An ECG data sampling method for home-use IoT ECG monitor system optimization based on brick-up metaheuristic algorithm

Mathematical Biosciences and Engineering

Qun Song¹  Simon Fong²  Tengyue Li²  Feng Wu³ 

[1] 1. College of Artificial Intelligence, Chongqing Technology and Business University, Chongqing, China;2. Department of Computer and Information Science, University of Macao, Macao SAR, China;3. Zhuhai Institute of Advanced Technology (ZIAT), Chinese Academy of Science, Zhuhai, China;

关键词: ecg data sampling;    in-home iot monitoring system;    brick-up metaheuristic optimization algorithm;    long short-term memory networks;   

DOI  :  10.3934/mbe.2021447

来源: DOAJ

【 摘 要 】

With the rise in the popularity of Internet of Things (IoT) in-home health monitoring, the demand of data processing and analysis increases at the server. This is especially true for ECG data which has to be collected and analyzed continuously in real time. The data transmission and storage capacity of a simple home-use IoT system is often limited. In order to provide a responsive and reasonably high-resolution analysis over the data, the ECG recorder sampling rate must be tuned to an acceptable level such as 50Hz (compared to between 100Hz and 500Hz in lab), a huge amount of time series are to be gathered and dealt with. Therefore, a suitable sampling method that helps shorten the ECG data transformation time and uploading time is very important for cost saving.. In this paper, how to down sample the ECG data is investigated; instead of traditional data sampling methods, the use of a novel Brick-up Metaheuristic Optimization Algorithm (BMOA) that automatically optimizes the sampling of ECG data is proposed. By its adaptive design in choosing the most appropriate components, BMOA can build in real-time a best metaheuristic optimization algorithm for each device user assuming no two ECG data series are exactly identical. This dynamic pre-processing approach ensures each time the most optimal part of the ECG data series is harvested for health analysis from the raw data, in different scenarios from different users. In this study various application scenarios using real ECG datasets are simulated. The experimentation is tested with one of the most commonly used ECG classification methods, Long Short-Term Memory Network. The result shows the ECG data sampling by BMOA is indeed adaptive, the classification efficiency is improved, and the data storage requirement is reduced.

【 授权许可】

Unknown