通过结构化剪枝让脑电癫痫检测模型更轻更快，精度还提升。
Accuracy-Constrained CNN Pruning for Efficient and Reliable EEG-Based Seizure Detection
- 用重要性评估剪掉一半卷积核，保留关键特征提取能力。
- 剪枝后精度升至92.87%，宏F1达0.8707，推理效率显著提高。
- 适合资源受限的实时脑电监测场景，兼顾准确与可靠。
深度学习模型，尤其是卷积神经网络（CNN），在脑电图（EEG）癫痫检测等生物医学信号处理中展现出巨大潜力。然而，这些模型因体积大、计算量高，在需要实时检测或资源受限的环境中面临挑战。本文提出一种轻量级一维CNN模型，结合结构化剪枝以提升效率与可靠性。模型采用温和早停策略训练，达到92.78%的准确率和0.8686的宏F1分数。通过对基线CNN进行结构化剪枝，基于对预测的重要性移除50%的卷积核。令人惊讶的是，尽管权重和内存减少50%，新网络仍保持预测能力，精确度提升至92.87%，宏F1增至0.8707。结果表明，结构化剪枝可消除冗余，增强泛化能力，结合温和早停，为提高癫痫检测的效率与可靠性提供可行路径，特别适用于资源受限环境。
原文摘要 · Abstract (English)
Deep learning models, especially convolutional neural networks (CNNs), have shown considerable promise for biomedical signals such as EEG-based seizure detection. However, these models come with challenges, primarily due to their size and compute requirements in environments where real-time detection or limited resources are available. In this study, we present a lightweight one-dimensional CNN model with structured pruning to improve efficiency and reliability. The model was trained with mild early stopping to address possible overfitting, achieving an accuracy of 92.78% and a macro-F1 score of 0.8686. Structured pruning of the baseline CNN involved removing 50% of the convolutional kernels based on their importance to model predictions. Surprisingly, after pruning the weights and memory by 50%, the new network was still able to maintain predictive capabilities, while modestly increasing precision to 92.87% and improving the macro-F1 score to 0.8707. Overall, we present a convincing case that structured pruning removes redundancy, improves generalization, and, in combination with mild early stopping, achieves a promising way forward to improve seizure detection efficiency and reliability, which is clear motivation for resource-limited settings.
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。