Claim Missing Document
Check
Articles

Found 7 Documents
Search

Comparative Analysis of Edge Detection Method on Cardboard Packaging Images Nanik Susanti; Catur Edi Widodo; Arif Setiawan
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
Image-Based Fish Freshness Classification Using Two-Phase Transfer Learning with Deep Learning Fusion Model Ellya Helmud; Catur Edi Widodo; Oky Dwi Nurhayati
Journal of Applied Data Sciences Vol 6, No 4: December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i4.988

Abstract

This study introduces a novel deep learning approach for automated fish freshness classification using image analysis. The objective is to design and validate a Deep Learning Fusion Model that combines the strengths of EfficientNetB0 and InceptionV3 architectures to improve accuracy and robustness in classifying fresh and non-fresh fish. Input images were subjected to extensive augmentation, including RandomFlip, RandomRotation, RandomZoom, RandomContrast, RandomBrightness, and RandomTranslation, applied exclusively to the training dataset to enhance generalization, followed by backbone-specific pre-processing. Extracted features were fused via global average pooling and forwarded to a newly designed classification head with dropout and L2 regularization to mitigate overfitting. A two-phase transfer learning strategy was employed: initially training the classification head with frozen backbones, followed by fine-tuning the backbone layers using the Adam optimizer with a reduced learning rate. To highlight the contribution of the fusion strategy, ablation studies were conducted with single-backbone models. The EfficientNetB0 model achieved 89.17% validation accuracy, 85.83% test accuracy, and an F1-score of 85.69%, while the InceptionV3 model achieved 86.67% validation accuracy, 81.67% test accuracy, and an F1-score of 81.59%. In contrast, the proposed Fusion Model achieved 93.33% validation accuracy, 95.00% test accuracy, and an F1-score of 94.95%. Additional evaluations with confusion matrices, ROC curves, AUC, and precision-recall curves confirmed the model’s superiority. The findings demonstrate that integrating features from diverse CNN architectures enables the model to learn richer representations, resulting in significantly improved classification performance. The novelty of this work lies in the effective fusion of complementary backbones through global average pooling and fine-tuned transfer learning, establishing a human-centric computational approach that offers a reliable solution for practical fish freshness assessment in food safety and market scenarios.
Application of Life Simulation Games in Teaching Network Security and Cryptography Agusta Rakhmat Taufani; Tri Retnaningsih Soeprobowati; Catur Edi Widodo
Journal of Information System and Informatics Vol 7 No 3 (2025): September
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v7i3.1161

Abstract

Information security-related mathematical methods are used in the science of cryptography. A collection of methods that offer information security, cryptography is more than just a means of concealing messages. Using only presentation slides or video links at each meeting, the interaction between lecturers and students via SIPEJAR e-learning hinders the Network Security and Cryptography learning process at the State University of Malang (UM) Information Engineering (IT) Undergraduate Study Program. To help students learn more about the area of encoding using SIPEJAR, a game that explicitly explains cryptography was created using these several challenges as the background. The creation of a cryptographic life simulation game is intended to serve as a teaching and learning aid for lecturers and students. Students are expected to better understand related material in a learning atmosphere that is new, more interesting, opens the horizons of the mind, and is more investigative. After going through the equivalence partitioning testing process, in general this system produces a total percentage of 100% in system item test success in the testing process of the 6 item tests carried out and a respondent satisfaction percentage of 84.3%. Thus, the system is running according to the prototype design.
Global Research Trends and Map on Machine Learning Applications in Stunting Detection in Vulnerable Populations: A Bibliometric Analysis Otong Saeful Bachri; Catur Edi Widodo; Oky Dwi Nurhayati
Journal of Information System and Informatics Vol 7 No 3 (2025): September
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v7i3.1248

Abstract

Stunting and malnutrition continue to be significant public health challenges, particularly in low-income and rural populations. With the growing reliance on data-driven strategies in public health, machine learning (ML) has emerged as a promising tool for identifying, classifying, and predicting conditions related to undernutrition. This study presents a bibliometric analysis of global research from 2019 to 2025, focusing on the application of ML techniques—such as clustering, support vector machines (SVM), and random forest—in addressing malnutrition and stunting. A total of 417 Scopus-indexed publications were analyzed using Biblioshiny (R) to assess research trends, key themes, influential authors, prominent journals, and thematic evolution. The analysis reveals a consistent growth rate of 10.72% in publications, with notable contributions from China and other low- and middle-income countries. Keyword mapping highlights that “machine learning,” “spatial analysis,” and “stunting” are central to the research, although they remain areas for further development. Thematic evolution indicates a shift towards more integrated, context-aware approaches, with a growing focus on built environments and vulnerable populations. The study concludes that while ML holds significant promise for advancing decision-making in child health and nutrition, its impact will depend on continued methodological refinement and effective implementation within public health systems.
Mapping Artificial Intelligence for Personalised Learning based on Learning Style: Scopus-Based Bibliometric Analysis (2006-2026) Heliawati Hamrul; Catur Edi Widodo; Bayu Surarso
Journal of Information System and Informatics Vol 8 No 5 (2026): October
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i5.1752

Abstract

The aims of this study is to conduct a bibliometric analysis of the development of learning style-based personalisation. The rapid advancement of AI-based learning personalisation has been accompanied by growing research attention to the role of learning style in the modern learning ecosystem. The research methodology involves a bibliometric analysis of 604 Scopus-indexed publications from the period 2006 to 2026 that were analyzed and visualized using Biblioshiny, VOSviewer and Open Refine. The results of the study indicate a significant increase in publications beginning in 2020, reflecting growing research attention to AI-based personalisation., the keywords patterns indicate an increasing association between learning style and machine learning analytics. Random Forest is one of the most commonly reported machine learning methods in the literature to identify learning styles. The findings further indicate that AI and learning style are increasingly discussed with the same research landscape. This study contributes by mapping the evolution of this field and demonstrating the convergence of educational theory and computational approaches. Further research should be extended beyond the Scopus database, combining bibliometric analysis and systematic literature review, and investigating the integration of learning styles with learner behavioral and cognitive data in AI-powered personalised learning systems.
Mapping E-Readiness Dimensions for Digital Village Development: A Systematic Literature and Bibliometric Review Yenni Fatman; Catur Edi Widodo; Dinar Mutiara Kusumo Nugraheni
Journal of Information System and Informatics Vol 8 No 5 (2026): October
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i5.1787

Abstract

Digital village development is a key strategy for narrowing the digital gap between rural and urban areas, yet research on e-readiness in this context remains fragmented and predominantly shaped by technical perspectives. This study maps e-readiness dimensions, identifies research trends, and uncovers research gaps in digital villages scholarship. A Systematic Literature Review (SLR) following the PRISMA 2020 framework was conducted on 55 articles published between 2020 and 2026, combining thematic synthesis with an author-keyword co-occurrence bibliometric analysis using VOSviewer. Five principal dimensions of e-readiness were identified: infrastructure and technology, human resources and digital literacy, social and cultural factors, governance and policy, and psychological and individual dimensions. The infrastructure and technology dimension remains the most dominant, reflecting a persistent technical bias not yet matched by attention to social, governance, and psychological readiness factors. Bibliometric analysis shows the research theme continues to be dominated by keywords such as digital transformation, digitalization, digital readiness, and smart village, while social aspects, governance, citizen participation, psychological factors, and rural development outcomes remain relatively underexplored. This research offers a multidimensional mapping of e-readiness for digital village development, framed using a socio-technical readiness perspective as a conceptual synthesis that requires further empirical validation.
Clustering-Based Data Mining for Healthcare Decision Support Systems: A Systematic Review Francka Sakti Lee; Catur Edi Widodo; Johanes Fernandes Andry
Journal of Information System and Informatics Vol 8 No 5 (2026): October
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i5.1801

Abstract

Clustering can organize heterogeneous healthcare data into clinically or operationally meaningful groups, but evidence of real decision-support use remains uneven. This systematic review examines healthcare domains, data types, clustering methods, validation practices, and implementation gaps in clustering-based Healthcare Decision Support Systems (DSS). Following PRISMA 2020, Scopus records published from 2015 to 2025 were screened using predefined eligibility criteria. Eighty-four records were identified; 36 remained after the open-access filter, 19 full-text reports were assessed, and 10 primary empirical studies were included. The studies covered fraud auditing, ICU profiling, chronic-disease risk and transition analysis, gestational-diabetes support, trauma pathways, radiology text, patient segmentation, and smart-home activity recognition. K-Means was the most frequently reported method, followed by Markov-based approaches, while other clustering techniques appeared less often. Most studies relied on retrospective, internal, or expert-based validation; only one reported prospective evaluation of a deployed web-based clinical DSS. Overall, clustering shows clear analytical value, but evidence for routine clinical deployment and patient-outcome improvement remains limited.