We present the implementation of seizure detection algorithms based on a minimal number of EEG channels on a parallel ultra-low-power embedded platform. The analyses are based on the CHB-MIT dataset, and include explorations of different classification approaches (Support Vector Machines, Random Forest, Extra Trees, AdaBoost) and different pre/post-processing techniques to maximize sensitivity while guaranteeing no false alarms. We analyze global and subject-specific approaches, considering all 23-electrodes or only 4 temporal channels. For 8s window size and subject-specific approach, we report zero false positives and 100% sensitivity. These algorithms are parallelized and optimized for a parallel ultra-low power (PULP) platform, enabling 300h of continuous monitoring on a 300 mAh battery, in a wearable form factor and power budget. These results pave the way for the implementation of affordable, wearable, long-term epilepsy monitoring solutions with low false-positive rates and high sensitivity, meeting both patient and caregiver requirements.

中文翻译：

---

通过可穿戴 EEG 设备实现对癫痫的长期无创监测

我们介绍了基于并行超低功耗嵌入式平台上最少数量的 EEG 通道的癫痫检测算法的实现。分析基于 CHB-MIT 数据集，包括对不同分类方法（支持向量机、随机森林、额外树、AdaBoost）和不同预处理/后处理技术的探索，以最大限度地提高灵敏度，同时保证没有误报。我们分析全局和特定主题的方法，考虑所有 23 个电极或仅 4 个时间通道。对于 8s 窗口大小和特定主题的方法，我们报告零误报和 100% 灵敏度。这些算法针对并行超低功耗 (PULP) 平台进行了并行化和优化，在可穿戴的外形和功率预算下，支持对 300 mAh 电池进行 300 小时的连续监控。