This Author published in this journals
All Journal POSITIF
Muh Syuaib
Fakultas Teknik, Jurusan Teknologi Informasi, Universitas Bosowa

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

Found 1 Documents
Search

MENDETEKSI KERUSAKAN JARINGAN INTERNET PADA CELEBES MEDIA JARINGAN (BNET) MENGGUNAKAN ALGORITMA FUZZY LOGIC DAN NAÏVE BAYES Sudirman; Muh Syuaib
POSITIF : Jurnal Sistem dan Teknologi Informasi Vol 9 No 1 (2023): Positif : Jurnal Sistem dan Teknologi Informasi
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/positif.v9i1.1640

Abstract

The use of cable internet service at home is often disrupted by problems or damage to the network. Not all cable internet service users understand how to solve problems on their internet network. While there are many ways to solve this problem, it often takes administrators and technicians a long time to find and fix the problem. Therefore, the purpose of this research is to develop an expert system that can detect and solve problems on the Celebes Media Network (Bnet) internet network. An expert system is a system that can store knowledge from an expert and use that knowledge to solve problems with the help of a computer. This expert system was created using the Fuzzy Logic method with Naive Bayes, where Fuzzy Logic can be used to change and transform the uncertainty of the value given by the user into a definite value, which is then processed and processed by Naive Bayes to calculate the weight of the user's answer. This method is particularly suitable for expert systems that require reliable safeguards to ensure the accuracy of defined values. The Expert System Development Life Cycle (ESDLC) method was used to develop this system. The benefit of this system is the ability to quickly and easily detect and solve problems on the internet network, which can assist administrators and technicians in dealing with problems on the network. The test results are then analyzed and optimized by administrators and technicians, resulting in an accuracy rate of 85% between the system and the original expert.