The research aimed to develop a web-based application using the certainty factor. The use of this certainty factor method allowed processing the data based on the degree of confidence from the experts and the users. The users inputted their symptoms each with the level of confidence. The inference engine drew some conclusions based on the matching process between the input and the rules in the knowledge-based. For every matching pair, the system would calculate the certainty factor. The knowledge-based was developed through discussion with three specialist physicians and literature in some previous studies. The evaluation of the system involved three specialists for validation testing and 51 respondents for BlackBox testing. The final result is displayed in the form of a percentage for each hepatitis type, explanation of first aid for hepatitis, and referral hospital for hepatitis patients. The result shows that the error rate in the diagnosis process is under 36%. Most of the respondents think that the quality of the system is good overall.

Basic Health Research data in 2018 show that around 95.5 percent of Indonesian people less consumption of fruit and vegetables. This condition then leads to the suspicion of vitamin and mineral deficiency in Indonesia people. Several methods have been used to detect vitamin and mineral deficiency, such as convolutional rule-based and certainty factor method. However, these methods are less adaptive to adapt to the changes in symptoms when detecting vitamin and mineral deficiencies. This paper proposes an artificial neural network (ANN) using backpropagation (BPN) to detect the vitamin and mineral deficiencies in the human body. Using 107 input of physical symptoms and 17 output of the type of vitamin and mineral, the architecture of the ANN consist of 107-50-17 neurons for the input layer, hidden layer, and output layer respectively. Based on some trial and error experiments, can be determined the epoch, the learning rate, and the error rate to produce the optimal result of the detection. This experiment using 623 epochs, 0.0517 error rate, and 0.1 for the learning rate. The performance measurement conducted using precision, recall, and F-score, for each class output. The experiment shows the proposed ANN using BPN reaches an accuracy level of 73%.

Salmonella bacterial infection often cause uncertainty during medical diagnostic phase. Two most common diseases caused by salmonella bacteria are typhus and diarrhea. This study aims to apply fuzzy inference system within medical diagnostic system so that the uncertainty of diagnostic process can be minimized. At first, a knowledge-based system was developed based on physician experience, containing 13 symptoms and 11 rules. Secondly, a web-based platform was designed as a media for physician and or patient to perform diagnostic process. Thirdly, an evaluation of the proposed system was conducted by using black box testing, white box testing, and error measurement via confussion matrix. This study found that by applying triangular membership function, Mamdani inference engine, and defuzzification centroid, the system was able to differenciate between typhus and diarrhea. Furthermore, the web-based medical diagnostic system showed an error rate of 0.3. In other words, the proposed fuzzy-based system was in line with the diagnostic result proposed by the physician.