Rizal Maulana, Dahnial Syauqy, Rint Zata Amani
The aim of the research is to present a design of early dehydration detection system by analyzing the urine condition. Dehydration is a condition that occurs when the body's organ function is disrupted caused by lack of fluid present in the human body. There are several causes of excessive fluid secretion which cause the body lack of fluid, including excessive sweating, burns, vomiting and diarrhea. There are three levels of dehydration: Mild, moderate and severe dehydration. Severe dehydration level can even cause death. Dehydration symptoms can be detected by various methods. One of them is by analyzing the urine condition. Urine condition has information related to dehydration detection: The color and odor of the urine. The higher level of dehydration experienced, the urine will be more concentrated and has a strong smell. In the proposed system, the color of urine was detected using a color sensor which provide urine color information in the form of RGB values. Meanwhile, the smell of urine is directly proportional to the levels of ammonia in the body and was detected by using an ammonia gas sensor that provides information on ammonia levels in the form of ppm values. In this research, testing is done by putting urine to be tested into a transparent test tube. The bottom part of the test tube is inserted into a black box which has been equipped with a color sensor to detect the color of the urine. While the top of the test tube is an open part, it is used to place the ammonia gas sensor to detect the ammonia levels in the urine. The dehydration level classification was done by using Naïve Bayes method. This method was chosen because it can work independently on each feature object that will be classified. The output features of each sensor became the input for Naïve Bayes classification. There were 66 datasets used in this research, 44 data as training data and 22 data as test data. From the test result, it can be seen that our proposed system has an accuracy of 95.45% in determining the level of dehydration based on urine condition. © 2017 Association for Computing Machinery.
Faculty of Computer Science, Brawijaya University, 8 Veteran Road, Malang, Indonesia
