187 hasil
Menampilkan 1–20 · 1,03 detik · RSS
IJCI International Journal of Computers and Information (2026)
ISSN 2735-3257 · Minufiya University, Faculty of Computers and Information · 187 artikel di indeks
-
Artikel Jurnal
Digital twin and Smart City Technologies in Disaster Management: A PRISMA-Based Systematic Review
The increasing frequency and severity of natural and human-induced disasters have highlighted the need for advanced technologies that extend beyond conventional disaster risk management (DRM) approaches. This study presents a PRISMA-based systematic review of the integration of Digital Twin (DT)…
-
Artikel Jurnal
Mitigating Backdoor Attacks in Federated Learning Systems Under Non‑IID Data: A Comprehensive Survey
Federated Learning (FL) enables collaborative model training while preserving data privacy, but its decentralized nature exposes it to backdoor attacks, where malicious clients inject poisoned updates that embed hidden triggers into the global model. This threat is significantly amplified under…
-
Artikel Jurnal
Semantic-Enhanced Link Prediction for COVID-19 Contact Networks: A Graph-Based Approach with Repetition Sampling
Link prediction in dynamic contact networks is a vital task in modeling and controlling the spread of infectious diseases. However, semantic redundancy—where nodes with similar meanings appear under different surface forms—often distorts the underlying graph structure, reducing the effectiveness of…
-
Artikel Jurnal
Lightweight Multi-Modal Attention U-Net for Micro-Lesion Segmentation in MS
Accurate detection of micro-lesions in Multiple Sclerosis (MS) MRI remains a persistent clinical challenge due to extreme class imbalance, low boundary contrast, and the computational demands of existing volumetric deep learning frameworks that limit their deployment in resource-constrained…
-
Artikel Jurnal
Interpreting AI Models-based Structured Data: A Survey of Local Model-Agnostic Explanation Methods
Modern Artificial Intelligence (AI), and Machine Learning (ML) models are widely used in numerous domains. However, their decision-making-based processes are complex for human understanding and interpretation. Such lack of transparency creates serious challenges, especially in sensitive domains as…
-
Artikel Jurnal
A New Hybrid Transformer-Based Framework for Automated Wheat Disease Classification
Wheat production is critically threatened by a wide spectrum of foliar diseases that substantially reduce yield and compromise global food security. Conventional visual inspection and classical machine learning approaches are limited by subjectivity, scalability constraints, and weak generalization…
-
Artikel Jurnal
A Hybrid Graph-Based Deep Learning Framework for Risk Assessment in Autonomous Vehicles
An essential part of developing and validating autonomous vehicles (AVs) is risk assessment of driving situations, which has a direct impact on decision-making and safety. Conventional techniques, including drivable area-based methods, offer assessments that are interpretable and scenario-adaptive…
-
Artikel Jurnal
Hybrid Aggregation Strategies in Federated Learning for Enhanced Lung Cancer Detection
Federated Learning (FL) offers a privacy-preserving paradigm for training robust machine learning models on decentralized medical datasets, a critical need in lung cancer detection. However, the inherent data heterogeneity non-IID (non-Independent and Identically Distributed) across different…
-
Artikel Jurnal
Deepfake Detection: A Domain-Based Survey of Techniques, Datasets, and Open Challenges
The rapid advancement of deepfake technology, driven by breakthroughs in artificial intelligence (AI), has enabled the development of highly sophisticated tools for manipulating visual and audio content, posing serious societal threats including disinformation, erosion of public trust, and…
-
Artikel Jurnal
Towards Trustworthy Explainable AI: A Quantitative Framework for Evaluating Model Explanations in Lung Cancer Diagnosis
Reliable evaluation of explanation quality is essential before explainable artificial intelligence (XAI) can be safely adopted in clinical decision support. Existing trust scores typically combine multiple criteria into a single composite measure, yet few studies examine whether these scores can…
-
Artikel Jurnal
Hybrid Deep Learning and Extreme Gradient Boost with Visualization for Trash Classification
Waste recycling is essential for a healthy environment and for building a sustainable economy. This paper proposes a hybrid deep learning model that combines deep transfer learning with eXtreme Gradient Boosting (XGBoost) to classify trash in the TrashNet dataset, which contains six categories of…
-
Artikel Jurnal
Enhanced ESRGAN for Single-Image Super-Resolution Multi-Loss Design and Dynamic Training Strategy
Single-image super-resolution (SISR) aims to recover a high-resolution (HR) image from a single low-resolution (LR) input, a task with critical applications in medical imaging, satellite surveillance, digital archiving, and multimedia restoration. While generative adversarial network (GAN)-based…
-
Artikel Jurnal
Hybrid model for brain tumor classification: Merging vision Transformer with various Transfer learning Models.
One of the most dangerous life-threatening conditions is brain tumors. It caused in the brain cells and tissues that grow in some abnormal ways. This abnormal grow may be diagnosis as benign (non-cancerous) or malignant (cancerous). The earlier and more accurate diagnosis acts the critical role in…
-
Artikel Jurnal
Integrating Gamification and Machine Learning for Personalized Support in Education: A Data Driven Approach to Student Motivation and Performance
Gamification has become a widely adopted strategy in education to enhance student motivation, engagement, and performance. While previous studies confirmed its potential, most relied on short-term measures, self-reported data, or outdated evaluation methods. Other works applied machine learning to…
-
Artikel Jurnal
Hybrid Gradient–Adversarial Trust Aggregation for Scalable and Secure Federated Learning
Federated Learning (FL) enables distributed model training without exposing raw data; however, it remains highly vulnerable to backdoor attacks, particularly under non-IID data distributions where statistical heterogeneity complicates reliable detection. This work introduces HyGrad, a hybrid…
-
Artikel Jurnal
Artificial Intelligence-Based Digital Twins: A Systematic Review Integrated with Machine Learning and Deep Learning
The integration of Artificial Intelligence (AI), particularly Machine Learning (ML) and Deep Learning (DL), has significantly enhanced the capabilities of Digital Twins (DTs) by enabling predictive modeling and adaptive intelligence. Collectively, these technologies transform DTs into intelligent…
-
Artikel Jurnal
An Enhanced Technique for Building Damage Assessment using Satellite Images
Rapid assessment of disaster-damaged buildings is essential for effective disaster recovery and response. However, the traditional methods of building damage assessment are often labour-intensive and time-consuming. In this study, an ensemble deep learning approach is proposed that combines…
-
Artikel Jurnal
A Unified Framework for Hyperspectral Image Classification Integrating LDA and Swin Transformers
Hyperspectral imaging provides fine-grained spectral information for land cover classification. Still, it faces critical challenges, including high dimensionality, spectral redundancy, and limited labeled samples, which can lead to overfitting in deep learning models. This paper introduces a…
-
Artikel Jurnal
Large Language Models for Automated Program Repair: Approaches, Evaluation, and Future Challenges
Automated Program Repair (APR) represents a transformative approach in software engineering that aims to reduce manual debugging efforts by automatically generating patches for software bugs. The recent emergence of Large Language Models (LLMs) has revolutionized this field, offering new…