Article Per Year (5 Year)
p-Index From 2021 - 2026
0.778
P-Index
This Author published in this journals
All Journal Progresif: Jurnal Ilmiah Komputer Jatilima : Jurnal Multimedia Dan Teknologi Informasi Jurnal Sistem Komputer dan Informatika (JSON) Jurnal Manajemen Informatika, Sistem Informasi dan Teknologi Komputer (JUMISTIK)
Arif, M Aidil
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Electrical & Electronics Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Prediksi Pergerakan Harga Ethereum Menggunakan Machine Learning dengan Algoritma Random Forest dan XGBoost Girinata, I Made Candra; Styawan, Budi; Saputra, Arwin Wahyu; Arif, M Aidil; Dahur, Arnoldus Janssen
Jurnal Manajemen Informatika, Sistem Informasi dan Teknologi Komputer (JUMISTIK) Vol 4 No 2 (2025): Jurnal Manajemen Informatika, Sistem Informasi dan Teknologi Komputer (JUMISTIK)
Publisher : STMIK Amika Soppeng

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70247/jumistik.v4i2.222

Abstract

ABSTRAK Perkembangan aset kripto yang pesat, khususnya Ethereum, menuntut adanya model prediksi harga yang akurat untuk mendukung strategi investasi dan manajemen risiko. Penelitian ini bertujuan untuk menganalisis dan membandingkan kinerja dua algoritma machine learning ensemble, yaitu Random Forest (RF) dan XGBoost, dalam memprediksi harga harian Ethereum. Dataset historis ETH/USD sebanyak 3.423 observasi dari periode September 2016 hingga Juli 2025 diperoleh dari platform Bitfinex. Setelah melalui tahap pra-pemrosesan data dan rekayasa fitur temporal, dataset dibagi dengan rasio 80:20 untuk pelatihan dan pengujian. Model dievaluasi menggunakan metrik Root Mean Square Error (RMSE) dan Koefisien Determinasi (R²). Hasil eksperimen menunjukkan bahwa XGBoost secara signifikan mengungguli Random Forest, dengan nilai RMSE 134.63 dan R² 0.958. Sebagai perbandingan, Random Forest menghasilkan RMSE 208.45 dan R² 0.899. Temuan ini mengindikasikan bahwa mekanisme boosting pada XGBoost lebih efektif dalam menangkap kompleksitas dan volatilitas data pasar kripto. Kata kunci: Prediksi Harga, Ethereum, Machine Learning, XGBoost, Random Forest.
Analyzing ChatGPT Impact on Student Productivity in Information Technology Program at Politeknik Negeri Tanah Laut Hafizd, Khairul Anwar; Manalu, Mamed Rofendi; Arif, M Aidil
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 7 No. 2 (2025): Desember 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v7i2.9495

Abstract

The rapid development of generative artificial intelligence, particularly ChatGPT, has transformed the way students complete academic tasks, especially in the field of Information Technology. Despite its widespread adoption, concerns remain regarding its impact on students’ productivity and learning quality. This study aims to analyze the effect of ChatGPT usage on the productivity of students in the Information Technology Study Program at Politeknik Negeri Tanah Laut. A quantitative research approach with a survey method was employed. Data were collected through a Likert-scale questionnaire distributed to active students who had used ChatGPT for academic purposes. The collected data were analyzed using validity and reliability tests, followed by simple linear regression analysis to examine the effect of ChatGPT usage on student productivity. The results indicate that ChatGPT usage has a positive and significant effect on student productivity. Productivity improvements are mainly observed in task efficiency and timely task completion. However, the quality of academic outputs remains highly dependent on students’ ability to critically evaluate, verify, and further develop the outputs generated by ChatGPT. These findings suggest that ChatGPT functions effectively as an academic assistant rather than a substitute for critical thinking and independent learning. This study concludes that ChatGPT can be utilized as a supportive academic tool to enhance student productivity when used appropriately and responsibly, supported by adequate AI literacy and academic supervision. The findings are expected to provide empirical insights for higher education institutions in formulating policies and guidelines for the ethical and productive use of ChatGPT in academic activities.
Implementasi Backpropagation Neural Network pada Sistem Electronic Nose untuk Klasifikasi Aroma Teh Arif, M. Aidil; Hidayat, Muhammad; Ridhani, M. Fadli
Progresif: Jurnal Ilmiah Komputer Vol 22, No 1 (2026): Januari
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/progresif.v22i1.3482

Abstract

Conventional tea aroma quality assessment is subjective and slow. This study aims to design and implement an Arduino Uno-based automatic Electronic Nose (e-nose) system with a TGS sensor array (880, 826, 822, 825) combined with a Backpropagation Neural Network (BPNN) for tea aroma classification. The method includes signal acquisition, normalization, feature extraction, and sensor correlation analysis to form a chemical fingerprint before modeling. Testing with a confusion matrix on three types of tea (black, green, and jasmine) showed performance with an accuracy of 0.71, precision of 0.71, recall of 0.72, and f-measure of 0.71. The results of this study provide an objective, fast, economical, and non-destructive aroma evaluation method and contribute to the development of smart sensor technology to support the competitiveness of Indonesian tea products. The main novelty of this study is the integration of sensor correlation analysis into the modeling pipeline with an end-to-end classification system that combines sensor correlation analysis to optimize the performance of the BPNN model on the tea aroma dataset.Keywords: Arduino; Tea Aroma; Backpropagation; Electronic Nose; TGS Sensor AbstrakPenilaian mutu aroma teh secara konvensional bersifat subjektif dan lambat. Penelitian ini bertujuan merancang dan mengimplementasikan sistem Electronic Nose (e-nose) otomatis berbasis Arduino Uno dengan array sensor TGS (880, 826, 822, 825) yang dikombinasikan Backpropagation Neural Network (BPNN) untuk klasifikasi aroma teh. Metode mencakup akuisisi sinyal, normalisasi, ekstraksi fitur, dan analisis korelasi sensor untuk membentuk chemical fingerprint sebelum pemodelan. Pengujian dengan confusion matrix pada tiga jenis teh (hitam, hijau, wangi melati) menunjukkan performa dengan akurasi 0,71, presisi 0,71, recall 0,72, dan f-measure 0,71. Hasil penelitian memberikan metode evaluasi aroma yang objektif, cepat, ekonomis, dan non destruktif, serta berkontribusi pada pengembangan teknologi sensor cerdas untuk mendukung daya saing produk teh Indonesia. Kebaruan utama penelitian ini adalah pada integrasi analisis korelasi sensor ke dalam pipeline pemodelan dengan sistem klasifikasi end-to-end yang menggabungkan analisis korelasi sensor untuk mengoptimalkan performa model BPNN pada dataset aroma teh.Kata kunci: Arduino; Aroma Teh; Backpropagation; Electronic Nose; Sensor TGS
Detection of Corn Leaf Blight Disease Based on GLCM and HSV Feature Extraction Using Support Vector Machine Chen, Sami'un, Defitroh; Dahur , Arnoldus Janssen; Manalu, Mamed; Arif, M Aidil; Jaya, Dery Yuswanto
Jurnal Multimedia dan Teknologi Informasi (Jatilima) Vol. 7 No. 06 (2026): Jatilima : Jurnal Multimedia Dan Teknologi Informasi
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jatilima.v7i06.2270

Abstract

Corn leaf blight is a major disease that reduces crop productivity, making early detection essential. This study proposes an image-based detection method using Gray Level Co-occurrence Matrix (GLCM) and HSV feature extraction with Support Vector Machine (SVM) classification. The dataset, obtained from Kaggle, consists of 2308 corn leaf images categorized into healthy and blight classes. The method includes preprocessing, segmentation, feature extraction, and classification. Preprocessing involves resizing, grayscale conversion, noise reduction, and normalization. Segmentation is performed using Otsu thresholding and K-Means clustering to isolate leaf regions and highlight disease areas. Feature extraction combines four GLCM texture features and three HSV color features to represent each image. The SVM model, evaluated using an 80:20 data split, achieved an accuracy of 94.8% with balanced precision, recall, and F1-score values of approximately 0.95. These results indicate that the proposed method is effective for detecting corn leaf blight and has potential for practical agricultural applications
Co-Authors Chen, Sami'un, Defitroh Dahur , Arnoldus Janssen Dahur, Arnoldus Janssen Hidayat, Muhammad I Made Candra Girinata Khairul Anwar Hafizd, Khairul Anwar M Fadli Ridhani Manalu, Mamed Manalu, Mamed Rofendi Saputra, Arwin Wahyu Styawan, Budi Yuswanto Jaya, Dery