cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Mustakim
Contact Email
officialmalcom.irpi@gmail.com
Phone
+6285275359942
Journal Mail Official
malcom@irpi.or.id
Editorial Address
INSTITUT RISET DAN PUBLIKASI INDONESIA Jl. Tuah Karya Ujung C7. Kel. Tuah Madani Kec. Tampan Kota Pekanbaru - Riau
Location
Kota pekanbaru,
Riau
INDONESIA
Malcom: Indonesian Journal of Machine Learning and Computer Science
Published by Institut Riset dan Publikasi Indonesia
ISSN : 27972313     EISSN : 27758575     DOI : -
Core Subject : Science,
Computer Science & IT
MALCOM: Indonesian Journal of Machine Learning and Computer Science is a scientific journal published by the Institut Riset dan Publikasi Indonesia (IRPI) in collaboration with several Universities throughout Riau and Indonesia. MALCOM will be published 2 (two) times a year, April and October, each edition containing 10 (Ten) articles. Articles may be written in Indonesian or English. articles are original research results with a maximum plagiarism of 15%. Articles submitted to MALCOM will be reviewed by at least 2 (two) reviewers. The submitted article must meet the assessment criteria and in accordance with the instructions and templates provided by MALCOM. The author should upload the Statement of Intellectual/ Copyright Rights when submitting the manuscript. Papers must be submitted via the Open Journal System (OJS) in .doc or .docx format. The entire process until MALCOM is published will be free of charge. MALCOM is registered in National Library with Number International Standard Serial Number (ISSN) Printed: 2797-2313 and Online 2775-8575. Focus and scope of MALCOM includes Data Mining, Data Science, Artificial Intelligence, Computational Intelligence, Natural Language Processing, Big Data Analytic, Computer Vision, Expert System, Text and Web Mining, Parallel Processing, Intelligence System, Decision Support System and Software Engineering
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 581 Documents
 49   50   51   52   53 
Web-Based E-Learning System Design with Integrated Webinar Features at STIT Al-Falah Rimbo Bujang Habibi Ul Akbar; Benni Purnama; Dodo Zaenal Abidin
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 1 (2026): MALCOM January 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i1.2545

Abstract

This study examines challenges faced by STIT Al-Falah Rimbo Bujang in implementing online learning that is not yet optimally integrated. Students and lecturers currently rely on multiple platforms such as WhatsApp, Zoom, email, and Google Drive to manage schedules, learning materials, assignments, and communication. This platform fragmentation leads to operational inefficiencies, coordination difficulties, limited monitoring, and decreased student engagement. Observations and interviews with academic administrators identified three main problems: the need to access multiple applications for a single course, the lack of automated attendance recording during webinar sessions, and inefficient assignment submission and grading via private messaging, which increases administrative workload and the risk of data loss. A student satisfaction survey conducted in the even semester of the 2023/2024 academic year showed that these issues reduced the effectiveness of online learning by up to 40%. To overcome these problems, this study proposes the design of a web-based e-learning system with integrated webinar features that centralizes learning activities into a single platform. The system is developed using the waterfall model, including requirement analysis, system design, implementation, testing, and maintenance. UML is applied for system modeling, while PHP, MySQL, and Bootstrap are used for implementation
Multivariat Support Vector Regression untuk Peramalan Permintaan Suku Cadang Intermittent pada Industri Perkeretaapian: Multivariate Support Vector Regression for Intermittent Spare Parts Demand Forecasting in the Railway Industry Syayid Al Afghoni; Iwan Vanany
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 2 (2026): MALCOM April 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i2.2549

Abstract

Manajemen persediaan suku cadang dalam industri perkeretaapian menghadapi tantangan kompleks akibat pola permintaan yang bersifat intermittent. Ketidakakuratan dalam meramalkan kebutuhan komponen perawatan sering kali berujung pada risiko stockout yang menghambat operasional atau overstock yang membebani biaya penyimpanan. Penelitian ini bertujuan untuk meningkatkan akurasi peramalan suku cadang dengan mengembangkan model Support Vector Regression (SVR) yang mengintegrasikan variabel eksogen berupa frekuensi jadwal perawatan dan klasifikasi umur armada. Menggunakan data historis pemakaian suku cadang perawatan kereta di workshop perawatan PT KAI periode 2020–2024, kinerja model SVR dievaluasi dan dibandingkan dengan metode Croston serta Random Forest. Hasil pengujian menunjukkan bahwa model SVR berbasis kernel RBF mampu menangani volatilitas data secara efektif dengan menghasilkan tingkat kesalahan terendah (MAE 8,424 dan MASE 0,449). Model ini terbukti superior dibandingkan metode Croston yang cenderung under-forecasting dan Random Forest yang kurang responsif terhadap nilai ekstrem. Temuan ini mengindikasikan bahwa integrasi informasi siklus perawatan dan profil usia armada secara signifikan memperbaiki kemampuan generalisasi model pada data yang fluktuatif. Secara manajerial, penerapan model ini memungkinkan perencanaan inventori yang lebih proaktif, mendukung optimalisasi safety stock, dan menjamin ketersediaan suku cadang untuk keandalan armada kereta api
Implementasi Perbandingan YOLO v8, v9, dan v11 dalam Penerapan Tata Tertib K3: Deteksi Penggunaan Helm Keselamatan di Lingkungan Konstruksi: Implementation and Comparison of YOLO v8, v9, and v11 in Occupational Safety Regulations: Detecting Safety Helmet Usage in Construction Environments Rafael Praseli; Nenden Siti Fatonah; Diah Aryani; Hani Dewi Ariessanti
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 2 (2026): MALCOM April 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i2.2554

Abstract

Penegakan aturan keselamatan kerja secara konsisten merupakan langkah penting dalam menciptakan lingkungan konstruksi yang aman dan tertib. Penelitian ini dilakukan dengan pendekatan eksperimen menggunakan dataset Hard Hats Computer Vision Project yang berjumlah sekitar 20.000 gambar beranotasi, dengan memanfaatkan teknologi kecerdasan buatan melalui algoritma YOLOv8, YOLOv9, dan YOLOv11. Model dilatih menggunakan dataset pekerja konstruksi dan dievaluasi berdasarkan tiga metrik utama, yaitu precision, recall, serta mean Average Precision (mAP) untuk mengukur akurasi dan kemampuan generalisasi deteksi. Hasil penelitian menunjukkan bahwa YOLOv8 menghasilkan performa yang stabil dengan nilai precision sebesar 0,895, recall sebesar 0,895, dan mAP@50–95 sebesar 0,597 pada 60 epoch, sedangkan YOLOv11 mencapai akurasi tertinggi dengan precision sebesar 0,903, recall sebesar 0,897, dan mAP@50–95 sebesar 0,600. Sementara itu, YOLOv9 menunjukkan efisiensi yang lebih rendah dibandingkan dengan kedua model lainnya. Dengan demikian, YOLOv8 lebih sesuai untuk implementasi real-time karena stabil dan efisien, sedangkan YOLOv11 memiliki potensi akurasi yang lebih tinggi. Penelitian ini memberikan kontribusi baik secara akademis dalam pengembangan sistem berbasis AI maupun secara praktis dalam meningkatkan keselamatan kerja di lingkungan konstruksi.
Predicting Students’ Mathematics Scores from Reading Scores Using Supervised Learning Nofita Fitriyani
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 2 (2026): MALCOM April 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i2.2555

Abstract

This study aims to predict students’ mathematics scores based on their reading scores using a supervised learning approach. The dataset used is from Students' Performance in Exams (Kaggle), consisting of 1,000 student records, and was analyzed using Microsoft Excel and Google Colaboratory. The data was divided into training and test data with a ratio of 80:20. The research stages included descriptive statistical analysis, data visualization, Pearson correlation testing, linear regression model development, and model performance evaluation using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and coefficient of determination (R²).  Prior to modeling, regression assumptions including linearity, normality of residuals, and homoscedasticity were examined to ensure model validity. The results showed a strong positive relationship between reading and math scores with a correlation coefficient of 0.818. The linear regression model produced an MAE of 7.281, an RMSE of 8.818, and an R² of 0.680. Decision Tree Regressor was selected as a comparison model because it represents a non-linear and non-parametric supervised learning approach commonly used in educational data mining. This study contributes to educational data mining literature by demonstrating that interpretable regression models explain significant mathematics achievement variance, rivaling the performance of non-linear alternatives.
Development of a Portable Smart Feeder Based on Scheduling and Precision Dosing for Fish Feeding in Aquaculture Arif Dwi Kuncoro; Tri Widodo; Yuri Rahmanto; Sahrial Ihsani Ishak
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 2 (2026): MALCOM April 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i2.2559

Abstract

Freshwater and marine fish farming is the backbone of the fisheries economy, especially for small to medium-scale farmers. Feed contributes approximately 60–70% of operational costs, so inaccurate feed scheduling and dosing can increase production costs, reduce feed efficiency, and increase waste. This research developed a Portable Smart Feeder based on precision scheduling and dosing, equipped with gradual feeding (sub-doses with intervals) and a spreader for even feed distribution. Development was carried out using a prototype method, then the system performance was tested through experiments in two ponds for 14 days (one sorting cycle): Pond A (conventional) and Pond B (using the system). Evaluation included feed consumption, mortality, and growth measured through a sorting process (grading) on ??the 14th day. The results showed that Pond B produced 70.90 kg of harvested biomass with 28.00 kg of feed and 13 fish mortality, while Pond A produced 68.17 kg of biomass with 33.80 kg of feed and 250 fish mortality. The FCR value of Pond B is 0.91:1, better than Pond A 1.20:1, so the system shows increased feed efficiency and maintenance stability.
Comparative Analysis of Random Forest, Explainable Boosting Machine and Ensemble Stacking Performance for Hepatitis C Disease Classification Anastasia Ngeni Bagur; Irfan Pratama
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 2 (2026): MALCOM April 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i2.2561

Abstract

This study analyzed and compared the performance of three machine learning methods: Random Forest, Explainable Boosting Machine, and a Stacking Ensemble method for Hepatitis C disease classification. The study evaluated the effects of handling extreme values using the interquartile range method and applying class-balancing oversampling to the training data. A dataset of 615 patient samples, categorized into five severity classes, was used. Experiments were conducted across four scenarios: with and without outlier correction, and with and without class balancing. Model performance was assessed using accuracy, precision, recall, F1-score, and the area under the receiver operating characteristic curve. Results showed that class balancing consistently improved all macro-averaged performance metrics. The combination of Random Forest with oversampling prior to outlier correction achieved the highest F1-score of 0.8086 and an area under the curve of 0.9710. These findings highlighted the importance of addressing class imbalance to improve the recognition of minority classes in clinical datasets and demonstrated the potential of ensemble methods for reliable severity classification in Hepatitis C.
Performance Evaluation of the DHT11 Sensor for MATLAB-Based Temperature and Humidity Measurements Muhammad Chusni Marzuki; Ulul Ilmi; Arif Budi Laksono; Eko Wahyu Santoso; Abdur Rohman Wakhid
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 2 (2026): MALCOM April 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i2.2565

Abstract

This study evaluates the performance of the DHT11 sensor in measuring temperature and humidity by comparing it with a conventional thermometer using a MATLAB-based statistical approach. The analysis includes descriptive statistics, error evaluation using Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE), linear regression modeling, and significance testing through ANOVA and the Durbin–Watson test. The results show that the DHT11 sensor provides consistent measurements (good precision) and exhibits a strong linear relationship with the reference instrument, as indicated by a high correlation coefficient (R = 0.944) and coefficient of determination (R² = 0.891). However, the sensor demonstrates a slight systematic bias, with temperature readings approximately 1–2 °C higher than those of the conventional thermometer. The obtained error values (MAE = 1 °C and MAPE ? 3.4%) indicate acceptable accuracy for general monitoring applications. Overall, the DHT11 sensor is a reliable, cost-effective, and practical solution for temperature and humidity monitoring. Nevertheless, calibration is recommended to improve measurement accuracy in applications requiring higher precision.
Estimasi Tax Gap Indonesia: Analisis Diskrepansi PDRB Resmi Berdasarkan Nighttime Lights Berbasis Machine Learning: Estimating Indonesia's Tax Gap: Analysis of Discrepancies in Official GRDP Based on Machine Learning-Based Nighttime Lights Fachri Husein Harahap
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 2 (2026): MALCOM April 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i2.2568

Abstract

Penelitian ini mengusulkan metodologi baru untuk mengestimasi 'True PDRB' dan 'shadow economy' di tingkat provinsi Indonesia menggunakan latent variable framework [7]. Peneliti menggunakan PDRB riil sebagai variabel laten yang diestimasi dari dua pengukuran independen yang tidak sempurna: PDRB resmi BPS, yang dimodelkan memiliki error underreporting sistematis, dan PDRB-geospatial, yang diprediksi dari multi-source proxy data (NTL, NO?, informalitas, konsumsi) menggunakan model machine learning XGBoost. Untuk menghindari penalaran melingkar, model XGBoost dilatih pada target tertimbang adaptif yang menyesuaikan bobot PDRB resmi berdasarkan tingkat informalitas provinsi. Model menunjukkan daya prediksi kuat (R² = 0.8256) pada data uji temporal 2023. Estimasi GMM mengungkap shadow economy agregat nasional sebesar 6,76% dari PDRB resmi, dengan estimasi tax gap nasional Rp 16,17 triliun (7,03% dari potensi). Temuan menunjukkan heterogenitas ekstrem: provinsi berbasis agrikultur seperti Kalimantan Tengah (46,9%) dan Papua Barat (37,8%) memiliki persentase shadow economy tertinggi. Sebaliknya, tax gap nominal terbesar terkonsentrasi di provinsi dengan PDRB sangat besar, yaitu Papua (Rp 34,5 T) dan Jawa Timur (Rp 8,9 T). Temuan ini menghasilkan pemetaan tax gap yang dapat ditindaklanjuti bagi DJP untuk merumuskan strategi ekstensifikasi berbasis data.
Graph-Based Optimization of Distribution Networks Using Minimum Spanning Tree Algorithms Muhung Anggarawan; Hadi Permana; Fatia Amalia Maresti
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 1 (2026): MALCOM January 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i1.2570

Abstract

Urban electric power distribution networks must operate efficiently while supporting sustainability and green economy objectives. This study analyzes the optimization of an urban power distribution network using graph theory approaches, specifically Minimum Spanning Tree methods. The electrical network is modeled as an undirected weighted graph, where substations are represented as nodes and cable connections as edges with distance-based weights. Kruskal and Prim algorithms are applied to determine the optimal network configuration that minimizes total cable length while maintaining full connectivity. A case study of an existing urban distribution network consisting of 229 substations is used to evaluate the proposed approach. The results show that the optimized network configuration reduces total cable length from 61,474.23 meters to 49,391.44 meters a 19.66% reduction (12,082.79 meters saved) leading to improved material efficiency and lower infrastructure costs. Both algorithms produce identical optimal results, confirming their reliability for practical network planning. The findings demonstrate that graph-based optimization techniques can provide effective decision support for designing more efficient and environmentally responsible power distribution systems. This research highlights the potential of mathematical and computational methods for sustainable infrastructure development and for implementing a green economy in urban energy systems.
Comparative Analysis of Naive Bayes and Support Vector Machine for Hate Speech Classification Rolanda Difandana; Ian Imaduddin; Indra Indra
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 1 (2026): MALCOM January 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i1.2571

Abstract

This study addresses the increasing need for automated hate speech detection in Indonesia due to the rapid growth of social media and the rise of abusive online content. It compares the performance of Naive Bayes (NB) and Support Vector Machine (SVM) algorithms in classifying Indonesian-language tweets into three categories: hate speech (27.52%), abusive language (34.25%), and neutral content (38.23%). The dataset consists of 13,169 manually annotated tweets collected from Twitter (now X), with moderate class imbalance handled using stratified sampling. Text preprocessing included tokenization, case folding, stopword removal, and stemming using the Nazief–Adriani algorithm, followed by TF-IDF feature extraction with a unigram configuration (min_df=3, max_df=0.95). Both algorithms were evaluated using 10-fold stratified cross-validation with accuracy, precision, recall, and F1-score as performance metrics. Experimental results show that SVM with a linear kernel outperformed NB, achieving an accuracy of 93.28%, precision of 92.45%, and F1-score of 92.89%, compared to NB’s accuracy of 84.71%, precision of 83.56%, and F1-score of 84.12%. Although effective, this study is limited to classical machine learning approaches with TF-IDF features and does not incorporate deep learning or contextual embeddings, while still providing practical guidance for algorithm selection in Indonesian hate speech detection systems.

Page 51 of 59 | Total Record : 581

 49   50   51   52   53 

Filter by Year

2021 2026


Reset
Filter By Issues
All Issue Vol. 6 No. 4 (2026): MALCOM October 2026 Vol. 6 No. 3 (2026): MALCOM July 2026 Vol. 6 No. 2 (2026): MALCOM April 2026 Vol. 6 No. 1 (2026): MALCOM January 2026 Vol. 5 No. 4 (2025): MALCOM October 2025 Vol. 5 No. 3 (2025): MALCOM July 2025 Vol. 5 No. 2 (2025): MALCOM April 2025 Vol. 5 No. 1 (2025): MALCOM January 2025 Vol. 4 No. 4 (2024): MALCOM October 2024 Vol. 4 No. 3 (2024): MALCOM July 2024 Vol. 4 No. 2 (2024): MALCOM April 2024 Vol. 4 No. 1 (2024): MALCOM January 2024 Vol. 3 No. 2 (2023): MALCOM October 2023 Vol. 3 No. 1 (2023): MALCOM April 2023 Vol. 2 No. 2 (2022): MALCOM October 2022 Vol. 2 No. 1 (2022): MALCOM April 2022 Vol. 1 No. 2 (2021): MALCOM October 2021 Vol. 1 No. 1 (2021): MALCOM April 2021 More Issue