Published: 2026-04-01

Expert System for Identifying Hardware Damage Using Naïve Bayes Method (Case Study: Computer Laboratory of Sepuluh Nopember University Papua)

DOI: 10.35870/ijsecs.v6i1.5400

No Cover Available
Article Metrics
Share:

Abstract

This research aims to design and implement an expert system based on the Naïve Bayes method to identify computer hardware failures in the Computer Laboratory of Universitas Sepuluh Nopember Papua. The laboratory operates approximately 40 computer units used daily by students across multiple study programs, yet is supported by only three technicians — a gap that frequently delays repairs and disrupts practical sessions. The system draws on a knowledge base covering 15 hardware failure categories and 11 observable symptoms, including failures in processors, memory/RAM, storage devices (HDD/SSD), and peripheral components such as keyboards, mice, and monitors. Development followed the Waterfall model, system design was documented using UML, the application was built with CodeIgniter, and evaluation was conducted through accuracy testing against expert diagnoses. Testing on 20 cases yielded a 75% accuracy rate, demonstrating that the system is capable of supporting technicians in accelerating the troubleshooting process, reducing dependence on manual inspection, and sustaining the quality of laboratory practice sessions for students

Keywords

Expert System; Naïve Bayes; Hardware Failure; Diagnosis; CodeIgniter

Peer Review Process

This article has undergone a double-blind peer review process to ensure quality and impartiality.

Indexing Information

Discover where this journal is indexed at our indexing page.

Open Science Badges

This journal supports transparency in research and encourages authors to meet criteria for Open Science Badges.

Most read articles by the same author(s)