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
 53   54   55   56   57 
Perbandingan Support Vector Machine dan Naïve Bayes untuk Klasifikasi Sentimen Ulasan E-Commerce: Comparison of Support Vector Machine and Naïve Bayes for E-Commerce Review Sentiment Classification Nurmadewi, Dita; Jailani, Zakiul Fahmi; Rafi, Haris; Anggoro, Dimas Aryo; Setiowati, Dewi
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.v6i2.2648

Abstract

Ulasan pelanggan di platform e-commerce memuat informasi penting tentang pengalaman pengguna terhadap produk dan layanan. Namun, mengingat jumlahnya sangat besar, analisis manual tidak efisien. Klasifikasi sentimen berbasis machine learning dapat secara otomatis mengidentifikasi opini dari teks ulasan. Penelitian ini ingin melakukan perbandingan antara performa Support Vector Machine (SVM) dan Naïve Bayes dalam melakukan klasifikasi sentimen pada ulasan di platform e-commerce. Dataset terdiri atas 11.606 ulasan pelanggan yang bersumber dari repositori dataset publik. Tahap pra-pemrosesan mencakup case folding, tokenization, penghilangan stopword, serta stemming. Fitur teks ditampilkan memakai Term Frequency–Inverse Document Frequency (TF-IDF). Kinerja model dievaluasi berdasarkan skema 5-fold cross-validation menggunakan metrik accuracy, precision, dan recall, serta F1-score. Hasil eksperimen menemukan algoritma Support Vector Machine mempunyai performa lebih unggul jika dibandingkan dengan Naïve Bayes, di mana perolehan nilai accuracy masing-masing mencapai 0.8717 dan 0.8555. Temuan ini sekaligus menunjukkan Support Vector Machine mempunyai kemampuan generalisasi yang lebih baik dalam membedakan kelas sentimen pada data ulasan e-commerce berbasis teks.
Comparative Sentiment Analysis of TheoTown Reviews on Steam and Google Play Store Using Support Vector Machine Aura, Shanda; Novianto, Dian
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.v6i2.2661

Abstract

The rapid expansion of the digital gaming industry has led to a substantial increase in player-generated textual reviews across major distribution platforms such as the Google Play Store and Steam. These reviews offer valuable insights into user experiences and perceived game quality; however, their large volume renders manual analysis inefficient. This study explores cross-platform sentiment patterns of TheoTown using a Support Vector Machine (SVM) classification approach. A dataset comprising 24,754 Google Play Store reviews and 1,452 Steam reviews, collected between January 2021 and December 2025, was processed using a structured pipeline that included text cleaning, normalization, tokenization, stopword removal, and stemming, followed by TF-IDF feature extraction. The findings indicate that a linear SVM model delivers consistently strong performance across both platforms, achieving F1 Scores exceeding 97%. Nevertheless, differences appear in probabilistic evaluation, where the Google Play Store dataset attains a higher AUC (0.8501) than Steam (0.6114). Both datasets are highly dominated by positive sentiment (above 94%), yet the Steam model fails to detect negative instances, highlighting the effects of severe class imbalance and limited data. These results emphasize that platform ecosystems influence both sentiment expression and model performance, underscoring the importance of cross-platform analysis.
Penerapan Squeeze-and-Excitation Attention pada DenseNet169 untuk Klasifikasi Multi-Kelas Citra X-Ray Dada: Squeeze-and-Excitation Attention on DenseNet169 for Multi-Class Classification of Chest X-Ray Images Daulay, Lyra Zulyanda; Negara, Benny Sukma; Vitriani, Yelfi; Iskandar, Iwan; Kurnia, Fitra
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.v6i2.2665

Abstract

Citra X-ray dada (CXR) ialah satu dari metode pencitraan medis yang banyak diterapkan guna mendeteksi banyak penyakit paru diantaranya COVID-19 serta pneumonia. Meskipun model deep learning yang basisnya Convolutional Neural Network (CNN) sudah banyak diterapkan untuk klasifikasi citra medis, model CNN konvensional masih memiliki keterbatasan dalam menyoroti fitur penting pada citra yang memiliki kompleksitas tinggi serta kemiripan pola antar kelas penyakit. Kondisi tersebut dapat menyebabkan model kesulitan dalam mengekstraksi fitur yang paling relevan untuk proses klasifikasi. Oleh sebab itu, penelitian mengusulkan penerapan attention mechanism berupa modul Squeeze-and-Excitation (SE) pada arsitektur DenseNet169 guna meningkatkan kemampuan model dalam menekankan fitur penting dari CXR. Kontribusi utama penelitian ini adalah menganalisis pengaruh mekanisme attention terhadap peningkatan kualitas ekstraksi fitur pada klasifikasi multi-kelas citra CXR. Dataset diterapkan pada penelitian ini terdiri dari 3.000 citra yang diklasifikasikan kedalam tiga kelas yakni Normal, COVID-19, serta Pneumonia dengan pembagian data sebesar 80% untuk pelatihan dan 20% untuk validasi. Pelatihan model menggunakan optimizer Adam. Evaluasi model menggunakan confusion matrix dengan accuracy, precision, recall, dan F1 score. Temuan eksperimen mengindikasi bahwasanya model DenseNet169 baseline memperoleh akurasi senilai 95,8%, sedangkan model DenseNet169 dengan modul SE mencapai akurasi 96,5%. Temuan ini menegaskan bahwa SE meningkatkan representasi fitur sehingga performa klasifikasi lebih optimal.
Perancangan Tata Kelola TI Laboratorium Internet of Things PNUP Menggunakan Kerangka COBIT 2019: IT Governance Design for PNUP Internet of Things Laboratory Using the COBIT 2019 Framework Dewantara, Amhar Davi; Yusri, Iin Karmila; Santoso, Budy
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.v6i2.2668

Abstract

Laboratorium Internet of Things, Jurusan Teknik Informatika dan Komputer, Politeknik Negeri Ujung Pandang (Lab IoT PNUP) menjalankan fungsi ganda sebagai sarana praktikum mahasiswa sekaligus pusat riset dosen. Meskipun Standar Operasional Prosedur (SOP) institusional telah tersedia di tingkat jurusan, SOP tersebut belum diadopsi secara formal di tingkat operasional laboratorium, sehingga menimbulkan permasalahan berupa dokumentasi inventaris yang tidak memadai, pencatatan peminjaman perangkat yang tidak konsisten, serta kontrol akses yang lemah. Penelitian ini merancang sistem tata kelola TI untuk Lab Internet of Things (IoT) PNUP menggunakan kerangka kerja COBIT 2019, dengan mengikuti empat tahap Governance System Design Workflow. Sebelas design factor dianalisis menggunakan COBIT 2019 Design Toolkit untuk mengidentifikasi tujuh objektif tata kelola prioritas: EDM03, APO12, APO13, MEA03, DSS05, DSS04, dan DSS06. Pengukuran kapabilitas melalui kuesioner yang diisi oleh empat responden menunjukkan bahwa seluruh domain berada pada Capability Level 1, dengan kesenjangan +2 hingga +3 level terhadap target masing-masing. Mempertimbangkan skala Lab IoT PNUP sebagai organisasi kecil, diusulkan peta jalan perbaikan bertahap dalam tiga fase: jangka pendek (0–6 bulan) berfokus pada formalisasi proses, jangka menengah (6–18 bulan) memperkuat keamanan dan kepatuhan, serta jangka panjang (18–36 bulan) menginstitusionalisasikan tata kelola risiko, sebagai panduan aksi terstruktur peningkatan kematangan tata kelola TI Lab IoT PNUP.
Factors Causing Ineffectiveness of Capex-Opex Management on the Reliability of Coal-Fired Power Plants Fachrudin, Mohammad Anang; Gunarta, I Ketut
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.v6i3.2670

Abstract

This study examines the ineffectiveness of Capital Expenditure (Capex) and Operational Expenditure (Opex) management in improving the reliability of coal-fired power plants in isolated electricity systems, using PLTU Bolok and PLTU Ropa in East Nusa Tenggara as case study units. The study is motivated by fluctuations in Equivalent Availability Factor (EAF) and Equivalent Forced Outage Rate (EFOR) during 2019-2024, despite recurring maintenance and investment expenditures. A descriptive case-study design was applied, combining reliability and maintenance performance analysis with Root Cause Analysis (RCA) using a Fishbone Diagram, Pareto Analysis, and Five Whys. The dataset includes Capex and Opex realization, FOH, POH, downtime, maintenance backlog, and the composition of preventive and corrective maintenance. The findings show that ineffective Capex-Opex management is primarily driven by equipment degradation, maintenance delays, high backlog levels, delays in spare-part procurement, delayed critical investments, and the dominance of corrective maintenance. The novelty of this study lies in integrating cost-allocation evaluation, reliability indicators, and root-cause diagnosis into a single analytical framework for isolated coal-fired power plant systems. In practice, the results imply that reliability improvement should prioritize reliability-based maintenance planning, backlog reduction, control of critical-spare procurement, and Capex prioritization based on asset criticality rather than budget magnitude alone.
Residential and Commercial Building Classification Based on Street-Level Images Using Deep Learning Atsari, Najmi Fadhila; Melia, Tisha; Sihombing, Aland Polma Naek; Fatayat, Fatayat
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.v6i3.2676

Abstract

The classification of buildings into residential and commercial categories is essential for computer vision applications that support urban analysis and automated decision-making. Accurate identification of building functions from visual data enables downstream applications, such as service differentiation and resource allocation. However, manual image-based classification is inefficient and subjective, particularly when applied to large-scale datasets. This study proposes a deep learning approach to classifying residential and commercial buildings using street-level images. A dataset comprising 882 images was collected from publicly available sources and categorized based on visual characteristics. The dataset was divided into training, validation, and test sets in a 60:20:20 ratio. The preprocessing stages included data cleaning, labeling, cropping, and resizing. Two models were evaluated: a conventional Convolutional Neural Network (CNN) and MobileNetV2 with transfer learning. Model performance was optimized by tuning the batch size and learning rate. The experimental results show that MobileNetV2 achieved the best performance with a batch size of 32 and a learning rate of 0.0001, attaining an accuracy of 92.05% and precision, recall, and F1-score values of 91.46%. Evaluation using a confusion matrix indicated low misclassification rates both building categories. These results demonstrate that deep learning models can effectively classify buildings based on visual data.
Lean Office in Administrative Billing and Vendor Payment Processes: A Systematic Literature Review Islamicsia, Princeca DW; Karningsih, Putu Dana
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.v6i3.2711

Abstract

Administrative billing and vendor payment processes frequently experience delays due to document waiting times, repeated verification, and fragmented information flows. Although Lean Office has been widely adopted to reduce non-value-added activities in office environments, evidence regarding its implementation remains fragmented, particularly in billing and vendor payment processes. This study systematically reviews Lean Office implementation in administrative activities, focusing on billing, document verification, approval flows, and vendor payments. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines, literature was collected from Scopus and Google Scholar using keywords related to Lean Office, administrative waste, billing, vendor payments, document verification, and non-value-added activities. From 59 initial records, eight articles met the inclusion and quality criteria and were analyzed using thematic synthesis. The findings reveal that waiting, extra processing, defective information, and document transportation are the most common forms of waste. Value Stream Mapping, Process Activity Mapping, root cause analysis, and standardization are the predominant analytical approaches. The review links major waste categories with practical improvement strategies, including document standardization, simplified approval procedures, digital integration, service-level targets, and early document validation. These findings provide practical guidance for redesigning billing and vendor payment processes to improve administrative efficiency, transparency,  process reliability.
Decision-Making on Additional Power Supply for the Timor System: A Systematic Literature Review of Analytic Network Process Applications Mahaprasetya, I Dewa Gde Budhita; Gunarta, I Ketut
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.v6i3.2712

Abstract

This study employs a Systematic Literature Review (SLR) to synthesize empirical findings on the application of the Analytic Network Process (ANP) in energy planning and power-supply decision-making. The review identifies commonly used evaluation criteria, assessed alternatives, and strategic implications for electricity-system planning, particularly in constrained or semi-isolated systems such as the Timor System. The review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 framework, including identification, screening, eligibility assessment, and inclusion. Relevant literature was retrieved from Scopus and Google Scholar using keywords related to ANP, power-system planning, energy storage, generation expansion, and electricity decision-making. Of 52 records identified, eight studies satisfied the inclusion, eligibility, and quality-assessment criteria and were synthesized. The findings show that ANP effectively evaluates alternatives involving interdependent technical, operational, economic, environmental, and policy criteria. Battery Energy Storage Systems (BESS) and other flexible low-carbon technologies are generally preferred when reliability, flexibility, and policy alignment are prioritized, whereas conventional thermal generation remains competitive under cost-oriented scenarios. This review transforms dispersed ANP evidence into a structured decision-making framework for the Timor System and recommends evaluating future power-supply alternatives using reliability-oriented, scenario-based, and policy-aligned weighting instead of relying solely on economic comparisons.
Klasifikasi Aritmia Menggunakan Fitur Sinyal Elektrokardiogram dan Heart Rate Variability dengan Algoritma XGBoost: Arrhythmia Classification Using Electrocardiogram Signal Features and Heart Rate Variability with the XGBoost Algorithm Salsabi, Siti; Antika, Bella; Martiza, Zahara; Lam, Theo Helena Rikie; Prabowo, 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.v6i3.2720

Abstract

Aritmia jantung merupakan gangguan kardiovaskular yang dapat menyebabkan stroke, gagal jantung, dan kematian mendadak akibat gangguan irama jantung apabila tidak terdeteksi sejak dini. Sinyal Elektrokardiogram (ECG) digunakan untuk mendeteksi aritmia, namun klasifikasi masih menjadi tantangan akibat kompleksitas pola gelombang, kemiripan antarkelas, dan ketidakseimbangan data. Penelitian sebelumnya umumnya memanfaatkan fitur morfologi ECG atau Heart Rate Variability (HRV) secara terpisah, sehingga belum merepresentasikan karakteristik sinyal secara menyeluruh. Penelitian ini bertujuan untuk mengklasifikasikan aritmia menggunakan kombinasi fitur ECG berbasis denyut jantung dan fitur HRV pada domain waktu dengan algoritma Extreme Gradient Boosting (XGBoost). Data berasal dari MIT-BIH Arrhythmia Database yang berisi sinyal ECG satu kanal beserta anotasi denyut jantung. Tahap prapemrosesan meliputi exploratory data analysis, penanganan nilai hilang, zero padding, interpolasi linier, dan normalisasi menggunakan StandardScaler. Fitur HRV yang digunakan meliputi MeanRR, SDNN, RMSSD, dan pNN50. Model dievaluasi menggunakan accuracy, precision, recall, F1-score, dan confusion matrix. Hasil menunjukkan akurasi sebesar 99,16%, yang menunjukkan kemampuan sangat baik dalam membedakan denyut jantung normal dan aritmia. Integrasi fitur HRV dan ECG meningkatkan representasi data serta performa klasifikasi, meskipun ketidakseimbangan kelas masih menjadi tantangan pada beberapa kategori.
Pengelompokan dan Prediksi Distribusi Guru ASN Orang Asli Papua dan Non-Orang Asli Papua dengan Pendekatan Data Mining: Clustering and Prediction of the Distribution of Civil Servant Teachers of Papuan and Non-Papuan Origin Using a Data Mining Approach Arfan, Usman; Fajriyati, Fauzia
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.v6i3.2742

Abstract

Pemerataan distribusi guru ASN menjadi isu penting dalam penyediaan layanan pendidikan yang berkeadilan, terutama di Kabupaten Nabire yang memiliki karakteristik wilayah yang beragam, termasuk perkotaan, pesisir, dan wilayah dengan aksesibilitas terbatas. Penelitian ini bertujuan untuk menganalisis distribusi guru ASN Orang Asli Papua (OAP) dan non-OAP pada satuan pendidikan di Kabupaten Nabire menggunakan pendekatan data mining. Data penelitian berupa data sekunder dari Dinas Pendidikan Kabupaten Nabire tahun 2025 yang mencakup 256 satuan pendidikan dengan total 2.147 guru ASN, terdiri atas 364 guru OAP (16,95%) dan 1.783 guru non-OAP (83,05%). Data ditransformasikan menjadi data agregat per satuan pendidikan melalui seleksi atribut, pembersihan data, penanganan nilai kosong, penghapusan duplikasi, agregasi, dan normalisasi. K-Means digunakan untuk mengelompokkan satuan pendidikan, sedangkan Naive Bayes, k-Nearest Neighbors, dan Decision Tree digunakan untuk mengklasifikasikan kategori distribusi. Hasil clustering menghasilkan tiga cluster utama. Cluster 1 menunjukkan keterwakilan OAP tinggi dengan jumlah guru relatif kecil, Cluster 2 didominasi non-OAP dengan jumlah guru besar, sedangkan Cluster 3 mencakup 179 satuan pendidikan (69,92%) dan menunjukkan dominasi guru non-OAP. Decision Tree memberikan performa terbaik dengan AUC 0,994, accuracy 0,992, precision 0,992, recall 0,992, dan F1-score 0,992. Temuan menunjukkan distribusi guru ASN OAP belum proporsional, terutama pada kategori Tidak ada OAP dan Rendah.

Page 55 of 59 | Total Record : 581

 53   54   55   56   57 

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