Article Per Year (5 Year)
p-Index From 2021 - 2026
7.507
P-Index
This Author published in this journals
All Journal Jurnal TIMES JITK (Jurnal Ilmu Pengetahuan dan Komputer) Jurnal Mantik Penusa INTECOMS: Journal of Information Technology and Computer Science The IJICS (International Journal of Informatics and Computer Science) JOURNAL OF SCIENCE AND SOCIAL RESEARCH Jurnal Riset Informatika ComTech: Computer, Mathematics and Engineering Applications Jurnal Mantik bit-Tech JATI (Jurnal Mahasiswa Teknik Informatika) Journal of Intelligent Decision Support System (IDSS) JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Instal : Jurnal Komputer Bulletin of Information Technology (BIT) Jurnal Minfo Polgan (JMP) BEES: Bulletin of Electrical and Electronics Engineering Jurnal Nasional Teknologi Komputer Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) Technologica Jurnal Hasil Pengabdian Masyarakat (JURIBMAS) Journal of Artificial Intelligence and Digital Business Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Jurnal Testing dan Implementasi Sistem Informasi Journal of Algorithmic Digital Engineering and Networks The Journal of Information Technology, Computer Science, and Electrical Engineering
Muhammad Iqbal
Universitas Pembangunan Panca Budi
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Languange, Linguistic, Communication & Media Library & Information Science Mathematics Social Sciences

Published : 58 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 58 Documents
Search

 2   3   4   5   6 
Analisis Algoritma Neural Network Dan Regresi Linier Untuk Memprediksi Permintaan Layanan Kampus Berbasis Data Mahasiswa di AMIK Medicom Robin Antoni; Muhammad Iqbal; Zulham Sitorus
Jurnal Nasional Teknologi Komputer Vol 6 No 3 (2026): Juli 2026
Publisher : CV. Hawari

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The increasing number of students and the growing adoption of digital services have made campus service demand more dynamic, creating a need for accurate prediction methods to support service planning and data-driven decision-making. This study aims to analyze and compare the performance of Neural Network and Linear Regression algorithms in predicting campus service demand based on student data at AMIK Medicom. The dataset consists of student-related variables, including the number of active students and the percentage of digital service utilization as predictor variables, while total campus service demand is used as the target variable. The data were collected from September 2025 to February 2026. The research procedure involved data collection, data preprocessing, the development of Linear Regression and Neural Network models, and model evaluation using the coefficient of determination (R²), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and prediction accuracy. The results indicate that both methods are capable of predicting campus service demand effectively. The Linear Regression model achieved an R² value of 0.987, an MAE of 245.60, an RMSE of 301.20, and an accuracy rate of 91.4%. Meanwhile, the Neural Network model achieved an R² value of 0.996, an MAE of 118.30, an RMSE of 156.50, and an accuracy rate of 96.8%. These findings demonstrate that the Neural Network model outperforms Linear Regression, as evidenced by its higher R² value and lower error rates. Therefore, Neural Network is recommended as a more effective prediction model for supporting data-driven planning and management of campus services at AMIK Medicom.
KLASIFIKASI TEKS KOMENTAR MOBILE LEGENDS DALAM GOOGLE PLAY PADA TAHUN 2025 DENGAN ALGORITMA NAIVE BAYES Eva Mufida Padilla; Muhammad Iqbal
Jurnal TIMES Vol 15 No 1 (2026): Jurnal TIMES
Publisher : STMIK TIME

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51351/jtm.15.1.2026902

Abstract

Penelitian ini bertujuan untuk mengklasifikasikan sentimen komentar pengguna aplikasi Mobile Legends di Google Play pada bulan November 2025 menggunakan algoritma Naive Bayes. Data diperoleh dengan melakukan web scraping terhadap 2.000 komentar dari aplikasi Mobile Legends dalam periode pengumpulan data setahun ke belakang hingga bulan November 2025. Komentar kemudian dikelompokkan berdasarkan rating bintang, dengan kriteria sentimen positif untuk rating 3-5 bintang dan sentimen negatif untuk rating 1-2 bintang. Dari dataset yang dikumpulkan, diperoleh 1.213 komentar dengan sentimen negatif (60,7%) dan 705 komentar dengan sentimen positif (35,2%). Tahapan penelitian mencakup preprocessing teks, vektorisasi TF-IDF dengan maksimal 1.000 fitur, serta pelatihan model Naive Bayes multinomial menggunakan split data 80:20. Evaluasi model menggunakan metrik classification report yang mencakup precision, recall, dan F1-score. Hasil penelitian menunjukkan bahwa algoritma Naive Bayes mencapai akurasi sebesar 83%, dengan precision 0,82 dan recall 0,94 untuk klasifikasi sentimen negatif, serta precision 0,84 dan recall 0,62 untuk sentimen positif. F1-score keseluruhan mencapai 0,82 dengan nilai rata-rata tertimbang, menunjukkan performa model yang baik dalam mengklasifikasikan sentimen komentar pengguna. Hasil ini menginformasikan bahwa pengguna Mobile Legends lebih banyak memberikan komentar negatif, yang dapat menjadi masukan berharga bagi pengembang untuk meningkatkan kualitas aplikasi.
LSTM DENGAN DEEP LEARNING UNTUK KLASIFIKASI OPINI PUBLIK KELANGKAAN BAHAN BAKAR PASCA BANJIR DI MEDIA SOSIAL X Aidul Safii; Muhammad Iqbal
Jurnal TIMES Vol 15 No 1 (2026): Jurnal TIMES
Publisher : STMIK TIME

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51351/jtm.15.1.2026903

Abstract

Penelitian ini berjudul Pemanfaatan LSTM dalam Deep Learning untuk Klasifikasi Opini Publik Kelangkaan Bahan Bakar Pasca Banjir di Media Sosial X. Penelitian bertujuan menganalisis sentimen publik terkait kelangkaan bahan bakar pasca banjir dengan menerapkan metode Long Short-Term Memory (LSTM) pada unggahan di platform X (dahulu Twitter). Data dikumpulkan menggunakan tool Tweet-Harvest melalui API X, kemudian diproses dengan tahapan preprocessing seperti case folding dan tokenizing, serta pelabelan otomatis menggunakan model transformer IndoBERT. Sebanyak 8.850 tweet tentang kelangkaan bahan bakar pasca banjir diklasifikasikan ke dalam dua kategori sentimen, yaitu positif dan negatif. Model LSTM dibangun dengan satu layer embedding, satu layer LSTM berukuran 128 unit, dan satu layer dropout, lalu dievaluasi menggunakan metrik akurasi, precision, recall, dan f1-score. Hasil pengujian menunjukkan bahwa model mencapai akurasi keseluruhan sebesar 85,11% dengan performa yang lebih baik dalam mengklasifikasikan sentimen negatif dibandingkan positif. Mayoritas tweet yang dianalisis cenderung menunjukkan sentimen negatif terhadap kelangkaan bahan bakar, mencerminkan keresahan masyarakat terhadap ketersediaan serta distribusi energi pasca bencana. Simpulan penelitian menegaskan bahwa metode LSTM efektif digunakan untuk menganalisis opini publik mengenai kelangkaan bahan bakar dan temuannya dapat menjadi masukan penting bagi pemangku kebijakan dalam merumuskan respons yang tepat. Penelitian ini juga memberikan kontribusi pada pengembangan studi analisis sentimen di Indonesia, khususnya terkait isu-isu kebencanaan dan krisis energi dengan pendekatan deep learning
ANALISIS SENTIMEN PUBLIK PADA PENANGANAN BENCANA DARI KOMENTAR LIVE YOUTUBE KUNJUNGAN PRESIDEN PRABOWO DI ACEH TENGGARA MENGGUNAKAN INDOBERT Maisya Fitri Anugrah; Muhammad Iqbal
Jurnal TIMES Vol 15 No 1 (2026): Jurnal TIMES
Publisher : STMIK TIME

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51351/jtm.15.1.2026904

Abstract

Penelitian ini dilatarbelakangi oleh tantangan dalam pemrosesan bahasa alami (NLP), khususnya pada tugas analisis sentimen, di mana metode konvensional seringkali kesulitan menangkap konteks semantik yang kompleks. Tujuan dari studi ini adalah untuk meningkatkan akurasi prediksi dengan menerapkan metode Transfer Learning menggunakan model BERT (Bidirectional Encoder Representations from Transformers). Metodologi penelitian meliputi tahap pra-pemrosesan data, tokenisasi menggunakan WordPiece, dan proses fine-tuning model IndoBERT-Base Uncased pada dataset komentar video YouTube. Kinerja model dievaluasi menggunakan metrik akurasi, presisi, recall, dan F1-score, serta dibandingkan dengan model baseline. Hasil penelitian menunjukkan bahwa model yang diusulkan berhasil mencapai akurasi sebesar 43%, yang menunjukkan peningkatan signifikan dibandingkan metode sebelumnya, hasil dan proses pengujian ada di https://github.com/tomylive/IndoBERT. Kesimpulannya, penerapan arsitektur BERT terbukti sangat efektif dalam menyelesaikan permasalahan analisis sentimen dan menawarkan solusi yang lebih handal untuk pemahaman teks otomatis.
Analysis and Classification of Emergency Conditions Endangering Humans Based on Operational Data Using Random Forest and Support Vector Machine Methods (Case Study: UPT Basarnas Medan) Dwika Ardya; Muhammad Iqbal; Muhammad Irfan Syarif
Bahasa Indonesia Vol 18 No 06 (2026): Instal : Jurnal Komputer
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jurnalinstall.v18i06.532

Abstract

Operation Search and Rescue (SAR) in phase DETRESFA demands fast and accurate decision-making because it involves real, life-threatening situations. The Medan Basarnas UPT faces challenges in classifying four main categories of incidents: ship accidents (Y1), accidents requiring special handling (Y2), natural disasters (Y3), and conditions endangering humans (Y4), which have so far been done manually and subjectively. This study aims to build a decision support system based on data collection. machine learning to improve the efficiency of resource deployment through objective classification of emergency conditions. Performance comparisons were conducted between the algorithms Random ForestAnd Support Vector Machine(SVM) based on operational features such asresponse time, number of victims, number of personnel, and distance of the incident. The test results show thatRandom Forestprovides superior performance compared to SVM across all evaluation metrics, with accuracy 86.4%, AUC value 93.9%, F1-score 85.5%, And Matthews Correlation Coefficient (MCC) 0.759. AnalysisConfusion Matrixconfirm that Random Foresthas better stability in recognizing operational feature patterns for most target categories, including its more consistent ability in handling less dominant classes than SVM. Although the Y2 category is still a challenge for both models, Random Forestproven to be much more robust with an accuracy of 49.6% compared to SVM which only achieved 16.5%. This research proves that Random Forestis a more reliable and consistent model to support SAR practitioners in improving the accuracy of field responses, efficiency of resource deployment, and minimizing the risk of loss of life.
Analysis of Artificial Neural Network and Support Vector Machine Algorithms in Predicting General or Vocational School Choices for Panca Budi Middle School Students in Medan Hindra Syahputra; Muhammad Iqbal; Khairul
Bahasa Indonesia Vol 18 No 06 (2026): Instal : Jurnal Komputer
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jurnalinstall.v18i06.534

Abstract

Determining the educational trajectory following junior high school graduation represents a pivotal decision shaped by students' academic competence, personal interests, and inherent personality inclinations. In practice, this selection process is frequently carried out in a subjective manner, which risks producing a disconnect between students' genuine potential and their eventual educational placement. The present research seeks to examine and compare the predictive performance of the Artificial Neural Network (ANN) and Support Vector Machine (SVM) algorithms in forecasting students' preference for either senior high school (SMA) or vocational high school (SMK) among learners at SMP Panca Budi Medan. A total of 220 student records were employed as the dataset, incorporating academic performance data alongside RIASEC personality scores as the predictor variables. All data processing was executed within the WEKA application environment utilizing 10-fold cross validation as the evaluation scheme. The ANN model was constructed through the Multilayer Perceptron approach, while SVM relied on the Sequential Minimal Optimization (SMO) technique. Experimental findings revealed that both classifiers attained an identical accuracy rate of 85.45%; however, the ANN model demonstrated a superior ROC Area value of 0.925 relative to the SVM's 0.849, signifying that ANN possesses stronger discriminative capability in distinguishing SMA from SMK selections. The study confirms that integrating academic metrics with RIASEC scores provides a viable foundation for constructing a machine learning-driven school-choice prediction system that is both more objective and better attuned to individual student profiles.
Optimization of Indosat's Fiber to the Home (FTTH) Network for Customer Satisfaction Using the Random Method Forest and Naïve Bayes Jelly Rolleys Sitompul; Muhammad Iqbal; Muhammad Irfan Sarif
Bahasa Indonesia Vol 18 No 06 (2026): Instal : Jurnal Komputer
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jurnalinstall.v18i06.536

Abstract

Currently, customer satisfaction is a crucial indicator in evaluating the quality of Fiber to the Home (FTTH) services. This study aims to analyze customer satisfaction with Indosat HiFi services and compare the performance of the Random Forest and Gaussian Naive Bayes algorithms in predicting customer satisfaction levels. The research dataset consists of Quality of Service (QoS) parameters and customer operational data, including latency, throughput, packet loss, downtime, response time, and complaint count. The data was processed using a Machine Learning approach through preprocessing, model training, and performance evaluation stages. The research results showed that Random Forest produced the best performance with 98.8% accuracy, 100% recall, 99.4% F1-score, and 95.9% CV Mean. Meanwhile, Gaussian Naïve Bayes obtained 97.6% accuracy, 98.8% F1-score and 95.2% CV Mean. The research findings show that service quality and user experience factors influence the level of customer satisfaction. The resulting model has great potential to support data-based decision making to improve the quality of FTTH services. The research data was processed and then tested with a ratio of 80:20. Model evaluation was carried out using accuracy, recall, F1-score and cross validation.
Integration of FP-Growth Algorithm with XGBoost and SHAP to Predict Consumer Product Sales Patterns at CV. Mitra Ridge Syaiful Rahman Lubis; Muhammad Syahputra Novelan; Muhammad Iqbal
Bahasa Indonesia Vol 18 No 06 (2026): Instal : Jurnal Komputer
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jurnalinstall.v18i06.545

Abstract

This study aims to develop an integrative model based on data mining and machine learning to analyze purchasing patterns and predict consumer product sales at CV. Mitra Ridge. The approach used combines the FP-Growth algorithm to discover product association patterns (frequent itemsets and association rules), XGBoost as a gradient boosting-based sales prediction model, and SHAP (SHapley Additive Explanations) to provide transparent interpretability of the model's prediction results. The data used is sales transaction data from October 2024 to September 2025, which includes 500 transactions with various types of consumer products. The results show that the integration of association pattern features from FP-Growth as additional input to the XGBoost model can improve prediction accuracy compared to a single XGBoost model without integration. SHAP analysis revealed that purchase frequency, product category, and product combination patterns are the most influential factors in sales prediction. This integrative model is proven to be superior in performance and provides deeper business insights, so it can be used as an operational decision support system in stock management, bundling strategies, and data-driven marketing planning in consumer retail companies.  
Analisis Pengelompokan Pengunjung Perpustakaan Fakultas Sains dan Teknologi Menggunakan Metode K-Means Clustering Maha Valne Datin; Muhammad Iqbal
Technologica Vol. 5 No. 2 (2026): Technologica
Publisher : Green Engineering Society

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55043/technologica.v5i2.561

Abstract

Penelitian ini bertujuan untuk mengelompokkan pengunjung Perpustakaan Fakultas Sains dan Teknologi berdasarkan jurusan dan intensitas kunjungan menggunakan metode K-Means Clustering, guna mendukung peningkatan kualitas layanan perpustakaan secara tepat sasaran. Data yang digunakan merupakan data absensi pengunjung Perpustakaan Fakultas Sains dan Teknologi tahun 2025 yang mencakup informasi program studi dan frekuensi kunjungan mahasiswa. Metode yang digunakan dalam penelitian ini adalah K-Means Clustering, yaitu salah satu teknik data mining yang berfungsi untuk mengelompokkan data berdasarkan tingkat kemiripan karakteristik. Sebelum dilakukan proses clustering, data melalui tahap pra-pemrosesan yang meliputi pembersihan data, seleksi fitur, normalisasi nilai, serta konversi data kategorik ke dalam bentuk numerik. Jumlah klaster yang digunakan dalam penelitian ini adalah tiga klaster yang merepresentasikan tingkat intensitas kunjungan rendah, sedang, dan tinggi. Hasil penelitian menunjukkan bahwa metode K-Means Clustering mampu mengelompokkan pengunjung perpustakaan secara objektif dan sistematis dengan distribusi klaster sebesar 20,6% pada klaster intensitas rendah (C1), 54,4% pada klaster intensitas sedang (C2), dan 25,0% pada klaster intensitas tinggi (C3), serta mengungkap adanya perbedaan pola pemanfaatan perpustakaan berdasarkan jurusan dan intensitas kunjungan mahasiswa. Hasil clustering ini dapat dimanfaatkan sebagai dasar pengambilan keputusan dalam pengembangan layanan, penyesuaian koleksi, serta peningkatan efektivitas pengelolaan perpustakaan
Clustering UMKM Berbasis Aktivitas E-Commerce Menggunakan K-Means untuk Strategi Pengembangan Usaha Siska Mayasari Rambe; Muhammad Iqbal
Technologica Vol. 5 No. 2 (2026): Technologica
Publisher : Green Engineering Society

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55043/technologica.v5i2.562

Abstract

Usaha Mikro, Kecil, dan Menengah (UMKM) memiliki peran penting dalam perekonomian Indonesia, khususnya dalam menciptakan lapangan kerja dan meningkatkan Produk Domestik Bruto (PDB). Perkembangan e-commerce mendorong UMKM untuk memanfaatkan platform digital dalam memasarkan produk sehingga menghasilkan data aktivitas penjualan yang dapat dianalisis lebih lanjut. Penelitian ini bertujuan untuk mengidentifikasi pola segmentasi UMKM berdasarkan aktivitas e-commerce menggunakan algoritma K-Means Clustering sebagai dasar penyusunan strategi pengembangan usaha berbasis data. Dataset yang digunakan merupakan data sintetis yang dibangun untuk mensimulasikan 50 UMKM berdasarkan distribusi aktivitas e-commerce yang umum ditemukan pada pelaku usaha digital. Data dibangkitkan menggunakan pendekatan random uniform distribution dengan rentang transaksi per bulan antara 50–2000 transaksi, revenue e-commerce antara Rp4.000.000–Rp180.000.000, engagement rate antara 0,10–0,90, serta jumlah platform antara 1–4 platform digital. Variabel revenue juga dirancang memiliki kecenderungan berkorelasi positif dengan jumlah transaksi agar lebih merepresentasikan kondisi aktivitas penjualan UMKM. Data dinormalisasi menggunakan metode Min-Max Scaling dan dikelompokkan ke dalam tiga klaster menggunakan algoritma K-Means. Hasil penelitian menunjukkan bahwa algoritma K-Means mampu mengelompokkan UMKM ke dalam tiga kategori utama, yaitu UMKM dengan performa tinggi, performa menengah, dan performa rendah berdasarkan aktivitas e-commerce. Evaluasi menggunakan metode Silhouette Coefficient menghasilkan nilai rata-rata sebesar 0,292, yang menunjukkan bahwa struktur klaster yang dihasilkan masih tergolong lemah dan masih terdapat tumpang tindih karakteristik antar klaster. Meskipun demikian, hasil clustering tetap mampu memberikan segmentasi awal UMKM yang dapat dimanfaatkan sebagai dasar penyusunan strategi pengembangan usaha berbasis data di era ekonomi digital
Co-Authors , Arpan Abdul Khaliq Abdul Muin Nasution Ade Guna Suteja Ahkyar Khadafi Aidul Safii Akmal Pratama Harahap Amin, Muhammad Andi Ernawati Andi Ernawati Andysah Putera Utama Siahaan Anzas Ibezato Zalukhu Anzas Ibezato Zalukhu Ardiansyah Ardiansyah Astri Aprilia Pratiwi Atja Ramadhan Ayu Ofta Sari Bagas Alivia M Boy Rizky Akbar Chairul Rizal Dadang Iskandar Mulyana` Darmeli Nasution Dika Dika Dimas Armadansyah DWI SURYANTO Dwika Ardya Efendi, Syahril Eko Hariyanto Eva Mufida Padilla Firdaus Firdaus Hafizh Sallam Hafni Hafni Hindra Syahputra Indra Nasution Irvanizam Irvanizam Irwan Irwan Irwan Syahputra Jelly Rolleys Sitompul Kairul Fahmi Khairul Khairunnisa Khairunnisa Kurnia Wira Syahputra Leni Marlina M. Azhari Rizko Maha Valne Datin Maida Indrayani Maisya Fitri Anugrah Marsini Sibuea Mhd Arfan Sitorus Muhammad Adli Afdika Muhammad Eka Muhammad Irfan Sarif Muhammad Irfan Syarif Muhammad Israr Fathoni Muhammad Noor Hasan Siregar Muhammad Syahputra Novelan Muhammad Zen Nadya Septiani Nadya Nelviony Parhusip Niska, Debi Yandra Nurlina Sari Harahap Puspita Wanny Putra, Randi Rian Rian Farta Wijaya Rian Farta Wijaya Wijaya Rindi Antika Robin Antoni Rudi Hermawan Sapna Indah Br Ginting Sartika Siburian Siska Mayasari Rambe Siti Hapsoh Lubis Siti Nurhaliza Sofyan Siti Nurhaliza Sofyan Sitorus, Zulham Sri Wahyuni Suhardiansyah Sumarno Supiyandi Supiyandi Susilawati Yahya Syaiful Asmi Hasibuan Syaiful Rahman Lubis Wina Aulia Zulham