cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Diny Syarifah Sany
Contact Email
mji@unsur.ac.id
Phone
+6281322535993
Journal Mail Official
mji@unsur.ac.id
Editorial Address
Gedung Fakultas Teknik UNSUR Jl. Pasir Gede Raya, Cianjur, Jawa Barat 43216
Location
Kab. cianjur,
Jawa barat
INDONESIA
Media Jurnal Informatika
Published by Universitas Suryakancana
ISSN : 20882114     EISSN : 24772542     DOI : https://doi.org/10.35194/mji.v12i2
Core Subject : Science,
Computer Science & IT
Media Jurnal Informatika merupakan oleh jurnal yang diterbitkan oleh Program Studi Teknik Informatika Universitas Suryakancana Cianjur yang terbit setiap 6 Bulan pada Juni dan Desember. Media Jurnal Informatika mulai terbit dengan versi cetak pada tahun 2009 dan terbit satu kali dalam satu tahun, namun kemudian frekuensi terbit dinaikan menjadi dua kali dalam satu tahun. Fokus dan lingkup bidang Media Jurnal Informatika meliputi Geography Information System Security Network Big Data Information System Enterprise Resource Planning Internet of Things, Cloud Computing Artificial Intelligent Soft Computing Multimedia dan Game Human Computer Interaction
Arjuna Subject : Ilmu Komputer (semua kategori) - Sistem Informasi
Articles 260 Documents
 22   23   24   25   26 
STRIDE-Based Threat Analysis and AI-Driven Dataset Design for Securing Educational E-Payment Systems Doddy Ferdiansyah; Leony Lidya; Miftahul Fadli Muttaqin
Media Jurnal Informatika Vol 17 No 2 (2025): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v17i2.5918

Abstract

The increasing adoption of electronic payment (e-payment) systems in educational settings introduces significant cybersecurity challenges. This study conducts a systematic security analysis of a web-based school canteen e-payment system using the STRIDE threat modeling framework. The methodology involves three stages: system modeling with a Data Flow Diagram (DFD), threat mapping across system components, and qualitative risk assessment based on potential impact and likelihood. The analysis identified six STRIDE threat categories, with high-risk findings in Tampering (balance and price manipulation), Spoofing (account takeover), and Denial of Service (flooding attacks). Recommended mitigation strategies include multi-factor authentication, strict server-side input validation, immutable logging, and secure session management. Beyond manual threat analysis, this research contributes by designing a structured threat dataset as a foundation for artificial intelligence (AI) integration. This dataset enables the development of AI models for automated threat classification, risk prediction, and adaptive mitigation recommendations. The findings highlight the importance of proactive and forward-looking security approaches while opening pathways for future research on data-driven security automation in educational digital infrastructures.
Emotion Detection in Indonesian Text Using the Logistic Regression Method Erfian Junianto; Mila Puspitasari; Salman Ilyas Zakaria; Toni Arifin; Ignatius Wiseto Prasetyo Agung
Media Jurnal Informatika Vol 17 No 2 (2025): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v17i2.5927

Abstract

Emotion detection in Indonesian text has become a crucial topic in the advancement of human–computer interaction and sentiment analysis on digital platforms. Despite its importance, challenges arise from the linguistic complexity and frequent use of slang in Indonesian text. This study aims to evaluate the performance of three classification models—Logistic Regression, K-Nearest Neighbors (KNN), and Naive Bayes—in detecting emotions from Indonesian text. The dataset comprises 1,000 texts categorized into four emotions: happy, sad, angry, and fear. Preprocessing steps included slang normalization, text cleaning, tokenization, stopword removal, and stemming, followed by TF-IDF weighting. Each model was trained and further optimized using ensemble bagging to improve classification performance. The optimized Logistic Regression model achieved the best performance, with an accuracy of 89%, precision of 0.90, recall of 0.89, F1-score of 0.89, and an average ROC-AUC score of 0.98. Both KNN and Naive Bayes models reached 81% accuracy after optimization, but their overall performance remained lower than Logistic Regression. The findings demonstrate that Logistic Regression is the most effective method for detecting emotions in Indonesian text, as it can effectively handle simple grammatical structures and slang variations. This study contributes to the development of emotion analysis models for Indonesian text, supporting applications in social computing and affective computing.
Classification of Banana Ripeness Using a VGG16-Based Convolutional Neural Network (CNN) Fikri Maulana
Media Jurnal Informatika Vol 17 No 2 (2025): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v17i2.5930

Abstract

The ripeness level of bananas is a crucial factor that affects the quality, taste, and selling value of the commodity, but the manual sorting process that is commonly carried out is still subjective, inconsistent, and time-consuming. This study aims to implement and evaluate the performance of a VGG16-based Convolutional Neural Network (CNN) architecture in automatically classifying the ripeness level of bananas. The research dataset consists of 5,616 digital images obtained from the Roboflow Universe platform and grouped into six specific classes: freshripe, freshunripe, overripe, ripe, rotten, and unripe. The system development methodology includes data division using stratified splitting techniques, image pre-processing with data augmentation strategies to prevent overfitting, and the application of transfer learning. The model was trained using the Stochastic Gradient Descent (SGD) optimization algorithm with a learning rate of 0.001 for 25 epochs on GPU-based hardware. Performance evaluation was conducted in depth using a confusion matrix, F1-Score metrics, and Precision-Recall curve analysis. The experimental results showed that the VGG16 model achieved an overall accuracy of 97.13%. Class-by-class analysis shows perfect performance in the freshunripe category, although there is a slight decrease in precision in the ripe class due to the similarity of visual characteristics with the overripe class. The stability of the training and validation accuracy curves also indicates that the model has good generalization capabilities. This study concludes that the VGG16 architecture is a reliable and accurate solution to support the efficiency of smart farming systems.
Autism Classification Using MobileNetV3 Feature Extraction and K-Nearest Neighbor Algorithm Rahayun Amrullah Husaini; Gede Yogi Pratama; Kurniadin Abd. Latif; Muhammad Zulfikri; Kartarina Augustin
Media Jurnal Informatika Vol 17 No 2 (2025): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v17i2.5934

Abstract

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by difficulties in social interaction, communication, and repetitive behaviors. Early detection of ASD is crucial; however, conventional diagnostic methods rely heavily on clinical observation and expert assessment, which can be time-consuming and resource-intensive. Along with the rapid development of artificial intelligence, especially in computer vision and machine learning, automated image-based approaches have gained attention as alternative tools for ASD screening. This study proposes a hybrid classification approach that integrates MobileNetV3 as a feature extraction model with the K-Nearest Neighbor (KNN) algorithm for autism classification using facial image data. Unlike previous CNN–KNN approaches, this study specifically explores the use of MobileNetV3’s lightweight architecture to generate compact and discriminative facial features, which are then classified using KNN to evaluate its effectiveness in low-complexity and resource-efficient settings. This design highlights the novelty of combining an optimized lightweight CNN with a distance-based classifier for autism detection from facial images. The dataset used in this research was obtained from Kaggle and consists of 2,940 labeled facial images of children categorized into Autism and non-Autism classes. This study proposes a hybrid classification approach that combines MobileNetV3 as a lightweight feature extraction model with the K-Nearest Neighbor (KNN) algorithm for autism classification. Experimental evaluations were conducted over multiple independent runs to improve statistical reliability, and model performance was assessed using accuracy, precision, recall, and F1-score. The results indicate that the proposed hybrid model achieves satisfactory and consistent performance while maintaining computational efficiency. These findings suggest that integrating lightweight deep learning models with classical machine learning algorithms can provide an effective and resource-efficient approach for autism classification, with potential applicability as a supportive tool for early ASD screening rather than a definitive clinical diagnosis.
Development Of A CNN Model For Recognizing The Indonesian Sign Language (BISINDO) Alphabet Sinta Siti Nuriah; Ahmad Zamakhsyari Sidiq; Zulkaida Akbar
Media Jurnal Informatika Vol 17 No 2 (2025): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v17i2.5936

Abstract

Deaf people in Indonesia face communication barriers due to the limited understanding of Indonesian Sign Language (BISINDO) among the general public. This results in limited social interaction between deaf people and their surroundings. This study aims to develop a Deep Learning and Computer Vision-based BISINDO alphabet translator model using the Convolutional Neural Network (CNN) method, addressing the limited availability of publicly documented BISINDO datasets for alphabet recognition . The method used involves training the model with a dataset of 3,120 BISINDO alphabet images, covering the letters A to Z. The dataset was divided into 80% for training and 20% for testing. The training process included model architecture design, parameter tuning, selection of the best model based on accuracy, and performance evaluation. The evaluation results showed that the developed CNN model achieved an accuracy of 99.84% in classifying BISINDO letters; however, challenges remain in generalizing the model to variations in lighting, hand orientation, and user differences. Nevertheless, the high accuracy achieved indicates the model’s potential to support effective BISINDO translation and improve communication accessibility. This research also opens up opportunities for further development towards comprehensive translation of gestures or sentences in BISINDO.
Rice Leaf Disease Classification Based on ResNet50 and MobileNetV3 Feature Extraction Using Random Forest Gede Yogi Pratama; Rahayun Amrullah Husaini; Muhammad Haris Nasri; Rifqi Hammad
Media Jurnal Informatika Vol 17 No 2 (2025): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v17i2.5939

Abstract

Diseases in rice plants are one of the main factors contributing to decreased agricultural productivity. Early and accurate disease identification is crucial to support effective decision-making in plant disease management. This study aims to compare the performance of deep learning models based on Convolutional Neural Networks (CNN), namely ResNet50 and MobileNetV3, as well as their integration with the Random Forest (RF) algorithm for rice leaf disease classification. The dataset used consists of rice leaf images categorized into several disease classes. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics with a macro-average approach. The results show that the standalone ResNet50 and MobileNetV3 models achieved accuracies of 62.5% and 65.7%, respectively, with macro F1-scores below 0.65, indicating moderate classification performance. However, combining CNN models with Random Forest significantly improved classification performance. The ResNet50 + RF model achieved an accuracy of 99.6%, while the MobileNetV3 + RF model attained the highest accuracy of 99.8%, along with equally high macro-averaged precision, recall, and F1-score values. These findings demonstrate that integrating CNN-extracted features with the Random Forest algorithm enhances the model’s ability to distinguish disease classes more accurately and consistently. Therefore, the hybrid CNN–Random Forest approach shows strong potential as an effective solution for image-based rice plant disease detection systems.
A Solution Recommendation System Based on Application Constraint History Using Cosine Similarity and Gemini AI Novi Dian Nathasia
Media Jurnal Informatika Vol 17 No 2 (2025): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v17i2.5940

Abstract

Problems with applications are potentially to disrupt business operational processes, especially in companies that depend entirely on applications. Therefore, speed and accuracy in handling every application problem that occurs is needed. One way to deal with various application problems effectively is to look for similar issues that have occurred before, and then take the handling solution as a reference for handling the current issue. This research aims to develop a recommendation system for handling application problems that can help the performance of the support services team. This system uses a cosine similarity algorithm with Term Frequency-Inverse Document Frequency weighting to find similar constraints based on the description. Before processing, the constraint description is summarized first using Gemini AI. Solutions to the obstacles found are used as a reference for handling current obstacles. The result of this research is that the system can summarize descriptions of issues and search for similar issues based on the dataset that has been trained. The recommendation system for handling application problems was well received by users, as evidenced by a score of 93.1% from 30 respondents who filled out the User Acceptance Test questionnaire.
Multi-Class Fault Detection under Class-Imbalance in Wireless Sensor Network Using Random Undersampling and Extra Trees David Yusup Saputra; Luh Kesuma Wardhani; Herlino Nanang
Media Jurnal Informatika Vol 17 No 2 (2025): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v17i2.5959

Abstract

Wireless Sensor Networks (WSNs) are widely used in various monitoring applications, including environmental observation, smart infrastructure, and Internet of Things (IoT) systems. Despite their widespread adoption, WSNs are highly susceptible to data errors caused by sensor degradation, hardware malfunctions, environmental disturbances, and communication issues. These faults can significantly reduce data reliability and lead to incorrect system decisions if not properly handled. This study proposes a multi-class data-fault detection approach for WSNs under imbalanced data conditions by integrating Random Undersampling (RUS) with the Extra-Trees classification algorithm. The proposed framework aims to address the class imbalance problem commonly found in sensor fault datasets while improving fault detection performance across multiple fault types. Experiments were conducted using a WSN dataset containing temperature and humidity measurements, in which three fault types: Bias, Drift, and Spike were analyzed alongside normal sensor data. The experimental results demonstrate that Random Undersampling leads to a substantial improvement in classification performance. Without RUS, the Extra-Trees classifier achieved an accuracy of 48% and failed to detect spike faults. After applying RUS, classification accuracy increased to 91%, accompanied by balanced precision, recall, and F1-score values across all classes. These findings indicate that the combination of Random Undersampling and Extra-Trees provides an effective and reliable solution for multi-class data fault detection in WSN environments.
Course Schedule Optimization Using a Java-Based Ant Colony Optimization Theo Buana Pongsumarre; Wahyuni Wahyuni; Muhammad Fahmi
Media Jurnal Informatika Vol 17 No 2 (2025): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v17i2.5961

Abstract

Course timetabling in higher education is a complex combinatorial problem due to constraints related to lecturer availability, limited classroom resources, and fixed weekly time-slot structures. As the number of courses and class sections increases, manual scheduling becomes increasingly inefficient and prone to conflicts, particularly room clashes and overlapping lecturer assignments. This study develops and evaluates an automatic course scheduling system based on the Ant Colony Optimization (ACO) algorithm and implements it as a Java-based desktop application to generate feasible timetables under real institutional conditions. An experimental computational approach is employed, in which artificial ants construct candidate schedules through probabilistic selection influenced by pheromone trails and heuristic information. Timetable quality is evaluated using a weighted cost function that prioritizes hard-constraint satisfaction, such as preventing lecturer and room clashes, while also incorporating soft-constraint penalties related to lecturer forbidden timeslots and schedule distribution balance. The system is tested using real academic data from an undergraduate study program, including courses, lecturers, classrooms, and predefined weekly timeslots. Experimental results show that the proposed system consistently generates conflict-free timetables, achieving a conflict value of zero across all repeated runs under the selected parameter configuration. Beyond feasibility, the optimization process continues to refine timetable quality by reducing soft-constraint penalties, as indicated by the convergence behavior observed across repeated executions. This repeated-run evaluation provides insight into the stochastic optimization characteristics of the ACO-based approach under fixed parameter settings. These findings indicate that the Java-based ACO approach effectively supports automated university course scheduling and provides a practical solution for producing feasible and well-structured timetables.
Evaluating Machine Learning Models Across Feature Extraction and Data Balancing Scenarios for Coretax Sentiment Analysis Subhan Syah Putra; Desti Riminarsih
Media Jurnal Informatika Vol 17 No 2 (2025): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v17i2.5968

Abstract

The implementation of the Core Tax Administration System (Coretax) by the Indonesian Directorate General of Taxes has generated diverse public responses on social media, particularly on platform X, making sentiment analysis a relevant approach to assess public perception of this policy. This study aims to evaluate the performance of machine learning classifiers across different feature extraction and data balancing scenarios. Three machine learning classifiers, namely Multinomial Naïve Bayes, Support Vector Machine (SVM), and Logistic Regression were evaluated under four experimental scenarios combining two feature extraction methods, namely Term Frequency–Inverse Document Frequency (TF-IDF) and Bag of Words (BoW), with original and balanced data distributions. A dataset of more than 50,000 Coretax-related posts collected from platform X was preprocessed and automatically labeled into positive, negative, and neutral sentiment classes using a pretrained IndoBERT sentiment model. A brief manual inspection of a random subset indicates moderate agreement between automatic and manual labels, highlighting potential noise while supporting the use of automatic labeling for comparative analysis. The results show that performance is shaped by the combined effects of representation and data distribution rather than algorithm choice alone. Logistic Regression consistently achieved the most stable and competitive performance across all scenarios, with accuracy values ranging from approximately 0.80 to 0.83 and macro F1-scores around 0.72–0.73. TF-IDF generally provided more stable performance, while data balancing improved prediction fairness for minority sentiment classes despite a slight decrease in overall accuracy. These findings demonstrate that Logistic Regression is the most robust model for Coretax sentiment analysis across varying feature extraction and data balancing conditions and provide practical insights into the influence of data representation and distribution on sentiment classification performance.

Page 26 of 26 | Total Record : 260

 22   23   24   25   26 

Filter by Year

2014 2026


Reset
Filter By Issues
All Issue Vol 18 No 1 (2026): Media Jurnal Informatika Vol 17, No 2 (2025): Media Jurnal Informatika Vol 17 No 2 (2025): Media Jurnal Informatika Vol 17 No 1 (2025): Media Jurnal Informatika Vol 17 No 1a (2025): Special Issue Information System Media Jurnal Informatika Vol 17, No 1a (2025): Special Issue Information System Media Jurnal Informatika Vol 17, No 1a (2025): Special Issue Information System Media Jurnal Informatika (On Progress) Vol 17, No 1 (2025): Media Jurnal Informatika Vol 16, No 2 (2024): Media Jurnal Informatika Vol 16, No 1 (2024): Media Jurnal Informatika Vol 15, No 2 (2023): Media Jurnal Informatika Vol 15, No 1 (2023): Media Jurnal Informatika Vol 14, No 2 (2022): Media Jurnal Informatika Vol 14, No 1 (2022): Media Jurnal Informatika Vol 13, No 2 (2021): Media Jurnal Informatika Vol 13, No 1 (2021): Media Jurnal Informatika Vol 12, No 2 (2020): Media Jurnal Informatika Vol 12, No 1 (2020): Media Jurnal Informatika Vol 11, No 2 (2019): Media Jurnal Informatika Vol 11, No 1 (2019): Media Jurnal Informatika Vol 10, No 2 (2018): Media Jurnal Informatika Vol 10, No 1 (2018): Media Jurnal Informatika Vol 9, No 2 (2017): Media Jurnal Informatika Vol 9, No 1 (2017): Media Jurnal Informatika Vol 8, No 2 (2016): Media Jurnal Informatika Vol 8, No 1 (2016): Media Jurnal Informatika Vol 7, No 2 (2015): Media Jurnal Informatika Vol 7, No 1 (2015): Media Jurnal Informatika Vol 6, No 1 (2014): Media Jurnal Informatika More Issue