A 48.6-to-105.2µW machine-learning assisted cardiac sensor SoC for mobile healthcare monitoring

Author

Shu-Yu Hsu ; Yingchieh Ho ; Po-Yao Chang ; Pei-Yu Hsu ; Chien-Ying Yu ; Yuhwai Tseng ; Tze-Zheng Yang ; Ten-Fang Yang ; Chen, Ren-Jie ; ChauChin Su ; Chen-Yi Lee

Author_Institution

Dept. of Electron. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan

fYear

2013

fDate

12-14 June 2013

Abstract

A machine-learning (ML) assisted cardiac sensor SoC (CS-SoC) is designed for healthcare monitoring with mobile devices. The architecture realizes the cardiac signal acquisition with versatile feature extractions and classifications, enabling higher order analysis over traditional DSPs. Besides, the dynamic standby controller further suppresses the leakage power dissipation. Implemented in 90nm CMOS, the CS-SoC dissipates 48.6/105.2μW at 0.5-1.0V for real-time arrhythmia/myocardial infarction syndrome detection with 95.8/99% accuracy.

Keywords

CMOS integrated circuits; cardiology; health care; learning (artificial intelligence); medical signal processing; system-on-chip; CMOS; CS-SoC; arrhythmia infarction syndrome detection; cardiac sensor SoC; cardiac signal acquisition; dynamic standby controller; feature classification; feature extraction; leakage power dissipation; machine-learning; mobile device; mobile healthcare monitoring; myocardial infarction syndrome detection; power 48.6 muW to 105.2 muW; size 90 nm; voltage 0.5 V to 1.0 V; Clocks; Computer architecture; Feature extraction; Medical services; Monitoring; Program processors; System-on-chip;

fLanguage

English

Publisher

ieee

Conference_Titel

VLSI Circuits (VLSIC), 2013 Symposium on

Conference_Location

Kyoto

Print_ISBN

978-1-4673-5531-5

Type

conf

Filename

6578683