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
 55   56   57   58   59 
Design and Implementation of NodeMCU ESP8266-Based Smart Home System as Residential Energy Efficiency Solution Aziza, Miladina Rizka; Widyanto, Hafidin Bangun; Dwiputra, Febrian Daniel; Cahayanti, Putri Nur; Prawimuliasta, Enggar Kabisafira; Nugroho, Rizky Wahyu
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 3 (2026): MALCOM July 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i3.2902

Abstract

The household sector accounts for approximately 42.41% of Indonesia's total electricity consumption (122,339.69 GWh in 2023), making it a strategic priority for energy efficiency efforts aligned with the Sustainable Development Goals (SDGs), particularly SDG 7, SDG 9, SDG 11, and SDG 13. This study presents the design of a NodeMCU ESP8266-based smart home system integrated with the ThingSpeak platform and an Android application built with MIT App Inventor. This system is capable of integrating three main functions, including controlling and monitoring room lights using an LDR sensor, controlling the AC along with monitoring temperature and humidity using a DHT11 sensor, and monitoring water levels using an HC-SR04 ultrasonic sensor within a single low-cost NodeMCU platform. System performance was evaluated through functional testing of each subsystem using calibrated reference instruments, with accuracy calculated by comparing measured values against theoretical reference values. The DHT11 sensor achieved 95.62% accuracy for temperature and 98.15% for humidity, while the HC-SR04 sensor achieved 97.06% accuracy. With a total component cost below IDR 1.5 million, this system demonstrates that a multi-subsystem smart home solution can be implemented affordably using locally available components, supporting residential energy efficiency and the SDGs 2030 agenda.
Cognitive-Oriented Serious Game Design for Manufacturing Production-Flow Problem Solving Using Mini Drone Assembly Sari, Handini Fatma; Ratnasari, Chanifah Indah; Mulyati, Rina
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 3 (2026): MALCOM July 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i3.2916

Abstract

Manufacturing production-flow problem-solving requires Industrial Engineering students to understand how queues, work-in-process (WIP), bottlenecks, quality control, rework, and system stability interact to determine production performance. Yet conventional materials rarely allow students to observe how a single decision affects the whole system. This study aims to produce a refined, cognitive-oriented serious game design that explicitly links cognitive problem-solving, simplified production-flow rules, and game-system interaction across four progressive levels, and to evaluate it formatively as a basis for further development. Using Design-Based Research, the design was represented through Figma-based static mockups covering level progression, rule-based production behavior, feedback, and performance reports, operationalizing an Observe–Diagnose–Predict–Adjust–Stabilize–Reflect loop. Two game-design experts and five Industrial Engineering students evaluated the design through researcher-guided walkthroughs. Expert judgment produced an overall mean of 2.86 out of 5, indicating refinement needs in dynamic-system behavior and feedback. In contrast, prospective users gave 3.74 out of 5, with the strongest perception in cognitive support. Consistent with its formative objective, these results were not treated as evidence of learning effectiveness but were directly used to refine production-flow rules, feedback, and level structure, producing a four-level design artifact that provides a basis for future prototype development and effectiveness testing.
Sentiment Analysis of E-Commerce Mobile Application Reviews for Digital Product Development Insights Balqis, Rugaiyah; Ermatita, Ermatita; Abdiansah, Abdiansah
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 3 (2026): MALCOM July 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i3.3045

Abstract

This paper presents a systematic sentiment analysis framework for Indonesian-language e-commerce reviews, designed for scalable extraction of insights for digital product development. The system applies a Support Vector Machine (SVM) classifier with a Radial Basis Function (RBF) kernel and TF-IDF bigram feature extraction to the PRDECT-ID dataset comprising 5,400 product reviews from Tokopedia across 29 categories. To ensure reliable classification under realistic class conditions, the proposed pipeline integrates multi-stage text preprocessing (case folding, slang normalization, stopword removal, and Sastrawi-based stemming) and stratified 80:20 train-test splitting without artificial resampling. The experimental evaluation confirmed a test-set accuracy of 92.04%, a weighted F1-score of 0.92, and an AUC-ROC of 0.9741. These results validate the efficacy of the proposed SVM-TF-IDF architecture for reliable, interpretable sentiment classification. Furthermore, category-level negative sentiment profiling identifies Computers and Laptops, Automotive, and Toys and Hobbies as priority intervention domains (negative rate ?60%), while keyword-level TF-IDF analysis reveals critical user concerns regarding delivery services, product specification mismatches, and quality disappointment, providing tangible guidance for product development teams. Future work should explore transformer-based architectures (BERT, IndoBERT) for contextual sentiment capture, investigate cross-marketplace generalizability, and address real-time deployment scalability.
Klasterisasi Sumber Daya Pendidikan Tinggi Antarprovinsi di Indonesia Tahun 2025 Menggunakan K-Means: K-Means Clustering of Higher Education Resources Across Indonesian Provinces in 2025 Yulilawan, Kristia; Hardiansyah, Agung
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 3 (2026): MALCOM July 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i3.3112

Abstract

Ketimpangan distribusi perguruan tinggi dan sumber daya pendidikan tinggi di Indonesia memengaruhi pemerataan akses dan kualitas layanan pendidikan tinggi. Dengan menggunakan data tahun 2025, penelitian ini mengelompokkan 38 provinsi menggunakan algoritma K-Means pada Orange Data Mining berdasarkan jumlah perguruan tinggi, tenaga pendidik, mahasiswa, rasio mahasiswa terhadap tenaga pendidik, dan kebutuhan tenaga pendidik. Data melalui tahap pra-pemrosesan, standardisasi z-score, pembentukan tiga cluster, dan evaluasi menggunakan Silhouette Score. Nilai silhouette rata-rata sebesar 0,520 menunjukkan struktur cluster yang cukup baik dan terpisah. Cluster 1 menggambarkan provinsi dengan kapasitas pendidikan tinggi yang relatif terbatas, Cluster 2 menunjukkan tekanan kebutuhan tenaga pendidik, dan Cluster 3 mencakup pusat-pusat aktivitas akademik nasional. Kebaruan penelitian terletak pada integrasi skala institusi, sumber daya akademik, jumlah mahasiswa, dan kecukupan tenaga pendidik dalam satu model clustering tingkat provinsi. Hasil penelitian ini menyediakan dasar empiris bagi kebijakan diferensial terkait pengembangan institusi, distribusi tenaga pendidik, dan penguatan kapasitas pendidikan tinggi.
An Explainable Artificial Intelligence Approach to Rice Leaf Disease Classification Using MobileNetV3-Large Susanto, Adyatma Imam; Anggraeny, Fetty Tri; Puspaningrum, Eva Yulia
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 4 (2026): MALCOM October 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i4.2658

Abstract

In Indonesia, rice is a vital component of food security, but persistent leaf diseases threaten productivity. Currently, field identification relies on labor-intensive, human-error-prone manual observation. To address this, we developed an accurate and interpretable classification model integrating the MobileNetV3-Large with Gradient-weighted Class Activation Mapping (Grad-CAM). The model obtained 98.82% validation accuracy after being trained via transfer learning on a public dataset with four classes: healthy, bacterial leaf blight, brown spot, and blast. The dataset was partitioned using a 90:10 data split (5,018 training and 612 validation samples). The model achieved a validation accuracy of 98.82% alongside robust multi-metric performance, obtaining a weighted average precision of 99.00%, a recall of 98.80%, Micro AUC and Macro AUC both reached 0.9977, and an F1-score of 98.90%. Furthermore, Grad-CAM analysis confirmed that the model's predictions are interpretable. The resulting heatmaps consistently concentrated on leaf regions exhibiting disease symptoms, demonstrating that the network learned visually meaningful features despite minor background activations. These findings validate that combining MobileNetV3-Large with Grad-CAM yields an effective, transparent classification system, offering strong potential for robust, user-verifiable rice disease diagnosis in agricultural deployments.
Klasifikasi Pneumonia dari Citra X-Ray Menggunakan Deep Learning dengan Metode Ensemble Stacking: Classification of Pneumonia from X-Ray Images Using Deep Learning with the Ensemble Stacking Method Situmorang, Bagas Renovan; Simanjuntak, Surya Alfredo; Sembiring, Lasia Tomi Giantama; Rambe, Asian; Dharma, Abdi
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 3 (2026): MALCOM July 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i3.2715

Abstract

Pneumonia merupakan salah satu penyebab utama kematian di dunia, terutama pada anak-anak dan lansia. Deteksi dini melalui citra rontgen dada sangat penting untuk membantu proses diagnosis dan menentukan pengobatan yang tepat. Namun, pembacaan gambar rontgen secara manual membutuhkan keahlian khusus dan berisiko menyebabkan kesalahan. Oleh karena itu, penelitian ini bertujuan untuk mengembangkan sistem klasifikasi pneumonia berbasis Deep Learning menggunakan metode Convolutional Neural Network (CNN) yang dikombinasikan dengan teknik ensemble learning. Penelitian ini menggunakan tiga model CNN, yaitu DenseNet161, ConvNeXt-Tiny, dan DenseNet201. Dataset berasal dari Kaggle dengan total 5.856 citra rontgen yang dibagi menjadi dua kelas, yaitu Normal dan Pneumonia. Proses penelitian mengikuti tahapan CRISP-DM, mulai dari pemahaman masalah hingga evaluasi model. Hasil pengujian menunjukkan bahwa DenseNet161 sebagai model tunggal terbaik dengan akurasi 65,85%. Setelah model digabungkan menggunakan ensemble stacking dengan regresi logistik sebagai meta-learner, akurasi meningkat menjadi 84,86% dengan recall 90,72%. Hasil ini menunjukkan bahwa pendekatan stacking ensemble mampu meningkatkan kinerja klasifikasi secara signifikan dibandingkan dengan model tunggal serta berpotensi membantu tenaga medis dalam mendiagnosis pneumonia. Kontribusi utama penelitian ini adalah menghasilkan sistem klasifikasi yang lebih andal dengan recall tinggi, sehingga dapat meminimalkan risiko false negative dan mendukung pengambilan keputusan medis untuk deteksi dini pneumonia yang lebih akurat dan efisien.
Redesigning the Oxygen Gas Distribution Business Process for Process Time Efficiency from Department to Shipping Hawari, Naufal Abdurrahman; Sinaga, Tuti Sarma; Napitupulu, Humala L.; Ukurta, Ukurta
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 4 (2026): MALCOM October 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i4.2781

Abstract

Inefficiencies often occur in company operations due to mismatches between business processes implemented in Enterprise Resource Planning (ERP) systems and operational practices. This study aims to improve the business processes of an industrial gas manufacturer that experiences delays in meeting customer needs due to inconsistencies within its ERP system. Business Process Reengineering (BPR) is applied through fundamental rethinking and radical redesign to improve process efficiency. The fundamental rethink stage begins with developing a Business Process Model and Notation (BPMN) model to map the current business process (As-Is), followed by 5W+1H analysis, Root Cause Analysis (RCA), and time study. The radical redesign stage involves developing a proposed business process (To-Be) based on the problems. The results indicate that the main problems are concentrated in the distribution unit, particularly manual communication, duplicate data entry, and limited integration between work units. The time study shows that the initial business process requires an average of 4 hours, 41 minutes, and 39 seconds. The proposed business process reduces the processing time to 3 hours, 37 minutes, and 25 seconds. These results demonstrate that the redesigned process improves operational efficiency by 22.8% and provides an integrated, efficient, and responsive business process
Pemodelan Topik dan Analisis Sentimen Komentar TikTok pada Program Makanan Bergizi Gratis Menggunakan BERTopic dan IndoBERT: Topic Modeling and Sentiment Analysis of TikTok Comments on the Free Nutritious Meal Program Using BERTopic and IndoBERT Model Kayadu, Owen Thomas; Limbong, Josua Josen A; Sumendap, Andreas Leonardo
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 3 (2026): MALCOM July 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i3.2790

Abstract

TikTok menjadi salah satu media sosial yang banyak digunakan masyarakat untuk menyampaikan opini terhadap berbagai kebijakan publik, termasuk Program Makan Bergizi Gratis (MBG). Penelitian ini bertujuan untuk menganalisis topik pembahasan dan sentimen masyarakat terhadap Program MBG berdasarkan komentar TikTok menggunakan metode BERTopic dan IndoBERT. Tahapan penelitian meliputi pengumpulan data, preprocessing, pemodelan topik, dan klasifikasi sentimen. Hasil penelitian menunjukkan bahwa BERTopic berhasil mengidentifikasi delapan topik utama yang berkaitan dengan gizi, pendidikan, lapangan kerja, kondisi ekonomi, transparansi anggaran, dan dukungan terhadap pemerintah. Topik 5 menjadi topik yang paling dominan dengan jumlah 5.422 komentar. Analisis sentimen menggunakan IndoBERT menunjukkan bahwa sentimen netral mendominasi dengan 3.614 komentar (43,29%), diikuti oleh sentimen positif sebanyak 2.611 komentar (31,27%) dan sentimen negatif sebanyak 2.124 komentar (25,44%). Selain itu, Topik 4 menjadi topik yang paling banyak muncul pada ketiga kategori sentimen. Model IndoBERT memperoleh akurasi sebesar 82,68%, yang menunjukkan performa yang baik dalam memahami konteks komentar berbahasa Indonesia. Hasil penelitian menunjukkan bahwa kombinasi BERTopic dan IndoBERT mampu memberikan analisis yang komprehensif terhadap topik pembahasan dan opini masyarakat mengenai Program MBG di TikTok.
Sistem Rekomendasi Makanan Sehat untuk Penderita Penyakit Kronis Menggunakan Algoritma K-Means: Healthy Food Recommendation System for Chronic Disease Patients Using the K-Means Algorithm Ilyasa, Haykal Kamal; Alfat, Latifah
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 3 (2026): MALCOM July 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i3.2791

Abstract

Meningkatnya prevalensi penyakit kronis seperti diabetes, hipertensi, penyakit jantung, dan gangguan ginjal di Indonesia mencerminkan pergeseran pola hidup masyarakat yang tidak sehat. Pola makan yang buruk dan kurangnya kesadaran gizi memperburuk kondisi penderita yang kesulitan memilih makanan sesuai dengan kebutuhan medisnya. Penelitian ini mengembangkan sistem rekomendasi makanan sehat bagi penderita penyakit kronis menggunakan algoritma K-Means Clustering. Sistem mengelompokkan makanan berdasarkan kandungan nutrisi seperti kalori, protein, karbohidrat, dan lemak, serta mempertimbangkan data pengguna seperti Indeks Massa Tubuh (IMT), tinggi badan, dan berat badan. Dataset terdiri dari 499 menu makanan siap saji halal yang bersumber dari katering kesehatan dan Tabel Komposisi Pangan Indonesia (TKPI) 2019, serta mencakup 7 variabel gizi. Setiap menu dilabeli kesesuaian dietnya dengan lima penyakit kronis berdasarkan pedoman klinis resmi di Indonesia. Sistem menerapkan normalisasi MinMaxScaler sebelum klasterisasi K-Means dengan k = 4, kemudian menghasilkan rekomendasi melalui mekanisme weighted scoring klinis yang menyaring menu aman dan merangkingnya berdasarkan prioritas gizi untuk setiap penyakit. Aplikasi diimplementasikan berbasis web menggunakan Plotly Dash. Hasil penelitian menunjukkan bahwa sistem mampu mengelompokkan data makanan berdasarkan karakteristik nutrisi serta memberikan rekomendasi personal sesuai dengan kondisi kesehatan pengguna.
Inovasi Sistem Manajemen Rambu Lalu Lintas Real-Time Berbasis Internet of Things: Evaluasi Kinerja Berdasarkan Waktu Respons Transmisi Data dan Deteksi Lokasi GPS: Innovation of a Real-Time Internet of Things-Based Traffic Sign Management System: Performance Evaluation Based on Data Transmission Response Time and GPS Location Detection Pratindy, Raka; Utami, Unggul; Winesti, Feby Ayu; Illiyun, Bani; Diaz, Ryandi Syahputra; Syamil, Zain Ad Dienusy
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 4 (2026): MALCOM October 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i4.2814

Abstract

Keselamatan lalu lintas tetap menjadi isu kritis pada wilayah dengan keterbatasan rambu jalan statis yang dapat meningkatkan kebingungan pengemudi dan risiko kecelakaan. Penelitian ini bertujuan merancang Sistem Rambu Lalu Lintas Otomatis berbasis Internet of Things (IoT) untuk menyampaikan informasi lalu lintas secara real-time dan adaptif. Sistem dikembangkan menggunakan Raspberry Pi 3B+ sebagai pengendali utama yang terintegrasi dengan LED dot matrix, Firebase, Google Maps API, dan aplikasi Android. Penelitian menggunakan metode Research and Development (R&D) yang meliputi analisis, perancangan, perakitan perangkat keras, pemrograman, dan pengujian sistem. Hasil evaluasi menunjukkan rata-rata waktu respons transmisi data sebesar 5,8 detik dan waktu deteksi lokasi GPS sebesar 11,6 detik. Sistem mampu menampilkan informasi batas kecepatan dan rambu arah secara akurat dalam radius deteksi 10–30 meter. Temuan tersebut menunjukkan bahwa sistem berbasis IoT layak secara teknis untuk mendukung manajemen rambu yang fleksibel, adaptif, dan responsif terhadap kondisi jalan. Kebaruan penelitian terletak pada integrasi Raspberry Pi 3B+, LED dot matrix, Firebase, Google Maps API, dan aplikasi Android dalam sistem rambu adaptif berbasis geofencing. Pengujian pada lima titik koordinat juga menunjukkan kinerja sistem yang konsisten serta berpotensi dikembangkan melalui integrasi sensor lalu lintas dan kecerdasan buatan

Page 57 of 59 | Total Record : 581

 55   56   57   58   59 

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