Article Per Year (5 Year)
p-Index From 2021 - 2026
5.421
P-Index
This Author published in this journals
All Journal Joined Journal (Journal of Informatics Education Jurnal Teknologi Informatika dan Komputer Jurnal Pemberdayaan Komunitas MH Thamrin International Journal of Engineering, Science and Information Technology Jurnal Informatika Dan Tekonologi Komputer (JITEK) Jurnal Informatika Dan Tekonologi Komputer
Sondang Sibuea
Universitas Mohammad Husni Thamrin Jakarta
Astronomy Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Medicine & Pharmacology Nursing Physics Public Health Social Sciences Transportation Other

Published : 41 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 41 Documents
Search

 1   2   3   4   5 
Pengembangan Model Machine Learning untuk Rekomendasi Produk Berdasarkan Analisis Pola Pembelian Sibuea, Sondang; Widodo, Yohanes Bowo
Jurnal Teknologi Informatika dan Komputer Vol. 10 No. 2 (2024): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v10i2.2354

Abstract

Dalam era digital saat ini, sistem rekomendasi menjadi komponen penting dalam platform e-commerce untuk meningkatkan pengalaman pengguna dan penjualan. Penelitian ini bertujuan untuk mengembangkan model machine learning yang mampu merekomendasikan produk secara personalisasi berdasarkan analisis pola pembelian pengguna. Algoritma Collaborative Filtering dan Content-Based Filtering diterapkan dalam penelitian ini untuk mengidentifikasi preferensi pelanggan dan memberikan rekomendasi yang relevan. Dataset yang digunakan terdiri dari riwayat transaksi pengguna, informasi produk, serta atribut demografis pengguna. Model Collaborative Filtering menggunakan pendekatan berbasis pengguna dan produk untuk mengidentifikasi kemiripan antara pola pembelian, sedangkan model Content-Based Filtering menganalisis fitur produk untuk memberikan rekomendasi produk yang mirip dengan yang telah dibeli pengguna. Hasil dari kedua model ini dikombinasikan menggunakan teknik Hybrid Filtering untuk meningkatkan akurasi dan relevansi rekomendasi. Evaluasi model dilakukan dengan menggunakan metrik seperti precision, recall, Mean Average Precision (MAP), dan Mean Squared Error (MSE). Hasil eksperimen menunjukkan bahwa model hybrid mampu memberikan rekomendasi produk dengan tingkat akurasi yang lebih tinggi dibandingkan model individu. Model ini juga menunjukkan peningkatan dalam keterlibatan pengguna dan potensi peningkatan penjualan melalui rekomendasi yang lebih tepat sasaran. Penelitian ini menyimpulkan bahwa pengembangan sistem rekomendasi berbasis machine learning yang efektif dapat memberikan keuntungan kompetitif bagi platform e-commerce dengan meningkatkan kepuasan pengguna serta memperluas cakupan produk yang dipromosikan. Model ini juga dapat disesuaikan dengan kebutuhan pasar yang berbeda melalui penyesuaian parameter dan pengoptimalan berkelanjutan.
Artificial Intelligence for Unstructured Data Processing Widodo, Yohanes Bowo; Widyahastuti, Febrianti; Narji, Mohammad; Sibuea, Sondang
Jurnal Teknologi Informatika dan Komputer Vol. 11 No. 1 (2025): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v11i1.2542

Abstract

In the digital era, the volume of unstructured data such as text, images, audio, and video continues to increase exponentially. Processing unstructured data is a major challenge for various industries due to its high complexity and the difficulty of extracting relevant information. Artificial Intelligence (AI) has become an innovative solution in addressing this challenge through techniques such as Natural Language Processing (NLP), Computer Vision, and Machine Learning. This study aims to explore various AI methods used in processing unstructured data and examine their effectiveness in improving the efficiency and accuracy of data analysis. adopts a multidisciplinary approach that combines natural language processing (NLP), machine learning, and data analytics techniques to extract information from unstructured data, especially in the context of electronic medical records (EMR). This study will be conducted in several stages including data collection, data processing, model development, and evaluation of results. The results show that AI is not only able to automate the information extraction process but also improve the accuracy and speed of data analysis, which is very important in the context of decision making in the fields of healthcare, finance, and business. By using deep learning models and advanced algorithms, AI can identify patterns and relationships in complex data, thereby providing deeper insights for better decision making. The results of this study are expected to provide insight for developers and practitioners in optimizing the use of AI to manage unstructured data more effectively and efficiently.
YOLOv12 for Human Object Detection in Real-time Video Surveillance Systems Widodo, Yohanes Bowo; Sibuea, Sondang; Agustino, Rano
Jurnal Teknologi Informatika dan Komputer Vol. 11 No. 2 (2025): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v11i2.2789

Abstract

This research discusses the application of the YOLO (You Only Look Once) model to detect human objects in real-time video surveillance systems. This model was developed in response to the increasing need for efficiency and accuracy in video surveillance analysis, particularly in identifying abnormal or malicious activities. The application of deep learning technology, especially the YOLO model, has been shown to provide better performance in object recognition compared to traditional methods, such as SVM and Haar-Cascade, which often experience limitations in terms of speed and accuracy. One significant contribution of the use of YOLO lies in its ability to detect objects simultaneously in high-speed video, which is crucial in surveillance contexts that require rapid response to incidents. The implementation of YOLO also promises better collaboration between edge and cloud computing, allowing video processing to be carried out closer to the data source, reducing latency and improving data security. With this approach, the system can generate relevant information for rapid decision-making, such as monitoring human behavior in public settings and detecting suspicious activity. The analysis of this study highlights the significant potential of YOLO in improving real-time video surveillance systems and demonstrates that more accurate object detection capabilities can improve overall public safety. Through this model, we hope to revolutionize surveillance practices, adapt to modern needs, and provide a solid foundation for further development in the field of video surveillance.
Penerapan Algoritma Neural Network Dalam Prediksi Kedatangan Wisatawan Mancanegara di DKI Jakarta Melalui Pintu Masuk Bandara Soekarno-Hatta Fenty Tristanti Julfia; Sondang Sibuea; Eka Satryawati
Joined Journal (Journal of Informatics Education) Vol 8 No 1 (2025): Volume 8 Nomor 1 (2025)
Publisher : Universitas Ivet

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31331/joined.v8i1.3813

Abstract

Prediksi kedatangan wisatwan mancanegara di DKI Jakarta dapat membantu pemerintah dalam meningkatkan pendapatan dari sektor pariwisata. Selain meningkatkan pendapatan dengan adanya prediksi yang tepat untuk kedatangan wisatwan mancanegara di DKI Jakarta membantu pemerintah dalam mempersiapkan langkah-langkah strategis dalam membangun industri pariwisata. Metode Neural Network sebagai sekumpulan algoritma machine learning yang dirancang untuk mengenali pola data dengan meniru cara kerja sel saraf manusia. Neural Network sering digunakan untuk menyelesaikan masalah-masalah yang rumit dan berkaitan dengan identifikasi input, prediksi, pengenalan pola dan sebagainya. Penelitian yang akan dilakukan adalah penelitian eksperimen, dengan tahapan pengumpulan data, pengolahan data awal (data pre-prosesing), metode data yang diusulkan pada penelitian ini menggunakan metode Neural Network, dan pada tahap evaluasi dan validasi hasil pada penelitian ini berupa akurasi dalam RMSE dengan menggunakan tools Rapid Miner 5.3. Berdasarkan penelitian yang telah dilakukan menggunakan Rapid Miner 5.3 terhadap data time series kedatangan wisatawan mancanegara sebanyak 145 dataset. Metode Neural Network sudah berhasil diterapkan dalam prediksi kedatangan wisatawan mancanegara ke DKI Jakarta melalui pintu masuk Bandara Soekarno Hatta dengan diperoleh RMSE cukup baik yaitu sebesar 40439,085.
Rancang Bangun Aplikasi Monitoring Bimbingan Skripsi Berbasis Mobile pada Fakultas Komputer Universitas Mohammad Husni Thamrin Muhammad Ridwan Effendi; Eka Satryawati; Abu Sopian; Sondang Sibuea; Mohammad Ikshan Saputro
Jurnal Teknologi Informatika dan Komputer Vol. 9 No. 1 (2023): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v9i1.1374

Abstract

Skripsi pada setiap perguruan tinggi baik negeri maupun swasta nilainya sekitar 6 (enam) sks. Setiap mahasiswa pada akhir semester sebelum mereka lulus dan menjadi sarjana wajib untuk membuat skripsi. Pada pembuatan skripsi banyak sekali kendala-kendala yang dihadapi oleh mahasiswa, seperti dosen pembimbing tidak mempunyai catatan mengenai sampai tahapan mana mahasiswa yang telah melakukan bimbingan. Masalah lainnya seperti laptop mahasiswa yang rusak sehingga file bimbingan skripsi tidak bisa diakses atau dibuka. Adapun tujuan dari penelitian yaitu membuat aplikasi monitoring bimbingan skripsi berbasis mobile pada Fakultas Komputer Universitas Mohammad Husni Thamrin Jakarta untuk mengatasi permasalahan bimbingan skripsi mahasiswa pada Fakultas Komputer. Metode perancangan aplikasi yang digunakan dalam Monitoring Bimbingan Skripsi adalah model waterfall yaitu model pengembangan yang menggambarkan secara sistematis dan terurut dalam merancang sistem informasi yang terdiri dari beberapa tahap yaitu tahapan analisa kebutuhan sistem (requirement analysis), perancangan sistem (system design), pengembangan sistem (system development), pengujian sistem (integration and testing) dan penyerahan sistem ke pengguna atau user yang langsung menggunakan aplikasi, sedangkan yang terakhir adaah perawatan sistem (operation and maintenance).Terakhir adalah hasil dan target dari penelitian berupa aplikasi berbasis mobile dalam monitoring bimbingan skripsi yang dapat di install di handphone sehingga memudahkan mahasiswa, dosen dan Kepala Program Studi untuk memantau bimbingan skripsi.
YOLO in Suspicious Human Activity Recognition for Intelligent Environmental Security Systems: A Review Yohanes Bowo Widodo; Sondang Sibuea; Rano Agustino; Mohammad Narji
Jurnal Teknologi Informatika dan Komputer Vol. 12 No. 1 (2026): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v12i1.3243

Abstract

The rapid growth of intelligent environmental security systems has intensified the need for accurate and real-time suspicious human activity recognition. Computer vision techniques, particularly deep learning–based object detection models, have emerged as key enablers in addressing these challenges. Among them, You Only Look Once (YOLO) has gained significant attention due to its high detection speed, end-to-end architecture, and suitability for real-time surveillance applications. This review paper presents a comprehensive analysis of the application of YOLO-based models in suspicious human activity recognition for intelligent environmental security systems. It examines the evolution of YOLO architectures, their adaptations for activity and behavior analysis, and their integration with surveillance frameworks. The review further discusses commonly used datasets, performance evaluation metrics, and comparative results reported in existing studies. In addition, key challenges such as occlusion, varying illumination, complex backgrounds, privacy concerns, and computational constraints are highlighted. Finally, the paper outlines future research directions, including hybrid models, multi-modal data fusion, edge-based deployment, and explainable AI, to enhance the robustness and reliability of YOLO-driven security systems. This review aims to provide researchers and practitioners with a structured understanding of current advancements and open issues in YOLO-based suspicious human activity recognition.
Pengembangan Aplikasi Manajemen Inventaris Berbasis Android Guna Digitalisasi UMKM di Wilayah Jakarta Abu Sopian; Yohanes Bowo Widodo; Mohammad Ikhsan Saputro; Sondang Sibuea; Muhammad Ridwan Effendi
Jurnal Teknologi Informatika dan Komputer Vol. 10 No. 2 (2024): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v10i2.3581

Abstract

Manajemen inventaris konvensional pada Usaha Mikro, Kecil, dan Menengah (UMKM) retail di wilayah DKI Jakarta masih menghadapi kendala struktural yang masif, seperti tingginya risiko salah hitung stok, selisih data logistik, serta keterlambatan kronis dalam proses pengadaan kembali barang dagangan yang habis akibat ketiadaan sistem pencatatan yang terintegrasi. Penelitian ini bertujuan untuk melakukan rekayasa perangkat lunak guna membangun aplikasi manajemen inventaris mandiri berbasis Android yang andal dan adaptif untuk mengakselerasi digitalisasi operasional internal pelaku UMKM retail. Perangkat lunak ini dikembangkan secara terstruktur menggunakan metodologi pengembangan sistem model Waterfall dengan mengimplementasikan bahasa pemrograman Kotlin pada lapisan antarmuka pengguna, serta memanfaatkan mesin basis data SQLite lokal tertanam sebagai media penyimpanan data utama guna mewujudkan arsitektur offline-first. Hasil penelitian menunjukkan bahwa aplikasi yang dibangun berhasil mengintegrasikan seluruh fungsionalitas utama yang mencakup komponen 'Menu Barang Masuk' untuk melakukan update penambahan jumlah stok secara otomatis (+) dan 'Menu Barang Keluar' untuk melakukan update pengurangan jumlah stok secara real-time (-). Di sisi penyimpanan persisten, basis data SQLite lokal secara otonom mengolah sirkulasi arus logistik tersebut dan sukses memicu fungsi 'Peringatan Stok Kritis (<)' ketika kuantitas barang berada di bawah batas aman, sekaligus menginisiasi fitur 'Generate Laporan Otomatis' dalam format digital. Validasi keabsahan sistem melalui metode Black-box testing memberikan hasil pemenuhan fitur sebesar 100% valid tanpa adanya galat kritis, serta terbukti secara signifikan memangkas waktu stock opname harian para staf dari yang semula memakan waktu hitungan jam menjadi kurang dari 30 menit saja. Rekomendasi operasional dari penelitian ini ditujukan bagi pengembang sistem selanjutnya untuk menambahkan modul sinkronisasi data awan hibrida (hybrid cloud-sync) guna memfasilitasi kebutuhan pemantauan data jarak jauh secara multi-user oleh pemilik usaha tanpa mengorbankan ketahanan fitur luring aplikasi.
Environmental Engineering Urban Environmental Intelligence Framework for Air Quality Prediction Using Multi-Source Mobility and Climate Data Sondang Sibuea; Yohanes Bowo Widodo
International Journal of Engineering, Science and Information Technology Vol 6, No 3 (2026)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v6i3.1916

Abstract

Rising urban mobility, intensive anthropogenic activity, and limitations in conventional monitoring systems capable of delivering continuous spatial coverage have turned urban air pollution into a pressing environmental concern. Existing air-quality prediction approaches tend to depend on single-source observations or are built primarily for large metropolitan areas, which limits how well they apply to secondary cities with localized pollution dynamics. To address this, the study introduces an Urban Environmental Intelligence Framework that brings together multi-source air quality, climate, spatial, temporal, and air-quality information for urban air-quality prediction. Evaluation of the framework was conducted using hourly observations of pollutant concentrations (PM2.5, NO2, and CO), mobility indicators (traffic volume, vehicle count, average speed, and congestion index), meteorological variables, and urban spatial attributes, collected from Lhokseumawe, Indonesia. A multi-source XGBoost model was benchmarked against Single-Source XGBoost, Random Forest, and LSTM models using a chronological data partition and multiple evaluation metrics, including MAE, RMSE, MAPE, and R². The proposed framework achieved the strongest predictive performance across all target variables evaluated, attaining an R² of 0.912 and an RMSE of 5.84 µg/m³ for PM2.5 prediction. Ablation analysis confirmed that temporal and mobility information contributed most substantially to prediction accuracy, while climate and spatial variables provided complementary contextual value. Feature interpretation further revealed that traffic intensity, historical pollutant levels, and meteorological conditions were the dominant drivers of urban pollution outcomes. Overall, the proposed framework offers an effective environmental approach for supporting short-term air-quality forecasting, pollution hotspot identification, and evidence-based urban environmental management in secondary cities
Retrieval-Augmented Large Language Model for Institutional Knowledge Management and Decision Assistance in Public Organizations Yohanes Bowo Widodo; Sondang Sibuea
International Journal of Engineering, Science and Information Technology Vol 6, No 3 (2026)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v6i3.1904

Abstract

The increasing volume and complexity of institutional documents in public organizations create challenges in accessing reliable knowledge for administrative processes and evidence-based decision-making. Conventional knowledge management systems often rely on keyword-based retrieval, while standalone Large Language Models (LLMs) may generate inaccurate responses when processing domain-specific institutional information. This study proposes a domain-specific Retrieval-Augmented Generation (RAG) framework to enhance institutional knowledge management and AI-assisted decision support in public-sector organizations. The framework was developed using a Design Science Research approach with Universitas Malikussaleh as a case study. The proposed architecture integrates institutional knowledge base construction, semantic retrieval, grounded language generation, and source attribution mechanisms. A knowledge base comprising 416 official institutional documents was developed through document preprocessing, semantic chunking, embedding generation, and vector database indexing. The framework was evaluated using 200 institutional queries based on retrieval performance, response quality, explainability, and system efficiency metrics. The results demonstrate effective retrieval capability, achieving Precision@5 of 0.884, Recall@5 of 0.921, and Mean Reciprocal Rank of 0.895. Generated responses achieved 94.6% factual accuracy, 91.8% contextual relevance, and 96.5% source attribution accuracy, while the hallucination rate was reduced to 3.2%. Furthermore, the framework achieved an average response latency of 1.18 seconds, indicating practical feasibility for institutional applications. These findings demonstrate that integrating semantic retrieval with grounded LLM generation can improve knowledge accessibility, transparency, and reliability for AI-assisted decision support in public organizations. The proposed framework provides a practical foundation for trustworthy institutional knowledge services and supports more efficient, explainable, and evidence-based administrative decision-making across diverse institutional contexts
PERANCANGAN ROBOT PEMADAM API DENGAN PENGONTROLAN GERAK METODE PROPORTIONAL INTEGRAL DERIVATIVE (PID) MENGGUNAKAN SENSOR SONAR BERBASIS MIKROKONTROLLER Sondang Sibuea; Agung Rahmaddoni; Yohanes Bowo Widodo
Jurnal Informatika Dan Tekonologi Komputer (JITEK) Vol. 1 No. 3 (2021): November : Jurnal Informatika dan Teknologi Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jitek.v1i3.83

Abstract

This research designs and implements a control algorithm on a wheeled wall follower robot that uses a PID controller (Proportional, Integral, Differential) as a navigation system for a wall follower fire fighting robot. The task of this robot is to walk along the walls of the area. The PID controller aims to smooth the movement of the robot when tracing the track space. With the help of the PID controller, the wall follower robot is able to navigate safely, smoothly, responsively and quickly. Fire fighting robots require a variety of sensors to run properly, one of which is using sonar sensors that are used for robot navigation. This sensor works based on the principle of wave reflection, where in this case the variable measured is the time of reflection since the wave was emitted. The sonar sensor detects an obstruction. The robot will turn and walk again without hitting obstacles or objects in the vicinity. To detect fire, fire sensor is used. This sensor also find hotspots by assessing the intensity of the light. Arduino ATMega328 microcontroller functions as a robot control. The output of the microcontroller will produce logic 1 to activate the motor driver to activate the right and left wheel motors. The DC motor is used as a driving force for the robot, and the battery here functions as a power supply for the robot. The result is, this robot can detect the fire point of the candle and extinguish the candle flame.
Co-Authors Achmad Rivaldi Agie Annan Agung Fadillah Agung Rahmaddoni Ahmad Fitriansyah Alfian Rivaldi Amin Sakaria, Muhammad Andrian, Feri Ari Bayu Untoro Bagas Saftaji Budi Setiawan Dedi Setiadi Dedi Setiadi Fadillah, Agung Fenty Tristanti Julfia Fenty Tristanti Julfia Feri Andrian Fitriansyah, Ahmad Fius Bryan Nigel M. Sinaga Ibrahim Aziz Istifadah Istifadah Julfia, Fenty Tristanti Khaliq, Muhammad Nur Lingga Hanggada Adi Saputra Mohammad Ikhsan Saputro Mohammad Ikhsan Saputro Mohammad Ikhsan Saputro Mohammad Ikhsan Saputro, Mohammad Ikhsan Mohammad Ikshan Saputro Muhammad Amin Sakaria Muhammad Nur Khaliq Muhammad Ridwan Effendi Narji, Mohammad Rahman, Taslim Idris Rano Agustino Sakaria, Muhammad Amin Satryawati, Eka Sinaga, Fius Bryan Nigel M. Sopian, Abu Taslim Idris Rahman Tata Sutabri Untoro, Ari Bayu Widyahastuti, Febrianti Yogi Pradiyatama Riyanto Yohanes Bowo Widodo