← 返回 JSSC 论文列表JSSC 2015第11期Other0.18µm
A 16-Channel Patient-Specific Seizure Onset and Termination Detection SoC With Impedance-Adaptive Transcranial Electrical Stimulator Muhammad Awais Bin Altaf, Student Member , IEEE, Chen Zhang, Student Member , IEEE, and Jerald Y oo,Senior Member , IEEE
一款16通道非侵入式闭环癫痫发作起止检测SoC，集成双通道电荷回收模拟前端和双检测器架构分类处理器。
0.18µm CMOS, 0.9µA/channel, NEF 3.29/channel, 2.45µW, 95.7%灵敏度, 98%特异性, 1s延迟
癫痫检测闭环系统模拟前端支持向量机经颅电刺激
▸双通道电荷回收（DCCR）模拟前端，实现放大器在双通道间同时斩波和时分复用
▸双检测器架构（D2A）分类处理器，采用基于数字滞后的线性支持向量机分类器
▸脉冲电压经颅电刺激器（PVTES），根据皮肤电极阻抗变化自动配置脉冲数以控制电荷量
Abstract
A 16-channel noninvasive closed-loop beginning- and end-of-seizure detection SoC is presented. The dual-channel charge recycled (DCCR) analog front end (AFE) achieves chop- ping and time-multiplexing an amplifier between two channels simultaneously which exploits fast-settling DC servo-loop with current consumption and NEF of 0.9 µA/channel and 3.29/chan- nel, respectively. The dual-detector architecture (D 2A) classifica- tion processor utilizes two linear support-vector machine (LSVM) classifiers based on digital hysteresis to enhance both the sen- sitivity and the specificity simultaneously. The pulsating voltage transcranial electrical stimulator (PVTES) automatically config- ures the number of pulses to control the amount of charge delivered based on skin-electrode impedance variation in efforts to suppress the seizure activity, while burning only 2.45 µW. The 25 mm 2 SoC implemented in 0.18 µm CMOS consumes 2.73 µJ/classification for 16 channels with an average sensitivity, specificity, and latency of 95.7%, 98%, and 1 s, respectively.