PSNA College of Engineering and Technology

Because of the heavy data and communication advances, the utilization of Internet of Things (IoT) gadgets has expanded dramatically. In the improvement of IoT, Wireless Sensor Network (WSN) plays out a crucial part and involves easy keen gadgets for data gathering. In any case, such savvy gadgets have requirements regarding calculation, preparing, memory, and energy assets. Alongside such requirements, the major difficulties for WSN are to accomplish dependability with the security of communicated information in a weak climate alongside pernicious nodes. This paper intends to build up an Anomalous Intrusion Detection Protocol and Intrusion Prevention Protocol for interruption evasion in IoT dependent on WSN to expand the network time frame and information reliability. The proposed framework makes dissimilar energy-efficient groups dependent on the natural characteristics of nodes. Also, in view of the (k, n) limit related Shamir mystery sharing plan, the unwavering quality also, the security of the tangible data within the Base Station and group head are accomplished. The proposed security conspires demonstrates a trivial answer to adapt to interruptions produced by malignant nodes. The trial results utilizing the network test system Network Simulator-2 show that the proposed directing convention accomplished improvement as far as network lifetime, end-to-end delay as 24%, packet delay ratio as 30%, when contrasted and the current work under unique network characteristics.

Accurate and early prediction of lane-change maneuvers is a critical requirement for advanced driver-assistance systems and autonomous driving applications. Lane-change behavior is influenced by complex visual cues, temporal driving patterns, and dynamic interactions among surrounding traffic participants. This paper presents an explainable deep neural architecture for lane-change prediction that integrates vision-based perception with vehicle interaction modeling in a unified engineering framework. The proposed system employs a Vision Transformer to extract high-level spatial representations from camera inputs, while a recurrent temporal model captures sequential driving behavior over time. In parallel, a graph neural network models interactions between the ego vehicle and surrounding vehicles, enabling the system to reason about traffic dynamics and relative motion. These multimodal representations are fused to predict lane-change intentions in a probabilistic manner. To enhance transparency and trustworthiness, multiple explainable artificial intelligence techniques are incorporated to interpret both visual and behavioral decision factors. Experimental evaluation on publicly available traffic datasets demonstrates that the proposed architecture achieves improved prediction accuracy and early detection of lane-change maneuvers under varying traffic conditions. The explainability analysis further provides human-understandable insights into model decisions, supporting safer deployment in real-world transportation systems. The proposed approach contributes to intelligent transportation engineering by combining perception, interaction modeling, and explainability within a single predictive framework, facilitating reliable decision-making for next-generation vehicular systems.

Medical image enhancement plays a vital role in the rapid development of medical technology, focusing on improving medical image quality and clarity to support accurate diagnosis and effective treatment. However, poor medical imaging, such as imbalanced intensity or non-uniform illumination, brings significant challenges to automated diagnosis analysis and screening of diseases. This paper proposes a novel adaptive degradation-aware medical image enhancement to improve the quality of poorly illuminated medical images captured under a lowlight enclosed intestinal environment while conserving the critical pathological details. In this work, a novel complementary illumination adjustment function is employed to improve the brightness of dark regions while preventing overexposure in bright areas. Then, the proposed method incorporates a guided and bilateral filter to improve delicate clinical details and anatomical structures while suppressing contrast degradation of medical images. Experiment results comprehensively illustrate the performance of contrast enhancement in clinical diagnosis by effectively preserving color information and structure details. Extensive experimental evaluation demonstrates the superior performance of the proposed method in terms of qualitative and different quantitative metrics compared to other recent existing methods.

An analytical model for a Nanoscale Tri-Material Tri-Gate MgZnO/ZnO High Electron Mobility Transistor (NS-TM-TG-MZO HEMT) is developed to investigate the channel potential, threshold voltage, and electric field distribution. A stepwise channel potential profile forms by incorporating three gate materials with different work functions, effectively suppressing short-channel effects (SCEs) and enhancing carrier transport efficiency. The model considers spontaneous and piezoelectric polarisation-induced charges at the MgZnO/ZnO interface, as well as the impact of trapped charges formed during device fabrication. The Poisson equation is solved using the finite difference method (FDM), which discretizes the governing equations to achieve a numerically stable and accurate solution for potential distribution. The proposed TMG structure demonstrates a 25 to 30

Imaging systems deployed in coal-mine environments suffer from severe illumination imbalance, particulate scattering, and pronounced chromatic distortion, which significantly degrade visual quality and hinder downstream analytical reliability. These degradations arise from limited photon availability, uneven artificial lighting, and wavelength-dependent attenuation induced by suspended dust particles. To address these challenges, this paper presents Mine-RecNet, a brightness-adaptive recursive enhancement framework for robust image restoration under extreme underground conditions. The proposed approach introduces a cross-color-space illumination inference module that synergistically integrates physical luminance and perceptual brightness characteristics to derive a noise-resilient illumination prior. A pixel-wise recursion depth estimator enables spatially selective iterative correction that adapts enhancement strength locally to address nonuniform lighting, structural degradation, and contrast inconsistencies. A physics-guided multi-scale chromatic normalization scheme subsequently corrects wavelength-selective distortions by jointly estimating global color bias and local spectral inconsistencies, preserving edges, textures, and perceptual constancy under extreme degradation. Experiments on six standard benchmark datasets demonstrate that Mine-RecNet consistently outperforms fourteen state-of-the-art methods, achieving an average EME of 84.43, NIQE of 2.82, and BRISQUE of 22.15 over 1350 images representing improvements of 37.8%, 16.4%, and 13.9% over the closest competing method, confirming its suitability for practical underground monitoring applications.