← 返回 JSSC 论文列表JSSC 2013第1期Memory0.18μmSRAMBiosignal
An 8-Channel Scalable EEG Acquisition SoC With Patient-Specific Seizure Classi fic
一款8通道可扩展EEG采集SoC，集成高动态范围AFE和机器学习分类处理器，用于癫痫发作检测。
0.18μm CMOS, 84.4%分类准确率, 2.03μJ/分类能效, 64KB SRAM存储120秒原始数据
EEG采集癫痫检测机器学习低功耗设计支持向量机
▸采用分布式Quad-LUT滤波器架构以最小化面积和开销
▸使用Chopper-Stabilized电容耦合仪表放大器实现低噪声
▸集成支持向量机分类器及实时增益带宽反馈控制
Abstract
An 8-channel scalable EEG acquis ition SoC is
presented to continuously det ect and record patient-speci fic
seizure onset activities from scalp EEG. The SoC integrates 8
high-dynamic range Analog Front-End (AFE )c h a n n e l s ,am a -
chine-learning seizure classification processor and a 64 KB SRAM.
The classi fication processor exploits the Distributed Quad-LUT
filter architecture to minimize the area w hile also minimizing the
overhead in . The AFE employs a Chopper-Stabi-
lized Capacitive Coupl