Spike‐driven gated recurrent neural network processor for electrocardiogram arrhythmias detection realised in 55‐nm CMOS technology. Issue 23 (25th September 2020)

• Record Type: Journal Article
• Authors: Wu, Yuancong; Liu, Y.H.; Liu, Shuang; Yu, Q.; Chen, T.P.; Liu, Y.
• Is Part Of: Electronics letters. Volume 56:Issue 23(2020)
• Page Start: 1230
• Page End: 1232
• Publication Date: 2020-09-25
• Subjects: electrocardiography -- logic gates -- medical signal detection -- CMOS integrated circuits -- medical signal processing -- recurrent neural nets; CMOS technology -- logic gates -- spike‐driven gated recurrent neural network processor -- electrocardiogram arrhythmias detection -- asynchronous spike‐driven processor -- gated recurrent neural network algorithm -- electrocardiogram cardiac arrhythmias detection -- ECG detection model -- gated recurrent unit layer -- fully connected layer -- MIT‐BIH arrhythmia database -- power 6.28 mW -- frequency 200.0 MHz -- voltage 1.2 V -- frequency 1.0 kHz; Electronics -- Periodicals; 621.381
• DOI: 10.1049/el.2020.2224
• Languages: English
• ISSNs: 0013-5194

Abstract

Abstract : In this Letter, an asynchronous spike‐driven processor based on gated recurrent neural network algorithm for electrocardiogram (ECG) cardiac arrhythmias detection has been designed. Based on the processor, the proposed ECG detection model, containing a many‐to‐many gated recurrent unit layer and a fully connected layer, can achieve a high classification overall accuracy of 97.8% using the MIT‐BIH arrhythmia database. The processor was fabricated in 55‐nm 1P6M CMOS technology. It integrates about 1.4 million logic gates, including 40 KB of on‐chip memory within a 4.0 mm 2 die area. The test chip consumes 6.28 mW at real‐time operation frequency (200 MHz) with 1.2 V core supply voltage and 2.65 μ W at 1 kHz.