cover
Contact Name
PPPM ITPA
Contact Email
sttplppm@gmail.com
Phone
+6285797169678
Journal Mail Official
sttplppm@gmail.com
Editorial Address
Jln. Masik Siagim NO.75 Simpang Mbacang Kel. Karang Dalo
Location
Kota pagar alam,
Sumatera selatan
INDONESIA
Jurnal Ilmiah Betrik : Besemah Teknologi Informasi dan Komputer
ISSN : 23391871     EISSN : 27157369     DOI : https://doi.org/10.36050/betrik.v10i03
Core Subject : Science,
Besemah Teknologi Informasi dan Komputer (BETRIK) is a national journal published by Pusat Penelitian dan Pengabdian kepada Masyarakat (P3M), Institut Teknologi Pagar Alam (ITPA). This scientific work was published in 3 editions, with topics related to Computers, Technology, and Science. Topics related to this field can be information systems, informatics, computer science, IT business, IT Governance, enterprise architecture planning, software engineering, modeling and simulation, Data Mining, Artificial Neural Network, Digital Image Processing, Algorithm and Programming, Internet of Things (IoT), artificial intelligence, information security, social networking, cloud computing, science, engineering and related topics. The Scientific Journal BETRIK is a peer journal -National review dedicated to the exchange of high-quality research results in all aspects of education and teaching. This journal publishes the latest works in basic theory, experiments and simulations, as well as applications, with systematically proposed methods, adequate reviews of previous works, extended discussions and conclusions. As our commitment to the advancement of education and teaching, the BETRIK Journal follows an open access policy that allows published articles to be available online for free without subscribing.
Articles 277 Documents
AI-Powered GRU untuk Prediksi Saham Syariah Indonesia Berbasis Analisis Multi Faktor Selvy Megira; Arief Zikry; Nina Dwi Putriani
BETRIK Vol. 17 No. 02 (2026): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/5dfrdm67

Abstract

This study aims to develop a predictive model for Indonesian Sharia stock prices using the Gated Recurrent Unit (GRU) algorithm with a multi-factor analysis approach. The main challenge in analyzing Sharia stocks lies in the high volatility influenced by fundamental, technical, bandarmology, and macroeconomic factors. GRU was chosen because it has a simpler structure compared to LSTM while remaining effective in processing complex time-series data. The dataset includes variables such as EPS, PER, PBV, ROA, ROE, MA, RSI, MACD, foreign buy/sell, and the IHSG index, normalized using the Min-Max Scaler. The results show that the GRU model achieves high predictive accuracy, with a MAPE of 0.0286 and an RMSE of 74.92. Visualizations including training vs validation loss, scatter plots, residual plots, and error distribution confirm that the model avoids overfitting and generalizes well. Furthermore, the deployment of an interactive interface based on Gradio enables real-time prediction simulations, making this research not only academically significant but also practically useful for investors and policymakers in the Sharia capital market.
Deteksi Kebiasaan Penggunaan Smartphone Menggunakan K-Means Clustering Ahmad Marsehan; Nopalia; Raniyah Ayu Lestari
BETRIK Vol. 17 No. 02 (2026): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/negszr43

Abstract

The rapid development of digital technology has led to a significant increase in smartphone usage in modern society. The intensity and diversity of smartphone usage form different behavioral patterns among individuals, resulting in complex data that are difficult to analyze using conventional methods. This study aims to detect and cluster smartphone usage behavior using the K-Means Clustering method. The data used include daily usage duration, application access frequency, and the most frequently used application categories. The research process begins with data preprocessing, normalization, determining the optimal number of clusters using the elbow method, and applying the K-Means algorithm. The clustering results are evaluated using the silhouette score, Davies-Bouldin Index, and inertia. The results show that the K-Means algorithm is able to group smartphone users into 5 (five) clusters with distinct characteristics, namely Heavy User, Light User, Minimal User, Moderate User, and Normal User. The quality of the resulting clusters is considered good with a Silhouette Score of 0.62 (good category), a Davies-Bouldin Index of 0.85 (low value indicating good separation between clusters), and an Inertia value of 1,245.78, which indicates stable compactness of data within clusters. This study is expected to provide a deeper understanding of smartphone usage patterns and serve as a basis for promoting healthier and more controlled smartphone usage.
Explainable Boosted Ensemble Penjualan Video Game Release Tahun 1980-2020 Nina Dwi Putriani; Yusi Nurmala Sari; Selvy Megira
BETRIK Vol. 17 No. 02 (2026): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/8a771z88

Abstract

This study aims to analyze video game sales trends of game released on 1980 to 2020 using the Explainable Boosted Ensemble approach. The XGBoost algorithm was selected for its strong predictive ability on tabular data, while SHAP integration provides transparency regarding the factors influencing predictions. The dataset includes variables such as genre, platform, publisher, and both regional and global sales, enabling a comprehensive analysis of market preferences in North America, Europe, Japan, and other regions. Findings reveal that regional sales, particularly in North America and Europe, contribute most significantly to global sales, while Japan shows dominance in Role-Playing and Platform genres. Model evaluation produced an R² score of 0.7788, indicating reliable accuracy in explaining sales variations. Furthermore, genre recommendations highlight Platform, Shooter, and Role-Playing as the backbone of the industry, with Action, Racing, Fighting, and Sports remaining relevant in specific segments. This research is expected to provide both academic and practical contributions, offering insights for developers to design more effective distribution strategies and genre portfolios.
Pengembangan Sistem Triase IGD Berbasis Web dengan Decision Tree dan Notifikasi Real-Time Muhammad Furqan Nazuli; Rudiansyah; Muhammad Hanif
BETRIK Vol. 17 No. 02 (2026): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/m22yhj49

Abstract

Manual triage processes in hospital Emergency Departments (ED) are prone to misclassification, treatment delays, and inter-rater inconsistency among medical staff. This study aims to design and develop a web-based ED patient triage system integrating the C4.5 Decision Tree algorithm to classify patient priority into four categories — Red, Yellow, Green, and Black — equipped with real-time notifications to the attending physician. The system was developed using the Extreme Programming (XP) method and built with the Laravel 10 framework, MySQL, and Bootstrap 5, along with Ajax polling integration for real-time notifications. Testing was conducted through Black-Box Testing for functional validation and a User Acceptance Test (UAT) using the System Usability Scale (SUS) instrument involving 15 ED medical personnel as respondents. Black-Box Testing results showed an overall functional success rate of 96.8%. UAT results yielded an average SUS score of 83.5, classified as Excellent (Grade A). The system has made a tangible contribution to accelerating the triage process, reducing manual classification inconsistencies, and improving critical patient response in the ED.
Prediksi Risiko Penyakit Jantung dengan Decision Tree yang Dioptimasi Algoritma Bald Eagle Search Yusi Nurmala Sari; Selvy Megira; Salamudin Salamudin
BETRIK Vol. 17 No. 02 (2026): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/d0q2c524

Abstract

Heart disease remains one of the leading causes of death worldwide, making early detection of its risk crucial to reducing mortality and morbidity rates. This study aims to develop a heart disease risk prediction model based on machine learning using a Decision Tree algorithm optimized with Bald Eagle Search (BES). The research employed a quantitative approach utilizing a clinical dataset containing demographic and medical variables such as age, gender, blood pressure, cholesterol levels, electrocardiographic results, and heart disease status. The baseline Decision Tree model was compared with the BES-optimized model (BES-DT) through evaluations of accuracy, confusion matrix, prediction probability distribution, feature importance analysis, and learning curves with respect to the max_depth parameter. The analysis revealed that the baseline Decision Tree achieved an accuracy of 70.5%, with 43 correct predictions out of 61 test samples, while the BES-DT model achieved an accuracy of 68.9%, with 42 correct predictions. Although the overall accuracy showed a slight decrease, BES-DT demonstrated greater consistency in identifying at-risk patients, with fewer misclassifications (4 cases compared to 7 in the baseline). Furthermore, the prediction probability distribution in BES-DT was more stable, with values concentrated near 0 and 1, indicating higher confidence in classification. The feature importance analysis highlighted chest pain type, oldpeak, and thal as dominant variables in risk classification. The learning curve confirmed that BES-DT reduced the risk of overfitting and improved the model’s generalization capability. This study contributes to the development of more accurate and interpretable machine learning classification methods in healthcare. Future work may involve testing the model on larger and more diverse datasets, integrating other optimization algorithms for performance comparison, and implementing web-based or clinical applications to support medical decision-making.
Penerapan Metode Waterfall pada Pengembangan Sistem Informasi Presensi Difa Ayu Hespitasari; Atik Nurmasani; Azis Catur Laksono; Irma Rofni Wulandari
BETRIK Vol. 17 No. 02 (2026): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/n6fy4726

Abstract

The attendance system used in schools still uses a conventional system, that records attendance in a book. This system often encounters problems such as lost attendance books, which leads to data loss, difficulty tracking attendance data, and time-consuming monthly recaps. Furthermore, teachers and employees are often reluctant to record attendance because they have to write it in a book. Based on this, the author aims to help schools simplify the teacher and employee attendance process by creating a website-based online attendance information system. The method used in this study is the waterfall method, with stages of data collection, needs analysis, system design, coding, and system testing. Data collection produces information in the form of constraints and needs of teachers and employees. The analysis produces the focus of the business process to be developed, and functional requirements. The system design produces a database design and flow design in the form of use case diagrams and activity diagrams. Coding using the Code Igniter framework produces an information system display that is ready for use by users. System testing using the blackbox testing method produces information on the feasibility of features in the attendance information system. With this attendance information system, the attendance process for teachers and employees is easier to do compared to conventional systems
Analisis Kinerja Algoritma Kirsch dan Robinson dalam Deteksi Tepi Citra Diana; Septa Riansyah
BETRIK Vol. 17 No. 02 (2026): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/vcxp9w08

Abstract

One of the important stages in digital image processing is edge detection, which serves to determine the boundaries of objects in an image. This process is very important for various applications, such as image segmentation, pattern recognition, and object analysis. Two very popular algorithms in gradient operator-based edge detection are Kirsch and Robinson. The Kirsch algorithm uses eight kernels with compass directions to detect pixel intensity changes maximally, while the Robinson algorithm uses eight simpler kernels with a lighter computational approach. The aim of this research is to examine how both algorithms detect image edges based on the sharpness of the results, sensitivity to noise, and computational efficiency. The study was conducted by testing both algorithms on several grayscale test images and comparing the visual and quantitative edge detection results using the parameters of accuracy, precision, recall, and F-Measure. The analysis results show that the Robinson algorithm is more efficient in the computation process but produces smoother edges. The Kirsch algorithm, on the other hand, produces sharper and more detailed edge detection but requires longer computation time. Therefore, which algorithm is most suitable for the application depends on whether the priority is on process efficiency or detection quality.
Implementasi Deteksi Tepi pada Citra Digital untuk Identifikasi Batas Objek Menggunakan Python di Google Colab Diana; DWI OKTA SULISTIANI; Gharrieb Nouvaldi; Iman Akbar Susilo; Mgs. M Fadjar Siddik
BETRIK Vol. 17 No. 02 (2026): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/7wbv4710

Abstract

Edge detection is a critical stage in digital image processing, where the quality of object boundary representation directly determines the accuracy of subsequent processes such as segmentation and pattern recognition. This study compares three edge detection operators—Sobel, Prewitt, and Canny—on five digital images of fruit objects based on Python thru Google Colab, with an analytical emphasis on the influence of Gaussian Blur preprocessing and variations in Canny threshold parameters on the quality of detection results. Unlike previous comparative studies, this research specifically analyzes the methodological implications of using MSE, PSNR, and SSIM in edge image evaluation—whose distribution characteristics fundamentally differ from natural images—and provides guidance on selecting Canny thresholds based on systematic testing on complex organic contour images. The evaluation was conducted thru a combination of visual analysis and quantitative measurements of Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index (SSIM). The results show that the Canny operator produces the best visual edge detection quality across all test images, despite having a higher average MSE value. This paradox is explained by the sparse output nature of Canny: most pixels have a value of zero, causing the deviation from the reference grayscale image to increase in aggregate, not due to inferior quality. Threshold configuration (100, 200) with a T_{high} /T_{low}\ ratio of 2 provides an optimal balance. These findings affirm that the evaluation of edge detection methods requires a multiparameter approach and careful contextual interpretation, rather than relying solely on pixel-level metrics.
Pengembangan Sistem Informasi Manajemen Toko Berbasis Web Pada Toko Tiga Saudara Jovan Yusa; Dorie Kesuma
BETRIK Vol. 17 No. 02 (2026): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/czvksc18

Abstract

Toko Tiga Saudara still manages transactions and stock manually using physical notes and Microsoft Excel, causing delayed reports, difficulties in real-time stock monitoring, and operational miscommunications. This study aims to develop a web-based store management information system that integrates cashier processes, stock management, online ordering, and reporting. The development method uses the Waterfall model through problem analysis (PIECES), requirements analysis (Use Case), design (UML, ERD, DFD), web implementation with Laravel and MySQL, and Black Box testing with 15 test scenarios involving 3 testers (cashier, manager, owner) to ensure data validity. The results show that the system successfully facilitates user roles (manager, owner, customer, courier) with real-time catalog, shopping cart, online ordering, stock adjustment requests, delivery validation, and analytical reports. All main features (login, transactions, receipt printing, order cancellation, stock validation, etc.) function as required. The implementation provides a digital solution for previously manual store management, improving operational efficiency, data accuracy, and supporting managerial decision-making.
Perancangan Sistem Informasi Customer Relationship Management Dengan Segmentasi Pelanggan Berbasis Laravel Ovan Kurniawan; Mulyati
BETRIK Vol. 17 No. 02 (2026): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/r9jdha97

Abstract

PT Cemerlang Sejahtera Semesta is a building materials distributor in Palembang that serves more than 300 partner stores or customers with a high daily transaction volume. Based on the results of an analysis using the PIECES method the current business processes exhibit weaknesses in ordering time efficiency and credit limit management, thereby creating the risk of non-payment and a lack of appreciation for loyal partners. This study aims to design a web-based Customer Relationship Management (CRM) information system using the Laravel framework and a MySQL database. The development method used is the Rational Unified Process (RUP) with model design through Use Case, Activity, and Entity Relationship Diagrams (ERD). The resulting system integrates self-service ordering features, digital receipt recording, shipment tracking, credit limit automation, and membership segmentation (Gold, Silver, Bronze) accompanied by reward points. System testing using the Black Box Testing method demonstrated that the application achieved a valid success rate across all key module functionalities. This CRM implementation is expected address previous operational challenges, minimize uncollectible receivables, and strengthen long-term partner loyalty.

Filter by Year

2022 2026