Claim Missing Document
Check
Articles

Found 3 Documents
Search

Development of a Web-based Geographic Information System for Locating Medical Practices Aman, Andryanto; Wisda, Wisda; Syamsu, Suryadi; Nasir, Khaidir Rahman; Maslihatin, Tatik; Iqlimah, Magfirah Nur
Ceddi Journal of Information System and Technology (JST) Vol. 2 No. 1 (2023): April
Publisher : Yayasan Cendekiawan Digital Indonesia (CEDDI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56134/jst.v2i1.32

Abstract

This research aims to develop a Decision Support System (DSS) that can assist in selecting the best bus for tourism purposes in Toraja. The objective of this research is to facilitate the decision-making process for prospective tourists who want to use buses as their means of transportation during their visit to Toraja. The method employed in this research is the Weighted Product (WP) method. This method was chosen due to its ability to handle multiple criteria, enabling selection based on various relevant factors such as price, service quality, bus capacity, operational schedule, and level of comfort. Furthermore, the collected data will be input into the developed DSS using the WP method. The DSS will calculate relative scores for each bus based on the predetermined criteria weights. The results of this research are expected to provide objective and accurate recommendations for selecting the best bus. These recommendations can serve as a guide for prospective tourists in choosing a bus that suits their needs and preferences. Additionally, this research can also provide valuable insights for bus operators in improving service quality and customer satisfaction.
Enhancing Intrusion Detection Using Random Forest and SMOTE on the NSL‑KDD Dataset Saputra, Febri Hidayat; Ilham, Ilham; Rizal, Muhammad; Wisda, Wisda; Wanita, First; Mursalim, Mursalim; Fadillah, Arif
Journal of System and Computer Engineering Vol 6 No 3 (2025): JSCE: July 2025
Publisher : Universitas Pancasakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61628/jsce.v6i3.2056

Abstract

Intrusion Detection Systems (IDS) play a crucial role in identifying suspicious activities on computer networks. However, a major challenge in developing machine learning-based IDS is the issue of class imbalance, where attacks—being minority classes—are often overlooked by classification models. This study aims to construct an intrusion detection system based on the Random Forest algorithm integrated with the Synthetic Minority Over-sampling Technique (SMOTE) to address this problem. The NSL-KDD dataset is used for evaluation, with the data split into 80% for training and 30% for testing. Experiments include Random Forest-based feature selection and performance evaluation using accuracy, precision, recall, and F1-score metrics. The results show that the Random Forest–SMOTE combination achieves an accuracy of 99.78%, precision of 99.70%, recall of 99.88%, and an F1-score of 99.79%. The confusion matrix indicates a very low rate of false positives and false negatives. Additionally, selecting the most influential features such as src_bytes and dst_bytes improves model efficiency. Thus, the integration of Random Forest and SMOTE proves to be effective in enhancing detection sensitivity toward attacks without compromising model precision. This approach offers a significant contribution to the development of adaptive, accurate, and deployable IDS in real-world network environments.
Optimasi Prediksi Kelulusan Mahasiswa Menggunakan Random Forest untuk Meningkatkan Tingkat Retensi Sulehu, Marwa; Wisda, Wisda; Wanita, First; Markani, Markani
Jurnal Minfo Polgan Vol. 13 No. 2 (2024): Artikel Penelitian
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/jmp.v13i2.14472

Abstract

Penelitian ini bertujuan untuk mengembangkan model prediksi berbasis algoritma Random Forest guna mengidentifikasi mahasiswa yang berisiko putus kuliah di Universitas Teknologi AKBA Makassar, di mana tingginya angka putus kuliah menjadi tantangan signifikan yang disebabkan oleh berbagai faktor akademik, sosial-ekonomi, dan psikologis. Dengan pendekatan kuantitatif melalui metode data mining, data dari sistem informasi akademik dan survei primer, menggunakan 1.425 data mahasiswa yang diolah melalui tahap preprocessing dan dibagi menjadi 80% untuk pelatihan dan 20% untuk pengujian. Hasil penelitian menunjukkan bahwa IPK, motivasi belajar, dan kehadiran merupakan variabel paling signifikan dalam memprediksi kelulusan, dengan model prediksi yang mencapai akurasi 70% serta performa precision dan recall yang memadai. Penelitian ini memberikan kontribusi penting dalam mendukung pengambilan keputusan strategis di institusi pendidikan tinggi untuk meningkatkan tingkat retensi mahasiswa dan mengurangi angka putus kuliah, meskipun masih terdapat ruang untuk peningkatan kinerja model, khususnya dalam menangani ketidakseimbangan data.