低功耗芯片实现癫痫发作提前8.4分钟预测，无需人工干预
SPIRIT: Low Power Seizure Prediction using Unsupervised Online-Learning and Zoom Analog Frontends
- 采用无监督在线学习算法，边端实时更新预测模型
- 平均灵敏度97.5%，特异性96.2%，提前8.4分钟预警
- 功耗仅17.2uW，面积0.14mm²，性能优于现有方案5.6倍以上
早期预测癫痫发作并及时干预对提升患者生活质量至关重要。尽管软件实现已验证预测可行性，但为降低延迟、实现及时预警，预测需在边缘设备上完成。理想设备应低功耗且能长期跟踪漂移，减少用户维护。本文提出SPIRIT：基于随机梯度下降的集成重训练与原位精度调优预测系统。SPIRIT是完整片上系统（SoC），集成8个14.4 uW、0.057 mm²、90.5 dB动态范围的Zoom模拟前端与无监督在线学习分类器。系统平均达97.5%敏感度/96.2%特异性，可提前8.4分钟预测发作。通过在线学习算法，预测准确率最高提升15%，预测时间延长最多7倍，无需外部干预。其分类器功耗17.2 uW，面积0.14 mm²，相较已有报道最低超134倍功耗和5倍面积。SPIRIT能效至少比当前最优方案高5.6倍。
原文摘要 · Abstract (English)
Early prediction of seizures and timely interventions are vital for improving patients' quality of life. While seizure prediction has been shown in software-based implementations, to enable timely warnings of upcoming seizures, prediction must be done on an edge device to reduce latency. Ideally, such devices must also be low-power and track long-term drifts to minimize maintenance from the user. This work presents SPIRIT: Stochastic-gradient-descent-based Predictor with Integrated Retraining and In situ accuracy Tuning. SPIRIT is a complete system-on-a-chip (SoC) integrating an unsupervised online-learning seizure prediction classifier with eight 14.4 uW, 0.057 mm2, 90.5 dB dynamic range, Zoom Analog Frontends. SPIRIT achieves, on average, 97.5%/96.2% sensitivity/specificity respectively, predicting seizures an average of 8.4 minutes before they occur. Through its online learning algorithm, prediction accuracy improves by up to 15%, and prediction times extend by up to 7x, without any external intervention. Its classifier consumes 17.2 uW and occupies 0.14 mm2, the lowest reported for a prediction classifier by >134x in power and >5x in area. SPIRIT is also at least 5.6x more energy efficient than the state-of-the-art.
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。