cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Salamun
Contact Email
salamun@univrab.ac.id
Phone
-
Journal Mail Official
Jurnal.ti@univrab.com
Editorial Address
Redaktur Jurnal RABIT Teknik Informatika Universitas Abdurrab: Gedung Universitas Abdurrab Pekanbaru Jl. Riau Ujung No. 73 Pekanbaru Riau - Indonesia
Location
Kota pekanbaru,
Riau
INDONESIA
RABIT: Jurnal Teknologi dan Sistem Informasi Univrab
Published by Universitas Abdurrab
ISSN : 24772062     EISSN : 2502891X     DOI : https://doi.org/10.36341/rabit
Core Subject : Science, Engineering,
Computer Science & IT Engineering
This journal is called RABIT, where the name comes from two words namely, RAB which means Abdurrab University and IT which means information technology, it can be interpreted as a journal of this journal Journal of Informatics Engineering Study Program Pekanbaru Abdurrab University. This RABIT journal contains various sciences related to the world of computers especially information technology and information systems, namely, this journal is published twice a year where the initial publication is on January 10 while for the second issue which is on July 10.
Arjuna Subject : Ilmu Komputer (semua kategori) - Sistem Informasi
Articles 696 Documents
 57   58   59   60   61 
CONTEXTUAL ANOMALY DETECTION ON AWS CLOUDTRAIL LOGS USING AN UNSUPERVISED MACHINE LEARNING APPROACH: DETEKSI ANOMALI KONTEKSTUAL PADA LOG AWS CLOUDTRAIL MENGGUNAKAN PENDEKATAN UNSUPERVISED MACHINE LEARNING Adji Putra Noor Pamungkas; Joko Sutopo
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 2 (2026): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i2.8056

Abstract

Cloud audit logs contain rich behavioral signals that can be leveraged for security monitoring, yet effective anomaly detection remains challenging due to the absence of labeled data and the limited use of contextual information. This study investigates whether contextual feature engineering improves unsupervised anomaly detection in AWS CloudTrail logs by incorporating temporal attributes, per-entity historical activity, and geographic diversity. A controlled experimental design is employed to compare contextual and non-contextual feature representations using two representative unsupervised algorithms: Isolation Forest and Autoencoder. Both models are evaluated under identical datasets and configurations to ensure that performance differences are attributable solely to feature representation. The results indicate that contextual features significantly enhance detection performance across various synthetic threat scenarios. The average detection rate across all scenarios for the Isolation Forest improved from 4.62% to 85.62%, while the Autoencoder demonstrated an increase from an average of 20.24% to 97.26%. In addition, contextual representations consistently improve sensitivity to behaviorally meaningful anomalies that are not identifiable through global statistical rarity alone. Stability analysis using top-1 percent overlap across multiple random seeds reveals a trade-off between robustness and expressiveness, where contextual models exhibit lower but still operationally acceptable stability compared to non-contextual baselines. Overall, the findings demonstrate that contextual feature engineering is a critical component for effective unsupervised anomaly detection in cloud audit logs. By shifting the detection paradigm from global rarity to entity-level behavioral deviation, contextual modeling enables more accurate identification of security-relevant anomalies in AWS environments.  
ANALISIS KOMPARATIF PENGGUNAAN AUGMENTASI DATA TERHADAP PERFORMA YOLO DALAM KLASIFIKASI INDIVIDU BERDASARKAN KEBERADAAN SENJATA: A COMPARATIVE ANALYSIS OF DATA AUGMENTATION TECHNIQUES ON YOLO PERFORMANCE IN CLASSIFYING INDIVIDUALS BASED ON WEAPON PRESENCE Nona Adinda Ariana Ariana; Kusrini
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 2 (2026): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i2.8059

Abstract

The increasing demand for security systems has encouraged the use of image processing technology to assist in identifying potential criminal activities. One important indicator in security surveillance is the presence of individuals carrying weapons. Therefore, this study aims to implement the YOLO11 deep learning algorithm to detect and classify individuals based on the presence of weapons in images. The dataset used consists of two classes, namely Person and Weapon, and four training scenarios were evaluated: the original dataset, the MixUp-augmented dataset, the CutMix-augmented dataset, and the combined MixUp-CutMix dataset. Model performance was evaluated using precision, recall, mAP50, and mAP50-95 metrics. The results show that the model trained on the original dataset achieved the highest recall of 0.84 and mAP50 of 0.92, while the model trained on the combined MixUp-CutMix dataset achieved the highest precision of 0.95 and mAP50-95 of 0.62. Among the augmentation methods applied, the combination of MixUp and CutMix produced the best performance, whereas MixUp yielded relatively lower performance than the other methods. The findings indicate that data augmentation can increase the diversity of training data; however, it does not always lead to better performance than the original dataset. Overall, the results demonstrate that YOLO11 has strong potential for application in computer vision-based surveillance systems to support the automatic detection of individuals carrying weapons.
PENGEMBANGAN MODEL DEEP LEARNING UNTUK DETEKSI SUARA MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK NORITA SINAGA; Imam Riadi; Herman
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 2 (2026): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i2.8061

Abstract

Sound detection and keyword recognition in audio signals have become rapidly growing research areas due to their wide range of applications, from intelligent audio surveillance to human-computer interaction systems. This study aims to develop a deep learning model based on Convolutional Neural Networks (CNN) to automatically detect and classify specific words in speech recordings. The focus of this research is the detection of the keywords "dog" and "children" contained in speech data. The research methodology includes data preprocessing through noise reduction and normalization, as well as data augmentation techniques such as pitch shifting to improve the robustness of the model. Audio features are extracted using the Short-Time Fourier Transform (STFT) to generate visual representations in the form of spectrograms, which serve as the primary input to the CNN architecture. Experimental results show that the developed model successfully classified the target keywords with an accuracy of 90,00%. The model proved effective in recognizing both spectral and temporal patterns of spoken keywords and has the potential to be implemented in real-time sound detection systems.
PENGEMBANGAN SISTEM AUTOMATIC WORKLOAD THROTTLING BERBASIS PYTHON UNTUK MITIGASI THERMAL THROTTLING CPU PADA PERANGKAT KOMPUTER Intan Oka Herdanis; Reza Pahlevi; Sunu Ilham Pradika; Hidayat Ramadhani; Jan Everhard Riwurohi
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 2 (2026): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i2.8063

Abstract

The increasing demand for modern computing drives processors to operate under heavy loads; however, this condition potentially elevates CPU operating temperatures and triggers thermal throttling. This study aims to develop the Python-based Yield Thermal Intelligent Handling & Automation (PYTHIA) system as a software-based CPU workload management mechanism to adaptively mitigate thermal throttling. The system utilizes real-time temperature monitoring from the Libre Hardware Monitor (LHM) Web Server and implements a duty-cycle worker control logic to adjust CPU workload based on predefined temperature thresholds. Testing was conducted on two processors with distinct characteristics, the AMD Ryzen 7 7730U and the Intel Core i7-10750H, through three experimental phases: pre-throttling, cooldown, and automatic throttling. The results indicate that PYTHIA successfully monitors processor temperature in real-time and reduces workload as temperatures rise. On the AMD Ryzen 7 7730U, the system effectively maintained stability following the cooldown and automatic throttling phases. Meanwhile, on the Intel Core i7-10750H, the system responded to temperature increases, although temperature fluctuations remained significant, occasionally approaching the 90–95°C range. It should be noted that the high temperature fluctuations on the Intel  Core i7-10750H processor indicate that the system still requires refinement in its adaptive control mechanism to achieve optimal thermal stability. Overall, PYTHIA is proven to assist in reducing thermal throttling risks through adaptive workload control, though the control mechanism requires further optimization for smoother duty-cycle transitions and improved temperature stability.
SUPPORT SYSTEM SELEKSI ANGGOTA KOPERASI MERAH PUTIH DESA BANDAR RAHMAT MENGGUNAKAN METHOD EDAS Andre Irfan Ramadhan Safaruddin; Dewi Maharani, M.Kom; Santoso, M.M
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 2 (2026): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i2.8064

Abstract

The member selection process at Koperasi Merah Putih Desa Bandar Rahmat is still carried out manually, making it time-consuming and prone to subjective decision-making. This study aims to design and develop a web-based Decision Support System (DSS) to assist cooperative administrators in determining the eligibility of prospective members more objectively and efficiently. The method applied is Evaluation Based on Distance from Average Solution (EDAS), a multi-criteria decision-making method that evaluates alternatives based on their distance from the average value of each criterion. Research data were collected through observation, interviews, and documentation. The system was developed using PHP and MySQL and designed with the Unified Modeling Language (UML) approach. The EDAS calculation process includes decision matrix formation, average value calculation, Positive Distance from Average (PDA), Negative Distance from Average (NDA), normalization, and Appraisal Score computation to produce candidate rankings. The results indicate that the developed system is capable of managing candidate data and conducting the selection process in a structured manner. The implementation of the EDAS method generates objective eligibility rankings based on predetermined criteria. Furthermore, system testing demonstrated that all system functions operated properly. The proposed system can support cooperative administrators in accelerating the selection process, improving transparency, and reducing subjectivity in decision-making.
KLASIFIKASI EKSPRESI WAJAH UNTUK IDENTIFIKASI INDIKASI KECEMASAN MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK (CNN) Aldrian Fidel Pranata Sunaryo; Maya Sofhia; Eighia Nita Perangin Angin; Esa Andriani Barus
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 2 (2026): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i2.8065

Abstract

This study aims to develop a facial expression classification system to identify indications of anxiety using the Convolutional Neural Network (CNN) method, utilizing the FER2013 dataset, which consists of seven emotion categories: angry, disgust, fear, happy, sad, surprise, and neutral. The research stages include data preprocessing, CNN model training, model performance evaluation, and real-time testing using a webcam. The developed system is capable of recognizing facial expressions and classifying them into PANIC, NORMAL, and UNCERTAIN statuses based on the confidence scores generated by the model. The expressions of fear, sad, angry, and disgust are interpreted as indicators of anxiety, whereas happy, neutral, and surprise are interpreted as normal conditions. Based on the testing results using the FER2013 test data, the CNN model achieved an accuracy of 92.58%, a precision of 93.48%, a recall of 92.58%, and an F1-score of 92.27%. The results demonstrate that the CNN method can be effectively utilized for facial expression classification and to provide early indications of anxiety based on the detected expressions. However, the system's performance remains influenced by factors such as lighting, camera quality, facial positioning, and limitations in the quantity and distribution of data within the utilized dataset. Therefore, further development is required to enhance the accuracy and reliability of the system in detecting indications of anxiety in real-time.
EVALUASI SISTEM ALPR BERBASIS YOLOV10 PADDLEOCR UNTUK PENGENALAN PLAT NOMOR KENDARAAN INDONESIA Esadhipa Raif Syihabuddin; MUHAMMAD NAUFAL
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 2 (2026): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i2.8073

Abstract

Automatic License Plate Recognition (ALPR) is an important component in intelligent transportation systems, utilized for traffic surveillance, automated parking, and law enforcement. This research develops an ALPR system based on YOLOv10l integrated with fine-tuned PaddleOCR to detect and recognize characters on Indonesian vehicle license plates. The dataset used consists of 532 Indonesian license plate images from Roboflow Universe, divided into 426 training images and 106 validation images. The YOLOv10l model was trained for 50 epochs using COCO pretrained weights, while PaddleOCR PP-OCRv4 was fine-tuned for 100 epochs on license plate crops from the dataset. Evaluation was conducted by comparing three OCR engines: fine-tuned PaddleOCR, EasyOCR, and Tesseract. Results show that the YOLOv10l model achieved an mAP@0.5 of 0.981, Precision of 0.920, and Recall of 0.943, with a Detection Rate of 97.17%. Fine-tuned PaddleOCR outperformed the other engines with a Readable OCR rate of 47.57% and Correct Recognition rate of 36.89%, followed by EasyOCR at 13.59% and Tesseract at 0.00%. This research confirms that fine-tuning PaddleOCR on a domain-specific dataset contributes positively to the accuracy of Indonesian license plate character recognition.
AGILE VERSUS WATERFALL IN AI DEVELOPMENT: A SYSTEMATIC LITERATURE REVIEW OF EFFICIENCY AND ADAPTABILITY Amelia Khairunnisa; Ni Wayan Trisnawaty; Teguh Raharjo
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 2 (2026): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i2.8076

Abstract

The adoption of Artificial Intelligence (AI) systems demands an efficient and flexible development approach to address evolving data and requirements. This study conducted a PRISMA 2020–based Systematic Literature Review (SLR) comparing Agile and Waterfall approaches in AI development, focusing on (RQ1) time/throughput-based and quality-related efficiency and (RQ2) adaptability to change. Searches covered publications from 2021 to 2026 across five databases, followed by stepwise screening, full-text assessment, and methodological quality appraisal. Eight studies were retained: five explicitly addressing AI/MLOps contexts and three related software-engineering studies used as contextual, transferable evidence. The studies were analyzed through narrative synthesis using predefined operational indicators for efficiency and adaptability, with greater interpretive weight given to higher-quality, AI-specific studies. The evidence indicates that Agile, particularly when aligned with MLOps practices (e.g., CI/CD/CT, pipeline automation, monitoring, and retraining), is often associated with faster iterations and better responsiveness to data changes. Waterfall remains relevant in settings with strong governance, relatively stable requirements, and strict documentation, traceability, and auditability needs. A hybrid approach can balance structured control with iterative adaptation in complex or multi-domain AI projects. Given the small number of included studies (n=8) and the partial reliance on related software engineering evidence, these findings are indicative and context-dependent rather than conclusive; the choice of approach is shaped by the project's level of uncertainty, data dynamics, and the organization's AI/MLOps maturity.
IMPLEMENTASI KARTU TANDA MAHASISWA DIGITAL BERBASIS BLOCKCHAIN Muhammad Ihsan; Erick Irawadi Alwi; Yulita Salim
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 2 (2026): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i2.8084

Abstract

Identity management in higher education still generally relies on physical cards and centralized systems that are vulnerable to loss, forgery, and limited independent verification. This study aims to design and implement a blockchain-based digital student identity card system that supports integrated credential issuance, verification, and revocation. The study uses the Design Science Research Methodology (DSRM) through the stages of problem identification, design, prototype development, demonstration, and evaluation. The system is built using a hybrid architecture, in which student identity data are stored off-chain, while credential hashes and revocation status are recorded on-chain through a smart contract deployed on the Polygon Amoy Testnet. Credentials are issued in the form of JWT-based Verifiable Credentials and signed using the ES256K algorithm. The test results show that the system successfully implements its main functions, namely credential issuance, verification, and revocation. Performance testing also shows that verification can be carried out without incurring gas costs and with a response time that remains feasible for practical use. Overall, the developed system is feasible to support digital student identity services with better credential integrity and easier verification.  
IMPLEMENTASI MOTION GRAPHIC PADA ANIMASI 'AKSI 3M PLUS' MENGENAI PENCEGAHAN PERKEMBANGBIAKAN NYAMUK AEDES AEGYPTI : IMPLEMENTATION OF MOTION GRAPHICS IN THE ANIMATION "AKSI 3M PLUS" ON THE PREVENTION OF AEDES AEGYPTI MOSQUITO BREEDING Viqki Nur Fajar; Rujianto Eko Saputro
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 2 (2026): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i2.8088

Abstract

Dengue Hemorrhagic Fever (DHF) remains a significant public health issue caused by the transmission of the dengue virus through Aedes aegypti mosquitoes. One of the most effective prevention efforts is the implementation of the 3M Plus movement; however, information dissemination is still largely conducted through conventional media, which are often less engaging and interactive. This study aims to implement motion graphics in the animation entitled “Aksi 3M Plus” as an educational medium for preventing the breeding of Aedes aegypti mosquitoes. The research employed the ADDIE development model, consisting of Analysis, Design, Development, Implementation, and Evaluation stages. The analysis stage involved identifying media requirements through interviews with the Banyumas Health and Family Planning Office. The design stage produced storyboards and visual asset concepts. During the development stage, vector-based visual assets were created and colored. Motion graphics were implemented using the CapCut application by applying keyframe animation techniques to create dynamic visual movements. The evaluation stage was conducted using the Alpha Testing method involving a subject matter expert and an animation expert. The evaluation results achieved an average score of 92.06%, categorized as excellent. Therefore, the “Aksi 3M Plus” motion graphic animation is considered suitable as an educational medium for DHF prevention.

Page 59 of 70 | Total Record : 696

 57   58   59   60   61 

Filter by Year

2016 2026


Reset
Filter By Issues
All Issue Vol 11 No 2 (2026): Juli Vol 11 No 1 (2026): Januari Vol 10 No 2 (2025): Juli Vol 10 No 1 (2025): Januari Vol 9 No 2 (2024): Juli Vol 9 No 1 (2024): Januari Vol 8 No 2 (2023): Juli Vol 8 No 1 (2023): Januari Vol 7 No 2 (2022): Juli Vol 7 No 1 (2022): Januari Vol 6 No 2 (2021): Juli Vol 6 No 1 (2021): Januari Vol 5 No 2 (2020): Juli Vol 5 No 1 (2020): Januari Vol 4 No 2 (2019): Juli Vol 4 No 1 (2019): Januari Vol 3 No 2 (2018): Juli Vol 3 No 2 (2018): Juli Vol 3 No 1 (2018): Januari Vol 3 No 1 (2018): Januari Vol 2 No 2 (2017): Terbitan Ke-4 Bulan Juli 2017 Vol 2 No 2 (2017): Juli 2017 Vol 2 No 1 (2017): Januari 2017 Vol 1 No 2 (2016): Juli 2016 Vol 1 No 1 (2016): Januari 2016 More Issue