JSSC 2022第9期RF & WirelessNeural Interface

A 16-Channel Neural Recording System-on-Chip With CHT Feature Extraction Process

提出一种16通道神经记录SoC，采用CHT特征提取技术，显著降低数据传输率。

10-bit 20-kS/s

神经记录SoCCHT特征提取机器学习无线带宽效率

▸采用压缩Hadamard变换（CHT）处理器进行特征提取

▸通过机器学习算法优化特征选择，降低80%数据率

▸支持接收端波形重构用于监控或后处理

Abstract

Next-generation invasive neural interfaces require fully implantable wireless systems that can record from a large number of channels simultaneously. However, transferring the recorded data from the implant to an external receiver emerges as a signiﬁcant challenge due to the high throughput. To address this challenge, this article presents a neural recording system- on-chip that achieves high resource and wireless bandwidth efﬁciency by employing on-chip feature extraction. Energy–area- efﬁcient