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 
Parkinson's Disease Classification Using Vocal Biomarkers, XGBoost, and SHAP Wafiq Mariatul Azizah; Irma Amelia Dewi
Media Jurnal Informatika Vol 18 No 1 (2026): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v18i1.6458

Abstract

Parkinson's disease (PD) is a progressive neurodegenerative disorder affecting more than 11.77 million people worldwide. Voice signal analysis has gained attention as a non-invasive screening approach because nearly 90% of PD patients experience measurable speech impairments. However, previous machine learning studies on PD voice datasets commonly face several limitations, including class imbalance that may lead to data leakage, the use of accuracy as the primary evaluation metric, and limited utilization of model interpretability methods. This study proposes a PD classification pipeline integrating SMOTE, XGBoost, and SHAP using the UCI Parkinson dataset, which consists of 195 samples and 22 acoustic features. A quantitative experimental approach was employed using 5-fold stratified cross-validation, where SMOTE was applied only to the training data within each fold to prevent data leakage, while SHAP was used for feature analysis and feature reduction experiments. The results showed that SMOTE improved the F1-Score from 0.9400 to 0.9527 and the Accuracy from 0.9077 to 0.9282. The final model achieved a mean AUC-ROC of 0.9614 and a Recall of 0.9592 across five folds. SHAP analysis showed differences between SHAP feature rankings and XGBoost built-in importance, with MDVP:Shimmer exhibiting the largest ranking change. In addition, the top-8 SHAP-ranked features achieved performance comparable to the full 22-feature model, obtaining an Accuracy of 0.9282 and an AUC of 0.9612. These findings indicate that the proper application of SMOTE and SHAP-based feature selection can improve model evaluation and provide additional information for feature analysis in Parkinson's disease classification.
Machine Learning Regression Model: Exploring Regression Algorithms for Mercedes-Benz Price Prediction Ridho Sholehurrohman; Muhaqiqin; Igit Sabda Ilman; Agung Pambudi; Wartariyus; Joko Triloka; Handoyo Widi Nugroho
Media Jurnal Informatika Vol 18 No 1 (2026): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v18i1.6476

Abstract

Predicting luxury car prices, such as Mercedes-Benz, remains challenging due to multiple interacting variables, including model, ratings, and market conditions. This study compares six regression algorithms, Linear Regression, Random Forest, Gradient Boosting, XGBoost, K-Nearest Neighbors, and AdaBoost, to identify the most effective model for Mercedes-Benz price prediction. A Kaggle dataset of 10,432 records was preprocessed through cleaning, removal of missing values (resulting in 10,307 records), One-Hot Encoding for categorical variables, and standardization of numerical features using StandardScaler, then split into 80% training and 20% testing data. Model performance was evaluated using MSE, RMSE, and R². Random Forest achieved the best performance (R² = 0.97; RMSE: $3,917), followed closely by Gradient Boosting (R² = 0.96; RMSE: $4,359) and XGBoost (R² = 0.96; RMSE: $4,305). Linear Regression achieved a similar R² (0.96) but higher errors (RMSE: $4,767), while AdaBoost (R² = 0.95; RMSE: $4,897) and KNN (R² = 0.90; RMSE: $5,657) showed lower performance. These findings confirm that ensemble methods, particularly Random Forest, significantly outperform traditional and distance-based approaches for luxury car price prediction. This study provides a comprehensive comparative framework for automotive pricing analytics, with future research directions including additional features, hyperparameter tuning, and integration of external market factors to further enhance prediction accuracy.
Real-Time Webcam-Based Hand Gesture Recognition with Face Authentication for 3D Drone Simulation in Godot Engine Muhammad Rizqi Sholahuddin; Siti Dwi Setiarini; Ardhian Ekawijana; Muhammad Samudera; Firas Atqiya
Media Jurnal Informatika Vol 18 No 1 (2026): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v18i1.6483

Abstract

Most hand gesture control systems for drones depend on specialized hardware such as Leap Motion or Kinect, which raises the cost barrier for educational institutions in developing countries. Integrating face authentication within the same low-cost pipeline remains under-explored. This study develops a real-time, webcam-based system that combines Google MediaPipe hand tracking with facial authentication and a Godot Engine 4.3 3D drone simulation for authenticated, responsive gesture control. A finger-counting algorithm classifies eight gestures across two hands. The left hand drives horizontal motion (forward, backward, left, right) and the right hand drives altitude and yaw (up, down, rotate left, rotate right). Commands travel over UDP to Godot, where a receiver node translates each packet into a native input action. Face authentication uses dlib and the face_recognition library with a 60-frame login counter. All metrics were collected under a fixed condition (normal lighting 300–500 lux, 0.8 m, one subject). The system achieved 100% gesture accuracy across 160 trials, 35.6 FPS pipeline throughput, 0.33 ms one-way UDP latency with 0% packet loss, and 23.9 ms end-to-end gesture-to-drone latency. Face authentication scored 100% recognition with 0% FRR and 19.0% FAR against an unregistered face at the default 0.6 tolerance. A standard-webcam pipeline built entirely from open-source components can deliver responsive, authenticated gesture control for interactive drone simulation, though the single-subject evaluation is an upper bound requiring multi-subject validation. However, the 100% accuracy represents an upper bound as evaluation was limited to a single subject under controlled lighting (300–500 lux) and a fixed distance (0.8 m), requiring further validation across diverse users and environments
Machine Learning-Based Classification of Family Planning Participant Status Using Random Forest and the CRISP-DM Framework Irmawati Irmawati; Syaifur Rahmatullah; Mohammad Syamsul Azis
Media Jurnal Informatika Vol 18 No 1 (2026): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v18i1.6498

Abstract

The Family Planning (FP) program requires accurate information to support evidence-based decision-making and improve the quality of reproductive health services. Classification of FP participant status can assist health authorities in identifying participant patterns and monitoring program implementation. Previous research using the Support Vector Machine (SVM) algorithm on the same dataset achieved an accuracy of 56.20%, indicating that improvements in classification performance are still required. This study proposes the Random Forest algorithm within the Cross-Industry Standard Process for Data Mining (CRISP-DM) framework to classify FP participant status. The dataset consists of 1,402 FP participant records obtained from SATPEL PPKB, Cilebar District, Karawang Regency. Data preprocessing included data transformation, One Hot Encoding for categorical predictor variables, Label Encoding for the target variable, and Hold-Out Validation with an 80:20 train-test split using stratified sampling. The predictor variables were registration month, wife's birth year, wife's age, and contraceptive method, while the target variable was FP participant status (New, Change Method, and Repeat). Model performance was evaluated using accuracy, precision, recall, F1-score, confusion matrix, classification report, and feature importance analysis. The Random Forest model achieved an accuracy of 59.43%, with weighted precision, recall, and F1-score of 59.00%. However, the macro-average precision, recall, and F1-score were 45.00%, 44.00%, and 44.00%, respectively, indicating performance differences across classes caused by class imbalance. The model achieved the highest F1-score for the New class (0.63), followed by the Repeat class (0.59), whereas the Change Method class obtained the lowest F1-score (0.11). Feature importance analysis identified wife's birth year and wife's age as the most influential predictor variables. Compared with the previous SVM-based model, Random Forest provided a modest improvement in accuracy and enhanced model interpretability through feature importance analysis. Nevertheless, the low macro-average performance indicates that further research should investigate class-balancing techniques and hyperparameter optimization to improve classification performance, particularly for minority classes.
A Cognitive Warehouse Inventory System: Progressive Web App with Economic Order Quantity Optimization, Predictive Analytics, and Multi-Tenant Architecture Rizza Muhammad Arief; Syaiful Arifin
Media Jurnal Informatika Vol 18 No 1 (2026): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v18i1.6499

Abstract

In many small and medium enterprises, inventory systems still function primarily as transaction-recording tools and provide limited support for anticipatory replenishment. This study introduces the Cognitive Inventory Management System (CIMS), a progressive web application that integrates mobile stock validation, tenant-isolated data management, machine-learning-driven demand forecasting, and economic order quantity (EOQ) ordering logic. Guided by design science principles, CIMS was evaluated over six months using anonymized primary operational inventory records from Indonesia, covering 35 warehouses, 2,184 stock-keeping units (SKUs), and 186,420 inventory transactions. A pre-post comparison was supplemented with a matched-pair robustness check, a paired t-test, a Wilcoxon signed-rank test, bootstrap confidence intervals, and multiple sensitivity analyses to assess the stability of the findings. Compared with the previous reorder-point practice, the system reduced monthly stockouts by 24.7%, decreased days sales of inventory by 31.2%, and shortened order-to-delivery cycles by 18.5%. Random Forest achieved lower mean absolute percentage error (MAPE) than naive, moving-average, and autoregressive integrated moving average (ARIMA) benchmarks, while the alert mechanism generated stockout warnings 7.3 days in advance on average. The main contribution is an empirically validated architecture that connects interpretable inventory rules with tenant-specific predictive signals in resource-constrained operational settings. The results also indicate that the fully integrated workflow outperforms separate use of forecasting, validation, or EOQ-based rules.
Comparative Analysis of Black-Box and White-Box Machine Learning Model in Explainable Phishing Detection Abdullah Fajar; Setiadi Yazid; Indra Budi
Media Jurnal Informatika Vol 18 No 1 (2026): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v18i1.6501

Abstract

Explainability in phishing detection model can support a further solution of phishing attack mitigation by increasing trust and understanding how phishing can be detected.  The aims of this study to determine and best recommendation to apply an approach which has several components with abilities to fulfil the critical needs A methodology starting with analyzing both black-box and white-box models to get the pros and cons specifically in phishing detection. The conclusion of the analysis will be validated by experiment using a set of well-known algorithms and public phishing datasets. Experimental metrics covers 3 measurements such as predictive accuracy and explainability metrics. Both models are comparable in terms of interpretability and consistency, with room for improvement in diverse datasets. EBM as an example of white-box model is generally better suited for applications requiring explainability and actionable insights. Finally, each model, white-box and black-box model has positive and negative aspects both for performance metric and for explainable metric. It is important to consider the objective of model usage.
Pengembangan Sistem siMenu Menggunakan Metode Waterfall dengan Integrasi Kecerdasan Bisnis dalam Mendukung Keputusan Bisnis dan Efisiensi Layanan Restoran Syifa Nursaadah; Ferrol Azki Mashudi; Fatih Kawakib Kartono; Dimas Akbar Tama; Aditya Wicaksono; Muhammad Nasir
Media Jurnal Informatika Vol 17 No 1 (2025): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v17i1.5304

Abstract

Tujuan dari penelitian adalah untuk mengembangkan sistem informasi restoran berbasis web bernama siMenu, yang dirancang untuk meningkatkan efisiensi layanan dan mendukung pengambilan keputusan bisnis secara berbasis data. Proses pengembangan membutuhkan tahapan yang terstruktur dan berurutan, mulai dari analisis kebutuhan hingga tahap evaluasi, oleh karena itu sistem ini dibangun menggunakan metode Waterfall. Integrasi kecerdasan bisnis (business intelligence) ke dalam sistem memungkinkan manajemen restoran untuk mengakses data operasional secara real-time, seperti penjualan, pesanan, jam sibuk, dan menu terpopuler, melalui tampilan dashboard interaktif. Fitur utama yang dikembangkan mencakup kelola produk, kelola meja, kelola inventaris, dan pemesanan digital. Hasil pengujian menunjukkan bahwa sistem dapat meningkatkan efisiensi operasional, mengurangi kesalahan pencatatan, serta mempercepat proses pelayanan kepada pelanggan. Selain itu, kemudahan diberikan oleh sistem ini bagi pihak manajemen dalam melakukan evaluasi dan perencanaan strategis berdasarkan analisis data yang tersaji secara otomatis. Dengan demikian, sistem siMenu tidak hanya mendukung kebutuhan teknis operasional, tetapi juga berkontribusi dalam transformasi digital sektor kuliner yang lebih cerdas dan adaptif terhadap perubahan pasar
Evaluation of Deflate Algorithm in Lossless Compression of Digital Document Formats Muhammad Irwan Nawawi; Finsa Nurpandi
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.v17i2.5746

Abstract

As the volume of digital data continues to escalate across sectors such as education, business, and government, the demand for efficient data storage and transmission methods grows increasingly critical. Data compression algorithms offer a prevalent solution to this challenge. This study undertakes an evaluation of the Deflate algorithm's performance in compressing digital document files, specifically examining its efficacy in reducing file size and its efficiency in processing time. Employing a comparative analysis methodology, the research involves measuring file sizes before and after compression, recording compression and decompression durations on a machine with an Intel Core i5 CPU, 8 GB RAM, running Windows 10 64-bit, and calculating compression ratios. The implementation utilizes Python and the Zlib library, which directly supports the Deflate algorithm. Tests were conducted on diverse document types, including plain text files, mixed-content files, and files rich in visual elements like images. The findings indicate that the Deflate algorithm achieves a significant compression ratio, reducing file sizes by over 90% and reaching a maximum ratio of 99.60% for text files. Compression and decompression operations were most rapid for text files, averaging 0.01 seconds. However, for documents containing images, the compression ratio was considerably lower and less impactful. Notwithstanding this, the compression and decompression times remained relatively swift and consistent across all document types. These results underscore the importance of aligning compression algorithm selection with the specific content characteristics of a document to attain optimal efficiency.
AI-Based Testing Using NLP Algorithm On Eggsperts Website Functionality Using Boundary Value Analysis Technique Zolla Perdana Putra Harahap; Akhfa Bagas Alfarizi; Rio Ferddinansya; Adrian Fardan Andi; Muhammad Nasir; Sofiyanti Indriasari
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.v17i2.5884

Abstract

The poultry farming subsector plays a crucial role in national food security, yet remains constrained by manual recording and efficiency constraints. Digital transformation offers solutions such as the Eggspert website, designed to assist farmers in managing production and sales data quickly and in an integrated manner. This study aims to test the reliability and functionality of the Eggspert system and assess the effectiveness of integrating Artificial Intelligence (AI) into the software testing process. Unlike previous AI-assisted testing studies that primarily focus on generic software applications, this research emphasizes the application of NLP-based AI Testing within a domain-specific digital livestock management system, addressing the lack of empirical testing frameworks tailored to the poultry farming sector. This research is an experimental quantitative approach using Black Box Testing and Boundary Value Analysis (BVA) techniques, combined with Natural Language Processing (NLP)-based AI Testing. The process follows the Software Testing Life Cycle (STLC) stages to ensure systematic and measurable testing. Of the 42 test cases executed, 33 passed and 9 failed, resulting in a success rate of 78.57%. Each test case was executed repeatedly under consistent test conditions to ensure functional stability, with failures indicating specific validation weaknesses rather than random system behavior. Most system functions met specifications, although minor deficiencies remained in text validation and zero pricing. The integration of AI Testing has been shown to improve error detection efficiency. The combination of BVA and AI Testing effectively verified the functionality of the Eggspert system, increased the reliability and efficiency of the testing process, and has the potential to serve as a basis for developing an AI-based testing system in the digital livestock sector.
Implementation of Smoothing and Noise Reduction for Digital Image Quality Enhancement Using Neighborhood Operations Agus Suheri; Sri Widaningsih; Abiyyatun Nazihah
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.v17i2.5893

Abstract

The rapid growth in digital imaging technology has brought profound changes to various sectors. However, the quality of digital images is often compromised by noise, such as gaussian noise, salt-and-pepper noise, and spackle noise. Noise not only reduces the aesthetics of an image, but can also hinder image analysis and interpretation. In addition, it can obscure important details in the image and reduce the clarity and accuracy of visual analysis. To improve the quality of digital images, effective smoothing and noise removal techniques are needed, one of which is the neighborhood operation. The main purpose of smoothing and noise removal is to improve visual quality so that images are clearer and easier to analyze. In this study, a mean filter is used for smoothing and a median filter is used for noise reduction. Combine mean and median filtering in this study is directly aligned with its emphasis on a pixel-domain, low-level analysis of convolution-based smoothing. The mask used has a size of 5, 9, 25, or 49 points as the kernel in the convolution mask operation to remove noise and smooth the image at the same time. The digital image processing application was created following the waterfall software development model stages.The BMP format was selected in this study primarily to ensure data integrity and experimental control. To measure the quality of the image produced after the smoothing process, the Mean Square Error (MSE) and Peak Signal to Noise Ratio (PSNR) standards are used. From the experimental results, the MSE values for mask sizes 5, 9, 25, and 49 are 12.96, 14.36, 14.72, and 16.80, respectively. Meanwhile, the PSNR values were 37, 36.56, 36.54, and 35.87, respectively. From the image quality results in the form of MSE and PSNR, it can be seen that the larger the mask size, the greater the MSE value, but the smaller the PSNR value. The smaller the PSNR value, the worse the image quality, and vice versa. This is supported by visual analysis, where more details of the original image are lost. However, the PSNR value is still in the range of 30-40 dB, which means the quality is still in the Good category. The quality is still acceptable with minimal distortion. The quality of the results is still very close to the original image. The highest image quality is found in mask 5.

Page 25 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 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 17 No 1 (2025): Media Jurnal Informatika Vol 17 No 1a (2025): Special Issue Information System 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