Human body skin temperature prediction based on machine learning
- PDF / 1,469,525 Bytes
- 6 Pages / 595.276 x 790.866 pts Page_size
- 74 Downloads / 284 Views
ORIGINAL ARTICLE
Human body skin temperature prediction based on machine learning Shin Morishima1 · Yingjie Xu1 · Akira Urashima1 · Tomoji Toriyama1 Received: 15 April 2020 / Accepted: 7 August 2020 © International Society of Artificial Life and Robotics (ISAROB) 2020
Abstract Body temperature is one of the vital indicators that reflects the human body health. It is used to diagnose different types of diseases. Generally, there are two types of body temperatures: the skin and core temperature. The body temperature is used to diagnose some diseases by assessing its abnormality. The core temperature is primarily used for diagnosis as a clear standard is available. However, core temperature measurement requires minutes and places a strain on the subjects, whereas the skin temperature can be monitored real time and measured without contact. Because the skin temperature is affected by many factors, a definite standard to assess its abnormality does not exist. Herein, we propose a prediction method for the skin temperature based on machine learning. Each estimator of the machine learning is generated in restricted conditions to limit the factors handled by machine learning at once. The root mean square error of the prediction is 0.315 ℃, and the root mean square percentage error is 0.90%. The prediction result can be used as a standard for the anomaly detection of the skin temperature. Keywords Machine learning · Human skin temperature · Body temperature
1 Introduction Body temperature is one of the typical and vital health indicators that reflects the human body health. This tem‑ perature is used to diagnose different types of diseases, such as heatstroke and hypothermia. There are two types of the body temperatures: the skin and core temperature. The body temperature is used to diagnose some diseases by judging whether it is abnormal. The core temperature is primarily used for diagnoses as a clear standard is available. How‑ ever, core temperature measurement requires minutes and places a strain on the subjects when a clinical thermometer is This work was presented in part at the 25th International Symposium on Artificial Life and Robotics (Beppu, Oita, January 22–24, 2020). * Shin Morishima morisima@pu‑toyama.ac.jp Yingjie Xu [email protected]‑toyama.ac.jp Akira Urashima a‑urasim@pu‑toyama.ac.jp Tomoji Toriyama toriyama@pu‑toyama.ac.jp 1
used. Alternatively, multiple temperature sensors resembling wearable devices are attached on the body to monitor the temperature in real time. Therefore, the burden of attaching the sensors on the body is inevitable. Meanwhile, the skin temperature can be monitored in real time and without con‑ tact with a subject because it can be measured using a ther‑ mographic sensor. However, no standard exists for assessing whether the skin temperature is abnormal. A uniform stand‑ ard for the skin temperature is difficult to set as it is often affected by many factors including individual differences, activities, and environmental temperature. In this paper, we propose a skin temperature pr
Data Loading...
