首页|面向可穿戴式的基于LSTM神经网络的智能心音异常诊断芯片

面向可穿戴式的基于LSTM神经网络的智能心音异常诊断芯片

扫码查看
心血管疾病是造成全球死亡人数最多的疾病之一,因此对心血管疾病的预防与提前诊断至关重要.人工听诊技术与计算机心音诊断技术无法满足对心音长时间听诊的需求,因而可穿戴式听诊设备越来越受到关注,但是其具有高精度与低功耗的要求.该文设计了低功耗的面向可穿戴式的基于长短期记忆网络(Long Short-Term Memory,LSTM)的智能心音异常诊断芯片,提出了包括预处理、特征提取以及异常诊断的心音异常诊断系统,并搭建了基于听诊器的心音采集FPGA系统,采用了数据增强的方法解决数据集的不平衡问题.基于预训练模型设计了智能心音异常诊断芯片,在SMIC180 nm工艺下完成了版图设计和MPW流片.后仿真结果表明,智能心音异常诊断芯片的诊断准确率为98.6%,功耗为762 mW,面积为3.06 mm×2.45 mm,满足可穿戴式智能心音异常诊断设备的高性能与低功耗的需求.
Intelligent Heart Sound Abnormal Diagnosis Chip Based on LSTM for Wearable Applications
The gravity of cardiovascular disease hazards necessitates the utmost importance of preventive measures and early diagnosis for such ailments. Conventional manual auscultation techniques and computer-based diagnostic methods prove inadequate in meeting the demands of auscultation. Consequently, wearable devices attract increasing attention, but they are required to obtain both a high accuracy and low-power consumption. An intelligent heart sound abnormal diagnostic chip based on LSTM for wearable applications is presented. The abnormal heart sound diagnostic system is developed, including preprocessing, feature extraction, and abnormal diagnosis. Furthermore, an FPGA-based system for heart sounds acquisition is constructed. The challenge of imbalanced datasets is addressed through the implementation of data augmentation techniques. By utilizing pre-trained model as a foundation, the intelligent heart sound abnormal diagnostic chip is developed, and the layout and MPW are finished under SMIC 180nm. The post-simulation results demonstrate that the chip achieves a diagnostic accuracy of 98.6%, a power consumption of 762 mW,and an area of 3.06 mm × 2.45 mm, meeting the high-performance and low-power consumption prerequisites of wearable devices.

Wearable applicationsHeart soundAbnormal diagnosisLSTMLow-power

周维新、高肇岗、肖宛昂

展开 >

中国科学院半导体研究所 北京 100083

中国科学院大学集成电路学院 北京 100049

中国农业大学 北京 100083

可穿戴式 心音 异常诊断 长短期记忆网络 低功耗

中国科学院先导科技专项培育项目

XDPB22

2024

电子与信息学报
中国科学院电子学研究所 国家自然科学基金委员会信息科学部

电子与信息学报

CSTPCD北大核心
影响因子:1.302
ISSN:1009-5896
年,卷(期):2024.46(2)
  • 23