Article Per Year (5 Year)
p-Index From 2021 - 2026
5.03
P-Index
This Author published in this journals
All Journal Jurnal Ilmu Komputer dan Informasi Journal of Information Systems Engineering and Business Intelligence JOIN (Jurnal Online Informatika) Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) JPF (Jurnal Pendidikan Fisika) Universitas Islam Negeri Alauddin Makassar JTERA (Jurnal Teknologi Rekayasa) The IJICS (International Journal of Informatics and Computer Science) JURIKOM (Jurnal Riset Komputer) Abdimas Umtas : Jurnal Pengabdian kepada Masyarakat Edsence: Jurnal Pendidikan Multimedia Building of Informatics, Technology and Science Jurnal ABDINUS : Jurnal Pengabdian Nusantara JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Journal of Innovation Information Technology and Application (JINITA) Media Jurnal Informatika Bulletin of Computer Science Research Jurnal Difusi Journal of Software Engineering, Information and Communication Technology Industrial Research Workshop and National Seminar Journal Serambi Engineering (JSE)
Muhammad Rizqi Sholahuddin
Politeknik Negeri Bandung
Religion Agriculture, Biological Sciences & Forestry Arts Humanities Chemical Engineering, Chemistry & Bioengineering 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 Industrial & Manufacturing Engineering Library & Information Science Mechanical Engineering Physics Social Sciences Other

Published : 31 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 31 Documents
Search

 1   2   3   4 
Optimizing YOLOv8 for Real-Time CCTV Surveillance: A Trade-off Between Speed and Accuracy Sholahuddin, Muhammad Rizqi; Harika, Maisevli; Awaludin, Iwan; Dewi, Yunita Citra; Dhia Fauzan, Fachri; Sudimulya, Bima Putra; Widarta, Vandha Pradiyasma
JOIN (Jurnal Online Informatika) Vol 8 No 2 (2023)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v8i2.1196

Abstract

Real-time video surveillance, especially CCTV systems, requires fast and accurate face detection. Object detection models with slow inference times are ineffective in real-time. This study addresses this challenge by improving the inference speed of the YOLOv8 model, a leading object detection framework known for its accuracy and speed. We focus on pruning the model's architecture, particularly the P5 head section, which detects larger objects. According to Bochkovskiy's 2020 research, this modification enhances the model's performance specifically for medium and small objects in CCTV footage. The standard YOLOv8 model and its modified version were compared for inference time, mean Average Precision (mAP), and model weight. The pruned YOLOv8 model cuts inference time by 15.56%, from 4.5 ms to 3.8 ms, and reduces model weight. The advantages mentioned above are offset by a 1.6% decrease in mean average precision. This research advances object detection technology by demonstrating architectural modifications' efficacy. These changes make the model faster and lighter, making it suitable for real-time surveillance. The accuracy trade-off is slight. The implications of these findings are crucial for implementing efficient object detection systems in CCTV surveillance. These findings also lay the groundwork for future research to improve such systems' speed-accuracy trade-off.
Uji Fungsionalitas Dan Kebermanfaatan Aplikasi Random Angka Soal Vektor Berbasis Web Sebagai Media Latihan Soal Yunita Citra Dewi; Muhammad Rizqi Sholahuddin; Topan Trianto
JPF (Jurnal Pendidikan Fisika) Universitas Islam Negeri Alauddin Makassar Vol 13 No 1 (2025)
Publisher : Pendidikan Fisika UIN Alauddin Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/jpf.v13i1.51091

Abstract

The fundamental role of vector concepts in engineering education underscores the development of a web-based application designed to facilitate vector problem-solving practice. To enhance students’ comprehension of vector material, repeated exposure to varied problem sets is essential. This study aims to design and evaluate a practice application that integrates randomized number generation, enabling users to encounter dynamically changing numerical values with each use. Employing a Research and Development (R&D) approach with experimental methods, the application was developed using the Laravel Model-View-Controller (MVC) framework. The database structure, built on MariaDB, was optimized for efficient storage of questions, solutions, and user responses. The application was implemented and tested by first-year students in the Diploma 3 Mechanical Engineering Program at Politeknik Negeri Bandung. Functional testing revealed that 92.89% of the features operated effectively. Furthermore, based on the usefulness assessment, the application received a total score of 254, classifying it as “highly useful.”
Hybrid IndoBERT and Support Vector Machine for Multi-class Emotion Classification of Indonesian Tourism Reviews Firas Atqiya; Afrida Helen; Muhammad Rizqi Sholahuddin
Media Jurnal Informatika Vol 18 No 1 (2026): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v18i1.6377

Abstract

Online reviews hold emotional nuances that binary sentiment analysis cannot adequately capture for targeted tourism management. Indonesian reviews pose additional computational challenges due to informal language, Sundanese vernacular, and severe class imbalance. Objective:   This study develops a hybrid classification framework using IndoBERT as a frozen feature extractor and a Support Vector Machine (SVM) across five emotional classes. It investigates integrating Principal Component Analysis (PCA) and SMOTE within a strict cross-validation pipeline to mitigate extreme minority class scarcity while preventing data leakage. The duplicate-free dataset comprises 446 manually annotated reviews from agro-tourism destinations in Rancakalong. Annotations followed Ekman’s emotions plus a neutral category, cross-validated by a Large Language Model (Cohen's Kappa = 0.7475). To satisfy oversampling constraints, three extreme minority classes (fear, surprise, disgust) were consolidated into an 'OTHER' class. Three configurations were evaluated via 5-Fold Stratified Cross-Validation: TF-IDF + SVM (M1 baseline), IndoBERT + SVM (M2), and IndoBERT + PCA + SMOTE + SVM (M3), utilizing Macro F1 as the primary metric. Results:  The M1 baseline yielded a Macro F1 of 0.3920. By capturing contextual semantics, M2 improved accuracy to 0.7131 and Macro F1 to 0.4133. The proposed M3 architecture achieved the highest Macro F1 (0.4321), demonstrating that combining dimensionality reduction and oversampling strengthens minority class decision boundaries. However, erratic performance on the synthetic 'OTHER' class confirms that merging distinct emotions disrupts cohesive semantic signatures. Integrating frozen IndoBERT embeddings with PCA and SMOTE within a cross-validated SVM architecture significantly outperforms traditional baseline models on highly imbalanced, low-resource Indonesian text data. This study contributes an empirically validated emotion corpus and establishes a foundational, data-driven behavioral modeling framework to guide targeted managerial interventions in local agro-tourism.
Real-Time Webcam-Based Hand Gesture Recognition with Face Authentication for 3D Drone Simulation in Godot Engine Muhammad Rizqi Sholahuddin; Siti Dwi Setiarini; Ardhian Ekawijana; Muhammad Samudera; Firas Atqiya
Media Jurnal Informatika Vol 18 No 1 (2026): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v18i1.6483

Abstract

Most hand gesture control systems for drones depend on specialized hardware such as Leap Motion or Kinect, which raises the cost barrier for educational institutions in developing countries. Integrating face authentication within the same low-cost pipeline remains under-explored. This study develops a real-time, webcam-based system that combines Google MediaPipe hand tracking with facial authentication and a Godot Engine 4.3 3D drone simulation for authenticated, responsive gesture control. A finger-counting algorithm classifies eight gestures across two hands. The left hand drives horizontal motion (forward, backward, left, right) and the right hand drives altitude and yaw (up, down, rotate left, rotate right). Commands travel over UDP to Godot, where a receiver node translates each packet into a native input action. Face authentication uses dlib and the face_recognition library with a 60-frame login counter. All metrics were collected under a fixed condition (normal lighting 300–500 lux, 0.8 m, one subject). The system achieved 100% gesture accuracy across 160 trials, 35.6 FPS pipeline throughput, 0.33 ms one-way UDP latency with 0% packet loss, and 23.9 ms end-to-end gesture-to-drone latency. Face authentication scored 100% recognition with 0% FRR and 19.0% FAR against an unregistered face at the default 0.6 tolerance. A standard-webcam pipeline built entirely from open-source components can deliver responsive, authenticated gesture control for interactive drone simulation, though the single-subject evaluation is an upper bound requiring multi-subject validation. However, the 100% accuracy represents an upper bound as evaluation was limited to a single subject under controlled lighting (300–500 lux) and a fixed distance (0.8 m), requiring further validation across diverse users and environments
Integrating Real-Time Facial Ethnicity Classification with a Godot Game Client for Personalized Cultural Interactive Exhibition Trisna Gelar; Muhammad Rizqi Sholahuddin; Aprianti Nanda Sari; Ais Laksana; Satryo Haryo; Rafli Fadhilah; Gianluigi Julian; Daffa Muzhaffar
Journal of Innovation Information Technology and Application (JINITA) Vol 8 No 1 (2026): JINITA, June 2026
Publisher : Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/jinita.v8i1.3021

Abstract

Addressing the recognized limitation of non-adaptive "one-size-fits-all" experiences in cultural and technical exhibitions, a novel, real-time system is introduced that integrates facial ethnicity classification with the Godot game engine to provide a personalized cultural interactive learning. The core objective was to design and quantitatively assess a performant artifact capable of dynamically classifying users into one of three major Indonesian regional categories (Barat, Tengah, or Timur) and instantly loading the appropriate personalized cultural gaming scenario. The study presents three significant contributions. First, an advanced machine learning model for Indonesian ethnicity categorization was created by utilizing an optimized feature combination of Gray Level Co-occurrence Matrix (GLCM) and Histogram of Oriented Gradients (HOG). The optimal feature set (GLCM+HOG) attained a high Cross-Validation Accuracy 95.82%±1.11%, significantly advancing the technical performance baseline for this domain. Second, a robust, real-time pipeline was successfully demonstrated, connecting the Python-based machine learning backend with the Godot gaming client via an API for immediate content customization. While the backend demonstrates high theoretical efficiency, achieving a throughput of approximately 46 FPS 21.51 ms classification latency), the final integrated system operates at a stable 12.0 FPS interface rate. This performance disparity highlights that integration overhead and feature dimensionality are the primary bottlenecks affecting the responsiveness of the on-demand classification event. Future endeavors will concentrate on enhancing real-time performance by lowering classification latency via feature dimensionality reduction (e.g., Local Binary Pattern variants) and conducting qualitative assessments to gauge user involvement and the transfer of cultural information.
Improving SAM 2 for Agricultural Land Segmentation through Fine-Tuning, Point Prompt Augmentation, and Negative Prompt Calibration Yayang Setia Budi; Fardan Al Jihad; Nurjannah Syakrani; Trisna Gelar; Muhammad Rizqi Sholahuddin; Djoko Cahyo Utomo Lieharyani
Journal of Information Systems Engineering and Business Intelligence Vol. 12 No. 2 (2026): June
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/jisebi.12.2.210-222

Abstract

Background: The Segment Anything Model 2 (SAM 2) represents a state-of-the-art foundation model for object segmentation; however, its application to satellite-based agricultural mapping faces significant challenges. Standard SAM 2 architectures often struggle with the spectral ambiguity of fragmented tropical landscapes and the domain gap inherent in remote sensing imagery. Furthermore, the model’s interactive nature requires precise spatial guidance, making it sensitive to both the location and density of input prompts, which limits its scalability for automated large-scale monitoring. Objective: This study aims to (1) analyze the impact of domain-specific fine-tuning combined with automated Point Prompt Augmentation (PPA) and Negative Prompt Calibration (NPC) on segmentation accuracy; (2) evaluate the performance of four SAM 2 variants (Tiny, Small, Base+, and Large) to identify the optimal backbone for agricultural tasks; and (3) determine the optimal prompt density for both positive and negative points. Methods: The SAM 2 variants were fine-tuned using the LoveDA satellite dataset. Evaluation was conducted through an automated pipeline comparing two initialization strategies: Largest Agricultural Area (LAA) Centroid and random placement. The study implemented PPA to strategically increase positive prompt density and NPC to suppress "mask leakage" into irrigation infrastructure. Performance was quantified using mean Intersection over Union (mIoU) and Jaccard & F-measure (J&F) metrics. Results: The Small variant emerged as the superior backbone, achieving a peak mIoU of 0.7255 and J&F of 0.7734, representing a significant improvement over the pretrained baseline. The results indicate that the LAA Centroid strategy provides a more stable spatial anchor, while the integration of three positive and three negative points optimized the boundary alignment. The Small variant maintained a high computational efficiency with an average inference time of 2.62 minutes. Conclusion: Domain-specific fine-tuning, coupled with the proposed PPA and NPC frameworks, successfully mitigates the limitations of SAM 2 in agricultural remote sensing. This research provides a robust methodology for automated, high-precision land segmentation, bridging the gap between foundation models and specialized geographic information systems.   Keywords: Agriculture Segmentation, Satellite Imagery, Segment Anything Model 2, Fine-tuning, Point Prompt Augmentation, Negative Prompt Calibration
Analisis Visual Perilaku Agen Q-Learning dan SARSA pada Cliff Walking Problem dengan Explainable Reinforcement Learning Firas Atqiya; Muhammad Rizqi Sholahuddin
Bulletin of Computer Science Research Vol. 6 No. 2 (2026): February 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v6i2.984

Abstract

Reinforcement Learning (RL) has achieved remarkable success in complex sequential decision tasks. However, modern RL models often lack explainability, creating a serious "black box" problem, especially in high-stakes domains. This study proposes a Pygame-based real-time visualization architecture for RL, and demonstrates its benefits in a Cliff Walking case study using Q-Learning and SARSA algorithms. Key contributions include: (1) a real-time visualization architecture that decouples training logic from graphics rendering with support more than 60 FPS, (2) interpretive visualization techniques including diverging heatmaps, dynamic policy arrows, and Ghost Policies, and (3) a comprehensive empirical study clarifying the distinct characteristics of both algorithms. Experimental results clearly show that Q-Learning selects an efficient but risky path aligned with its optimistic off-policy nature, while SARSA converges on a safer path reflecting its on-policy nature that considers exploration safety. Quantitatively, Q-Learning successfully achieved an optimal 13-step path with an accumulation of 10,642 falls, whereas SARSA converged to a safe 23-step path with a significantly higher collision frequency (232,844 times) to avoid extreme penalties from the cliff zone.
Pengembangan SiPaDI: Platform Marketplace Penyedia Jasa Terlatih Binaan Disnakertrans Kabupaten Karawang Maisevli Harika; Asri Maspupah; Djoko Cahyo Utomo Lieharyani; Muhammad Rizqi Sholahuddin; Nurjannah Syakrani; Sofy Fitriani
Jurnal Difusi Vol. 9 No. 1 (2026): Jurnal Difusi
Publisher : Pusat Penelitian dan Pengabdian Masyarakat (P3M) Politeknik Negeri Bandung

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

Abstract

Transformasi digital pada sektor layanan jasa diperlukan untuk meningkatkan akses promosi tenaga kerja terampil dan mempermudah masyarakat memperoleh layanan yang terpercaya. Namun, alumni Balai Latihan Kerja (BLK) binaan Disnakertrans Kabupaten Karawang masih menghadapi keterbatasan dalam memasarkan kompetensi secara digital. Kegiatan Pengabdian kepada Masyarakat (PkM) ini bertujuan mengembangkan SiPaDI (Sistem Pasar Digital Alumni) sebagai platform marketplace jasa berbasis web yang menghubungkan alumni BLK dengan masyarakat pengguna jasa. Metode pelaksanaan menggunakan pendekatan participatory iterative development melalui tahapan analisis kebutuhan, perancangan sistem, implementasi aplikasi, pengujian, pelatihan, dan evaluasi bersama mitra. Sistem dikembangkan menggunakan Next.js, React, TypeScript, dan MariaDB. Hasil kegiatan menunjukkan bahwa SiPaDI berhasil mendukung pengelolaan layanan jasa secara digital melalui fitur registrasi pengguna, verifikasi penyedia jasa, pemesanan layanan, dan ulasan pelanggan. Selain menghasilkan platform digital, kegiatan ini juga meningkatkan kesiapan mitra dalam mengelola layanan tenaga kerja terampil berbasis teknologi informasi secara mandiri dan berkelanjutan
Evaluating RAG Performance on Small Language Models for Low-Resource Devices through Chunking and Retrieval Methods Amelia Dewi Agustiani; Salsabila Maharani Putri; Jonner Hutahaean; Muhammad Rizqi Sholahuddin; Muhammad Riza Alifi; Ade Hodijah
JOIN (Jurnal Online Informatika) Vol 11 No 1 (2026)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v11i1.1733

Abstract

Retrieval-Augmented Generation (RAG) combines generative capabilities of language models with external document retrieval to answer questions grounded in reference texts. However, deploying RAG on low-resource devices like Android smartphones is challenging because SLMs have limited computational capacity and depend heavily on efficient chunking and retrieval. Although interest in on-device processing is growing, research on RAG configurations for SLMs under strict resource constraints especially for domain-specific tasks remains limited. This study therefore investigates which combinations of chunking technique, chunk size, overlap, and retrieval strategy best balance accuracy and speed on low-resource devices. The evaluation uses 148 Indonesian questions sourced from an official Hajj guidebook. The study consists of two phases retrieval and generation. Retrieval is evaluated using BLEU, ROUGE-L, MRR, MAP, and Hit@k, while answer quality is measured with BERTScore. The experiments compare different chunking methods (fixed-size or semantic), chunk sizes (128 or 256 tokens), overlaps (25, 50 and 100 tokens), and retrieval methods (dense, sparse, or hybrid). Results show that sparse retrieval with 256-token chunks and 100-token overlap yields the best answer quality (F1 = 0.726). However, 128-token chunks with the same overlap provide the fastest generation time (69.737 seconds). The main contribution of this study is a systematic evaluation of RAG configurations for fully on-device SLMs using a domain-specific Hajj and Umrah dataset not explored in prior research. The findings provide practical guidance for designing efficient and accurate RAG-based question-answering systems on low-resource devices.
YOLOv8 to YOLO11 Performance Benchmark and Comprehensive Architectural Comparative Review Priyanto Hidayatullah; Nurjannah Syakrani; Muhammad Rizqi Sholahuddin; Trisna Gelar; Refdinal Tubagus
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 2 (2026): April 2026
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i2.6598

Abstract

In the domain of deep learning-driven computer vision, YOLO is revolutionary. However, not all YOLO models are accompanied by academic articles and architectural diagrams. It complicates the comprehension of the model's operation. Moreover, the existing review papers fail to examine each model comprehensively. This work aims to provide a thorough comparative analysis of the architectures from YOLOv8 to YOLO11, allowing readers to swiftly understand the operational mechanisms and differences among the models. We analyzed the architecture of each YOLO version by reviewing relevant scholarly articles, official documentation, and examining the source code. In particular, we discovered that YOLOv8 through YOLO11 differ in novelty while sharing similarities in the anchor-free and Non-Maximum Suppression (NMS) aspects, except YOLOv10 (NMS-free). Each also has drawbacks, such as differing levels of complexity in the way features are connected (v8), architectural structure and training (v9), training methods or dual assignments (v10), inference, and code implementation (v11). While each version improves architecture, some blocks remain unchanged. This study helps readers understand different YOLO version architectures and inspires how to improve their performance. It also provides readers with a comprehensive architecture diagram and detailed descriptions of each block, serving as a reference for both academic and practical applications. In terms of performance, a benchmark using the Roboflow 100 dataset reveals that YOLOv9 achieves superior accuracy; however, it is eight times slower owing to its NMS mechanism. YOLOv10 is the fastest but least accurate, whereas YOLOv8 and YOLO11 provide a balanced compromise between speed and accuracy.
Co-Authors Ade Hodijah Afrida Helen Agustiani, Amelia Dewi Ais Laksana Amelia Dewi Agustiani Aprianti Nanda Sari Ardhian Ekawijana Asri Maspupah Bakhrun, Akhmad Bima Putra Sudimulya Carolina Magdalena Lasambouw Daffa Muzhaffar Dewi, Yunita Citra Dhia Fauzan, Fachri Dimas Kurniawan Djoko Cahyo Utomo Lieharyani Djoko Cahyo Utomo Lieharyani Djoni Djatnika Eddy Bambang Soewono Elfada, Berliana Fachri Dhia Fauzan Fardan Al Jihad Farida Agoes FENNY MARTHA DWIVANY Firas Atqiya Firdaus, Lukmannul Hakim Gantini, Annisa Dinda Gelar, Trisna Gianluigi Julian Hayati, Hashri Husna Faridah Ihsani, Nisa Iwan Awaludin Jonner Hutahaean Kadhafi, Irvan Lukmannul Hakim Firdaus Maisevli Harika Maisevli Harika Maisevli Harika Malika, Adinda Faayza Meilinda, Lina Melinia, Gina Muhammad Riza Alifi Muhammad Samudera Mulia, Syelvie Ira Ratna Nugraha, Wili Akbar Nuri Nurianti Nurjannah Syakrani Nurjannah Syakrani Nuryati, Neneng Priyanto Hidayatullah Priyanto Hidayatullah, Priyanto Putri, Salsabila Maharani Putriadhinia, Salma Syawalan Rafli Fadhilah Refdinal Tubagus Salsabila Maharani Putri Santosa, Yoseph Sari, Aprianti Nanda Satryo Haryo Setiadi Rachmat Sitepu, Rezky Wahyuda Siti Dwi Setiarini Siti Dwi Setiarini Sofy Fitriani Sofy Fitriani SONY SUHANDONO Sudimulya, Bima Putra Suharsih, Ririn Syakrani, Nurjannah Topan Trianto Trisna Gelar Abdillah Vandha Pradiyasma Widarta Widarta, Vandha Pradiyasma Wisnuadhi, Bambang Wulan, Sri Ratna Yayang Setia Budi Yudi Widhiyasana Yunita Citra Dewi Yusuf Sofyan Yusuf Sofyan, Jurusan Teknik Elektro Politeknik Negeri Bandung, Parno Raharjo, Tria Maariz, Jurusan