cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Fristi Riandari
Contact Email
hengkitamando26@gmail.com
Phone
+6281381251442
Journal Mail Official
hengkitamando26@gmail.com
Editorial Address
Romeby Lestari Housing Complex Blok C Number C14, North Sumatra, Indonesia
Location
Unknown,
Unknown
INDONESIA
Jurnal Mandiri IT
Published by Institute of Computer Science
ISSN : 23018984     EISSN : 28091884     DOI : https://doi.org/10.35335/mandiri
Core Subject : Science, Education,
Computer Science & IT Library & Information Science Mathematics
The Jurnal Mandiri IT is intended as a publication media to publish articles reporting the results of Computer Science and related research.
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 217 Documents
 18   19   20   21   22 
Development of a laravel-based web information system for network device maintenance management using the rapid application development method Bimorogo, Sembada Denrineksa; Lediwara, Nadiza; Heikhmakhtiar, Aulia Khamas; Aulia, Regifia Ningrum Nur; Sunami, Yoga; Priyani, Kadek Jana; Azahra, Manda Fatimah
Jurnal Mandiri IT Vol. 14 No. 2 (2025): Computer Science and Field
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i2.456

Abstract

Information and Communication Technology (ICT) infrastructure is essential for government operations, particularly in managing network devices. Within the ICT Hardware Infrastructure Subdivision (Subbidang Harinfra TIK) of the Data and Information Center at the Indonesian Ministry of Defense, documentation of maintenance activities remains fragmented, making monitoring, analysis, and historical data storage less effective. This study developed a web-based information system using the Laravel framework and the Rapid Application Development (RAD) approach to address these issues. The system automates documentation, monitoring, and reporting, ensuring more structured, transparent, and efficient processes. Black Box testing confirmed reliable functionality, data validation, and improved efficiency in maintenance activities. Unlike previous studies that focused on general asset or helpdesk systems, this research emphasizes ICT infrastructure maintenance in a defense environment, highlighting security and adaptability for sensitive data. The implementation enhances systematic documentation and operational transparency, with future improvements directed toward intelligent notifications and platform integration in line with Industry 4.0 trends.
Implementation of PZEM-004T and LoRa for Internet of Things–Based Monitoring of Power Supply Sources in Laboratory Building Sirait, Regina; Pardede, Morlan; Hutajulu, Elferida; Junaidi, Junaidi; Pardede, Stephanie Ch Y; Pakpahan, Arnold
Jurnal Mandiri IT Vol. 14 No. 2 (2025): Computer Science and Field
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i2.457

Abstract

This research develops an Internet of Things (IoT)-based system to monitor electrical voltage parameters in two rooms of the Telecommunication Laboratory at Medan State Polytechnic. The system employs two sensor nodes (PZEM-004T, ESP32, and LoRa SX1276) and a gateway node integrated with WiFi and the Blynk cloud. The sensors measure voltage, current, power, energy consumption, frequency, and power factor, which are processed by ESP32 and transmitted via a LoRa multi-point network to the gateway for online monitoring. An automatic cut-off mechanism and email notifications are provided when abnormal voltage or current conditions occur. Experimental results show high measurement accuracy with a maximum error of 0.29% for voltage and 2.52% for current. However, data transmission experienced 20% packet loss, with an average delay of 11 seconds on Blynk and 37 seconds for email notifications. These findings indicate that the proposed system is effective in protecting laboratory equipment from abnormal power sources and provides reliable online and offline monitoring, although transmission performance requires further optimization.
Comparison of MobileNetv2 and MobileNetv3 architectures in rice leaf disease classification using transfer learning Mifthauddin, Adlim; Lutfi, Moch.; Saadah, Zulfatun Nikmatus
Jurnal Mandiri IT Vol. 14 No. 2 (2025): Computer Science and Field
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i2.459

Abstract

Rice is of the main food commodities in Indonesia that is susceptible to various leaf diseases, one of which is Bacterial Blight, Brown Spot, and Leaf Smut. Manual identification by farmers is often less accurate and time-consuming, thus requiring a technology-based detection system. The objective of this research is to categorize rice leafdiseases through the use of deep learning with a transfer learning approach based on MobileNetV2 and MobileNetV3 architectures. The dataset, comprising 4,684 rice leaf images, was divided into training and validation sets using an 80:20 ratio. Preprocessing included resizing images to 224×224 pixels, normalization, and augmentation to increase data variation. Training was carried out across 30 epochs with a mini-batch size set to 32. while applying an EarlyStopping mechanism to reduce the likelihood of overfitting. The result of the experiment indicate that MobileNetV2 reached an 96% accuracy, while MobileNetV3 outputperformed is with an accuracy of 99%. Therefore, MobileNetV3 is more effective for rice leaf disease classification.
Enhancing application design for integrated evaluation through user-centered prototyping with figma Tiana, Ade Hikma; Prasetyo, Rizky Tito; Yulistiawan, Bambang Saras; Masruriyah, Anis Fitri Nur
Jurnal Mandiri IT Vol. 14 No. 2 (2025): October: Computer Science and Field
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i2.462

Abstract

This study developed an integrated evaluation application using a User-Centered Design (UCD) approach combined with user-centered prototyping via Figma, aiming to improve academic service management in educational institutions. The application focused on four main features: service request submission, complaint reporting, lecturer evaluation, and a knowledge base for self-service solutions. Requirements were gathered through questionnaires and interviews with students, lecturers, and faculty leaders to ensure the design met user needs. The prototype was iteratively refined based on quantitative and qualitative evaluations using Likert scale questionnaires. Results showed high user satisfaction with an average score of 4.41, indicating excellent usability, visual appeal, and feature relevance. Thematic analysis highlighted key themes of ease of use, interface consistency, and system security. The integrated UCD and Figma prototyping approach proved effective in producing an adaptive, interactive, and user-friendly application design that supports continuous improvement in academic services.
Analysis and design of an inset-feed microstrip antenna for a LEO satellite IoT ground station at 921 MHz Taqwa, Rangga; Rimbawa, H.A. Danang; Miptahudin, Apip; Hasibuan, Bayu Nuar Khadapi; Sastradinata, Aria Kusumah; Bangun, Abbas Madani
Jurnal Mandiri IT Vol. 14 No. 2 (2025): Computer Science and Field
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i2.464

Abstract

The evolution of the Internet of Things (IoT) demands global connectivity that terrestrial networks alone cannot provide1. Low Earth Orbit (LEO) satellites equipped with Long Range (LoRa) communication technology offer a promising solution to bridge this connectivity gap2. This paper presents a specific case study calculation for a LoRa-based IoT satellite mission, defining the system's operational constraints based on selected hardware3. This analysis is framed by the RFM95W LoRa transceiver for the ground station and the Satlab Polaris receiver for the satellite4. The datasheet specifications of these components establish the critical link parameters that dictate performance: a maximum Transmit Power (Pt) ) of 20 dBm from the RFM95W 5and a Receiver Sensitivity threshold of -130 dBm for the Satlab Polaris6. The objectives are: (1) to conduct a comprehensive link budget analysis to validate the communication viability between a LEO satellite and a ground station 77, and (2) to design and predict the performance of an inset-feed microstrip antenna operating in the 920-925 MHz Indonesian LoRa frequency band using an FR-4 substrate. The detailed link budget analysis, performed for an uplink to a 500 km orbit 9, reveals that these specific parameters create a stringent performance requirement: while a reliable link margin of $+7.8 \text{ dB}$ is achieved at a 90°  elevation (best case) 10101010, the system reaches its theoretical critical threshold (0.0 dB margin) at 19.1° and enters link failure with a -2.8 dB margin at the target 10°  elevation. This failure is directly linked to the preliminary simulation of the initial antenna design, which shows a suboptimal return loss (S11) of -9.41 dB. This paper concludes that the system's target for low-elevation communication has not been met. The performance gap, defined by the hardware constraints, confirms that the initial antenna design is insufficient15. Therefore, systematic optimization of the antenna design is identified as the crucial next step to achieve a positive link margin at the 10° target elevation and ensure a robust communication link across all operational scenarios.
Bayesian-Optimized XGBoost Model for Predicting Mushroom Toxicity Sastradinata, Aria Kusumah; Sunarta, Sunarta; Miptahudin, Rd. Apip; Abdurrahman, M. Daffa; Taqwa, Rangga
Jurnal Mandiri IT Vol. 14 No. 2 (2025): Computer Science and Field
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i2.465

Abstract

Mushroom poisoning remains a significant public health concern due to the morphological similarities between edible and poisonous species, making traditional identification unreliable. This study aims to develop an accurate and interpretable machine learning framework for mushroom toxicity prediction using a Bayesian-Optimized Extreme Gradient Boosting (XGBoost) model. The dataset consists of morphological and ecological features derived from the secondary mushroom dataset, which underwent preprocessing through imputation, standardization, and one-hot encoding. Bayesian Optimization, implemented via the Hyperopt Tree-structured Parzen Estimator (TPE) algorithm, was employed to automatically fine-tune the XGBoost hyperparameters, thereby improving convergence and reducing manual experimentation. The model’s performance was evaluated using 10-fold cross-validation and standard metrics, including accuracy, precision, recall, F1-score, and the Area Under the ROC Curve (AUC). Experimental results demonstrated that the proposed framework achieved an exceptionally high performance with an accuracy of 99.99% and an AUC of 1.0000, indicating near-perfect discrimination between edible and poisonous mushrooms. Feature importance analysis further revealed that habitat, veil color, and stem root were the most influential predictors of toxicity. The findings highlight the effectiveness of Bayesian-optimized ensemble learning in handling high-dimensional biological data, offering a reliable, transparent, and computationally efficient approach for biosafety assessment and ecological data analysis.
Optimizing the performance of the K-Nearest Neighbors algorithm using grid search and feature scaling to improve data classification accuracy Manurung, Jonson; Saragih, Hondor; Prabukusumo, Muhammad Azhar; Firdaus, Eryan Ahmad
Jurnal Mandiri IT Vol. 14 No. 2 (2025): Computer Science and Field
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i2.466

Abstract

The performance of distance-based classification algorithms such as K-Nearest Neighbors (KNN) is highly dependent on proper feature scaling and optimal parameter selection. Without systematic optimization, KNN may experience decreased accuracy due to feature scale disparities and suboptimal k-values. This study aims to enhance the performance of the KNN algorithm through the integration of Feature Scaling and Grid Search Cross-Validation as a parameter optimization strategy. The research employs the Breast Cancer Wisconsin Dataset, divided into 80% training and 20% testing data. Feature normalization was performed using StandardScaler, while Grid Search was applied to determine the optimal combination of parameters, including the number of neighbors (k), weighting function (weights), and distance metric (metric). The optimized KNN configuration with k = 9, weights = distance, and metric = manhattan achieved an average accuracy of 97.19%, outperforming the baseline accuracy of 93.86%. A paired t-test confirmed that the improvement was statistically significant (p < 0.05). These findings demonstrate that the synergy between feature scaling and parameter tuning can substantially improve both the accuracy and stability of KNN models. The scientific novelty of this study lies in the systematic integration of normalization and parameter optimization through Grid Search, providing an empirical framework that enhances KNN’s robustness across datasets with heterogeneous feature distributions. The proposed approach is recommended for medical data classification and can be adapted to other domains with heterogeneous numerical feature distributions.
Design of a web-based car rental service portal information system for 123 Lampung Utara Sari, Devika; Jihad, M. Abu
Jurnal Mandiri IT Vol. 14 No. 2 (2025): Computer Science and Field
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i2.467

Abstract

This study aimed to design and implement a web-based car rental service information system for 123 Lampung Utara. The system was developed using the CodeIgniter framework with PHP as the programming language and MySQL as the database. The main features included vehicle category and data management, user registration and authentication, rental transactions, order status tracking, and transaction reporting in PDF format. The system was designed to enhance operational efficiency and customer satisfaction through the digitalization of the rental process. The development followed the Waterfall methodology and the Model-View-Controller (MVC) architecture. Black Box testing results showed that all system functions operated correctly according to predefined scenarios, and no critical bugs were found. Therefore, the system was deemed feasible for operational implementation and ready for further development through integration with a payment gateway and automated notification services.
Optimization of XGBoost hyperparameters using grid search and random search for credit card default prediction Firdaus, Eryan Ahmad; Manurung, Jonson; Saragih, Hondor; Prabukusumo, Muhammad Azhar
Jurnal Mandiri IT Vol. 14 No. 2 (2025): Computer Science and Field
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i2.468

Abstract

This study explores the optimization of the Extreme Gradient Boosting (XGBoost) algorithm for credit card default prediction through systematic hyperparameter tuning using Grid Search and Random Search methodologies. Utilizing the publicly available Default of Credit Card Clients dataset from the UCI Machine Learning Repository, the research focuses on enhancing model performance by fine-tuning critical parameters such as learning rate, maximum tree depth, number of estimators, subsample ratio, and column sampling rate. The baseline XGBoost model achieved an accuracy of 0.8118, while the tuned models using Grid Search and Random Search improved the accuracy to 0.8183 and 0.8188, respectively. Although the improvement appears modest, the optimized models exhibited enhanced balance between precision and recall, particularly in identifying defaulters within an imbalanced dataset—an essential aspect in credit risk assessment. The results demonstrate that systematic hyperparameter optimization not only improves predictive performance but also contributes to model stability and generalization. Moreover, Random Search proved to be more computationally efficient, achieving near-optimal performance with fewer evaluations than Grid Search, thereby emphasizing its practicality for large-scale financial risk modeling applications. The novelty of this study lies in the comparative evaluation of two optimization techniques within the context of financial risk prediction, providing practical insights into how efficient hyperparameter tuning can enhance the reliability and scalability of machine learning models used in real-world credit risk management systems.
Hyperparameter optimization of graph neural networks for predicting complex network dynamics using bayesian meta-learning Saragih, Hondor; Manurung, Jonson; Prabukusumo, Muhammad Azhar; Firdaus, Eryan Ahmad
Jurnal Mandiri IT Vol. 14 No. 2 (2025): Computer Science and Field
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i2.469

Abstract

The rapid growth of graph-structured data in domains such as transportation, social networks, and biological systems has increased the demand for more adaptive and efficient Graph Neural Network (GNN) architectures. However, GNN performance remains highly sensitive to hyperparameter configurations, which are often tuned through computationally expensive manual or heuristic methods. This study proposes a novel Bayesian Meta-Learning (BML)-based framework for hyperparameter optimization of GNNs aimed at improving the prediction accuracy of complex network dynamics. The framework integrates Bayesian optimization with a meta-learning prior adaptation mechanism, enabling the model to learn optimal hyperparameter distributions across multiple graph tasks. Experimental evaluations conducted on three benchmark datasets—Cora, Citeseer, and PubMed—comprising up to 20,000 nodes with diverse structural complexities, demonstrate that the proposed BML-GNN framework achieves faster convergence, lower validation loss, and higher predictive accuracy than both baseline GNN and traditional Bayesian Optimization approaches. Quantitatively, the BML-GNN model attains an R² score exceeding 0.97 with a significant reduction in RMSE, confirming its strong generalization capability. Although the method shows notable performance improvements, its computational overhead during meta-training and reliance on well-defined prior distributions represent potential limitations. Overall, the integration of Bayesian Meta-Learning provides a robust, scalable, and uncertainty-aware optimization strategy that advances the development of reliable GNN models for complex network modeling and intelligent system design.

Page 20 of 22 | Total Record : 217

 18   19   20   21   22 

Filter by Year

2020 2026


Reset
Filter By Issues
All Issue Vol. 14 No. 3 (2026): Jan: Computer Science and Field Vol. 14 No. 2 (2025): October: Computer Science and Field Vol. 14 No. 2 (2025): Computer Science and Field Vol. 14 No. 1 (2025): July: Computer Science and Field. Vol. 13 No. 4 (2025): April: Computer Science and Field. Vol. 13 No. 3 (2025): January: Computer Science and Field. Vol. 13 No. 2 (2024): CALL FOR PAPER !!! Scope Computer Science Vol. 13 No. 1 (2024): July: Computer Science and Field Vol. 12 No. 4 (2024): April: Computer Science and Field. Vol. 12 No. 3 (2024): January: Computer Science and Field. Vol. 12 No. 2 (2023): October: Computer Science and Field. Vol. 12 No. 1 (2023): July: Computer Science and Field. Vol. 11 No. 4 (2023): April : Computer Science and Field. Vol. 11 No. 3 (2023): January: Computer Science and Field. Vol. 11 No. 2 (2022): October: Computer Science and Field. Vol. 11 No. 1 (2022): July: Computer Science and Field. Vol. 10 No. 2 (2022): January: Computer Science and Field. Vol. 10 No. 1 (2021): July: Computer Science and Field. Vol. 9 No. 2 (2021): January: Computer Science and Field. Vol. 9 No. 1 (2020): July: Computer Science and related. Vol. 8 No. 2 (2020): January: Coputer Science and related. More Issue