DistilCLIP-EEG: Enhancing Epileptic Seizure Detection Through Multi-modal Learning and Knowledge Distillation

脑电图 癫痫发作 计算机科学 情态动词 人工智能 癫痫 蒸馏 模式识别(心理学) 心理学 神经科学 材料科学 化学 色谱法 高分子化学
作者
Zexin Wang,Lin Shi,Haoyu Wu,Junru Luo,Xiangzeng Kong,Jun Qi
出处
期刊:IEEE Journal of Biomedical and Health Informatics [Institute of Electrical and Electronics Engineers]
卷期号:PP: 1-12 被引量:23
标识
DOI:10.1109/jbhi.2025.3603022
摘要

Epilepsy is a prevalent neurological disorder marked by sudden, brief episodes of excessive neuronal activity caused by abnormal electrical discharges, which may lead to some mental disorders. Most existing deep learning methods for epilepsy detection rely solely on unimodal EEG signals, neglecting the potential benefits of multimodal information. To address this, we propose a novel multimodal model, DistilCLIP-EEG, based on the CLIP framework, which integrates both EEG signals and text descriptions to capture comprehensive features of epileptic seizures. The model involves an EEG encoder based on the Conformer architecture as a text encoder, the proposed Learnable BERT (BERT-LP) as prompt learning within the encoders. Both operate in a shared latent space for effective cross-modal representation learning. To enhance efficiency and adaptability, we introduce a knowledge distillation method where the trained DistilCLIP-EEG serves as a teacher to guide a more compact student model to reduce training complexity and time. On the TUSZ, AUBMC, and CHB-MIT datasets, both the teacher and student models achieved accuracy rates exceeding 97%. Across all datasets, the F1-scores were consistently above 0.94, demonstrating the robustness and reliability of the proposed framework. Moreover, the student model's parameter count and model size are approximately 58.1% of those of the teacher model, significantly reducing model complexity and storage requirements while maintaining high performance. These results highlight the potential of our proposed model for EEG-based epilepsy detection and establish a solid foundation for deploying lightweight models in resource-constrained settings.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
ma发布了新的文献求助10
刚刚
栩栩完成签到,获得积分10
刚刚
bylee完成签到,获得积分10
刚刚
刚刚
1秒前
2秒前
2秒前
周周发布了新的文献求助10
2秒前
豪123完成签到,获得积分10
2秒前
超级大馒头完成签到,获得积分10
2秒前
兖州牧发布了新的文献求助30
2秒前
兖州牧发布了新的文献求助30
3秒前
兖州牧发布了新的文献求助30
3秒前
5秒前
跳跃的雯完成签到,获得积分10
5秒前
1234发布了新的文献求助10
6秒前
兖州牧发布了新的文献求助10
6秒前
6秒前
6秒前
7秒前
7秒前
7秒前
8秒前
yee完成签到 ,获得积分10
8秒前
8秒前
9秒前
周芷卉发布了新的文献求助10
9秒前
10秒前
10秒前
10秒前
11秒前
跳跃的雯发布了新的文献求助10
11秒前
11秒前
芋泥完成签到,获得积分10
12秒前
慕青的应助被nhzz2023采纳,获得10
12秒前
12秒前
12秒前
runrun发布了新的文献求助10
12秒前
runrun发布了新的文献求助10
12秒前
runrun发布了新的文献求助10
13秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183601
求助须知:如何正确求助?哪些是违规求助? 9572875
关于积分的说明 21827816
捐赠科研通 7780716
什么是DOI,文献DOI怎么找? 3434031
关于科研通互助平台的介绍 2558197
邀请新用户注册赠送积分活动 2480485