cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Arief Hidayat
Contact Email
arief.hidayat@unwahas.ac.id
Phone
+628156529309
Journal Mail Official
jinformatika@unwahas.ac.id
Editorial Address
JL. Menoreh Tengah X / 22, Sampangan, Gajahmungkur, Sampangan, Gajahmungkur, Kota Semarang, Jawa Tengah 50232
Location
Kota semarang,
Jawa tengah
INDONESIA
Jurnal Informatika dan Rekayasa Perangkat Lunak
Published by Universitas Wahid Hasyim Semarang
ISSN : 26562855     EISSN : 26855518     DOI : http://dx.doi.org/10.36499/jinrpl
Core Subject : Science,
Computer Science & IT
Journal of Informatics and Software Engineering accepts scientific articles in the focus of Informatics. The scope can be: Software Engineering, Information Systems, Artificial Intelligence, Computer Based Learning, Computer Networking and Data Communication, and Multimedia.
Arjuna Subject : Ilmu Komputer (semua kategori) - Perangkat Lunak
Articles 244 Documents
 21   22   23   24   25 
Comparative Performance Analysis of ML, DL, and Transformer Models for Sentiment Classification of Indonesian Mobile Banking User Reviews Bismi, Waeisul; Qomaruddin, Muhammmad; Marlina, Siti
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 8 No. 1 (2026): Maret
Publisher : Universitas Wahid Hasyim

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

Abstract

The rapid development of digital technology has encouraged the adoption of mobile banking applications in Indonesia, but it has also led to an increase in user complaints and reviews regarding performance and ease of use. This study aims to conduct a comparative analysis of the performance of Machine Learning, Deep Learning, and Transformer (IndoBERT) models in classifying the sentiment of user reviews of Indonesian-language mobile banking applications. Data was collected through web scraping from the Google Play Store on ten leading banking applications in Indonesia with a total of 200,000 reviews. After going through the preprocessing stages of cleaning, normalisation, tokenisation, and stemming, automatic labelling was carried out based on ratings into three sentiment classes: positive, neutral, and negative. Machine learning models (Naïve Bayes, Logistic Regression, Random Forest, and SVM) were built using TF-IDF feature representation, while deep learning models (LSTM, Bi-LSTM, GRU, and CNN) utilised 128-dimensional word embeddings. The Transformer-based IndoBERT model was fine-tuned with a sequence classification configuration. The evaluation used accuracy, precision, recall, and weighted F1-score metrics, accompanied by an analysis of training and testing time efficiency. The results show that the Bi-LSTM model performs best with an accuracy of 83.47% and an F1-score of 80.78%, followed by CNN (83.11%) and SVM (82.85%), while IndoBERT records an accuracy of 81.73% with a precision of 76.96%. In terms of efficiency, Logistic Regression showed an optimal balance between accuracy and training time (27.7 seconds), while deep learning and transformer models required higher computational resources. This study emphasises the importance of model selection based on requirements, between maximum accuracy and computational efficiency, and enriches the literature on Indonesian sentiment analysis in the domain of digital financial services.
Transfer Learning-Based Convolutional Neural Network for Classifying Organic and Recyclable Waste Nafiiyah, Nur; Zulkarnaen, M. Ari; Harjoko, Agus; Hidayanto, Achmad Nizar
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 8 No. 1 (2026): Maret
Publisher : Universitas Wahid Hasyim

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

Abstract

The problem of waste management continues to increase along with population growth and lifestyle changes, highlighting the need for a fast and accurate waste classification system to support recycling processes. This study implements a transfer learning approach using seven Convolutional Neural Network (CNN) architectures: MobileNet, MobileNetV2, Xception, EfficientNetB0, VGG16, VGG19, and ResNet50 to classify waste into two categories: organic and recyclable. Each model is modified by adding a Global Average Pooling layer followed by a fully connected layer with 256 neurons before the output layer. The models are trained twice using 30 epochs, a batch size of 2, the Adam optimizer, and a learning rate of 0.0001. Experimental results show that ResNet50 achieves the best performance, with an accuracy of 89.84%, precision of 96.34%, recall of 82.82%, and an F1-score of 89.07%, followed by MobileNet with an accuracy of 89.25%. In contrast, Xception demonstrates the lowest performance, with an accuracy of 83.81%. Analysis of training and validation curves indicates that ResNet50 and MobileNet exhibit better stability and lower overfitting tendencies compared to other models.
Identification of Facial Wrinkles using Gabor Filters and the Naïve Bayes Algorithm Munawir, Munawir; Harahap, Siti Rafah Sa`dia; Akram, Rizalul
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 8 No. 1 (2026): Maret
Publisher : Universitas Wahid Hasyim

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

Abstract

Facial Wrinkles are one of the key indicators in identifying signs of aging on the skin. Detecting facial wrinkles poses a challenge in image processing due to their complex, coarse texture, which is often difficult for computers to recognize, especially under varying lighting conditions, camera angles, and facial expressions. This study focuses on the application of features using Gabor Filters for the texture feature extraction, with the final results determined by the Naïve Bayes classification algoritm. In this study, 200 facial images were used, divided into two clases, with 100 images per class serving as training data. For the test data, 100 facial images were used, consisting of 50 wrinkled facial images and 50 non-wrinkled facial images. Based on the test result using the Confusion Matrix, the accuracy was 74%, precision 80%, recall 64% and F1-Score 71%. These results indicate that the combination of Gabor filters and Naïve Bayes is quite effective in recognizing wrinkle patterns on the face based on extracted texture feature, and can serve as a faoundation for developing more accurate facial wrinkle detection systems in the future.
Comparison of Blind Search and Heuristic Search Algorithms in Finding Solutions to the 8-Puzzle Game: Introduction to Endemic Wallacea Animals Muchtar, Mutmainnah
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 8 No. 1 (2026): Maret
Publisher : Universitas Wahid Hasyim

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

Abstract

Search algorithms play a crucial role in artificial intelligence, particularly in solving pathfinding and combination problems such as the 8-Puzzle game. This study presents the development of a web-based 8-Puzzle game designed to introduce endemic Wallacea fauna by comparing the performance of Blind Search and Heuristic Search algorithms. The system is built using HTML, CSS, and JavaScript, developed with Notepad++, and executed using a standard web browser. Four search algorithms are implemented, consisting of two blind search methods (Breadth First Search and Depth First Search) and two heuristic search methods (Greedy Best First Search and A*). Performance testing is conducted using three scenarios: testing easy puzzle configurations, testing high-complexity configurations, and cross-platform testing on desktop and mobile devices. The experimental results show that heuristic search consistently outperforms blind search. A* produces optimal solution paths with fewer expanded nodes, while Greedy achieves the fastest execution time. In contrast, DFS performs the worst, requiring in-depth node exploration and long execution time. Multi-platform evaluation shows that the game runs quite smoothly on both desktop and mobile devices. These results indicate that heuristic search, especially A*, is the most effective method for solving the educational 8-puzzle game of Wallacea endemic animal recognition.
A Systematic Review of Machine Learning and Deep Learning Techniques for Deepfake Image Detection: Trends, Challenges, and Future Directions Samuel Rhesa; Aditiya Hermawan
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 8 No. 1 (2026): Maret
Publisher : Universitas Wahid Hasyim

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

Abstract

The rapid development of deep learning based face manipulation techniques has produced synthetic images that are increasingly realistic and visually indistinguishable from authentic ones. The deepfake phenomenon poses serious challenges to digital information authenticity and cybersecurity. This research presents a Systematic Literature Review (SLR) of publications from the 2020–2025 period to map trends, methodological approaches, and key challenges in machine learning and deep learning based image deepfake detection. Through an analysis of 24 empirical studies, this review identifies a shift in research direction from conventional convolutional architectures toward hybrid and attention based approaches that emphasize efficiency, adaptivity, and cross domain generalization. Findings show that although recent models such as Vision Transformer and hybrid CNN–LSTM are capable of achieving high accuracy under controlled conditions, their performance remains limited when tested on new domains. Key challenges identified include limited generalization against new manipulation types, vulnerability to image distortion and compression, and low transparency in model decision-making. This study fills research gaps by providing a comprehensive methodological map of architectural evolution, feature representation strategies, and evaluation metrics. Theoretically, this research expands the understanding of deepfake detection research dynamics, while practically, the results provide direction for developing adaptive, transparent, and efficient detection systems for real-time implementation.
Development of the UI/UX for the Madrasah Adaptation E-Module Using the Design Thinking Method Widjaja, Stephanus; Putro Wicaksono, Adityo; Rozacky, Abdul; Nikolaus Putra, Farrell Feodora; Musoffa, Chanif
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 8 No. 1 (2026): Maret
Publisher : Universitas Wahid Hasyim

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

Abstract

Technological developments have brought major changes in the world of education, especially in the development of digital learning media. This study aims to design a user interface and user experience on a mobile-based habituation e-module application at MA Taqwiyatul Wathon as a solution to the limitations of physical modules that have been used in students' daily habituation activities. The method used is Design Thinking which consists of five stages, namely Empathize, Define, Ideate, Prototype, and Test. The research process involved three groups of users, namely students, teachers, and admins through observation, interviews, and direct testing of the High-Fidelity Prototype (Hi-fi) using the In-Person Usability Testing method based on a Likert scale (1–5). The test results showed a Usability Score of 91.7 for students, 97.2 for teachers, and 90 for admins, with the category "Excellent". These results indicate that the designed application is easy to use, has a clear display, and is efficient in navigation. Thus, the habituation e-module application is worthy of further development to support digital learning and habituation activities in the madrasa environment.
Design of an MSME Information System for Via Fresh Vegetables using the Unified Process Method Satria, Satria; Wijayanti, Ikka Novia
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 8 No. 1 (2026): Maret
Publisher : Universitas Wahid Hasyim

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

Abstract

Technology plays a crucial role in facilitating human activities, including in the agribusiness sector. Vegetables, as a primary food commodity, require a fast and accurate sales system to meet consumer demands. The Via Fresh Vegetables store still applies conventional sales methods, resulting in suboptimal sales management and customer service. The purpose of this study is to develop a web-based online vegetable sales information system that can assist the store in improving operational efficiency, information accuracy, and expanding its marketing reach. This study uses the Unified Process method, which applies iterative and incremental stages to understand requirements, design, build, and test the system repeatedly. This approach was chosen because it can produce a system that better meets user needs. The result of this research is a web-based sales information system that provides features such as product management, online ordering, transaction history, and customer management. The developed system can help Via Fresh Vegetables improve the effectiveness of its sales process, accelerate services, and provide more accurate information access for customers.
Comparative Analysis of Edge Detection Method on Cardboard Packaging Images Susanti, Nanik; Widodo, Catur Edi; Setiawan, Arif
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 8 No. 1 (2026): Maret
Publisher : Universitas Wahid Hasyim

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

Abstract

Edge detection is a crucial process in digital image processing, particularly in automated visual inspection systems for packaging quality control. Cardboard packaging used in traditional food products often experiences deformation due to mechanical stress or poor distribution, thus requiring a reliable damage detection method. This study aims to compare the performance of five classical edge detection algorithms, Canny, Sobel, Prewitt, Roberts, and Laplacian of Gaussian (LoG), in identifying contours and structural deformations in product packaging images. Data were obtained through the acquisition of five cardboard images using a high-resolution smartphone camera. The processing steps include image conversion to grayscale, application of the edge detection algorithm, and quantitative evaluation of the results. The evaluation was conducted using three main metrics: Peak Signal-to-Noise Ratio (PSNR), Mean Squared Error (MSE), and processing time. The results show that the Sobel algorithm provides the best performance, with the highest PSNR and lowest MSE values consistently, despite having the longest processing time. In contrast, the Canny algorithm shows the highest efficiency in speed, but with low detection quality. Prewitt and LoG yielded relatively balanced intermediate results between accuracy and efficiency, while Roberts performed moderately across all aspects. These findings indicate that algorithm selection should be tailored to system requirements. Sobel is more appropriate for applications that prioritise accuracy, while Canny is recommended for real-time systems. This study provides an initial basis for the development of lightweight visual inspection systems in the traditional food industry and the MSME sector
Vehicle Routing Problem (VRP) Approaches for Waste Collection Optimization: A Systematic Literature Review Bunga, Munengsih; Mochamad Agung Wibowo; Sutikno
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 8 No. 1 (2026): Maret
Publisher : Universitas Wahid Hasyim

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

Abstract

An effective route is necessary because waste transport is an important part of the urban waste management system. The most popular technique is the Vehicle Routing Problem (VRP) to maximize fleet movement while reducing risk, time, cost, and energy. To identify developments in VRP models in the context of waste transportation, this study used a Systematic Literature Review (SLR), conducted in accordance with PRISMA guidelines, to review 96 articles. The SLR results indicate that VRP models have evolved from basic models such as CVRP and VRPTW to more constraint-rich models such as MTVRP, ARP, risk-aware VRP, EVRP, and multi-objective VRP. Hybrid and metaheuristic algorithms such as ALNS, GA, ACO, and SA have become the most popular in solving this problem due to their ability to handle large problem sizes and high operational complexity. Route planning can now utilize real-time data thanks to the integration of IoT, WSN, and GIS technologies. Overall, these results indicate that VRP research in waste transport is moving towards smarter, more adaptive, and sustainable approaches. These results also enable the development of more contextual models and algorithms in the future.
Comparative Approaches to Clustering for Profiling Students in Educational Data Mining Azizah, Noor; Kusworo Adi; Catur Edi Widodo
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 8 No. 1 (2026): Maret
Publisher : Universitas Wahid Hasyim

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

Abstract

This study aims to compare the performance of five clustering algorithms, a K-Means, K-Medoids, Fuzzy C-Means (FCM), DBSCAN, and Gaussian Mixture Model (GMM) in profiling 239 students using quantitative data. The methodology includes data collection, refinement, transformation, application of clustering algorithms, and evaluation using the Silhouette Score, Davies–Bouldin Index, and execution time. The results indicate that K-Means provides the most balanced performance, achieving the highest Silhouette score with well-defined cluster separation. K-Medoids and GMM demonstrate competitive performance, while DBSCAN excels in detecting outliers but produces an excessive number of clusters, limiting its interpretability for profiling. FCM performs the weakest due to poor cluster separability. Overall, K-Means is recommended as the primary approach for student profiling, while other algorithms may complement specific analytical needs.

Page 24 of 25 | Total Record : 244

 21   22   23   24   25 

Filter by Year

2019 2026


Reset
Filter By Issues
All Issue Vol. 8 No. 1 (2026): Maret Vol. 7 No. 2 (2025): September Vol. 7 No. 1 (2025): Maret Vol. 6 No. 2 (2024): September Vol 6, No 2 (2024): September Vol 6, No 1 (2024): Maret Vol 5, No 2 (2023): September Vol 5, No 1 (2023): Maret Vol 4, No 2 (2022): September Vol 4, No 1 (2022): Maret Vol 3, No 2 (2021): September Vol 3, No 1 (2021): Maret Vol 2, No 2 (2020): September Vol 2, No 1 (2020): Maret Vol 1, No 2 (2019): September Vol 1, No 1 (2019): Maret More Issue