Nandha Engineering College

Enhancing underwater images and videos is essential for a number of applications, including underwater autonomous vehicles, marine ecosystems, and submarine archaeology. Due to water turbidity, light scattering, and absorption, these conditions present additional challenges such as color distortion, low brightness, and blurring. While equalization of histograms and Retinex-based techniques have been employed to improve underwater photos, they are insufficient to address these problems holistically. Over the past few years, deep learning (DL) techniquesin particular, Convolutional Neural Networks, and Generative Adversarial Networks have been increasingly popular for improving underwater photos and videos. By restoring missing data, boosting contrast, color weighing, and minimizing noise, these models may enhance image quality and discover intricate patterns from massive datasets. Hybrid techniques that integrate deep learning with physical models, i.e., scattering and absorption models, hold promise in addressing actual underwater challenges. Nevertheless, not withstanding these developments, there are some challenges that are yet to be addressed, which include high computational expense, requirements for large amounts of labelled datasets, and complexity in real-time processing. The future should entail the development of real-time enhancement models, multi-modal enhancement strategies, and hybrid techniques, and also addressing the limitations of datasets. On-going development in these fields will enhance underwater imaging systems for more efficient use in marine biology, archaeology, environmental monitoring, and autonomous navigation.

Underwater Friction Stir Welding has arisen as proficient solid-state joining method for aluminium alloys necessitating stringent heat regulation. This work experimentally tested and systematically optimized the mechanical performance of 5 mm thick AA5754 butt joints produced by Underwater Friction Stir Welding. The influence of tool rotational speed, axial force and welding speed, on microhardness and tensile strength was assessed by an experimental design based on Taguchi orthogonal array. ANOVA were utilized to assess significance and impact of each process parameter. A multi-criteria decision-making (MCDM) MEREC and CoCoSo approaches was employed to determine best parameter combination, thereby addressing constraints of traditional single-response optimization. The findings indicate that tool rotational speed is the predominant contributor, succeeded by axial force and welding speed. Ideal process parameters for enhanced ki was determined at a a tool rotation speed of 1100 rpm, an axial force of 6 kN, and welding speed of 20 mm/min, corresponding to (X2 Y2 Z2). The enhanced UFSW condition led to a significant enhancement in joint efficiency and tensile strength, achieving approximately 90

Mobile ad hoc networks (MANETs) are wireless networks ideally designed for applications such as specific outdoor events, communication in areas without wireless infrastructure, crisis situations, natural disasters, and military operations, as they do not need preexisting network infrastructure and can be rapidly deployed. Security is a major problem in ad hoc networks, and extensive research has concentrated on lowering energy consumption in order to extend node a long lifespan. To overcome these challenges, this work proposes an energy-efficient and secure routing framework ASAO-DST for MANETs, addressing the dual challenge of prolonging network lifetime while ensuring trustworthy route selection. The proposed method uses Improved Fuzzy C-Means (IFCM) clustering, which efficiently organizes network nodes into clusters by enhancing membership functions for optimal formation, while Cluster Head (CH) selection is optimized through Electric Eel Foraging Optimization (EEFO), which emulates the foraging behavior of electric eels to determine the most energy-efficient CH. CH selection in EEFO utilizes CH selection because its multi-phase foraging model simultaneously satisfies the criteria of residual energy, mobility, and connectivity, which cannot be simultaneously optimized with a single-objective energy-aware heuristic, thus prolonging the network lifetime compared to conventional clustering techniques. Trust evaluation is performed using Dempster–Shafer Theory (DST) to integrate several evidence sources for evaluating node dependability. The routing path selection utilizes the Adaptive Snow Ablation Optimizer (ASAO), which replicates snow melting processes to determine optimum and secure paths while preserving Quality of Service (QoS) under fluctuating circumstances. In MANETs, Improved Fuzzy C-Means (FCM) clustering organizes network nodes into efficient clusters by refining membership functions for better formation, while CH selection is optimized using EEFO, which mimics the foraging behavior of electric eels to identify the most energy-efficient CH. The trust evaluation is conducted using DST to combine multiple evidence sources for assessing node reliability. For routing path selection, the ASAO is employed, which simulates snow melting patterns to identify optimal and secure routes, maintaining QoS under dynamic conditions. The suggested approach empirically compares the suggested approach to existing methods based on energy consumption 30 mJ, throughput 0.96 Mbps, end-to-end delay 2.03063 s, network lifetime 6100 rounds indicating LND criterion for the 100-nodes, packet delivery rate 99.8

This study involved the fabrication of AZ61 magnesium alloy reinforced with nano-sized Zinc Oxide (nZnO) particles by a squeeze-casting process, and examined its properties at different melt temperatures (720, 750, 780, and 810 °C). Mechanical characterization encompassed tensile, hardness, and impact, also wear testing, supplemented by comprehensive microstructural investigation were studied. Experimental findings indicated that melt temperature is crucial in influencing the composite’s ultimate characteristics. A melt temperature of 780 °C resulted in superior dispersion, a refined grain structure, and improved compatibility for plastic deformation, attributed to sufficient superheat and efficient stirring at a squeeze pressure of 80 MPa. The AZ61/nZnO composite demonstrated enhanced wear resistance relative to the base alloy, with diminished wear rates resulting from the synergistic effects of nZnO reinforcements, optimized load transmission, and decreased porosity. The wear rate analysis emphasized the effects of sliding velocity, applied stress, and surface topography on material degradation during sliding. Microstructural analyses validated superior particle dispersion and diminished porosity at optimal values, directly enhancing mechanical performance.

The growing demand for wear-resistant materials have driven investigators to create substitute materials which incorporate various fillers and reinforcements. Recent research indicates that the amalgamation natural fibers with ceramic fillers had produced HCs with enhanced tribological properties for aerospace applications and automotive. Despite the drawbacks of natural fibers, the synergistic impact of ceramics and natural fibers, when paired with appropriate multi-response optimization approaches can mitigate these limits and yield a composite with superior tribological properties and mechanical at a reduced expenditure. This study investigates wear characteristics of a hybrid composite composed of zinc oxide (ZnO) and luffa cylindrica/cassia fistula bark fibers. The design of tests utilized Taguchi L27 orthogonal array to achieve smallest coefficient of friction (COF) and wear rate. This research employed multicriteria decision-making (MCDM) methodologies to address the challenge of selecting optimal estimates across diverse opportunities. The ideal combinations for favorable wear performance of the composite were determined utilizing a performance selection index (PSI) methodology. The research focuses on the creation and validation of a predictive model in machine learning utilizing random forest (RF) algorithm, designed to predict two essential behaviour metrics: the coefficient of friction (COF) and the specific wear rate (SWR). This investigation revealed that the peak performance selection index (PSI) and random forest (RF) values were 0.8761 and 0.7695, respectively, for determining the ideal operating condition of 30 wt