cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota yogyakarta,
Daerah istimewa yogyakarta
INDONESIA
International Journal of Informatics and Communication Technology (IJ-ICT)
Published by Institute of Advanced Engineering and Science
ISSN : 22528776     EISSN : 27222616     DOI : -
Core Subject : Science,
Computer Science & IT
International Journal of Informatics and Communication Technology (IJ-ICT) is a common platform for publishing quality research paper as well as other intellectual outputs. This Journal is published by Institute of Advanced Engineering and Science (IAES) whose aims is to promote the dissemination of scientific knowledge and technology on the Information and Communication Technology areas, in front of international audience of scientific community, to encourage the progress and innovation of the technology for human life and also to be a best platform for proliferation of ideas and thought for all scientists, regardless of their locations or nationalities. The journal covers all areas of Informatics and Communication Technology (ICT) focuses on integrating hardware and software solutions for the storage, retrieval, sharing and manipulation management, analysis, visualization, interpretation and it applications for human services programs and practices, publishing refereed original research articles and technical notes. It is designed to serve researchers, developers, managers, strategic planners, graduate students and others interested in state-of-the art research activities in ICT.
Arjuna Subject : -
Articles 601 Documents
 57   58   59   60   61 
A multi-cancer detection framework using deep learning and hybrid machine learning approaches Karan Singh; Amruta Pawar; Drishya Tomar; Amrita Yadav; Aditi Chhabria; Vaibhav Narawade
International Journal of Informatics and Communication Technology (IJ-ICT) Vol 15, No 3: September 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijict.v15i3.pp1443-1452

Abstract

The diagnostic solutions offered by the present artificial intelligence (AI) solutions suffer from non-generalizability and heavy reliance on complex models. In an attempt to solve these issues, we propose a lightweight yet versatile method consisting of a combination of ResNet50 transfer learning and hybrid machine learning. Image features are extracted using dermoscopy, magnetic resonance imaging (MRI), and histopathological images. These are subjected to principal component analysis (PCA) dimensionality reduction followed by classification using support vector machine (SVM), random forest (RF), logistic regression (LR), and XGBoost algorithms. This segregation of the two processes improves efficiency. The hybrid approach using ResNet50 + LR yielded an accuracy of 91.01% in the case of breast cancer detection compared to 86.26% of a baseline convolutional neural network (CNN). Also, ResNet50 gave an accuracy of 96.61% in diagnosing skin cancer. Custom CNN provided an accuracy of 99.42% for lung cancer and 96.33% for brain tumor detection.
Advanced materials for crosstalk and power optimization in TSV-enabled 3D ICs Tappeta Chinna Sanjeeva Rayudu; Merrin Prasanna Nagadasari
International Journal of Informatics and Communication Technology (IJ-ICT) Vol 15, No 3: September 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijict.v15i3.pp1143-1153

Abstract

The continued scaling of semiconductor devices has exposed the limitations of traditional two-dimensional (2D) integrated circuit architectures. To address performance bottlenecks and interconnect constraints, the industry is increasingly adopting three-dimensional (3D) integration technologies. through-silicon vias (TSVs) are a fundamental enabler of this advancement, facilitating vertical signal transmission between stacked silicon layers. Despite their benefits, TSVs face critical challenges related to crosstalk, power dissipation, and signal delay issues that are especially pronounced in dense via arrays. This research explores the use of multi-walled carbon nanotube (MWCNT) based TSVs insulated with different dielectric liners, including silicon dioxide (SiO₂), PPC, polyimide, and benzocyclobutene (BCB). HSPICE simulations are used to evaluate crosstalk noise, power dissipation, power delay product (PDP), and energy delay product (EDP) across varying TSV pitches. Among the materials studied, BCB demonstrates the most promising results. Specifically, MWCNT TSVs with BCB at a 10,000 μm pitch achieve up to 58% reduction in functional crosstalk, 75% in dynamic crosstalk, 78% in power dissipation, and a 52% improvement in PDP compared to single-walled CNT (SWCNT) based TSVs. These findings confirm the suitability of combining MWCNT cores with low-k BCB liners for enhancing performance, energy efficiency, and signal reliability in advanced 3D integrated circuits.
Navigating digital parenting: a bibliometric exploration of trends on children’s digital soothing practices Rita Wong Mee Mee; Noor Hanim Harun; Lim Seong Pek; Suzulaikha Mohamed; Tengku Shahrom Tengku Shahdan; Nurul Asyiqin Jalil; Anisa Ahmad; Tirzah Zubeidah Zachariah
International Journal of Informatics and Communication Technology (IJ-ICT) Vol 15, No 3: September 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijict.v15i3.pp1431-1442

Abstract

The digital age has transformed parenting practices, with an increasing reliance on digital devices for managing children’s behavior, particularly as calming tools. This study addresses the growing phenomenon of digital parenting, highlighting its implications on child development and family dynamics. Despite the benefits of digital media, concerns persist regarding its overuse for emotional regulation, which may impede children’s self-regulation skills and parent-child interactions. This study aims to explore the evolution of research on digital parenting using bibliometric analysis. A comprehensive dataset was extracted from the Scopus database, focusing on publications from 2020 to 2024 within the Social Sciences domain. The inclusion criteria included peer-reviewed, open-access articles written in English. A systematic methodology ensured the analysis of performance metrics, trends, and co-authorship patterns. Results indicate a significant increase in scholarly attention to digital parenting, with 837 articles meeting the inclusion criteria. Leading contributions emerged from journals such as Sustainability Switzerland and Education Sciences, with prolific authors and institutions from the United Kingdom and the United States dominating the field. The analysis underscores the interdisciplinary nature of the topic, reflecting contributions from education, media studies, and child development. This study offers valuable theoretical insights and practical recommendations, emphasizing balanced digital media use and informed parenting strategies to foster healthier family dynamics.
AI-powered cardiovascular risk prediction using deep learning images in IoT-blockchain systems Deepika Prabhakar; Agusthiyar Ramu
International Journal of Informatics and Communication Technology (IJ-ICT) Vol 15, No 3: September 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijict.v15i3.pp1016-1025

Abstract

The increasing prevalence of cardiovascular diseases (CVDs) necessitates the development of intelligent, secure, and scalable diagnostic systems capable of accurate and early disease prediction. The importance of this research is to develop a robust and secure system for predicting CVD risk from echocardiogram imaging integrated within an internet of things (IoT) framework and enhanced by blockchain technology. Due to non-invasive feature identification problems and dimensionality, prediction accuracy is degraded due to higher false positives, which leads to lower precision and recall rates. To resolve this problem, implement AI-powered CVD risk prediction based on smart-featured deep learning in Echocardiogram images for an IoT-blockchain environment. The first phase contains data analysis echocardio-dataset vision transformation technique is functional to find the risk level of the disease. The adaptive gaussian filter is applied for normalization process and design a spread-spectral canny edge morphological segmentation and SURF-scaled invariant feature selection for dimensionality scaling. Then, visual geometry network (VGNet) convolutional neural network (CNN) is applied for disease classification. In second phase, the advanced blockchain technology will provide a decentralized and immutable record of patient data, thereby ensuring data integrity and security. The proposed system produces higher performance by analysing the sensitivity specificity as well by ensuring the disease detection level. The blockchain provides higher security to safe in repository for image data for carrying sensitive data with a platform for sharing and validating predictive insights among healthcare providers, researchers, and patients, thus fostering collaborative healthcare efforts.
Early detection of vascular streak dieback (VSD) disease in cocoa plants using deep learning Dewi Marini Umi Atmaja; Arif Rahman Hakim; Fadhil Rozi Hendrawan; Komang Diah Devi Pramesty; Naufal Fadhilah Fitrah; Faiz Rochmatullah Widhaputra
International Journal of Informatics and Communication Technology (IJ-ICT) Vol 15, No 3: September 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijict.v15i3.pp1087-1096

Abstract

Vascular streak dieback (VSD), caused by Ceratobasidium theobromae, poses a significant threat to cocoa (Theobroma cacao) production, leading to substantial yield losses and plant mortality. Early detection is critical to mitigate disease spread and reduce economic impact. While convolutional neural network (CNN) architectures like VGG-16 and ResNet-50 excel in leaf disease detection, no prior studies address stem-based VSD symptomatology where the disease originates in vascular tissues. This study presents the first CNN specifically developed for cocoa stem VSD detection, achieving 99.16% test accuracy with a lightweight architecture that outperforms VGG16/ResNet50 in both accuracy and mobile inference speed. A novel dataset of 215 cocoa stem images was curated and augmented for robustness. Additional evaluation metrics, including precision, recall, specificity, and F1-score, further confirm the reliability of the model. The model was successfully converted into TensorFlow Lite (TFLite) format, enabling deployment on mobile devices for real-time disease detection. This study highlights the potential of integrating deep learning into mobile and drone-based agricultural systems to support precision farming and early intervention strategies.
Smart drones for human detection in disaster response Menakadevi Nanjundan; Y. L. Ajay Kumar; V. R. Seshagiri Rao; Nagarjuna Telagam; Seetha Chaithanya; Manikadan S.
International Journal of Informatics and Communication Technology (IJ-ICT) Vol 15, No 3: September 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijict.v15i3.pp1179-1187

Abstract

Natural disasters require swift, coordinated responses to minimise human casualties and infrastructure damage. This paper presents a novel AI-assisted drone system designed to enhance disaster relief efforts through advanced human detection and a distributed emergency Wi-Fi network. This drone system, equipped with state-of-the-art machine learning algorithms and thermal imaging, excels at locating and identifying individuals even in challenging conditions, such as smoke, debris, or low visibility. The drone fleet operates autonomously, dynamically forming an ad-hoc network that adapts to the evolving needs of the disaster zone. By integrating real-time data processing with efficient network management, our system provides a critical lifeline for communication and a powerful tool for rescuers to navigate and respond effectively. The detection and communication times are observed to be within the range of 5 to 8 seconds for this proposed system, which is widely used in disaster response.
Lightweight parallel feedback network based on CRL with policy transfer and enhancement for image super-resolution S V R Manimala; T Kavitha
International Journal of Informatics and Communication Technology (IJ-ICT) Vol 15, No 3: September 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijict.v15i3.pp944-954

Abstract

Image super-resolution (SR) is essential in applications such as surveillance, medical imaging, and remote sensing, but existing deep learning (DL) models often require high computational resources and struggle to recover fine details in lightweight architectures. Although feedback and attention based methods have shown improvements, they still lack an effective combination of efficient feature refinement, edge enhancement, and low parameter complexity. To address this gap, we propose a lightweight parallel feedback network (LPFN) that combines three key components: a feedback block for repeated feature refinement, a dispersion-aware attention residual block (DARB) for highlighting important spatial and channel details, and EdgeNet for edge sharpening for sharper boundaries. These components are supported by curriculum reinforcement learning (CRL), an adaptive training strategy that gradually improves the model’s learning behavior. Instead of relying on a fixed loss function, LPFN uses a dynamically learned global feedback loss to refine reconstruction quality at each stage. Experiments on DIV2K and Flickr2K show that LPFN achieves higher PSNR and SSIMscores while keeping the model lightweight and efficient. This study emphasizes an effective lightweight feedback framework, an enhanced attention and edge-refinement mechanism, and an adaptive learning strategy that improves both accuracy and stability under different degradation conditions.
Neural network-based diagnosis of type 2 diabetes using an iridology approach Alaa Abdulkareem Ahmed; Mohammad Tariq Yaseen
International Journal of Informatics and Communication Technology (IJ-ICT) Vol 15, No 3: September 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijict.v15i3.pp1226-1237

Abstract

The growing global occurrence of type 2 diabetes requires the development of non-invasive and effective diagnostic methods. This work proposes a novel approach to detecting type 2 diabetes using iridology and machine learning (ML) techniques. By analyzing the iris of the right eye, a single region of interest (ROI) corresponding to the head of the pancreas is recognized for feature extraction. A total of 112 statistical and texture features are extracted using gray-level co-occurrence matrix (GLCM) and discrete wavelet transform (DWT) algorithms. Five neural network (NN) models, narrow, medium, wide, bi-layered, and tri-layered are deployed to classify healthy and diabetic people. The models are trained and assessed using a range of k-fold values (2 to 20) to optimize performance. The highest classification accuracy of 83.2% was reached using the narrow neural network (NNN) model at 7-fold cross-validation. This work exhibts the potential of iridology-based ML approaches for non-invasive diabetes diagnosis, providing a promising substitute to traditional blood tests.
Probabilistic inventory modeling for chlorine gas using minitab and python: a comparative study of demand distributions Oki Dwipurwani; Fitri Maya Puspita; Siti Suzlin Supadi; Evi Yuliza
International Journal of Informatics and Communication Technology (IJ-ICT) Vol 15, No 3: September 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijict.v15i3.pp1026-1037

Abstract

The availability of chlorine gas (Cl2) is a critical component in the drinking water disinfection process at the regional drinking water company (PDAM), as it plays a vital role in ensuring microbiological safety. Disruptions in the chlorine gas supply may lead to interruptions in water distribution and pose significant public health risks. This study investigates the application of a probabilistic (Q, r) inventory model for managing chlorine gas stock, incorporating several probability distributions that satisfy the underlying model assumptions. The resulting optimal inventory policies derived from each distribution are then compared. Chlorine gas demand forecasting is also performed using the seasonal autoregressive integrated moving average (SARIMA) model. The objective of this research is to generate an optimal inventory policy and accurate demand forecasts, with the entire implementation carried out in Python software. The results show that the best model obtainis the SARIMA (0,1,0)(0,1,1)12 model, with a MAPE value of 5.48%, and that the chlorine gas demand data follow normal, gamma, exponential, and erlang probability distributions. The comparison results show that the optimal policy of the gamma probabilistic model provides the best results, as well as being better than Normal and exponential policies in previous studies.
A multi-expert approach to content-based image retrieval using feature fusion and late re-ranking Ali Abdulazeez Mohammed Baqer Qazzaz; Yousif Samer Mudhafar
International Journal of Informatics and Communication Technology (IJ-ICT) Vol 15, No 3: September 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijict.v15i3.pp1376-1384

Abstract

As digital data rapidly grows, content-based image retrieval (CBIR) has become important for optimizing collections of visual data. This work proposes a retrieval framework which operates in two stages and improves accuracy by using systematic fusion of features. In the first stage, first-stage wide-scope descriptors called bag-of-visual-words (BoVW), scattering wavelet transform (SWT), discrete cosine transform (DCT), and principal component analysis (PCA) retrieve initial candidate images. The second stage undertakes detailed re-ordering of candidate images by implementing the local binary pattern (LBP), histogram of oriented gradients (HOG), and singular value decomposition (SVD) descriptors to re-evaluate similarity scores. Each individual descriptor returned results for mean average precision for the top 10 retrieved images (mAP, top-10) of between 0.63 and 0.79 and the fused framework achieved 0.88, which is evidence of the viability of complementary feature integration. These findings support the hypothesis that while multiple descriptors performed well and delivered high retrieval accuracy, hierarchical fusion of multiple handcrafted descriptors does not involve the computational costs associated with deep learning methods.

Page 60 of 61 | Total Record : 601

 57   58   59   60   61 

Filter by Year

2012 2026


Reset
Filter By Issues
All Issue Vol 15, No 3: September 2026 Vol 15, No 2: June 2026 Vol 15, No 1: March 2026 Vol 14, No 3: December 2025 Vol 14, No 2: August 2025 Vol 14, No 1: April 2025 Vol 13, No 3: December 2024 Vol 13, No 2: August 2024 Vol 13, No 1: April 2024 Vol 12, No 3: December 2023 Vol 12, No 2: August 2023 Vol 12, No 1: April 2023 Vol 11, No 3: December 2022 Vol 11, No 2: August 2022 Vol 11, No 1: April 2022 Vol 10, No 3: December 2021 Vol 10, No 2: August 2021 Vol 10, No 1: April 2021 Vol 9, No 3: December 2020 Vol 9, No 2: August 2020 Vol 9, No 1: April 2020 Vol 8, No 3: December 2019 Vol 8, No 2: August 2019 Vol 8, No 1: April 2019 Vol 7, No 3: December 2018 Vol 7, No 2: August 2018 Vol 7, No 1: April 2018 Vol 6, No 3: December 2017 Vol 6, No 2: August 2017 Vol 6, No 1: April 2017 Vol 5, No 3: December 2016 Vol 5, No 2: August 2016 Vol 5, No 1: April 2016 Vol 4, No 3: December 2015 Vol 4, No 2: August 2015 Vol 4, No 1: April 2015 Vol 3, No 3: December 2014 Vol 3, No 2: August 2014 Vol 3, No 1: April 2014 Vol 2, No 3: December 2013 Vol 2, No 2: August 2013 Vol 2, No 1: April 2013 Vol 1, No 2: December 2012 Vol 1, No 1: June 2012 More Issue