cover
Contact Name
Imam Rangga Bakti
Contact Email
imamranggabakti@gmail.com
Phone
+6281262552956
Journal Mail Official
imamranggabakti@gmail.com
Editorial Address
Jl.Tuanku Tambusai Jl. Raya Kumu, Rambah, Kec. Rambah Hilir, Kabupaten Rokan Hulu, Riau 28558
Location
Kab. rokan hulu,
Riau
INDONESIA
Riau Jurnal Teknik Informatika
ISSN : -     EISSN : 28292529     DOI : https://doi.org/10.30606/rjti.v1i1
Core Subject : Science,
Riau Jurnal Teknik Informatika dimaksudkan sebagai media kajian ilmiah hasil penelitian, pemikiran dan kajian analisis-kritis mengenai penelitian bidang ilmu komputer dan teknologi. Sebagai bagian dari semangat menyebarluaskan ilmu pengetahuan hasil dari penelitian dan pemikiran untuk pengabdian pada Masyarakat luas dan sebagai sumber referensi akademisi di bidang Ilmu Komputer dan Teknologi. Riau Jurnal Teknik Informatika menerima artikel ilmiah dengan lingkup penelitian pada: Rekayasa Perangkat Lunak Rekayasa Perangkat Keras Keamanan Informasi Rekayasa Sistem Sistem Pakar Sistem Penunjang Keputusan Data Mining Sistem Kecerdasan Buatan Jaringan Komputer Teknik Komputer Pengolahan Citra Algoritma Genetik Sistem Informasi Business Intelligence and Knowledge Management Database System Big Data Internet of Things Enterprise Computing Machine Learning Topik kajian lainnya yang relevan
Articles 176 Documents
Pengembangan Aplikasi To-Do List Adaptif Berbasis Android untuk Intervensi Distraksi Digital Michael Reynald Manoppo Manoppo; Salvius Paulus Lengkong Lengkong; Salaki Reynaldi Joshua Salaki
Riau Jurnal Teknik Informatika Vol. 5 No. 2 (2026): Juli 2026
Publisher : Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjti.v5i2.4553

Abstract

Academic procrastination is a common problem among university students and can be intensified by digital distractions from social media notifications and entertainment applications on smartphones. A preliminary study involving 40 students from the Faculty of Engineering at Sam Ratulangi University showed that 72.5% of respondents frequently completed assignments close to deadlines, 80.0% were often distracted while working on assignments, and 60.0% experienced difficulty maintaining focus. Existing to-do list applications are generally passive, as they mainly function as task recording and reminder tools without active mechanisms to help users limit digital distractions. This study aims to design and develop an Android-based adaptive to-do list application named MyTask, equipped with proactive intervention features. The development method used was Research and Development (R&D) with the ADDIE model. The application was developed using a hybrid approach, combining a Flutter-based user interface with native Android services to support distraction application blocking and notification filtering based on the urgency level of user tasks. User experience evaluation was conducted with 20 student participants using the User Experience Questionnaire (UEQ), which consists of 26 items across six measurement scales. The results showed that all UEQ scales achieved an Excellent classification, with the highest score obtained by Efficiency (2.450) and the lowest score by Novelty (1.950). These findings indicate that MyTask is feasible to use and well received from a user experience perspective. However, this study did not directly measure the application’s effectiveness in reducing procrastination; therefore, further experimental evaluation is required.
Komparasi Supervised dan Self-Supervised Learning untuk Klasifikasi Sel Darah pada Skenario Keterbatasan Data Berlabel Misella Mambu; Oktavian Abraham Lantang; Salaki Reynaldo Joshua
Riau Jurnal Teknik Informatika Vol. 5 No. 2 (2026): Juli 2026
Publisher : Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjti.v5i2.4555

Abstract

The development of blood cell image classification models is often hindered by the scarcity of labeled data. This study evaluates the effectiveness of supervised baseline models, supervised fine-tuning, and self-supervised learning (SSL) based on SimCLR and BYOL using the ResNet-50 and DenseNet-121 architectures. Data-limited simulation was performed using 10% labeled data for the classification stage and 90% unlabeled data for SSL pre-training on 17,092 images from 8 morphological classes. The results show that SSL achieves competitive performance, with the highest accuracy on ResNet-50 at 95.31% (SimCLR) and 94.27% (BYOL), and on DenseNet-121 at 93.75% (SimCLR) and 89.58% (BYOL). The SSL approach also demonstrated robustness against overfitting, good robustness against class imbalance, and Grad-CAM visualizations that align with medical expert assessments on ResNet-50. In conclusion, SSL effectively optimizes unlabeled data to improve the performance of classification models in scenarios with limited data annotation.
Klasifikasi Performa Akademik Siswa Menggunakan KNN Berdasarkan Keterhubungan Data Siswa dan Akademik Saffira Izzati; Dedy Hartama; Rizki Alfadillah Nasution
Riau Jurnal Teknik Informatika Vol. 5 No. 2 (2026): Juli 2026
Publisher : Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjti.v5i2.4576

Abstract

This study aims to apply the K-Nearest Neighbor  (KNN) algorithm to classify student academic performance based on several variables, namely age, study hours, attendance percentage, additional activities, and student academic grades. Academic performance is classified into three categories: low, medium, and high. The study was conducted using a data mining approach through data preprocessing, categorical to numeric data transformation, data normalization using StandardScaler, division of training and test data, and the classification process using the KNN algorithm. To determine the best parameters, several K values ​​were tested and the optimal value of K = 1 was obtained based on the highest accuracy. The results showed that the KNN algorithm was able to classify student academic performance with an accuracy level of 96.4%. Evaluation results based on precision, recall, F1-score, and confusion matrix showed that the model had good classification performance with a relatively small error rate. In addition, the results of parameter testing showed that the selection of the K value affected the performance of the classification model. Based on the results of the study, the K-Nearest Neighbor  algorithm has proven effective as a classification method to assist in analyzing student academic performance and can be an alternative to support decision-making in the field of education.
Peningkatan Akurasi Deteksi Penyakit Daun Padi Menggunakan Augmentasi Data Berbasis Generative Adversarial Networks (GAN) Nasya Sunia Tubuon; Nancy Jeane Tuturoong; Salaki Reynaldo Joshua
Riau Jurnal Teknik Informatika Vol. 5 No. 2 (2026): Juli 2026
Publisher : Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjti.v5i2.4585

Abstract

Rice is a staple food crop for more than half of the global population, with Asia contributing approximately 90% of global production. Leaf diseases, particularly Blast and Bacterial Blight, are major factors contributing to reduced rice productivity in Indonesia. Conventional detection methods based on visual observation are often subjective and time-consuming, highlighting the need for more reliable automated detection systems. This study aims to implement StyleGAN2-ADA to generate synthetic rice leaf disease images and evaluate its impact on the performance of Convolutional Neural Network-based classification. This research employed a quantitative experimental approach by comparing two scenarios: Baseline without GAN augmentation and Proposed with StyleGAN2-ADA synthetic image augmentation. Two CNN architectures, EfficientNetB0 and ResNet50, were evaluated using accuracy, precision, recall, F1-Score, and confusion matrix metrics. The quality of synthetic images was assessed using the Fréchet Inception Distance. The results demonstrated that StyleGAN2-ADA augmentation improved the overall F1-Score of EfficientNetB0 from 97.62% to 98.20%, with the largest improvement observed in the Blight class, increasing by 3.11%. For ResNet50, the overall F1-Score increased from 97.60% to 98.20%, although the Blast class showed no performance improvement after augmentation. GAN augmentation provided the most consistent benefits for the minority Blight class, while its impact on the Blast class varied across metrics. In EfficientNetB0, improvements in precision and F1-Score were accompanied by a decrease in recall. These findings indicate that model evaluation should consider class-specific performance and the trade-off between precision and recall rather than relying solely on aggregate metrics
Aplikasi Smart Title Checker Laporan Mahasiswa Menggunakan Metode Cosine Similarity Berbasis Website Pada Politeknik Xyz Yudistira Sira Permana; Muhammad Syahril; Agus Setiawan
Riau Jurnal Teknik Informatika Vol. 5 No. 2 (2026): Juli 2026
Publisher : Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjti.v5i2.4597

Abstract

The increasing number of student final reports each year presents challenges for higher education institutions in maintaining the uniqueness and novelty of proposed titles. The title-checking process, which is still commonly conducted manually, tends to require considerable time and may lead to inconsistencies in the validation process. This study aims to design and develop a web-based Smart Title Checker application capable of detecting the similarity level of student report titles using the Cosine Similarity method. This method is applied to measure the similarity between titles, thereby supporting a more objective validation process. The system development was carried out through several stages, including requirements analysis, design, implementation, and application testing. The results show that the application can perform title similarity checking quickly and accurately by displaying similarity percentages against stored title data in the database. The system implementation also helps students obtain initial information regarding potential title similarities and improves the efficiency of the validation process conducted by academic administrators. Therefore, the developed application can support more effective, efficient, and structured management of student report titles.
Rancang Bangun Aplikasi Berbasis Android dalam Mengembangkan UMKM Lapangan Futsal di Kota Medan Fidelis Elinus Zebua; Arjon Samuel Sitio; Taufik Ismail Simajuntak
Riau Jurnal Teknik Informatika Vol. 5 No. 2 (2026): Juli 2026
Publisher : Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjti.v5i2.4654

Abstract

The development of futsal field Micro, Small, and Medium Enterprises (MSMEs) in Medan City faces obstacles in terms of disseminating field rental information to the wider community. Field owners struggle to promote their services, while customers often experience difficulties finding information about available fields and must visit locations directly. This research aims to produce an Android-based application that connects futsal field owners with customers to facilitate the information and field rental process in Medan City. The research methods used include data collection through literature study, observation, and field surveys. The research results show that the application can function properly based on black box testing of all features. The application successfully facilitates field owners in providing digital field rental information and makes it easier for customers to search for and rent futsal fields without having to come directly to the location. This application is expected to support the development of MSMEs in the sports sector, particularly futsal fields in Medan City.
Evaluasi UI/UX dan Rancang Bangun Sistem Informasi Penjualan Toko Buku Al-Fithrah Menggunakan UCD Dori Gusti Alex Candra; Irzon Meiditra; Fauziah Fauziah; Rizky Rahmansyah; Yulia Yulia
Riau Jurnal Teknik Informatika Vol. 5 No. 2 (2026): Juli 2026
Publisher : Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjti.v5i2.4656

Abstract

Al-Fithrah Bookstore faces operational challenges in sales due to conventional processes that are still manual. This results in long service times, a high rate of calculation errors, and a high risk of losing report records. This study aims to design a web-based Sales Information System interface using the User-Centered Design (UCD) method. The UCD method was implemented through four iterative stages: understanding the usage context, determining user needs, designing the interface solution, and evaluating the design. This design process resulted in two main interface modules. The customer module is focused on facilitating hybrid search navigation, providing transparency in the shopping cart, and offering up-selling features. Meanwhile, the administrator module is designed to centralize master data management and automatically digitize the printing of daily through annual reports. Usability testing was conducted on 20 respondents using the System Usability Scale (SUS) instrument. The evaluation results showed a significant increase in the usability score, from an initial baseline of 38.5 (the “Awful” category) to a final score of 87.5 (the “Excellent” category). In conclusion, the UCD approach has been empirically proven to reduce users’ cognitive load, minimize interaction errors, and streamline administrative processes, thereby delivering an optimal digital experience
Rancang Bangun Game Edukasi 2D Pengenalan Buah-Buahan Berbasis Android Menggunakan Metode Game Development Life Cycle (GDLC) Tito Surya; Tommy Bustomi; Farindika Metandi
Riau Jurnal Teknik Informatika Vol. 5 No. 2 (2026): Juli 2026
Publisher : Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjti.v5i2.4662

Abstract

Technological developments have brought significant changes to the field of education, including early childhood education. However, there are still many learning methods that are less effective in attracting early childhood students’ interest in learning, especially in the digital era through fruit recognition game applications. Based on these issues, the problem formulation in this study is how to design and develop an engaging and interactive 2D educational game for fruit recognition aimed at early childhood learners. This study uses the Game Development Life Cycle (GDLC) method, which consists of six stages: initiation, pre-production, production, testing, beta, and release. The game was developed using Construct 2 and is intended for Android devices to make it easily accessible for early childhood users. The purpose of this study is to create an enjoyable and effective learning medium for early childhood children to learn fruit recognition while increasing learning interest through interactive digital media. The result of this study is the creation of an educational game that can be used as an alternative learning medium, helping early childhood children recognize various types of fruits in a fun, interactive, and more engaging way. Black box testing showed that all features functioned successfully, and beta testing involving teachers and the school principal obtained an average score of 89%, placing the game in the “very feasible” category as a fruit-recognition learning medium.
Rancang Bangun Website Profil Dan Layanan Administrasi UKM Olahraga Politeknik Negeri Samarinda Berbasis Laravel Fayad Zabihulloh; Noor Alam Hadiwijaya; Anton Topadang
Riau Jurnal Teknik Informatika Vol. 5 No. 2 (2026): Juli 2026
Publisher : Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjti.v5i2.4667

Abstract

The development of the Sports Student Activity Unit (UKM Olahraga) profile and administrative service website at the Samarinda State Polytechnic aims to provide a centralized web-based platform for organizational information and service management. The system enables students to access UKM profiles, sports divisions, activity schedules, news, galleries, member registration, and inventory loan services online. The system was developed using Laravel 11 as the backend, Filament v4 as the administration panel, Bootstrap 5 for the user interface, and MySQL as the database. The development method applied is the Web Development Life Cycle (WDLC), covering feasibility, analysis, design, coding, testing, deployment, and maintenance. The implemented features include UKM profile management, sports divisions and branches, activity and training schedules, news, galleries, new member registration, inventory borrowing, and an administration panel. Black Box Testing on 15 admin and user scenarios showed that all scenarios were successful, resulting in a 100% functional success rate. User Acceptance Testing (UAT) with UKM administrators on information access, content management, registration, borrowing, and ease of use indicators showed that the system was in accordance with organizational needs. Therefore, the website can support faster, more structured, and better documented management of UKM data and information dissemination.
Rancang Bangun Sistem Pakar Berbasis Web untuk Diagnosis Kerusakan Smartphone Menggunakan Metode Forward Chaining Atika Fauziyyah; Dori Gusti Alex Candra; Eka Sofiati; Budi Permana Putra; M. Agung Vafky Ideal; Asep Supriyanto
Riau Jurnal Teknik Informatika Vol. 5 No. 2 (2026): Juli 2026
Publisher : Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjti.v5i2.4672

Abstract

The rapid advancement of information technology has made smartphones essential devices for supporting various daily activities. Intensive smartphone usage may lead to hardware and software failures, while users' limited knowledge in identifying these failures often results in improper troubleshooting. This study aims to design and develop a web-based expert system for diagnosing smartphone failures using the Forward Chaining method. The system was developed through requirements analysis, expert knowledge acquisition, knowledge base design, rule base construction, method implementation, and system testing. The knowledge base consists of 15 symptoms, 10 types of smartphone failures, and 20 diagnostic rules. The results of Black Box Testing showed that all system functions operated according to the specified requirements with a 100% success rate. Furthermore, validation using 20 test cases demonstrated that 19 system diagnoses were consistent with expert diagnoses, resulting in an accuracy of 95%. The developed expert system can assist users and technicians in performing initial smartphone failure diagnosis quickly, accurately, and efficiently.