LiteNet: Lightweight Neural Network for Detecting Arrhythmias at Resource-Constrained Mobile Devices

Sensors

Ziyang He¹  Yangjie Cao¹  Xiaoqing Zhang¹  Xiaoyan Wang²  Zhi Liu³  Bo Zhang⁴ 

[1] Collaborative Innovation Center for Internet Healthcare, Zhengzhou University, 75 University North Road, Erqi District, Zhengzhou 450000, China;College of Engineering, Ibaraki University, 4-12-1 Nakanarusawa, Hitachi, Ibaraki 316-8511, Japan;Department of Mathematical and Systems Engineering, Shizuoka University, 5-627, 3-5-1 Johoku Hamamatsu 432-8561, Japan;School of Software Engineering, Zhengzhou University, 97 Culture Road, Jinshui District, Zhengzhou 450000, China;

关键词: deep learning algorithms;    lightweight neural network;    resource-constrained mobile devices;    electrocardiogram;   

DOI  :  10.3390/s18041229

来源: DOAJ

【 摘 要 】

By running applications and services closer to the user, edge processing provides many advantages, such as short response time and reduced network traffic. Deep-learning based algorithms provide significantly better performances than traditional algorithms in many fields but demand more resources, such as higher computational power and more memory. Hence, designing deep learning algorithms that are more suitable for resource-constrained mobile devices is vital. In this paper, we build a lightweight neural network, termed LiteNet which uses a deep learning algorithm design to diagnose arrhythmias, as an example to show how we design deep learning schemes for resource-constrained mobile devices. Compare to other deep learning models with an equivalent accuracy, LiteNet has several advantages. It requires less memory, incurs lower computational cost, and is more feasible for deployment on resource-constrained mobile devices. It can be trained faster than other neural network algorithms and requires less communication across different processing units during distributed training. It uses filters of heterogeneous size in a convolutional layer, which contributes to the generation of various feature maps. The algorithm was tested using the MIT-BIH electrocardiogram (ECG) arrhythmia database; the results showed that LiteNet outperforms comparable schemes in diagnosing arrhythmias, and in its feasibility for use at the mobile devices.

【 授权许可】

Unknown