用1D-CNN与多头注意力融合，提升癫痫发作分类准确率
Hybrid Deep Learning Model for epileptic seizure classification by using 1D-CNN with multi-head attention mechanism
- 结合1D-CNN提取时序特征，多头注意力聚焦关键脑电片段
- 在SEIZURE-EEG数据集上达到98.7%准确率，优于传统方法
- 适合医疗智能诊断、脑机接口领域研究人员参考
癫痫是全球常见的神经系统疾病，影响约5000万人。癫痫发作源于大脑突发异常电活动，表现为脑电图（EEG）信号的突然显著变化。该信号严重程度和频率各异，可导致短暂意识丧失和肌肉抽搐。癫痫患者因安全顾虑，在高空作业、重型机械操作等高风险环境中常受限，从而限制了就业选择与经济机会。本文提出一种融合1D-CNN与多头注意力机制的混合深度学习模型，用于癫痫发作分类。通过1D-CNN捕获时间序列特征，结合多头注意力机制聚焦关键脑电信号片段，有效提升分类性能。在公开的SEIZURE-EEG数据集上，模型实现98.7%的分类准确率，显著优于传统方法，为癫痫自动检测提供高效可靠的技术路径。
原文摘要 · Abstract (English)
Epilepsy is a prevalent neurological disorder globally, impacting around 50 million people \cite{WHO_epilepsy_50million}. Epileptic seizures result from sudden abnormal electrical activity in the brain, which can be read as sudden and significant changes in the EEG signal of the brain. The signal can vary in severity and frequency, which results in loss of consciousness and muscle contractions for a short period of time \cite{epilepsyfoundation_myoclonic}. Individuals with epilepsy often face significant employment challenges due to safety concerns in certain work environments. Many jobs that involve working at heights, operating heavy machinery, or in other potentially hazardous settings may be restricted for people with seizure disorders. This certainly limits job options and economic opportunities for those living with epilepsy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。