Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Journal of Computer Networks, Architecture and High Performance Computing
Ramadhani, Daib Jidan
Unknown Affiliation
Computer Science & IT Education

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
APPLICATION OF K-NEAREST NEIGHBOUR, RECURSIVE ELIMINATION AND ADASYN ALGORITHMS ON DERMATITIS DISEASE CLASSIFICATION DATA Ramadhani, Daib Jidan; Siswa, Taghfirul Azhima Yoga; Pranoto, Wawan Joko
Journal of Computer Networks, Architecture and High Performance Computing Vol. 7 No. 3 (2025): Articles Research July 2025
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v7i3.6656

Abstract

Dermatitis is a common type of non-infectious skin disease frequently found in Indonesia. Its prevalence is influenced by several factors such as poor hygiene, environmental conditions, and climate change. Data from RSUD Jagakarsa recorded that from 1,066 skin disease cases between February 2023 and January 2024, approximately 62.2% were non-infectious, and 34.4% of those were classified as dermatitis. The diagnostic process for dermatitis is often challenging due to its symptom similarity with other skin conditions, leading to potential misclassification. Therefore, a more accurate and efficient classification approach is required to support medical professionals in identifying dermatitis cases effectively. This study proposes the use of a combination of machine learning methods: K-Nearest Neighbor (KNN) as the core classification algorithm, Recursive Feature Elimination (RFE) for feature selection, and Adaptive Synthetic Sampling (ADASYN) to handle class imbalance within the dataset. The data was sourced from UPTD Puskesmas Bontang Barat in 2024, consisting of 392 samples and 10 main features. Evaluation was conducted using a 10-fold cross-validation scheme. Results showed that the baseline KNN model achieved an average accuracy of 62.23%. With ADASYN applied, the accuracy improved to 63.56%, and further increased to 92.71% when combined with feature selection using RFE.
Co-Authors Tagfirul Azima Yoga Siswa, Muspidar Mulyadi Wawan Joko Pranoto