cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Prajanto Wahyu Adi
Contact Email
jmasif@live.undip.ac.id
Phone
+6281222260833
Journal Mail Official
jmasif@live.undip.ac.id
Editorial Address
Ruang E305 Ged. E Lt.3 Jurusan Ilmu Komputer / Informatika Fakultas Sains dan Matematika Universitas Diponegoro Jl. Prof. Soedarto, S.H Tembalang, Semarang, 50275 Telp. 024-7474754 ext. 5001
Location
Kota semarang,
Jawa tengah
INDONESIA
Jurnal Masyarakat Informatika
Published by Universitas Diponegoro
ISSN : 20864930     EISSN : 27770648     DOI : https://doi.org/10.14710/jmasif.crossmark
Core Subject : Science,
Computer Science & IT
JURNAL MASYARAKAT INFORMATIKA - JMASIF is a Journal published by the Department of Informatics, Universitas Diponegoro invites lecturers, researchers, students (Bachelor, Master, and Doctoral) as well as practitioners in the field of computer science and informatics to contribute to JMASIF in the form of research articles and review articles. We accept articles in English and Bahasa. Detailed information about the submission process can be read HERE. Authors can also download Templates at HERE. JMASIF Topics include, but are not limited to Applied Computer Science, Artificial Intelligence, Text and Natural Language Processing, Image Processing and Pattern Recognition, Computer Vision, Data Mining, Cryptography, Cybersecurity, Computer Network, Computational Theory and Mathematics, Game Technology, Human and Computer Interaction or UI/UX, Information System, Software Engineering.
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 196 Documents
 16   17   18   19   20 
Applying the Scrum Method in Software Development for Undergraduate Thesis Project Implementation Ramadhan, Attaf Riski Putra; Waspada, Indra; Bahtiar, Nurdin; Pramayoga, Adhe Setya
Jurnal Masyarakat Informatika Vol 16, No 1 (2025): May 2025
Publisher : Department of Informatics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jmasif.16.1.73187

Abstract

The Scrum Method, as one of the frameworks within Agile-based software development, has become the de facto standard in industry practices. However, to date, there is no specific guideline or adaptation model that directs the application of Scrum in undergraduate thesis project settings, particularly within the Bachelor of Informatics Study Program at Diponegoro University. In this program, the final project is carried out individually by a student under the supervision of two academic advisors, forming a small team structure that differs from conventional Scrum configurations. This study proposes an adaptation model of the Scrum method for such a scenario, assigning the roles of Product Owner and Tester to the First Supervisor, Scrum Master and Tester to the Second Supervisor, and Developer as well as Assistant to the Student. The implementation of Scrum in this context facilitates structured communication between supervisors and the student, while also supporting flexibility in accommodating changing requirements throughout the development process. Moreover, active stakeholder involvement during the requirements gathering and Sprint Review stages contributes to the enhanced quality of the final deliverable. The project was executed over four sprints within a total of 40 working days, covering 13 product backlog and several derivative tasks. The findings indicate that adapting Scrum to the context of a final project enables timely project completion with outcomes that are academically and technically accountable.
Systematic Literature Review on Medical Image Captioning Using CNN-LSTM and Transformer-Based Models Fadhilah, Husni; Utama, Nugraha Priya
Jurnal Masyarakat Informatika Vol 16, No 1 (2025): May 2025
Publisher : Department of Informatics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jmasif.16.1.73127

Abstract

Creating descriptive text from medical images to aid in diagnosis and treatment planning is known as medical image captioning, and it is a crucial duty in the healthcare industry. In this study, medical image captioning techniques are systematically reviewed in the literature with an emphasis on Transformer-based models and Convolutional Neural Network-Long Short Term Memory (CNN-LSTM). Aspects like as model designs, datasets, evaluation measures, and difficulties encountered in practical implementations are all examined in this paper. According to the results, Transformer-based models, specifically Swin Transformer and Vision Transformer (ViT), perform better than CNN-LSTM-based models in terms of BLEU, ROUGE, CIDEr, and METEOR scores, resulting in more accurate clinically relevant caption generation. However, there are still a number of issues, including interpretability, computing requirements, and data restrictions. Potential future routes to increase the efficacy and practical application of medical image captioning systems are covered in this paper, including hybrid model approaches, data augmentation techniques, and enhanced explainability methodologies.
Analysis of the Correlation Between Playtime, Design, and Game Mechanics to Positive Reviews on the Fighting Games Genre using Large Language Models Vicoriza, Vicoriza; Aryotejo, Guruh; Widodo, Aris Puji
Jurnal Masyarakat Informatika Vol 16, No 1 (2025): May 2025
Publisher : Department of Informatics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jmasif.16.1.72576

Abstract

The video game  industry is experiencing rapid growth, with the fighting game  genre remaining a favorite due to its tactical challenges and deep mechanics. This study explored the relationship between playtime, game design, and game mechanics to positive reviews from players, using Large Language Models (LLMs) for sentiment and emotion analysis. The data was collected from more than 200,000 Steam user reviews on 12  popular fighting games. The results show that the correlation between playtime and positive reviews tends to be weak, although in some titles, longer playing duration is associated with better sentiment. In terms of game design, players prefer games with fantasy settings  (92.34%), 2D graphics (94.21%), and anime visual style  (95.12%), which significantly drives positive reviews. In the mechanical aspects of the game, features such as multiple meters (93.11%), advanced blocking (93.56%), and wall boundaries (91.72%) get higher satisfaction, suggesting that the complexity and variety of mechanics can increase player engagement. LLM-based sentiment analysis  also reveals that technical factors play an important role in player perception. The most common complaints in negative reviews relate to lag, character balancing, and additional content quality (DLC).
Classification of Real and Fake Images Using Error Level Analysis Technique and MobileNetV2 Architecture Baihaqi, Muhamad Nur; Sugiharto, Aris; Tantyoko, Henri
Jurnal Masyarakat Informatika Vol 16, No 1 (2025): May 2025
Publisher : Department of Informatics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jmasif.16.1.73283

Abstract

Advancements in technology have made image forgery increasingly difficult to detect, raising the risk of misinformation on social media. To address this issue, Error Level Analysis (ELA) feature extraction can be utilized to detect error level variations in lossy-formatted images such as JPEG. This study evaluates the contribution of ELA features in classifying authentic and forged images using the MobileNetV2 model. Two scenarios were tested using the CASIA 2.0 dataset: without ELA and with ELA. Fine-tuning was performed to adapt the model to the new problem. Experimental results show that incorporating ELA improves model accuracy up to 93.1%, compared to only 76.41% in the scenario without ELA. Validation using k-fold cross-validation yielded a high average f1-score of 96.83%, confirming the effectiveness of ELA in enhancing the classification performance of authentic and forged images.
A Comparative Analysis of the CRITIC and Entropy Methods for Objective Weighting of Priority Criteria Dwi Putri Ariyanti, Yunila; Fu'adi, Dhena Kamalia
Jurnal Masyarakat Informatika Vol 16, No 2 (2025): Issue in Progress
Publisher : Department of Informatics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jmasif.16.2.73143

Abstract

Various criteria weighting methods are available, and this study aims to compare the Criteria Importance Through Inter Criteria Correlation (CRITIC) and Entropy methods to determine the criteria weights. This case study focuses on identifying priority customers from 2 years of sales transactions in an online retail company, which processes more than 1 million transactions with 8 features. The researcher selected 100 high-value customers as alternative data, prioritizing research efficiency and high-value insights. Four criteria were set for customer prioritization. Sensitivity analysis was conducted using the Additive Ratio Assessment (ARAS) method to measure the stability of the method. The CRITIC method produced balanced weights (0.23-0.27), while Entropy produced more variable weights, with C3 being the largest criterion weight with a value of 0.46, indicating its strong dependence on the data distribution. Sensitivity analysis revealed that the Entropy-ARAS method was more sensitive to weight changes (75.11134%) in this customer prioritization case compared to the CRITIC-ARAS method (56.95372%).
A Comparative Analysis of Convolutional Neural Network (CNN): MobileNetV2 and Xception for Butterfly Species Classification Pradnyatama, Mehta; Sari, Christy Atika; Rachmawanto, Eko Hari; Islam, Hussain Md Mehedul
Jurnal Masyarakat Informatika Vol 16, No 1 (2025): May 2025
Publisher : Department of Informatics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jmasif.16.1.72957

Abstract

This study aims to compare the effectiveness and efficiency of two convolutional neural network architectures, MobileNetV2 and Xception, for automated butterfly species classification. As biodiversity monitoring gains significance, effective species identification technologies are crucial for conservation. The research utilized a dataset of 100 butterfly species with 12,594 training images and 1,000 validation and test images. Transfer learning with pre-trained ImageNet weights was implemented, and both models were enhanced with custom classification layers. Data augmentation and class weighting mitigated dataset imbalance issues. Experimental results show Xception attained 93.40% test accuracy compared to MobileNetV2's 93.20%. These high accuracy rates were achieved through effective transfer learning that preserved general feature extraction capabilities, comprehensive class balancing techniques, and carefully tailored learning rate strategies for each architecture. Despite minimal performance difference, MobileNetV2 offers significant computational efficiency advantages with 4.15M parameters compared to Xception's 25.27M, while Xception provides marginally better classification. This study contributes to entomological research and highlights trade-offs between model complexity and performance in fine-grained classification tasks, supporting implementation decisions for butterfly identification systems in practical applications.
Optimizing VGG16 Architecture with Bayesian Hyperparameter Tuning for Tomato Leaf Disease Classification Arkan, Tsaqif Muhammad; Sugiharto, Aris; Wibawa, Helmie Arif
Jurnal Masyarakat Informatika Vol 16, No 2 (2025): Issue in Progress
Publisher : Department of Informatics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jmasif.16.2.73168

Abstract

This study proposes an optimized VGG16 architecture enhanced through Bayesian Optimization to improve the classification of tomato leaf diseases. The modified model integrates tunable parameters such as dropout rates, convolutional filters, and dense units, while maintaining the foundational structure of VGG16. To further refine performance, Bayesian Optimization is employed to search for the most effective combination of hyperparameters. Experiments conducted using the Tomato Leaf Disease Detection dataset demonstrate that the proposed method outperforms the original VGG16 model, achieving a test accuracy of 97.1% compared to 89.0%. These results underline the importance of architecture customization and systematic hyperparameter tuning for domain-specific deep learning tasks in agriculture.
A Comparative Study of Machine Learning Models for Short-Term Load Forecasting Vianita, Etna; Tantyoko, Henri
Jurnal Masyarakat Informatika Vol 16, No 1 (2025): May 2025
Publisher : Department of Informatics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jmasif.16.1.73130

Abstract

Short-Term Load Forecasting (STLF) was a critical task in power system operations, enabling efficient energy management and planning. This study presented a comparative analysis of five machine learning models namely XGBoost, Random Forest, Multi-Layer Perceptron (MLP), Support Vector Regression (SVR), and LightGBM using real-world electricity demand data collected over a four-month period. Two modeling approaches were explored: one using only time-based features (hour, day of the week, month), and another incorporating historical lag features (lag_1, lag_2, lag_3) to capture temporal patterns. The results showed that MLP with lag features achieved the best performance (RMSE: 57.63, MAE: 34.54, MAPE: 0.22), highlighting its ability to model nonlinear and sequential dependencies. In contrast, SVR and LightGBM experienced performance degradation when lag features were added, suggesting sensitivity to feature dimensionality and data volume. These findings emphasized the importance of model-feature alignment and temporal context in improving forecasting accuracy. Future work could explore the integration of external variables such as weather and holidays, as well as the application of advanced deep learning architectures like LSTM or hybrid models to further enhance robustness and generalizability.
Development and Optimization of a Construction Personal Protective Equipment (PPE) Detection Model on YOLOv8 Architecture Utomo, Zidan Rafindra; Adi, Prajanto Wahyu; Sasongko, Priyo Sidik; Rahman, Gohar
Jurnal Masyarakat Informatika Vol 16, No 1 (2025): May 2025
Publisher : Department of Informatics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jmasif.16.1.71622

Abstract

Workplace safety in the construction sector remains a critical issue due to frequent accidents caused by non-compliance with Personal Protective Equipment (PPE) regulations. Manual supervision is inefficient and prone to errors, necessitating an automated detection approach. The prior YOLOv5 version trained on the Construction Safety dataset from Roboflow-100, achieves a mean Average Precision (mAP@0.50) of 0.867. However, class imbalance, particularly the underrepresentation of "no-helmet" and "no-vest" categories, limited detection performance. This study improves the model by tuning hyperparameters for optimal training using grid search and applying data augmentation techniques to address dataset imbalance. Mosaic and Mixup augmentation technique is applied on the dataset. The augmented dataset is used to retrain YOLOv8, further optimizing detection accuracy. Results indicate an improved mAP@0.50 of 0.921, demonstrating enhanced performance in PPE violation detection. These refinements aim to strengthen workplace safety enforcement through more accurate and balanced PPE detection.
Artificial Intelligence-Aided In Silico Screening of Syzygium polyanthum Phytochemicals for Antidiabetic Drug Discovery Using ACO (Ant Colony Optimization) Algorithm Samsuri, Ahmad; Hermawan, Faris; Zikri, Adi Tiara; Vifta, Rissa Laila; Puspitasari, Anita Dwi
Jurnal Masyarakat Informatika Vol 16, No 2 (2025): Issue in Progress
Publisher : Department of Informatics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jmasif.16.2.73574

Abstract

This research employs an artificial intelligence (AI)-driven molecular docking approach to identify potential antidiabetic compounds from Syzygium polyanthum phytochemicals targeting the α-glucosidase enzyme. The docking simulations were conducted using the PLANTS software, which utilizes an ant colony optimization (ACO) algorithm, a nature-inspired AI technique that mimics the foraging behavior of ants to explore ligand binding conformations efficiently. PLANTS integrates multiple empirical scoring functions, including ChemPLP, to evaluate protein-ligand interactions by modeling steric complementarity, hydrogen bonding, and torsional potentials, enabling accurate prediction of binding affinities. The protein structure with PDB code 2JKE was validated with a root-mean-square deviation (RMSD) of 0.2912 Å, confirming the reliability of the docking protocol. Screening results revealed seven phytochemical compounds Hexadecanoic acid 2-hydroxy-1-(hydroxymethyl), Methyl oleate, Methyl palmitate, Phytol, 9,12,15-Octadecatrien-1-ol, Nerolidol, and Eicosane exhibited lower docking scores (-96.2919 to -80.5188) than both the reference drug miglitol (-80.2642) and the native ligand (-77.2910), indicating stronger and more stable binding to the α-glucosidase active site. These findings suggest that the identified compounds have superior theoretical inhibitory potential compared to miglitol, a clinically used α-glucosidase inhibitor. The AI-based in silico screening using PLANTS thus provides a powerful, cost-effective strategy for accelerating antidiabetic drug discovery by prioritizing promising natural compounds for further experimental validation.

Page 19 of 20 | Total Record : 196

 16   17   18   19   20 

Filter by Year

2010 2025


Reset
Filter By Issues
All Issue Vol 16, No 1 (2025): May 2025 Vol 16, No 2 (2025): Issue in Progress Vol 15, No 2 (2024): November 2024 Vol 15, No 1 (2024): May 2024 Vol 14, No 2 (2023): JURNAL MASYARAKAT INFORMATIKA Vol 14, No 1 (2023): JURNAL MASYARAKAT INFORMATIKA Vol 13, No 2 (2022): JURNAL MASYARAKAT INFORMATIKA Vol 13, No 1 (2022): JURNAL MASYARAKAT INFORMATIKA Vol 12, No 2 (2021): JURNAL MASYARAKAT INFORMATIKA Vol 12, No 1 (2021): JURNAL MASYARAKAT INFORMATIKA Vol 11, No 2 (2020): JURNAL MASYARAKAT INFORMATIKA Vol 11, No 1 (2020): JURNAL MASYARAKAT INFORMATIKA Vol 10, No 2 (2019): JURNAL MASYARAKAT INFORMATIKA Vol 10, No 1 (2019): JURNAL MASYARAKAT INFORMATIKA Vol 9, No 2 (2018): JURNAL MASYARAKAT INFORMATIKA Vol 9, No 1 (2018): JURNAL MASYARAKAT INFORMATIKA Vol 8, No 2 (2017): JURNAL MASYARAKAT INFORMATIKA Vol 8, No 1 (2017): JURNAL MASYARAKAT INFORMATIKA Vol 7, No 2 (2016): JURNAL MASYARAKAT INFORMATIKA Vol 7, No 1 (2016): JURNAL MASYARAKAT INFORMATIKA Vol 6, No 12 (2015): JURNAL MASYARAKAT INFORMATIKA Vol 6, No 11 (2015): JURNAL MASYARAKAT INFORMATIKA Vol 5, No 10 (2014): JURNAL MASYARAKAT INFORMATIKA Vol 5, No 9 (2014): JURNAL MASYARAKAT INFORMATIKA Vol 4, No 8 (2013): JURNAL MASYARAKAT INFORMATIKA Vol 4, No 7 (2013): JURNAL MASYARAKAT INFORMATIKA Vol 3, No 6 (2012): JURNAL MASYARAKAT INFORMATIKA Vol 3, No 5 (2012): JURNAL MASYARAKAT INFORMATIKA Vol 2, No 4 (2011): Jurnal Masyarakat Informatika Vol 2, No 3 (2011): Jurnal Masyarakat Informatika Vol 1, No 2 (2010): Jurnal Masyarakat Informatika Vol 1, No 1 (2010): Jurnal Masyarakat Informatika More Issue