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
 36   37   38   39   40 
IMPLEMENTASI ALGORITMA FHSAR DALAM MENYEMBUNYIKAN ATURAN ASOSIASI SENSITIF PADA DATASET TRANSAKSI Cintana Rendra Salsabila; Dedi Gunawan
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.7115

Abstract

Transaction data is one of the assets in the digital era that can be used to analyze consumer behavior through the application of data mining algorithms, such as association rules. Not all association rules are safe to publish because some contain sensitive information that can impact customer privacy or a company's business strategy. This study aims to implement the Fast Hiding Sensitive Association Rule (FHSAR) algorithm with an item suppression approach that removes certain items with high frequency and supports sensitive rules so that these rules no longer meet the minimum support and confidence values. Sensitive association rules are explicitly determined by the user based on a combination of items considered confidential and predetermined support and confidence values. The dataset used is a public dataset from SPMF. The algorithm implementation is carried out in the form of a Python and Flask-based web application to upload datasets, set threshold values, view suppression results, and display item support visualizations using Charts.js. Evaluation of the algorithm's effectiveness is carried out using four metrics: Misses Cost (MC), Artificial Rules (AR), Item Loss (IL), and Data Dissimilarity (DD). The test results show that the FHSAR algorithm is able to effectively hide sensitive rules with MC values ​​of 1.4%, AR of 0%, IL of 0.9%, and DD of 0.04%. The data sanitization process has minimal impact on the structure and quality of the data, so that the resulting dataset is still suitable for further analysis.
KLASIFIKASI CITRA WAJAH BERDASARKAN PENGGUNAAN KACAMATA MENGGUNAKAN ALGORITMA CNN DAN IMPLEMENTASI FLASK Rahayu Fathan Asri; Subektiningsih Subektiningsih
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.7122

Abstract

Face image classification is an important branch of computer vision and artificial intelligence, commonly applied in various fields such as facial recognition and facial attribute analysis. One facial attribute that is particularly interesting to classify is the use of eyeglasses, as it can affect the overall accuracy of facial recognition systems. This study aims to develop an eyeglass-use classification system based on a Convolutional Neural Network (CNN) and implement it in a web application using Flask to enable real-time prediction results. The research methodology includes collecting facial image datasets from Kaggle, performing preprocessing steps such as resizing, augmentation, and normalization, designing the CNN architecture, training the model, and evaluating its performance using a confusion matrix and classification report. The designed CNN model consists of three convolutional layers, max pooling, a flattening process, two fully connected layers, and a dropout layer to reduce the risk of overfitting. During the training phase, the model achieved 90% training accuracy and 96% validation accuracy, while testing on the test dataset resulted in an overall accuracy of 82%. The Flask-based system is capable of displaying real-time predictions, including the input image, classification label, accuracy percentage, and inference time. In the detection process, the accuracy of the model implementation reached 93% and the time required was in the range of a few milliseconds. The results demonstrate that the CNN can effectively classify faces with and without eyeglasses, and its implementation through a web interface offers broad potential for visual identification applications.  
HYBRID REFERENCE GENERATION WITH MMR AND TRANSFORMER MODELS FOR AUTOMATIC SHORT ANSWER SCORING Affan Hilmy Natsir; Clara Diva; Husni Mubarak
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.7123

Abstract

The rapid transition to online learning during the COVID-19 pandemic has accelerated the demand for automated assessment systems capable of evaluating students’ understanding objectively, consistently, and efficiently. Automatic Short Answer Scoring (ASAS) has emerged as a central challenge within Natural Language Processing (NLP), particularly for assessing short or open-ended answers. This research proposes an ASAS framework that integrates Reference Answer Generation using Transformer-based models (BART and GPT-2) with the Maximum Marginal Relevance (MMR) method. While MMR has been widely used as an extractive technique to select diverse student answers as reference candidates, its performance remains limited by the availability and variability of student responses. To address this limitation, the proposed approach supplements MMR-generated references with paraphrased reference answers generated by fine-tuned Transformer models, thereby increasing lexical and syntactic diversity. Experimental evaluation was conducted on the Texas Short Answer Corpus, consisting of 2,442 student responses across 10 tasks. The results demonstrate that the proposed hybrid approach improves scoring performance, as indicated by an increase in Pearson correlation and a reduction in RMSE and MAE compared to the baseline MMR-based method.  
ANALISIS KINERJA MACHINE LEARNING UNTUK DETEKSI KONTEN PENIPUAN BERBAHASA INDONESIA DI TWITTER Imroatul Khuluqi Izzah; Imam Riadi; Abdul Fadlil
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.7124

Abstract

The development of information technology has changed the way people interact in the digital space, including through the Twitter platform, which is widely used to share information and opinions. However, this convenience has also led to the emergence of fraudulent content such as fake investments, fictitious sweepstakes, and fictitious donation requests. This study aims to analyze and compare the performance of five machine learning algorithms, namely Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), and Naïve Bayes (NB), in detecting fraudulent Indonesian language content on Twitter. The dataset consists of 5.221 Indonesian language tweets that have been manually labeled into two classes, fraud and non-fraud. All tweets were processed through text preprocessing stages, including data cleaning, case folding, normalization, tokenization, filtering, and stemming, before being represented as numerical vectors using Word2Vec. Classification was performed using 10-fold cross-validation with evaluation metrics of accuracy, precision, recall, and F1-score. The results show that Random Forest achieved the best performance with accuracy of 85.6%, followed by SVM (84.0%), Logistic Regression (83.6%), Decision Tree (81.2%), and Naïve Bayes (78.4%). The main contribution of this study is to provide a systematic empirical comparative analysis of classification algorithms for detecting Indonesian fraudulent content on Twitter, which remains relatively underexplored. These findings show that the combination of Word2Vec and Random Forest can effectively capture the semantic context of short texts and can serve as a reference for developing automatic detection systems for fraudulent content on social media.
IMPLEMENTASI SISTEM ABSENSI BERBASIS FACE RECOGNITION DENGAN MEKANISME BLINK DETECTION MENGGUNAKAN SVM SECARA REAL-TIME: IMPLEMENTATION OF A FACE RECOGNITION-BASED ABSENCE SYSTEM WITH A BLINK DETECTION MECHANISM USING SVM IN REAL-TIME Valeria Rahayu; Erlin Dolphina; Ricardus Pramunendar
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.7127

Abstract

Employee attendance is an important aspect of attendance management in office environments. Face recognition technology offers a modern approach to employee attendance systems; however, its implementation remains vulnerable to spoofing attacks. On the other hand, many companies still rely on traditional methods such as manual signatures, which are inefficient, prone to fraud, and time-consuming. To address these issues, this study develops a real-time face recognition-based employee attendance system aimed at improving the efficiency, accuracy, and security of attendance recording by integrating blink detection as an anti-spoofing mechanism. The proposed system utilizes MTCNN for face detection, ArcFace for facial feature extraction in the form of vector embeddings, and Support Vector Machine (SVM) as the classification algorithm. Experimental results show that the system is able to recognize employee faces with an accuracy of 95%, achieving precision, recall, and F1-score values of 95.86%, 93.58%, and 93.89%, respectively. The blink detection mechanism is proven to prevent attendance spoofing using static photos. In addition, the system supports dynamic addition of new employee data without requiring long waiting times through a controlled data update process. With the implementation of this system, the employee attendance process becomes faster, more accurate, and security-verified, making it a practical solution for modern and efficient attendance data management in companies.
PEMANFAATAN TEKNIK TWEENING PADA ANIMASI 2D UNTUK EDUKASI GIZI IBU HAMIL DAN PENCEGAHAN STUNTING Awwali Zahra Brillianti; Dani Arifudin; Deuis Nur Astrida
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.7128

Abstract

Stunting remains a significant public health issue that affects children’s growth and development, highlighting the need for effective educational media for pregnant women to improve their understanding of nutrition. This study aims to develop a 2D educational animation themed B2SA by applying tweening techniques as the primary method to achieve consistent motion and a more efficient production process. The research method includes pre-production (idea development, concept creation, storyboard, and asset design), production (asset creation, layout, and animation), and post-production stages (editing, rendering, and alpha testing), complemented by validation from health experts and animation specialists. The results indicate that the animation is deemed feasible based on expert assessment, with tweening increasing production efficiency by 90–97% in reducing manual frames compared to frame-by-frame animation while producing smooth, stable motion aligned with educational needs. The study concludes that the developed animation is feasible as an educational medium for pregnant women in supporting stunting prevention efforts.
PERANCANGAN SISTEM REKOMENDASI LOWONGAN KERJA DENGAN PENDEKATAN NATURAL LANGUAGE PROCESSING (NLP) BERBASIS TF-IDF DAN WORD2VEC Ipham Ahmad Fahrezy Farid; Nouval Trezandy Lapatta
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.7132

Abstract

The abundance of job vacancy information on various digital platforms often creates inefficiencies in the job search process because applicants must manually select job descriptions, while companies also experience difficulties in assessing applicant suitability quickly and objectively. This study develops a web-based job vacancy recommendation system with a Natural Language Processing (NLP) approach using the Term Frequency–Inverse Document Frequency (TF-IDF) and Word2Vec methods to represent applicant profiles and job descriptions, which are analyzed using cosine similarity. The system was developed using a prototyping method so that it can be iteratively adapted to user needs. Evaluation of the characteristics of the recommendation results was carried out exploratively through analysis of similarity scores and changes in job rankings in several test scenarios. Based on the test scenarios and descriptive analysis of similarity scores and ranking changes, TF-IDF tends to produce lower suitability scores when there are variations in terms, while Word2Vec provides relatively more stable scores due to its ability to represent the closeness of meaning between words. In addition, usability evaluation using the System Usability Scale (SUS) obtained an average score of 89.5 with an Excellent category, indicating that the system is easy to use and comfortable for users. This system is expected to help applicants find relevant vacancies and support a more systematic applicant screening process.
IMPLEMENTASI SISTEM MONITORING DAN KENDALI GENSET LPG SECARA NEAR REAL-TIME MENGGUNAKAN ESP32-S3 DAN FIREBASE: IMPLEMENTATION OF A NEAR REAL-TIME LPG GENERATOR MONITORING AND CONTROL SYSTEM USING ESP32-S3 AND FIREBASE Muhammad Arzu Prasetyo; Arya Kusumawardana; Soraya Norma Mustika; Royb Fatkhur Rizal
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.7135

Abstract

Manual monitoring of generators often leads to delays in detecting malfunctions and is unable to provide near real-time data. This study aims to design and implement an Internet of Things (IoT)-based monitoring and control system for LPG generators using an ESP32-S3 microcontroller integrated with Firebase and an Android application called GENMON (Genset Monitoring System). The system is designed to measure various operational parameters of the generator, including voltage, current, power, temperature, and gas pressure, and to transmit these data continuously to Firebase for display through the Android application. In addition to presenting parameter information, the system is equipped with an automatic notification feature that triggers when abnormal conditions are detected, as well as remote-control functionality for starting and shutting down the generator. This research adopts a practice-based methodology encompassing the design of both hardware and software, followed by system performance testing and application functionality evaluation. Based on the test results, the system demonstrated good performance, with voltage sensor accuracy reaching 98.5%, frequency sensor accuracy reaching 99.33%, and current sensor accuracy reaching 100%, an average notification delay of 1.76 seconds, data transmission latency ±1 second, data synchronization success rate of 90%, and a control response time ranging from 1 to 2 seconds.
OPTIMALISASI KONSUMSI AIR RUMAH TANGGA MENGGUNAKAN SISTEM PEMANTAUAN AIR PINTAR BERBASIS IOT Fauzan Ishlakhuddin; Fachrul Pralienka Bani Muhamad; Eka Ismantohadi; Lucky Dawamuz Dzikri; Mohamad Muhgni Rahadiansyah; Ramadhani
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.7136

Abstract

This study develops an Internet of Things (IoT)-based Smart Water Monitoring System for periodic (near real-time) and comprehensive monitoring of household water consumption. The system consists of two main devices: a device for monitoring PDAM water flow rate and pressure using a YF-S201 flow sensor and a pressure sensor, and a device for monitoring water tank conditions using an SR04T ultrasonic sensor for water level measurement and a turbidity sensor for water clarity detection. Both devices are connected to ESP32/ESP8266 microcontrollers and transmit sensor data to a server every five minutes via a WiFi network. The implementation results indicate that the system is capable of performing stable sensor readings and data transmission during the household testing period, with consistent data delivery success and relatively low latency suitable for domestic monitoring purposes. Sensor evaluation was conducted using simple comparative methods, showing consistent measurement patterns after the initial calibration process. The collected data are visualized through web and mobile applications in the form of flow rate graphs, supply pressure graphs, water tank level charts, and turbidity indicators. This system has the potential to enhance the visibility of household water consumption and provides a technical foundation for early detection of water supply anomalies and the future development of data-driven water conservation systems.
KOMPARASI ALGORITMA MACHINE LEARNING UNTUK DETEKSI MALWARE MENGGUNAKAN SELEKSI FITUR PADA DATASET CLAMP: COMPARISON OF MACHINE LEARNING ALGORITHMS FOR MALWARE DETECTION USING FEATURE SELECTION ON THE CLAMP DATASET Desmondy; Wildanil Ghozi; Fauzi Rafrastara
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.7138

Abstract

Malware attacks are a significant cyber threat requiring sophisticated detection methods. This research aims to compare the performance of four machine learning algorithms (Gradient Boosting, Neural Network, k-Nearest Neighbors, and Support Vector Machine) in detecting malware on the ClaMP dataset. The research method includes data preprocessing, feature selection using Information Gain to select the Top 40 best features, and model testing across four feature subset scenarios (ALL, DDoS, File Features, and Optional Features). Model evaluation used the 10-Folds Cross-validation method to ensure result stability. The results show that the Gradient Boosting model combined with all 40 best features (ALL scenario) achieved the highest performance with 98.7% accuracy. This result surpasses the primary reference study, which recorded 96.91% accuracy using 68 features. The Neural Network model also showed excellence in the File Features scenario (9 features) with 91.9% accuracy. In conclusion, applying Information Gain feature selection combined with the Gradient Boosting algorithm proved to significantly increase detection accuracy while simultaneously reducing the number of features required (efficiency).   Keyword: Malware, Machine Learning, Gradient Boosting, Feature Selection, Classification.

Page 38 of 70 | Total Record : 696

 36   37   38   39   40 

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