辅助
提出BRIDGE-EEG高效多任务EEG分类流程，通过预训练教师模型蒸馏出紧凑学生模型，在保持准确率的同时显著降低边缘部署能耗，支持跨数据集分类。
中文摘要 AI 辅助
脑电图（EEG）的日益普及推动了准确、可迁移且能在资源受限硬件上部署的自动化分析需求。近期EEG基础模型通过大规模预训练学习通用表征，但其规模和计算成本限制了边缘和可穿戴设备的部署。我们提出BRIDGE-EEG，一种高效的多任务EEG分类流程，在保留预训练优势的同时减小模型规模。统一的预处理方案将具有不同通道数、导联设置和采样率的异构记录映射为设备无关的62通道时频表示。我们使用SimCLR在来自五个异构数据集的未标记EEG上预训练SE-ResNet18教师模型（11.84M参数），然后通过任务无关和任务特定蒸馏将其压缩为SE-ResNet8（1.56M）和SE-ResNet4（0.48M）学生模型。我们评估了涵盖异常检测、运动想象和情绪识别的六个基准。对于异常检测和情绪识别，学生模型达到了与近期多个EEG基础模型相当或更优的准确率，而这些基础模型的参数量是学生模型的10至1000倍。运动想象仍存在表征差距，凸显了预训练多样性的重要性。在服务器GPU、桌面CPU和NVIDIA Jetson Orin Nano上的推理性能分析显示，每次推理的边缘能耗降低高达3.0倍（15.64mJ对比46.67mJ）。紧凑模型进一步支持未来在MCU级可穿戴设备上的部署。
英文摘要
The growing use of electroencephalography (EEG) motivates automated analysis that is accurate, transferable, and deployable on constrained hardware. Recent EEG foundation models learn general representations from large-scale pretraining, but their size and computational cost limit edge and wearable deployment. We introduce BRIDGE-EEG, an efficient multi-task EEG classification pipeline that preserves the benefits of pretraining while reducing model size. A unified preprocessing scheme maps heterogeneous recordings with different channel counts, montages, and sampling rates to a device-agnostic 62-channel time--frequency representation. We pretrain an SE-ResNet18 teacher (11.84 M parameters) with SimCLR on unlabeled EEG from five heterogeneous datasets, then compress it into SE-ResNet8 (1.56 M) and SE-ResNet4 (0.48 M) students using task-agnostic and task-specific distillation. We evaluate six benchmarks spanning abnormality detection, motor imagery, and emotion recognition. For abnormality detection and emotion recognition, the students achieve accuracy comparable to or better than several recent EEG foundation models with 10--1,000$\times$ more parameters. Motor imagery shows a remaining representation gap, highlighting the importance of pretraining diversity. Inference profiling on a server GPU, desktop CPU, and NVIDIA Jetson Orin Nano shows up to 3.0$\times$ lower edge energy per inference (15.64 mJ vs. 46.67 mJ). The compact models further support future deployment on MCU-class wearables.
发表机构
- Purdue University（普渡大学）
- Case Western University（凯斯西储大学）
机构由 AI 辅助整理，请以论文原文为准。
