当前位置: X-MOL 学术Comput. Intell. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Analysis of real-time heartbeat monitoring using wearable device Internet of Things system in sports environment
Computational Intelligence ( IF 1.8 ) Pub Date : 2020-07-03 , DOI: 10.1111/coin.12337
Zhonghua Wang 1 , Zhonghe Gao 2
Affiliation  

Technology in the field of Internet of Things (IoT) with smartphones is enormously growing at a rapid pace for assisting people with their health conditions. Wearable sensors can provide real time data in the field of sports for monitoring the heartbeat of the athletes which can assist in physical activities. Heartbeat rate of the players change during different positions while playing sports and heartbeat monitoring will help the players to know the health condition thus improving the health of an individual. In this research, we propose a new method of wearable sensor device for collecting real time data of athletes using IoT-based system for monitoring electrocardiogram (ECG) patterns along with acceleration of body using smart phone and classify the obtained data using Radial-basis Function Network and Levenberg-Marquardt with Probabilistic Neural Network. The experimental setup of the proposed model performed using 100 persons and effectively classifies the data and predicts the heart rate with the precision of validation and training sample being 73.58% and 73.45 respectively. Thus the proposed IoT-based prediction system can be used to monitor health data of the athletes in real time as an alternate solution for monitoring physical health of the athletes.

中文翻译:

运动环境下可穿戴设备物联网系统实时心跳监测分析

智能手机物联网 (IoT) 领域的技术正在快速发展,以帮助人们改善健康状况。可穿戴传感器可以提供运动领域的实时数据,用于监测运动员的心跳,有助于体育活动。运动员在进行运动时,在不同位置的心跳率会发生变化,心跳监测有助于运动员了解健康状况,从而提高个人的健康水平。在这项研究中,我们提出了一种可穿戴传感器设备的新方法,用于使用基于物联网的系统收集运动员的实时数据,使用智能手机监测心电图 (ECG) 模式以及身体的加速度,并使用径向基函数网络和 Levenberg 对获得的数据进行分类- Marquardt 与概率神经网络。所提出模型的实验设置使用 100 人进行,有效地对数据进行分类并预测心率,验证和训练样本的精度分别为 73.58% 和 73.45。因此,所提出的基于物联网的预测系统可用于实时监测运动员的健康数据,作为监测运动员身体健康的替代解决方案。所提出模型的实验设置使用 100 人进行,有效地对数据进行分类并预测心率,验证和训练样本的精度分别为 73.58% 和 73.45。因此,所提出的基于物联网的预测系统可用于实时监测运动员的健康数据,作为监测运动员身体健康的替代解决方案。所提出模型的实验设置使用 100 人进行,有效地对数据进行分类并预测心率,验证和训练样本的精度分别为 73.58% 和 73.45。因此,所提出的基于物联网的预测系统可用于实时监测运动员的健康数据,作为监测运动员身体健康的替代解决方案。
更新日期:2020-07-03
down
wechat
bug