Design of Physical Fitness Training Management Device Based on IoT

• Main Authors: Lu Cheng Hsien, 呂政憲
• Other Authors: Dr. Yu-Xiang Zhao
• Format: Others
• Language: zh-TW
• Published: 2017
• Online Access: http://ndltd.ncl.edu.tw/handle/48428109722007134303

碩士 === 國立金門大學 === 理工學院工程科技碩士在職專班資訊系統組 === 105 === In recent years, many people in order to enhance the quality of life and promote health, they keen on marathon, cycling, and other outdoor sports. However, many accidents have followed with the development of exercise activities, such as heat stroke, heart disease, shock, lack of blood oxygen, etc. These accidents have made the exercise to promote health into a harm to the body. Therefore, how to ensure their body safety during exercise is an important issue. Many sensors that detect and alert human health come out with advances in technology. Through the integration of these sensors can be established to deal with injury procedures and exercise intensity control, while avoiding the occurrence of sports accidents and create safe exercise environment. With the popularity of wearable devices and internet of things (IoT), the combination of IoT with the function of the wearable devices development and applications of more and more widely. Although there are many wearing devices, such as heartbeat detecting bracelet and smart watches and other devices can detect personal physical fitness state, but the lack of the body in the state of exercise in the judgments and assessment. Therefore, this paper proposes a physical fitness training management device based on the IoT. The device is mainly through the sensor and the cloud monitoring platform to assist the subjects to implement physical fitness training management and control. The device can also be extended to training by the coach or manager of the way to implement a one-to-many training management and monitoring. The sensors in this device contains the risk factor, body temperature, heart rate and blood oxygen, we use the fuzzy theory to calculate and immediately show the physical fitness state of the subjects. In the system design and testing, we simulate the subjects in the training environment and sampling 100 of the simulated data, and through the system test and parameter adjustment to complete the physical fitness state determination algorithm. The experimental results show that the device achieves recognition rate of 94% and it can also effectively monitor and record different exercise intensity and physical fitness state under the environment. We hope that through this device, the subjects in the exercise can immediately reflect the intensity of training and dangerous warning to achieve the purpose of safety.