Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Jutisi: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Jurnal Bumigora Information Technology (BITe)
Ihsan, M Khaerul
Universitas Bumigora
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering

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

Found 2 Documents
Search

 1 
Perbandingan Algoritma Boosting Untuk Klasifikasi Gaya Belajar Siswa Sekolah Menengah Kejuruan Ihsan, M Khaerul; Saputri, Dian Syafitri Chani; Sulistianingsih, Neny
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol 14, No 2: Agustus 2025
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v14i2.2701

Abstract

Education is a planned activity to improve human resources. However, based on interviews at SMKN 2 Mataram, the learning process has not been running optimally because the teaching method is not in accordance with the student learning styles. This study aims to identify students learning styles (Visual, Auditory, and Kinesthetic) using the Boosting method, namely AdaBoost, Gradient Boosting, and XGBoost. Data were obtained from questionnaires that had been tested for validity and reliability, and distributed to 203 students in grades X and XI from the TKJ, RPL, and ULW department. The dataset was divided into tree schemes: 70:30, 80:20, and 90:10. The best result were obtainet from XGBoost in the 70:30 scheme with an accuracy of 0.93, precision of 1.00, recall of 0.97, anf f1-score of 0.97. GradentBoost followed with an accuracy of 0.92, while ADaBoost had the lowest accuracy of 0.80. thus, XGBoost is superior and can be used as a refence in determining learning methods according to student charateristics.Keywords: Boosting Algorithm; Classification; Learning Style; Algorithm Comparison AbstrakPendidikan merupakan aktivitas terencana untuk meningkatkan mutu sumber daya manusia. Namun, berdasarkan wawancara di SMKN 2 Mataram, proses pembelajaran belum berjalan optimal karena metode pengajaran tidak sesuai dengan gaya belajar siswa. Penelitian ini bertujuan untuk mengidentifikasi gaya belajar siswa (Visual, Auditori, dan Kinestetik) menggunakan metode Boosting, yaitu AdaBoost, Gradient Boosting, dan XGBoost. Data diperoleh dari kuesioner yang telah diuji validitas dan reliabilitasnya, dan disebarkan kepada 203 siswa kelas X dan XI dari jurusan TKJ, RPL, dan ULW. Dataset dibagi dalam tiga skema: 70:30, 80:20, dan 90:10. Hasil terbaik diperoleh dari XGBoost pada skema 70:30 dengan akurasi 0.93, precision 1.00, recall 0.97, dan f1-score 0.97. Gradient Boosting menyusul dengan akurasi 0.92, sedangkan ADaBoost memiliki akurasi terendah sebesar 0.80. Dengan demikian, XGBoost lebih unggul dan dapat dijadikan referensi dalam menentukan metode pembelajaran sesuai karakteristik siswa. 
Peningkatan Kinerja Klasifikasi Scabies Sapi MenggunakanEdited Nearest Neighbours (ENN) pada Model Random Forestdan XGBoost Ihsan, M. Khaerul; Maulana, Muhammad; Tanwir, Tanwir; Mas’ud, Abi; Hanif, Naufal; Resmiranta, Dading Oktaviadi
Jurnal Bumigora Information Technology (BITe) Vol. 7 No. 2 (2025)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/bite.v7i2.6055

Abstract

Background: Scabies disease in cattle causes significant economic losses for farmers due to declines in the animals’physical condition and productivity.Objective: This study aims to evaluate the effectiveness of the Edited Nearest Neighbours (ENN) method in improvingclassification performance for scabies in cattle.Methods: This research employs machine learning methods, including Random Forest and XGBoost. A dataset of 600clinical symptom samples was converted to numerical data and cleaned of noise using the ENN technique.Result: Applying ENN significantly improved the accuracy of both the Random Forest and XGBoost models, increasing itfrom around 0.60 to 0.91. In addition, both models achieved a perfect recall of 1.00, indicating maximum capability todetect positive cases.Conclusion: This study concludes that noise reduction using ENN can produce a more accurate and reliable diagnosticsystem. This method is highly recommended to optimize the performance of classification algorithms on animal clinicaldata with high levels of inconsistency. 
Co-Authors Mas’ud, Abi Muhammad Maulana Naufal Hanif Resmiranta, Dading Oktaviadi Saputri, Dian Syafitri Chani Sulistianingsih, Neny Tanwir, Tanwir