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
 30   31   32   33   34 
KLASIFIKASI TINGKAT KECANDUAN PENGGUNA APLIKASI TIKTOK PADA MAHASISWA UNIVERSITAS MALIKUSSALEH MENGGUNAKAN METODE NAÏVE BAYES Wardina Ningsih; Mukti Qamal; Fadlisyah
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.v11i1.6603

Abstract

Penggunaan media sosial, khususnya TikTok , meningkat pesat di kalangan pelajar. Hal ini dapat menyebabkan kecanduan yang mempengaruhi pendidikan dan kehidupan sehari-hari mereka. Penelitian ini bertujuan untuk mengetahui tingkat Kecanduan TikTok di kalangan mahasiswa Universitas Malikussaleh dengan mengumpulkan data dari 466 mahasiswa dari tujuh fakultas dan menggunakan metode Naïve Bayes . Kelas yang akan dihasilkan tiga kategori yaitu Kecanduan ingan, Kecanduan Sedang, dan Kecanduan Berat. Dataset dibagi menjadi data pelatihan dan pengujian dengan rasio 80:20. Hasil analisis menunjukkan bahwa sebagian besar siswa (258 orang atau 69,4%) berada pada tingkat kecanduan sedang, diikuti oleh tingkat kecanduan ringan (22,6%) dan berat (8,1%). Menurut evaluasi kinerja model, metode Naive Bayes menunjukkan akurasi sebesar 85%, presisi rata-rata sebesar 84%, dan recall sebesar 83% pada data pengujian, yang menjadikannya pilihan yang tepat. Fakultas Pertanian memiliki proporsi kecanduan ringan tertinggi sebesar 14,6%, sedangkan Fakultas Ekonomi memiliki proporsi kecanduan ringan tertinggi sebesar 27,1%. Penelitian ini menunjukkan bahwa teknik Naive Bayes efektif dalam mengklasifikasikan tingkat kecanduan pengguna TikTok dan dapat digunakan sebagai acuan untuk upaya pencegahan dampak negatif Kecanduan media sosial di dunia akademik.
USING CORRELATION BASED FEATURE SELECTION TO ENHANCE PREDICTIVE PERFORMANCE FOR EARLY CERVICAL CANCER DETECTION Maryam
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.v11i1.6606

Abstract

Cervical cancer data is high-dimensional with numerous features. Reducing the number of features in the analysis can provide advantages in more effective data processing and prevent overfitting, which can lead to detection errors. This study aimed at improving the classification performance for early identification of cervical cancer through the CFS technique based on the Naive Bayes classification algorithm. The dataset used was the primary data with three classes of cancer conditions. Feature reduction was applied to decrease data dimensionality and improve processing efficiency. The selected feature subset comprised 10 attributes that showed a strong correlation with the target class. The performance evaluation yielded an accuracy of 83.50%, recall of 83.57%, and precision of 88.30%. These findings suggest that the proposed method can enhance the early detection of cervical cancer, which support early detection of cervical cancer and assist clinical decision-making
VIDEO TRANSCRIPTION DAN VOICE SYNTHESIS UNTUK SISTEM PENERJEMAH ISYARAT BAHASA INDONESIA: VIDEO TRANSCRIPTION AND VOICE SYNTHESIS FOR INDONESIAN LANGUAGE SIGN TRANSLATION SYSTEM Nazwa Aulia; Muhammad Fikry; Ar Razi
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.v11i1.6608

Abstract

Communication is a way for humans to convey information, ideas, thoughts, feelings, or massages verbally or nonverbally. People with hearing impairments use expressions and symbols due to hearing limitations, the term tuna means less and rungu means hearing. To bridge communication, sign language translation through the development of systems such as text-to-speech can help improve accessibility between people with hearing impairments and spoken language users in various contexts of everyday life. The Indonesian Sign Language (SIBI) translation system in this study was built the waterfall research method in which each process will be carried out in stages and sequentially, starting from problem analysis and creating a conceptual system in order to strengthen the theorectical foundation and answer the formulation of the problems raised, this study uses the Keras deep learning model and the Convolutional Neural Network (CNN) approach. The test results show that the system is able to classify hand gestures and convert them into text and voice, in addition to the average respone time of less than one second, which is around 104 miliseconds per step. This shows that the system can operate in real-time with a fast and consistent response. Video transcription and voice synthesis for an Indonesian sign language translation system using the Python programming language were successfully implemented, supported by various libraries such as OpenCV, CVZone, and GTTS (Google Text-To-Speech). Testing results on 15 movement classes with 150 trials showed an average movement classification accuracy of 87%. Further research is recommended to increase the number of subjects and dataset diversity to improve the model’s generalizability.
SISTEM PENDUKUNG KEPUTUSAN PEMILIHAN FRAMEWORK WEB MENGGUNAKAN METODE WEIGHTED PRODUCT: DECISION SUPPORT SYSTEM FOR WEB FRAMEWORK SELECTION USING WEIGHTED PRODUCT METHOD Muhammad Alfath Frandhana Sihotang; Fadlisyah; Fajriana
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.v11i1.6610

Abstract

There are many types of web frameworks available today, each with its own characteristics, advantages, and limitations. This diversity often makes it difficult for developers to determine the most appropriate framework to meet all project needs. This study aims to help developers determine the best framework that can be used optimally on small and large-scale projects. The research process includes determining framework selection criteria based on literature studies, assessing the weight of criteria from developers and students, and collecting framework data through online platforms such as Official Documentation (official websites of the frameworks studied), Github, and Stack Overflow. Based on the results of the analysis and evalution of the collected data, it was found that the Next.js framework ranked highest as the best front-end framework with a final score of 0.04566 on a scale of 0-1, and the FastAPI framework ranked highest as the best back-end framework with a final score of 0.04385 on a scale of 0-1. Thus, Next.js (front-end framework) and FastAPI (back-end framework) are considered to have superior performance, high scalability, and extensive community support, making it easier for developers to find solutions, documentation, and development references. If an error or bug occurs, developers can ask questions on the Github website, Stack Overflow and the Official Documentation of the framework.  
ANALISIS SENTIMEN ULASAN MASYARAKAT TERHADAP APLIKASI SIREKAP 2024 PADA GOOGLE PLAY STORE MENGGUNAKAN METODE K-NEAREST NEIGHBORS (KNN) Zahlul Fasya; Muhammad Daud; Lidya Rosnita
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.v11i1.6612

Abstract

In the last general election, the Sirekap application experienced a series of failures that resulted in delays and inaccuracies in the delivery of election results data. This study aims to analyze and classify public sentiment towards the application. The method used is K-Nearest Neighbors (KNN) utilizing 21,593 reviews from the Google Play Store. The research stages included data collection and text pre-processing in the form of cleaning, tokenizing, normalization, stopword removal, and stemming. Sentiment labeling was performed automatically using a weighted lexicon method to divide the data into two classes, namely positive and negative. Features were extracted using TF-IDF, and the model was evaluated with 10-fold cross-validation before being tested using a ratio of 70% training data and 30% test data. The results showed extreme class imbalance, with negative sentiment dominating 90.1% of the dataset. This causes a significant performance disparity: the model achieves a recall of 98.31% for the negative class but only 50.79% for the positive class. These findings indicate that although KNN is effective for majority patterns, the model experiences prediction bias towards the minority class. As a final implementation, an interactive web application was created to demonstrate the model and display visualizations of the research results.  
METODE K-MEANS UNTUK KLASIFIKASI PENJUALAN DI TOKO SINAR FASHION DAN BANANA BABY SHOP DI KOTA KISARAN Dhea Nurul Utami; Dewi Anggraeni; Mardalius
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.v11i1.6620

Abstract

Sinar Fashion and Banana Baby Shop are businesses that sell children's supplies with a wide variety of products. However, the problem they face is suboptimal inventory management due to the lack of an accurate sales classification system. This makes it difficult to understand consumer preferences and determine efficient procurement strategies. This study aims to apply a web-based K-Means Clustering algorithm to automatically group children's product sales based on characteristics and sales volume. The research methodology includes six stages: data collection, problem identification, literature review, system design using UML, system development using PHP and Sublime Text, and system implementation. Sales data from February to May 2025 was used as training data for the clustering process. The system is designed to group products into several clusters, such as best-selling, less popular, and non-selling products. The results of the study indicate that the K-Means method is effective in identifying similar sales patterns between products. The quality of the clustering was evaluated using two metrics, namely the silhouette score and the Davies-Bouldin Index. A silhouette score of 0.74 indicates good clustering quality, while the Davies-Bouldin Index of 0.42 shows a fairly clear separation between clusters. The combination of these two metrics reinforces the validity of the clustering results. The application of this system helps store owners make more informed decisions, such as inventory planning, promotional strategies, and distribution efficiency.
ANALISIS ARSITEKTUR CONVOLUTIONAL NEURAL NETWORK DAN TRANSFER LEARNING DALAM KLASIFIKASI KUALITAS BUAH: ANALYSIS OF CONVOLUTIONAL NEURAL NETWORK ARCHITECTURE AND TRANSFER LEARNING IN FRUIT QUALITY CLASSIFICATION Muhammad Yusril Mushoffah Sekarwati; Nur Nafiiyah
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.v11i1.6622

Abstract

The quality of fresh fruits and vegetables plays a crucial role in consumer health. Manual assessment of product freshness is often ineffective because it is subjective and time-consuming. This study implements a Convolutional Neural Network (CNN) architecture and transfer learning using VGG16 and ResNet50 to classify the condition of fruits (apples and bananas) as fresh or rotten. The model design adapts previous research by modifying the input image size, restricting the target labels to four classes (freshapples, freshbanana, rottenapples, and rottenbanana), and removing the Dropout layer. The dataset, obtained from Kaggle, includes two fruit types (apples and bananas) and two conditions (fresh and rotten). The experimental results show that VGG16 achieved the highest accuracy at 93.9%, outperforming both ResNet50 and the custom CNN model. The custom CNN exhibited notably lower performance, indicating its limited ability to extract deep hierarchical features compared to pretrained architectures. These findings highlight the effectiveness of CNN-based transfer learning for supporting automated classification of fresh agricultural products.  
SISTEM PEMETAAN PEMASANGAN PAPAN IKLAN DAN VIDEOTRON DAERAH KISARAN BERBASIS WEBGIS DENGAN METODE LOCATION BASED SERVICE Syahdan; Adi Prijuna Lubis; Andri Nata
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.v11i1.6629

Abstract

The billboard and videotron installation service system in Kisaran is designed to utilize Location-Based Service (LBS) technology integrated with WebGIS to improve marketing effectiveness. This research was conducted through several stages, including problem identification, data collection of billboard locations from the Department of Public Works, system design using UML, system development with PHP and MySQL, and Google Maps API integration for real-time location mapping. The Haversine algorithm was applied to calculate the distance between points, while system testing was performed on coordinate accuracy and response time. The results show a coordinate accuracy of 95.6% with an average position error of ±12 meters and an average response time of 1.8 seconds. The proposed system not only maps billboard locations but also integrates services such as tenant validation, booking, and payment. Compared to previous studies, this system demonstrates advantages in integrating LBS with advertising business services. Its implementation is expected to support local governments and advertising managers in planning more effective and efficient promotional strategies.
ANALISIS PENERAPAN SISTEM MANAJEMEN RANTAI PASOK BERBASIS WEB UNTUK MENINGKATKAN EFISIENSI PRODUKSI GULA AREN (STUDI KASUS: FAMILY GULA AREN KISARAN) Tati Hidyati; Rizaldi; Sumantri
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.v11i1.6630

Abstract

The rapid development in the business world encourages the importance of implementing Supply Chain Management (SCM) to improve the efficiency and effectiveness of business operations. Family Gula Aren Kisaran, a business engaged in palm sugar production, faces various obstacles in supply chain management, such as delays in raw material supplies due to still relying on manual ordering processes through agents. Information irregularities and the absence of a computerized system also hamper the production process. This study aims to analyze the implementation of supply chain management at Family Gula Aren Kisaran and propose a web-based system. The results of the study indicate that the designed system is able to manage inventory, supplier, production, and distribution data more efficiently, improve data accuracy, and minimize the risk of errors due to information delays with an average transaction recording time of 4 seconds per transaction. With the implementation of this system, business operations become more coordinated and sustainable.
SISTEM PENDETEKSI KESUBURAN TANAH MENGGUNAKAN NODEMCU ESP32 BERBASIS INTERNET OF THINGS: DETECTIESYSTEEM VOOR BODEMVRUCHTBAARHEID MET BEHULP VAN NODEMCU ESP32 OP BASIS VAN INTERNET DER DINGEN Farhani Farhani
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.v11i1.6632

Abstract

This research aims to design and build an Internet of Things (IoT)-based soil fertility detection system using the NodeMCU ESP32 microcontroller. The system is equipped with three main sensors, namely soil pH sensor, capacitive soil moisture sensor, and TCS3200 color sensor. The data obtained is sent in real-time and displayed through a web interface and Arduino IDE serial monitor. The system is able to classify soil fertility based on pH, moisture, and soil color values, and provide recommendations for food crops such as rice, corn, green beans, and cassava. This research uses a quantitative method by taking soil samples from four different locations in North Aceh District: coastal, agricultural rice fields, mountains, and highlands. The test results show the system is able to provide accurate fertility classification and crop recommendations according to soil conditions in each location. The average system response time from sensor reading to data display is 1 second, indicating responsive and real-time system performance. Although the free web version does not yet support soil color display (RGB), all complete data can be accessed through the serial monitor. This system has the potential to be an innovative solution in supporting farmers in digital data-based decision-making to improve agricultural productivity.

Page 32 of 70 | Total Record : 696

 30   31   32   33   34 

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