Phishing Website Detection System using Machine Learning
A Distributed Improved Group Finite Residual Element Pied Kingfisher Integrated Attention Network Framework System for Web Attack Detection on Edge Devices
Distributed Agricultural Big Data Platform: Enhanced AICA-Plus and TPRS Algorithms for Real-Time Soil Classification and Anomaly Detection
TerraDefender: A Unified Platform for Strategic Battlefield Intelligence Preparation
Privacy-Preserving Medical Data Sharing to Unlock Healthcare Innovations for Society
Hybrid Deep Learning Network-Based Approach for Air Combat Maneuver Decision- Making
Efficient Agent Based Priority Scheduling and LoadBalancing Using Fuzzy Logic in Grid Computing
A Survey of Various Task Scheduling Algorithms In Cloud Computing
Integrated Atlas Based Localisation Features in Lungs Images
A Computational Intelligence Technique for Effective Medical Diagnosis Using Decision Tree Algorithm
A Viable Solution to Prevent SQL Injection Attack Using SQL Injection
Phishing websites continue to pose a significant threat to online security by tricking users into revealing sensitive data such as login credentials and financial information. Traditional detection methods like blacklists typically fail to identify newly launched phishing websites. This paper presents a machine learning-based system that classifies websites as phishing or legitimate based on URL features. Supervised algorithms, including Random Forest and Decision Tree, were used for training and testing. The system extracts lexical and structural features from URLs and uses these to train models. Random Forest outperformed other models in accuracy, robustness, and execution efficiency. A web interface was developed to allow real-time URL submission and classification. Experimental evaluation shows that the system achieves a 96.2% accuracy and a ROC-AUC of 0.98, outperforming baseline blacklist approaches by 17.8% in accuracy. The system is lightweight, making it practical for real-time phishing detection in resource-constrained environments. This work demonstrates the potential of machine learning to enhance phishing prevention and strengthen cybersecurity defenses.
Web-based attacks remain a critical threat to edge-enabled systems, particularly with the rapid growth of IoT and mobile computing. Limited bandwidth and real-time operations challenge centralized security tools, necessitating lightweight distributed detection solutions. This study presents a novel framework, Distributed Improved Group Finite Residual Element Pied Kingfisher Integrated Attention Network (Imp-GrFi-REPK-IAN), for web attack detection on edge devices. Data collection involves real-time URL gathering, decoding, and normalization, followed by balanced distribution into three datasets (CSIC 2010, FWAF, and HttpParams), each containing benign and malicious traffic. Preprocessing employs a time series min-max visualization-aware method to capture temporal signal patterns. Features are represented using an Elastic Decision Transformer, while classification is performed by Imp-GrFi-REPK-IAN, integrating a Finite Element-Integrated Neural Network (FEINN) with a Residual Group Attention Network (ResGANet). Parameter optimization is handled by the Improved Pied Kingfisher Optimizer (IPKO), ensuring faster convergence and enhanced precision. Experimental results show that the proposed system achieves 99.9% accuracy, surpassing existing edge- based detection approaches.
This work offers a new framework to modify precision agriculture methods by combining dynamic soil categorization with pattern recognition-based anomaly detection. Conventional approaches of soil classification neglect the temporal fluctuations of soil parameters and cannot sufficiently detect abnormalities that greatly affect agricultural productivity. Through a dual-phase design that integrates adaptive incremental clustering with advanced pattern- based anomaly detection, the proposed system effectively addresses these constraints. An enhanced Auto-Incremental Clustering Algorithm (AICA-Plus) enables dynamic soil classification by adapting to new soil samples and real-time environmental changes. Complementing this, a Temporal Pattern Recognition System (TPRS) employs sophisticated sequence modeling to detect abnormal soil conditions based on temporal variations in soil parameters. From field- collected soil samples, including pH levels, moisture content, nutrient concentrations, electrical conductivity, and organic matter content, the integration employs multi-dimensional feature extraction. The proposed methodology achieves a 22% improvement over existing techniques, reaching 94.7% classification accuracy. Anomaly detection performance demonstrates 96.2% sensitivity for actual abnormalities and a 35% reduction in false positive rates. Furthermore, the technique enables proactive agricultural interventions by identifying critical patterns of soil degradation three to five days earlier than conventional monitoring methods. Measurable agricultural advantages, including an 18% increase in crop yields, a 25% decrease in fertilizer waste, and a 30% improvement in water use efficiency, came from the application. These findings provide farmers with data-driven insights for best decision-making and sustainable farming methods, therefore proving the practical feasibility of the suggested framework for large-scale precision agriculture uses.
TerraDefender's Military Intelligence Preparation of the Battlefield (IPB) leverages advanced geospatial intelligence, real-time data analytics, and machine learning to enhance battlefield awareness. It enables commanders to anticipate threats, evaluate terrain, and optimize decision-making in modern military operations, ensuring accurate, timely intelligence for strategic and tactical planning. Beyond military applications, TerraDefender's integration of secure image processing and encryption offers significant value for environmental monitoring, disaster response, and urban planning. By combining adaptability with strong data protection, it bridges operational needs across diverse domains. Ultimately, TerraDefender demonstrates the transformative potential of AI-driven, secure geospatial systems in shaping both defense strategies and civilian resilience.
A significant challenge in the digital healthcare environment is protecting patient privacy and security while allowing for successful utilization of patient data for clinical and research analysis. This study presents a blockchain-based system that allows patients to safely upload their medical data by means of homomorphic encryption. The technology permits academics and medical experts to perform operations on encrypted data with explicit patient consent, ensuring confidentiality and patient control. The structure keeps a tamper-proof record of all data access done by the patients. Disease tracking, predictive modeling, clinical trials, precision medicine, and public health research are the applications supported by this system's transformative potential for public health and social well-being. These tokens can then be utilized or exchanged for patient health insurance savings, reduced prescription costs, or other healthcare benefits, making the healthcare sector more accessible and advantageous. The integration of these cryptographic homomorphic techniques with blockchain technology provides a strong way for safeguarding and upholding patients' confidential data, promoting trust in healthcare data sharing analysis.
This paper introduces a hybrid deep learning model for maneuver decision-making in air combat scenarios. The model combines a stacked sparse autoencoder (SSAE) for dimensionality reduction of high-dimensional, dynamic time-series combat data with a long short-term memory (LSTM) network to model the quantitative relationship between the reduced data and maneuver control variables. Key features of the model include leveraging time-series data as the foundation for decision-making, which aligns closely with real-world processes, and using SSAE to enhance prediction accuracy by reducing data dimensionality. Additionally, the model outputs maneuver control variables, enabling flexible and effective control of maneuvers. Experimental results demonstrate that the proposed approach significantly improves prediction accuracy and convergence speed, making it a robust solution for autonomous air combat decision-making systems.
