Development of Urine Hydration System Based on Urine Color and Support Vector Machine

Abstract

Nowadays, to maintain hydration in human body has becoming an important issue in health research. The water needs depend on many factors like body size, dietary intake, gender and physical activity, consequently the indicator of hydration status is highly individual. Based on recent research that said the urine color is reliable indicator for hydration status, we would like to develop a prototype for detecting hydration status automatically. To use the color indicator precisely, we tested several color sensors to performance in detecting color and chose TCS34725 as the color sensor. The prototype of urine hydration system (UHS) is designed to record hydration status data in daily basis in cloud computing and the urine information can be accessed by Android smartphone. The prototype employs a set of microcontrollers and sensors as IoT devices and support vector machine (SVM) as a classifier. To evaluate the accuracy of hydration status, we compared the prediction with urine specific gravity (USG) as golden standard. The accuracy of our UHS prototype can reach up to 84%, which is nearly similar with the accuracy of manual prediction using only human eyes.