Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal International Journal Software Engineering and Computer Science (IJSECS)
Muhammad Farhan
Institut Sains dan Bisnis Atma Luhur
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Design of a Student Thesis Topic Recommendation System Using the K-Nearest Neighbor Algorithm Muhammad Farhan; Eza Budi Perkasa
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 2 (2026): AUGUST 2026
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i2.7659

Abstract

Determining the right thesis topic is a challenge for students because it is often not aligned with their abilities, interests, and experience, resulting in a less than optimal research process. This study aims to design a data-based thesis topic recommendation system using the K-Nearest Neighbor (KNN) algorithm. Data were collected through a questionnaire that measures three main aspects of students, namely abilities, interests, and experience in the fields of programming, web development, system security, and computer networks. Qualitative data were then converted into a numeric format using a Likert scale and binary values ​​to be processed as a classification dataset. The KNN algorithm was implemented with Euclidean Distance calculations and a majority voting mechanism using K = 3 and K = 5 values. System testing with a training and test data division ratio of 80:20 resulted in an accuracy rate of 80%. These results indicate that the system is able to provide relevant and objective topic recommendations according to student profiles. This study proves that a data-driven approach and the KNN algorithm can be an effective solution to support systematic academic decision-making.
Accuracy Testing of Laptop Damage Diagnosis Using Forward Chaining and Certainty Factor Algorithms Muhammad Farhan; Eza Budi Perkasa
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 2 (2026): AUGUST 2026
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i2.7726

Abstract

Laptops are widely used for educational and professional activities, but non-technical users often have difficulty identifying hardware problems, which can delay repairs and increase costs. This study developed and evaluated a web-based expert system for diagnosing laptop hardware damage using the Forward Chaining (FC) algorithm and the Certainty Factor (CF) method. The knowledge base consisted of 30 symptoms and 11 hardware damage categories derived from observations and interviews with professional laptop technicians. Accuracy testing was conducted using 20 test cases, consisting of 16 general user questionnaire cases and 4 technician-verified real-world cases. The diagnostic results generated by the system were compared with technician diagnoses as the reference. The hybrid FC-CF approach correctly diagnosed 15 of 20 cases, resulting in an accuracy of 75%, while standalone Forward Chaining correctly diagnosed 5 cases, resulting in an accuracy of 25%. The results indicate that the use of Certainty Factor allows the system to produce diagnoses when user-provided symptoms are incomplete or uncertain. The remaining incorrect diagnoses were associated with user subjectivity in assigning confidence levels and overlapping symptoms among hardware damage categories. Based on the test results, the developed system can be used as a preliminary diagnostic aid for laptop hardware problems and should not be considered a replacement for professional technician assessment.
Co-Authors Eza Budi Perkasa