cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
+6282161108110
Journal Mail Official
jurikom.stmikbd@gmail.com
Editorial Address
STMIK Budi Darma Jalan Sisingamangaraja No. 338 Simpang Limun Medan - Sumatera Utara
Location
Kota medan,
Sumatera utara
INDONESIA
JURIKOM (Jurnal Riset Komputer)
Published by Sekolah Tinggi Manajemen Informatika dan Komputer Budi Darma
ISSN : 2407389X     EISSN : 27157393     DOI : http://dx.doi.org/10.30865/jurikom.v7i1.1927
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering
JURIKOM (Jurnal Riset Komputer) membahas ilmu dibidang Informatika, Sistem Informasi, Manajemen Informatika, DSS, AI, ES, Jaringan, sebagai wadah dalam menuangkan hasil penelitian baik secara konseptual maupun teknis yang berkaitan dengan Teknologi Informatika dan Komputer. Topik utama yang diterbitkan mencakup: 1. Teknik Informatika 2. Sistem Informasi 3. Sistem Pendukung Keputusan 4. Sistem Pakar 5. Kecerdasan Buatan 6. Manajemen Informasi 7. Data Mining 8. Big Data 9. Jaringan Komputer 10. Dan lain-lain (topik lainnya yang berhubungan dengan Teknologi Informati dan komputer)
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 1,099 Documents
 106   107   108   109   110 
Brain Tumor Detection and Classification from MRI Images Using a Convolutional Neural Network Approach Andiharsa Sih Setiarto, Rahardian; Ahmad Zainul Fanani
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 2 (2026): April 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i2.9610

Abstract

Brain tumors are a serious neurological disease that require rapid and accurate diagnosis to improve treatment success. However, conventional interpretation of brain MRI images is often time-consuming and highly dependent on radiologists’ expertise, which may lead to diagnostic inconsistency. This study aims to develop a brain tumor detection and classification model from MRI images using a Convolutional Neural Network (CNN) approach. The dataset consists of four classes, namely glioma, meningioma, pituitary, and no tumor. The research stages include data collection, image preprocessing, model training, and evaluation using accuracy, loss, precision, recall, and F1-score. The results show that the CNN model achieved a training accuracy of 1.0000 at the final epoch, while the testing phase produced an accuracy of 58.75% with a loss value of 1.9600. These findings indicate that the model was able to learn important patterns from MRI images, although the gap between training and testing performance suggests overfitting. This study contributes to the development of AI-based medical image classification for brain tumor identification and shows that CNN has potential as a supportive tool for assisting medical personnel in brain tumor diagnosis. Further improvements can be achieved through data augmentation, hyperparameter tuning, and optimization of model architecture.
Implementasi Sistem Deteksi Visual Cacat Pengelasan Menggunakan Metode Image Processing Berbasis Raspberry Pi Fathoni, Taufik; Devan Junesco Vresdian; Ariep Jaenul
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 2 (2026): April 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i2.9614

Abstract

This study develops a visual welding defect detection system based on Raspberry Pi by utilizing Gray Level Co-occurrence Matrix (GLCM), Histogram of Oriented Gradients (HOG), Principal Component Analysis (PCA), and Support Vector Machine (SVM) methods to identify various types of welding defects, including porosity, undercut, burn-through, overlap, and spatter. The system is designed to operate automatically and in real-time through several processing stages, including image acquisition, preprocessing to enhance image quality, Region of Interest (ROI) segmentation, feature extraction of texture and shape, dimensionality reduction using PCA, and multiclass classification using SVM. In addition, this study aims to evaluate the effect of image acquisition conditions on system performance, particularly variations in lighting, distance, and camera angle, which are critical factors in industrial implementation. Experiments were conducted under several scenarios to determine the optimal parameters that yield the best performance. The results show that the optimal condition is achieved at a lighting level of 50 lux, a camera distance of 10 cm, and a viewing angle of 20°. Under these conditions, the system achieves an accuracy of 100% for normal part classification and 94.4% for multiclass classification. The precision and recall values both reach 94%, with an F1-score of 93%, indicating a balanced performance in detecting different types of welding defects. Overall, the results demonstrate that the proposed system has strong potential as an effective, efficient, and real-time automated inspection solution for welding quality in industrial manufacturing environments.
Evaluasi Efektivitas Firewall Pre-filtering berbasis eBPF/XDP menggunakan Random Forest untuk Deteksi Anomali Trafik pada Docker Swarm Rohliyanto, Ahmad; Utami, Ema
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 2 (2026): April 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i2.9618

Abstract

Overlay networks in container orchestration platforms such as Docker Swarm are vulnerable to volumetric DDoS attacks, while conventional firewall solutions impose high overhead when processing large attack volumes. This paper presents the implementation and evaluation of an eBPF/XDP-based pre-filtering firewall that integrates detection rules derived from a Random Forest model to identify traffic anomalies in Docker Swarm overlay networks. Unlike previous studies that employ a single Decision Tree or process classification in user-space, this research extracts Random Forest rules into per-source-IP thresholds executed directly in the kernel via XDP and stored in an eBPF config_map to enable runtime updates without recompilation. The model was trained on the CIC-DDoS-2019 dataset (174,221 records, 65 features), achieving 99.88% accuracy, 99.90% detection rate, 0.14% false positive rate, and ROC-AUC of 0.9999. Experimental evaluation across seven testing scenarios with 10 iterations demonstrates that the XDP firewall drops over 99.9% of attack packets with a median response time of 0.69 ms, comparable to baseline conditions. CPU overhead remains low (0.92–1.18%) and throughput is maintained at approximately 920 Mbps. Differences between scenarios are statistically significant (p < 0.05) but with negligible practical effect (d < 0.25). Comparative analysis with iptables, both global rate limiting and per-IP hashlimit, indicates that all three approaches (XDP, global iptables, and per-IP iptables) effectively mitigate DDoS with comparable median response times.
Analisis Performa Class Weight Dan Focal Loss Pada Model Indobert Untuk Klasifikasi Teks Depresi Berbahasa Indonesia Rafi Jonathan Siger; Muhammad Naufal; Farrikh Alzami
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 2 (2026): April 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i2.9620

Abstract

The development of depression detection can be done using exploration of social media content. However, the classification of depression indicative texts faces a major challenge in the form of class distribution imbalances, which can degrade the model's generalization capabilities. This study aims to analyze how the method of overcoming class imbalance affects the performance of the IndoBERT model in the classification of Indonesian depression indication texts by emphasizing the analysis of training stability based on the dynamics of training loss and validation loss. The dataset used consists of 3,863 data, data that has gone through the process of cleaning, removing duplicate data, tokenization, encoding, and dividing data into stratification into training data, validation data, and test data. The IndoBERT-base-p1 model was fine-tuned using three training scenarios, namely baseline, class weight, and focal loss with an early stopping mechanism based on validation loss. The test results showed that the baseline IndoBERT scenario produced an accuracy of 77.52%, a weighted precision of 0.7752, a weighted recall of 0.7752, a weighted F1-score of 0.7737, and a ROC-AUC of 0.8528 with a relatively stable training pattern. The class weight method produced an accuracy of 74.68%, a weighted F1-score of 0.7467, and a ROC-AUC of 0.8342 which showed an increase in class discrimination ability but accompanied by a decrease in overall accuracy. Meanwhile, the focal loss method produced an accuracy of 72.87%, a weighted F1-score of 0.7291, and a ROC-AUC of 0.8188 with more balanced training characteristics than the weight class. The findings suggest that handling classroom imbalances does not necessarily improve global performance, so model evaluations need to consider a balance between accuracy, sensitivity, and stability of training.
Analisis Perbandingan Pelabelan Inset Lexicon dan MBERT pada Sentimen Danantara Menggunakan SVM dengan Kernel Trick Rusmini; Heliawati Hamrul; A. Amirul Asnan Cirua
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 2 (2026): April 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i2.9629

Abstract

This study aims to compare the Inset Lexicon and MBERT sentiment labeling methods for analyzing sentiment related to the Danantara issue using a Support Vector Machine (SVM) with Linear, RBF, Polynomial, and Sigmoid kernels. The main issues in this study are the suboptimal sentiment labeling methods for Indonesian-language data that can accurately capture linguistic context, as well as the uncertainty regarding the best labeling method when combined with various TF-IDF-based SVM kernels. Model evaluation uses metrics such as Accuracy, Precision, Recall, F1-score, and Cross-validation (CV). The results show that the Inset Lexicon labeling method with a Linear kernel yields the highest Accuracy of 81% with a CV of 78%, Precision of 87%, and Recall of 92%. The RBF kernel achieved an Accuracy of 78% with a CV of 76%, followed by the Sigmoid kernel at 79% Accuracy with a CV of 76%, and the Polynomial kernel at 65% Accuracy with a CV of 65%. The highest F1-score for the negative class using the Linear kernel reached 89%. Meanwhile, in MBERT labeling, the highest accuracy was achieved by the RBF kernel at 72% with a CV of 71%, followed by the Linear kernel with an accuracy of 71%, then the Polynomial kernel with an accuracy of 68%, and the Sigmoid kernel with an accuracy of 67%. The highest F1-score was found in the negative class at 79% using the RBF kernel. Overall, the negative class showed the most consistent performance, while the neutral class had the lowest Recall and F1-score values for almost all kernel types. These findings confirm that an in-depth comparative analysis between lexicon-based and deep learning-based approaches demonstrates that methods such as the Inset Lexicon can deliver better and more stable performance on Indonesian-language data.
Pendeteksian Dini pada Potensi Banjir dengan Berbasis Internet of Things Menggunakan Algoritma Random Forest Ardyka Bayu Reovan; Guruh Putro Dirgantoro; Muhammad Jauhar Vikri
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 2 (2026): April 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i2.9644

Abstract

Flood is a natural disaster that frequently occurs and causes significant material and social losses. Conventional flood monitoring systems are generally reactive and rely on threshold-based approaches, which limits their effectiveness in supporting early detection. This study proposes an Internet of Things (IoT)-based early flood detection system using the Random Forest algorithm. The developed system collects hydrological data, including water level and flow velocity, through IoT sensors that periodically transmit data to a server for further processing. The collected data are then aggregated and classified into flood and non-flood conditions using a Random Forest model. Model performance is evaluated using accuracy, precision, recall, f1-score, confusion matrix, and 5-fold cross-validation. Experimental results indicate that the proposed model achieves an accuracy of 97.26% with a mean cross-validation score of 0.9863. However, the recall for flood events remains limited due to data imbalance and the relatively small number of flood occurrences. Despite these limitations, the proposed system demonstrates potential to support the development of early flood warning systems and can be further improved by incorporating longer and more diverse historical datasets.
Data Mining Dengan Pendekatan Multiple Linear Regression Untuk Prediksi Hasil Panen Padi Alwi Syahbirin; William Ramdhan; Wan Mariatul Kifti
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 2 (2026): April 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i2.9652

Abstract

The rice agricultural sector plays an essential role in Asahan Regency, but current harvest predictions are still carried out conventionally and subjectively. This causes data inaccuracies that impact uncertainty in logistics planning and production policies by the local government. Therefore, this study aims to build a more accurate rice harvest prediction model to assist the Department of Agriculture of Asahan Regency in making strategic decisions. The research methodology used is data mining techniques by implementing the multiple linear regression method, utilizing historical data on land area and rainfall to predict harvest yields. The main results of this study indicate that the web-based prediction model designed is capable of performing valid calculations, producing a harvest projection for 2025 of 54,308.79 tons that aligns with mathematical model calculations. The implication of this research is that the relevant agencies have a reliable decision support tool for planning food security, irrigation systems, and fertilizer provision more efficiently, thereby minimizing errors caused by manual calculations
Metode Mobile-D untuk Pengembangan Aplikasi Sales Performance Management Berbasis Real-Time Geotagging dan Area Mapping Wisnu Wendanto; Tutus Praningki
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 2 (2026): April 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Sales often work outside the office to visit clients, hold meetings, and conduct surveys, making their activities difficult to monitor directly. This situation can lead to decreased productivity, missed targets, and reduced company profits. Sales activity management plays an important role in improving the effectiveness of a company’s marketing strategy. However, monitoring sales activities often faces several challenges due to manual recording processes and the lack of accurate location-based information. This study aims to develop a mobile-based Sales Performance Management system that utilizes geotagging and area mapping technologies to support more effective monitoring of sales activities. The system development adopts the Mobile-D method, which emphasizes an iterative and adaptive approach to mobile application development. The proposed system enables sales personnel to record customer visit activities through a mobile device equipped with a geotagging feature integrated with Google Maps services. The collected location data are then visualized through area mapping to provide a clearer overview of sales activity distribution. This functionality allows managers to monitor field activities and evaluate sales performance more efficiently. The implementation results indicate that the system is documenting sales activities accurately while supporting the validation process conducted by managers. In addition, the mapping feature provides useful insights into the spatial distribution of sales activities across different operational areas. Therefore, the developed system can improve the effectiveness of monitoring processes and managing sales personnel performance more efficiently.  
Implementasi GIS Dan Metode MOORA Dalam Pemetaan Dan Pemilihan Lokasi Terbaik Penanaman Pohon Nora Asyiqin; Triase
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 2 (2026): April 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i2.9658

Abstract

Amid rapid technological advancement, the use of digital systems such as Geographic Information Systems (GIS) plays a crucial role in enhancing the effectiveness of environmental conservation programs by enabling spatial analysis and efficient determination of suitable tree-planting locations. KSE UINSU (Karya Salemba Empat, State Islamic University of North Sumatra) annually conducts tree-planting activities involving hundreds of students across various regions in Indonesia, particularly in areas requiring reforestation, such as degraded land, flood-prone zones, coastal abrasion areas, and landslide-prone regions, including the City of Medan and Deli Serdang Regency. However, previous practices in location selection were often carried out without adequate data, resulting in time-consuming field verification and uncertainty regarding land suitability, soil conditions, accessibility, and regional characteristics. Therefore, a more systematic and data-driven approach is required to support faster, more accurate, and measurable decision-making. This study adopts a quantitative approach by integrating Geographic Information Systems (GIS) and the Multi-Objective Optimization on the Basis of Ratio Analysis (MOORA) method to identify the most suitable locations for tree planting in the City of Medan and Deli Serdang Regency
Penerapan Algoritma C4.5 dalam Klasifikasi Tingkat Konsumsi Harian Masyarakat untuk Mengurangi Food Waste pada UMKM di Kota Medan Dea Khairani; Puji Sari Ramadhan; Rina Mahyuni
JURNAL RISET KOMPUTER (JURIKOM) Vol. 13 No. 2 (2026): April 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v13i2.9660

Abstract

This study addresses the issue of inaccurate production forecasting among breakfast-serving SMEs in Medan due to fluctuations in demand, which often result in food waste and financial losses. The objective of this study is to develop a classification model for daily consumption levels (high, medium, low) to serve as the basis for production recommendations. The method used is the C4.5 Decision Tree algorithm with a dataset of 92 daily operational records covering the attributes of production catesgory, menu type, weather conditions, and operational days. The data was preprocessed through attribute categorization, then analyzed using entropy and gain ratio calculations to form a decision tree. Model evaluation was performed using 10-fold cross-validation in RapidMiner. The results showed that the production category attribute had the highest gain ratio, making it the root of the decision tree. The resulting model achieved an accuracy of 57.56% with a deviation of ±7.85%, performing best in the moderate consumption class. The primary contribution of this study is the generation of IF–THEN-based decision rules that can be practically applied by SMEs to adjust daily production volumes based on operational conditions, thereby helping to reduce potential food waste without requiring complex calculations.

Page 109 of 110 | Total Record : 1099

 106   107   108   109   110 

Filter by Year

2015 2026


Reset
Filter By Issues
All Issue Vol. 13 No. 2 (2026): April 2026 Vol. 13 No. 1 (2026): Februari 2026 Vol. 12 No. 6 (2025): Desember 2025 Vol. 12 No. 5 (2025): Oktober 2025 Vol. 12 No. 4 (2025): Agustus 2025 Vol 12, No 3 (2025): Juni 2025 Vol. 12 No. 3 (2025): Juni 2025 Vol 12, No 2 (2025): April 2025 Vol. 12 No. 2 (2025): April 2025 Vol 12, No 1 (2025): Februari 2025 Vol. 12 No. 1 (2025): Februari 2025 Vol 11, No 6 (2024): Desember 2024 Vol. 11 No. 6 (2024): Desember 2024 Vol. 11 No. 5 (2024): Oktober 2024 Vol 11, No 5 (2024): Oktober 2024 Vol 11, No 4 (2024): Augustus 2024 Vol. 11 No. 4 (2024): Augustus 2024 Vol. 11 No. 3 (2024): Juni 2024 Vol 11, No 3 (2024): Juni 2024 Vol 11, No 2 (2024): April 2024 Vol. 11 No. 2 (2024): April 2024 Vol 10, No 3 (2023): Juni 2023 Vol 10, No 2 (2023): April 2023 Vol 10, No 1 (2023): Februari 2023 Vol 9, No 6 (2022): Desember 2022 Vol 9, No 5 (2022): Oktober 2022 Vol 9, No 4 (2022): Agustus 2022 Vol 9, No 3 (2022): Juni 2022 Vol 9, No 2 (2022): April 2022 Vol 9, No 1 (2022): Februari 2022 Vol 8, No 6 (2021): Desember 2021 Vol 8, No 5 (2021): Oktober 2021 Vol 8, No 4 (2021): Agustus 2021 Vol 8, No 3 (2021): Juni 2021 Vol 8, No 2 (2021): April 2021 Vol 8, No 1 (2021): Februari 2021 Vol 7, No 6 (2020): Desember 2020 Vol. 7 No. 5 (2020): Oktober 2020 Vol 7, No 5 (2020): Oktober 2020 Vol 7, No 4 (2020): Agustus 2020 Vol 7, No 3 (2020): Juni 2020 Vol 7, No 2 (2020): April 2020 Vol 7, No 1 (2020): Februari 2020 Vol 6, No 6 (2019): Desember 2019 Vol 6, No 5 (2019): Oktober 2019 Vol 6, No 4 (2019): Agustus 2019 Vol 6, No 3 (2019): Juni 2019 Vol 6, No 2 (2019): April 2019 Vol 6, No 1 (2019): Februari 2019 Vol 5, No 6 (2018): Desember 2018 Vol 5, No 5 (2018): Oktober 2018 Vol 5, No 4 (2018): Agustus 2018 Vol 5, No 3 (2018): Juni 2018 Vol 5, No 2 (2018): April 2018 Vol 5, No 1 (2018): Februari 2018 Vol 4, No 5 (2017): Oktober 2017 Vol 4, No 4 (2017): Agustus 2017 Vol 3, No 6 (2016): Desember 2016 Vol 3, No 5 (2016): Oktober 2016 Vol 3, No 4 (2016): Agustus 2016 Vol 3, No 1 (2016): Februari 2016 Vol 2, No 6 (2015): Desember 2015 More Issue