Government Engineering College, Kishanganj

Vehicular Ad Hoc Networks (VANETs) are employed through Cooperative Intelligent Transport Systems (C-ITS) to distribute safety-critical data, including Decentralized Environmental Notification Messages (DENMs). Semantic-level identification for malicious node detection has been analyzed in recent research. However, accurate detection of malicious nodes is not achieved due to manipulation, especially under multi-hop dissemination. Additionally, message-level identification is insufficient because malicious nodes may continue to participate in the network and persistently obstruct the connectivity. To resolve this, a hybrid malicious node detection framework is developed to accurately detect vehicles that manipulate valid DENMs during multi-hop propagation. This study proposes a novel Federated Learning based Variational AutoEncoder with Multi-level Hierarchical Attention-assisted Depthwise Separable Dilated Convolution network (FLVAE-MHADSDC) for misbehaviour detection with robustness, attack mitigation, and data privacy. The proposed framework uses hop-wise temporal backtracking to rebuild message propagation pathways and determine the status of a DENM when it is transmitted through each node. This reconstruction has been utilized to extract behavioural, temporal, structural, and semantic features of misbehaviour. These features are combined using a weighted feature fusion technique. The proposed framework has achieved the accuracy of 98.5 %, a precision of 96.25 %, a recall of 99.25 %, F1-score of 97.72 %, a specificity of 98.74 %, and a latency of 27.3 ms for 2500 nodes.

The development of effective and sustainable desalination technology is imperative due to the increasing need for freshwater in arid and semi-arid countries. Low productivity and poor energy utilization often constrain the performance of solar stills, despite their simplicity and low cost. In the Present study, an analytical simulation has been conducted to evaluate and compare the performance of a conventional passive solar still with two PVT–CPC (Photovoltaic Thermal–Compound Parabolic Concentrator) integrated active solar stills operating under the natural and forced circulation modes. The governing energy balance equations for the system components were formulated and numerically solved in MATLAB software using representative summer climatic data of New Delhi, India. The model predicted transient temperatures of the glass cover, basin water, absorber plate, PV module, and working fluid. These thermal states were subsequently used to determine the hourly distillate yield, instantaneous efficiency, daily thermal efficiency, and exergetic efficiency. Results showed that the passive still produced 3.16 kg/m2 day, whereas natural and forced circulation modes yielded 4.178 and 7.668 kg/m2 day, respectively. The overall thermal efficiency of the system enhanced from 5.03

This study presents a hybrid machine learning framework for stability assessment of anchored sheet pile walls under uncertainty of soil. Monte Carlo Simulation was employed to generate 1,000 stochastic realizations by incorporating variability in the angle of internal friction, unit weight, and submerged unit weight of sandy soil. Factors of safety against sliding and overturning were computed for each realization to establish a comprehensive dataset. Extreme Gradient Boosting models were optimized using Particle Swarm Optimization, Tiki-Taka Algorithm, Whale Optimization Algorithm, and Reptile Search Algorithm to predict stability responses. Model performance was assessed using statistical error metrics and comparative analyses. The model optimized with Reptile Search Algorithm achieved the highest predictive accuracy for both sliding and overturning stability, surpassing the models optimized with the other metaheuristic algorithms. Explainable artificial intelligence analysis based on SHapley Additive exPlanations was performed to quantify the contribution of input variables and improve model interpretability. The analysis identified the angle of internal friction as the most influential parameter, followed by soil unit weight. The developed framework provided accurate, computationally efficient, and interpretable predictions, demonstrating its applicability for reliability-based assessment and design of anchored sheet pile wall systems under uncertain geotechnical conditions.