cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Elsa Aditya
Contact Email
redaksijurnalupu@gmail.com
Phone
+6285175205250
Journal Mail Official
redaksijurnalupu@gmail.com
Editorial Address
JL. KL. Yos Sudarso Km. 6,5 No. 3A, Tanjung Mulia, Medan, Sumatera Utara, 20241
Location
Kota medan,
Sumatera utara
INDONESIA
CSRID
Published by Universitas Potensi Utama
ISSN : 20851367     EISSN : 2460870X     DOI : https://doi.org/10.22303/csrid
Core Subject : Science,
Computer Science & IT
CSRID (Computer Science Research and Its Development Journal) is a scientific journal published by LPPM Universitas Potensi Utama in collaboration with professional computer science associations, Indonesian Computer Electronics and Instrumentation Support Society (IndoCEISS) and CORIS (Cooperation Research Inter University).
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 9 Documents
 1 
Search results for , issue "Vol. 17 No. 3 (2025): Oktober 2025" : 9 Documents clear
Implementasi Deep Learning Untuk Identifikasi Jenis Biji Kopi Menggunakan Metode Convolutional Neural Network Pratama, Munawwar Anugrah; Hadiwandra, T. Yudi
CSRID (Computer Science Research and Its Development Journal) Vol. 17 No. 3 (2025): Oktober 2025
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.17.3.2025.387-398

Abstract

Indonesia is one of the largest coffee producers in the world, with various types of coffee beans such as Arabica, Robusta, and Liberica. Each type of coffee bean has unique characteristics that influence the taste, aroma, and overall quality of the coffee. However, many people are still unable to visually distinguish between these types of beans. This research aims to develop a Deep Learning-based system using the Convolutional Neural Network (CNN) method with the Xception architecture to identify coffee bean types from images. The dataset was obtained from direct image collection and online sources, then processed through preprocessing and data augmentation stages. The model training process was conducted using transfer learning techniques to improve classification performance. The resulting model is capable of classifying coffee bean images into three main categories with an accuracy 81.63%. The system is implemented as a web interface using Flask, allowing users to upload images of coffee beans and obtain classification results via a website. This study demonstrates that the CNN method with Xception architecture is effective for visual recognition of coffee bean types and can be a solution to help the general public in identifying different coffee bean varieties. This study aims to develop a deep learning–based system using the Convolutional Neural Network (CNN) method with the Xception architecture to identify coffee bean types from images. A total of 600 images of Arabica, Robusta, and Liberica beans were collected from primary and online sources, and then divided into training (80%), validation (10%), and testing (10%) sets. The dataset was processed through image preprocessing and augmentation techniques such as rotation, flipping, zooming, and brightness adjustment to improve model generalization. The training was performed using a transfer learning approach, followed by fine-tuning several deeper layers to enhance feature extraction. Evaluation was conducted using a confusion matrix and F1-score to validate class-wise performance. The model achieved an accuracy of 81.63% using the testing dataset. In practical implementation through a Flask-based website, the system achieved above 90% accuracy for several input angles, indicating strong recognition ability under controlled image conditions. This work demonstrates that the CNN Xception model is effective for visual identification of coffee bean types and can be applied as a practical solution to assist the general public, farmers, and coffee industry practitioners. Future enhancement may include expanding bean classes, optimizing architecture, and real-world testing.
Perancangan Manajemen Bandwidth Pada Jaringan Internet Menggunakan Hierarchical Teken Bucket (HTB) Di SMAN 12 Pekanbaru Siregar, Vivi Devina; Marpaung, Noveri Lysbetti; Hutabarat, Sakti; Ervianto, Edy; Nurhalim, Nurhalim; Amri, Rahyul
CSRID (Computer Science Research and Its Development Journal) Vol. 17 No. 3 (2025): Oktober 2025
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.17.3.2025.421-431

Abstract

In today’s digital era, the availability of a stable and efficient internet network is a crucial need to support teaching and learning activities in educational environments. SMAN 12 Pekanbaru, as one of the schools implementing technology-based learning, is experiencing issues related to uneven bandwidth distribution, especially during peak usage hours. This often disrupts access to essential school services such as online exams and digital learning platforms. This study aims to design a bandwidth management system using the Hierarchical Token Bucket (HTB) method with the Mikrotik RB750Gr3 device to optimize internet bandwidth distribution at SMAN 12 Pekanbaru. The methodology involves analyzing the existing network issues, designing a new network topology, configuring HTB, measuring Quality of Service (QoS) parameters, and conducting data analysis. he results show an improvement in network performance, with more stable average throughput, reduced delay and jitter, and minimal packet loss during peak hours. The implementation of the HTB method proves effective in providing better control over bandwidth allocation based on user and service priorities, thereby supporting more efficient and effective digital-based teaching and learning activities.
Sistem Deteksi URL Phishing Menggunakan Random Forest dan Gradient Boosting untuk Pencegahan Kejahatan Dunia Maya Khairunnisya, Aqilla; Lindawati, Lindawati; Zefi, Suzan
CSRID (Computer Science Research and Its Development Journal) Vol. 17 No. 3 (2025): Oktober 2025
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.17.3.2025.296-310

Abstract

Phishing attacks through malicious URLs have become a critical cybersecurity threat, resulting in substantial financial losses and data exposures on a global scale. Conventional approaches like blacklisting and rule-based detection often fall behind as phishing methods become more advanced, including zero-day phishing URLs. In this research, machine learning models based on Random Forest and Gradient Boosting are designed and tested to accurately identify phishing URLs. The dataset, obtained from Kaggle, consists of 11,430 URLs with extracted features representing URL characteristics such as length, subdomain count, HTTPS status, and domain age. The two models underwent training and validation with the help of stratified train-test splits and cross-validation techniques. To evaluate the models, several performance indicators—such as accuracy, precision, recall, F1-score, and ROC AUC—were applied. Results from the experiments reveal that Gradient Boosting slightly exceeds the performance of Random Forest, achieving an accuracy of 98.0%, precision of 98.1%, and an F1-score of 98.0%. The best-performing model was integrated into a web application built with Streamlit, providing real-time phishing detection for end-users. This research contributes to developing adaptive and efficient phishing URL detection systems, enhancing cybersecurity defenses against evolving phishing threats. The implementation demonstrates practical applicability and ease of use for non-expert users.
Evaluasi Kinerja YOLOv8 dalam Klasifikasi Kualitas Telur Berbasis Warna dan Tekstur Cangkang Khairy, Khafizh; Candra, Feri
CSRID (Computer Science Research and Its Development Journal) Vol. 17 No. 3 (2025): Oktober 2025
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.17.3.2025.326-339

Abstract

Egg quality plays a vital role in the food industry, directly affecting shelf life, food safety, and consumer health. Conventional quality assessment methods, such as manual inspection and laboratory testing, are often time-consuming, labor-intensive, and prone to subjectivity, leading to inconsistent classification results. To address these challenges, this research proposes the development of an automated egg quality classification system based on computer vision and artificial intelligence. The system focuses on evaluating external egg characteristics—specifically shell color and texture—using a combination of Convolutional Neural Network (CNN) for feature extraction and the YOLO (You Only Look Once) algorithm for real-time object detection and classification. The development stages include dataset collection, image preprocessing (such as augmentation and segmentation), model training, and performance evaluation using accuracy, precision, recall, and F1-score. The goal is to achieve an accuracy rate above 90% in classifying eggs into quality categories. This study evaluates the performance of YOLOv8 for automatic egg quality classification based on shell color and texture. A dataset consisting of 1,200 egg images was collected from both production facilities and online sources, and labeled into three categories: Good, Fair, and Poor quality. The model was trained on Google Colab with GPU acceleration using a batch size of 16, learning rate of 0.001, and 50 epochs. Performance was assessed using mean Average Precision (mAP), precision, and recall, where the results achieved mAP of 0.87, average precision of 0.91, and recall of 0.89. The “Fair” class obtained lower accuracy (72%) due to high visual similarity with the “Good” class and dataset imbalance (250 images vs. 450 images for “Good”). Compared to previous studies that reported mAP ≈ 0.80 using YOLOv5, this research demonstrates improved performance and highlights YOLOv8 as a more competitive solution for industrial egg quality control. This work contributes a practical implementation pipeline and an analysis of visual factors influencing misclassification. Future developments include dataset expansion, advanced balancing techniques, and real-time industrial deployment testing.
Data Visualization to Analyze Consumer Behavior for Strategic Business Decision Making in the Retail Industry: Walmart Case Study Bakhrun, Akhmad; Maghfyra, Yasyfa; Putri, Rintan Nurhayati; Larassati, Dewi Ayu
CSRID (Computer Science Research and Its Development Journal) Vol. 17 No. 3 (2025): Oktober 2025
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.17.3.2025.354-371

Abstract

This research focuses on data visualization to analyze consumer behavior in an effort to make strategic business decisions in the retail industry, taking the Walmart Case Study. The main objective of this study is to explore customer consumption patterns and generate data-based insights that can be utilized in formulating marketing strategies and managing retail operations. A quantitative approach is applied through systematic stages, including problem identification, literature study, data collection, Extract, Transform, Load (ETL) process, analysis, visualization, and data interpretation. The dataset used includes 50,000 Walmart customer transactions during the period January 2024 to February 2025. The use of interactive data visualization using Microsoft Power BI successfully transformed raw data into strategic insights. Key findings from the analysis indicated that the majority of transactions came from loyal customers at $6.46 million (50.58%), emphasizing the importance of customer retention strategies. In addition, customer purchasing activity was much more dominant on weekdays, with weekday purchases totaling $9.07 million compared to weekend purchases totaling $3.70 million. The data also shows that Generation X dominates the overall purchase value compared to other age groups, with purchases totaling $5.04 million. In addition, in-depth analysis of the most popular product categories, segmentation by gender, and payment method preferences provided comprehensive insights. These visualization results significantly support fast and evidence-based business decision-making. This research contributes to retail business practice through an applicable data visualization approach, and opens up opportunities for further development such as the integration of machine learning for predictive analysis and wider exploration of BI tools to improve the accuracy and scope of business analysis in the future.
Retinex-Based Algorithm to Enhance Underlit Archaeology Images Taken in Semi-or-Fully Enclosed Environments Al-Ameen, Zohair; Younis, Zainab Khalid
CSRID (Computer Science Research and Its Development Journal) Vol. 17 No. 3 (2025): Oktober 2025
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.17.3.2025.285-295

Abstract

Archaeology is strongly related to digital images, as they visually represent scenes and objects. Archaeological images are rarely obtained in perfect quality, as degradations often affect them. One constant degradation is uneven illumination. It leads to dim, underlit results with unpleasant appearances. This paper provides a fast Retinex-based algorithm to better brighten underlit archaeological images. The Retinex model is adapted using statistical and image processing methods. This aids in providing brighter and more perceptually pleasing results. The main modifications to the Retinex algorithm include the following: (i) utilize a new approach to compute the reflectance component; (ii) add a statistical method to further improve the reflectance; (iii) apply a linear stretching procedure to guarantee full dynamic range pixel distribution. These modifications help to get more uniform illumination in the results. The algorithm efficiently enhanced brightness and tonality, revealing fine textures and intricate details. The resulting images demonstrate significant balance in illumination compared to the original counterparts. Likewise, comparisons are made with six algorithms having dissimilar concepts, and evaluations are made using two assessment methods. The results are promising as the proposed algorithm performed well visually and objectively, scoring an average LOE of 195.14 and average runtime of 0.798 seconds. This indicates a successful tackling of a distinctive challenge, offering a non-complex solution.
Sistem Pakar Diagnosa Penyakit Busuk Kuncup Pada Tanaman Sawit Menggunakan Trend Moment Siddik, Muhammad; Abdullah, Iqbal; Samsir, Samsir; Sirait, Azrai
CSRID (Computer Science Research and Its Development Journal) Vol. 17 No. 3 (2025): Oktober 2025
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.17.3.2025.408-420

Abstract

Bud rot disease in oil palm is one of the most serious threats that can significantly reduce productivity and even cause plant death if not detected early. To support a faster and more accurate diagnosis process, this study developed a web-based expert system that applies the Trend Moment method. The system is built on a knowledge base containing the main symptoms of the disease, including wilted and rotting young leaves (G001), foul odor from the bud (G002), easily detached young leaves due to decay (G003), and rotting crown with brown mucus (G004). The system is able to identify three types of diseases, namely bud rot, Phytophthora palmivora, and Erwinia spp.. The diagnosis process is carried out by calculating the weight of symptoms selected by the user and determining the most probable disease based on the highest Trend Moment value. Experimental results on 20 test cases showed that the system achieved an accuracy rate of 100% when compared with expert diagnoses. These findings indicate that the developed expert system has strong potential to be an effective tool for farmers and field extension workers in detecting and managing oil palm diseases at an early stage.
Sistem Pakar Diagnosa Penyakit Perokok Menggunakan Metode Backward chaining Subagio, Selamat; Rahmayani, Rahmayani; Samsir, Samsir; Azhar, Wahyu
CSRID (Computer Science Research and Its Development Journal) Vol. 17 No. 3 (2025): Oktober 2025
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.17.3.2025.340-353

Abstract

he rapid development of information and computer technology has had a significant impact on various fields, including healthcare. One of its applications is the expert system, a computer-based system utilizing Artificial Intelligence (AI) designed to imitate the reasoning and decision-making abilities of human experts. Expert systems are widely used to assist in diagnosing diseases based on symptoms experienced by patients, providing fast, efficient, and accurate solutions without requiring direct consultation with medical professionals. This study focuses on developing an Expert System for Diagnosing Smoking-Related Diseases among Lecturers at Universitas Al Washliyah Labuhanbatu. The system aims to help users, particularly active smokers, identify potential diseases caused by smoking habits. Based on preliminary studies and interviews conducted with the Health Department of Rantauprapat City, it was found that common diseases suffered by smokers include oral disease, lung disease, respiratory disorders, throat disease, and heart disease. These illnesses often develop unnoticed in the early stages, making early diagnosis essential for prevention and health awareness. The research applies the Backward Chaining inference method, which works by reasoning backward from a possible conclusion (disease) to find supporting facts (symptoms). The relationship between symptoms and diseases is represented through IF–THEN rules derived from expert knowledge. The system was developed using Macromedia Dreamweaver 8 as a web editor and MySQL as the database management system to store information on diseases, symptoms, and diagnostic results. The implementation results show that the system can provide early diagnoses quickly and accurately based on user-input symptoms. Furthermore, the system includes a confidence level feature that presents diagnostic certainty in percentage form. Hence, the developed expert system not only serves as a medical decision-support tool but also as a digital health education medium that promotes awareness of smoking dangers and the importance of maintaining a healthy lifestyle.
AHP-Based Expert System untuk Mengidentifikasi dan Mengklasifikasikan Kesulitan Belajar Anak Samsir, Samsir; Sahmuda, Arjana; Subagio, Selamat
CSRID (Computer Science Research and Its Development Journal) Vol. 17 No. 3 (2025): Oktober 2025
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.17.3.2025.311-325

Abstract

The rapid development of information technology has significantly impacted various sectors, including education. One of the common problems encountered in the educational field is learning difficulties in children, which may arise from internal or external factors such as poor concentration, limited reading ability, writing difficulties, or challenges in arithmetic skills. Undetected learning difficulties can hinder a child’s potential development and reduce learning motivation. Therefore, an intelligent system is needed to assist counseling teachers and parents in conducting early and objective identification. This study aims to design and implement an Expert System for Identifying Children’s Learning Difficulties using the Analytic Hierarchy Process (AHP) method. The AHP method was chosen due to its ability to assign priority weights to criteria and alternatives based on their level of importance. The study utilizes four main criteria: concentration (30%), reading ability (40%), writing ability (20%), and numerical ability (10%). The system was developed using a research and development (R&D) approach consisting of stages of requirement analysis, system design, implementation, and testing. The results indicate that the developed expert system can provide accurate and consistent identification results compared to manual AHP calculations. System validation tests achieved an accuracy rate of 99%, demonstrating high reliability in the decision-making process. Furthermore, the system has proven effective in assisting teachers and parents in detecting potential learning difficulties at an early stage, enabling faster and more precise interventions.

Page 1 of 1 | Total Record : 9

 1 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol. 17 No. 3 (2025): Oktober 2025 Vol. 17 No. 2 (2025): Juni 2025 Vol. 17 No. 1 (2025): Februari 2025 Vol. 16 No. 3 (2024): October 2024 Vol. 16 No. 2 (2024): June 2024 Vol. 16 No. 1 (2024): February 2024 Vol. 15 No. 3 (2023): October 2023 Vol. 15 No. 2: June 2023 Vol. 15 No. 1: February 2023 Vol. 14 No. 3: October 2022