31 July 2022 in JINAV: Journal of Information and Visualization
GWGentur Wahyu Nyipto Wibowo
Gentur Wahyu Nyipto Wibowo
This study aims to evaluate the performance of k-NN algorithm in recommending career paths for students based on their interests, past courses, and career goals. The k-NN algorithm was applied to a dataset of student information and its performance was evaluated using quantitative or qualitative measures such as accuracy or user satisfaction. The results indicated that the algorithm provided accurate recommendations and that the choice of k and the use of Euclidean distance measure were crucial for the performance of the algorithm. However, the study also highlighted the limitations of the research, such as the size and diversity of the dataset used, which could have affected the generalizability of the results. This study emphasizes the potential of data-driven approaches in career guidance in education and the k-NN algorithm as a valuable tool in this field. Future research could include incorporating additional factors such as student demographics or academic performance into the algorithm and using more diverse and larger datasets
29 July 2022 in JINAV: Journal of Information and Visualization
The equipment is not sterile when the health equipment is used repeatedly. Thus, it is at risk of infection. Data published by WHO reveals that one out of every ten hospital patients gets an infection. In developed countries, the number of infected hospital patients reaches 30%, while in developing countries it is at least 2-3 higher. One way to reduce the occurrence of infection is to sterilize medical equipment through a dry heat sterilization process at 1700 C for 60 minutes. The high price of sterilizers means that many health centers and clinics do not have this equipment. The aim of this study was to design a low-cost dry heat type health equipment sterilizer using fuzzy logic as a controller and evaluate the performance of the controller. Regarding to the research result, it indicated that the controller performance evaluation was very good with the highest overshoot value of 1.1%, the steady state error value was 1.1%, and the fastest rise time was 240 seconds.