University College of Engineering, Nagercoil

The demand for efficient prediction methods to evaluate and treat post-COVID disorders has increased due to the COVID-19 epidemic. This work presents a novel strategy for anticipating and addressing these health risks that makes use of transformer-based models. To improve the disease prognosis accuracy, this study integrates detailed tabular data and X-ray images of chest, who pretentious with COVID-19.A hybrid transformer model that incorporates the most recent advancements helps to predict the course of the disease. This approach makes it possible for the model to successfully adjust to each patient’s distinctive characteristics and disease progression. Preliminary findings indicate that the proposed approach demonstrates promising results in accurately prognosing post-COVID diseases. Integrating diverse datasets significantly improves the model’s predictive capabilities and treatment efficacy, allowing for tailored recommendations that align with individual patient needs. The Vision Token Transformer (ViToT) architecture is a Hybrid transformer, which contains Vision Transformer in order to train a model with chest X-ray (CXR) images and Feature Tokernizer transformer in order extract features from tabular data to capable of recognizing and categorizing key patterns in CXR images while also extracting optimal features from tabular data. Late fusion technique is applied to combine an extracted feature which leads to cardiovascular disorder. Across 150 training epochs, the model demonstrated a robust performance, achieving a final accuracy of 97.6

This research investigates a vinyl ester composites system strengthened with chemically modified flax fibers and finely milled Caesalpiniabonducella seed shell particulates (CBSSP) (1 μm) with emphasis on its mechanical response and drilling characteristics including performance after moisture exposure. The application of vinyl silane treatment promoted stronger bonding at the fiber-matrix interface and curing was facilitated using methyl ethyl ketone peroxide. Among all compositions fabricated, the hybrid laminate labelled FC2, containing 3 vol

The investigation evaluates the mechanical and thermal properties of glass fiber reinforced epoxy hybrid composites incorporated with mahogany and teak sawdust powder (TSP and MSP). For the development of hybrid sandwich composites, a manual lay-up method was used with numerous amounts of filler. It employed tensile, flexural, and impact tests to look at mechanical properties and thermogravimetric analysis (TGA) and differential scanning calorimetry (DSC) to analyze at thermal behavior and Scanning electron microscopy (SEM) was employed to explore microstructural characteristics. The experimental results indicated that filler dispersion and interfacial bonding significantly influenced the properties of the composite. Sample 4 had the overall best performance of the developed samples. It had a tensile strength of 12.5 N/mm2, a flexural strength of 48 N/mm2, and an impact strength of 5.7 J/m. It indicated that it was more effective in carrying loads and upholding structural integrity. TGA analysis revealed that Sample 4 had multi-stage thermal deterioration and DSC data, on the various aspects, indicated that Sample 4 carried improved thermal stability with less enthalpy change. In addition, samples were investigated at how the epoxy/sawdust/glass fiber composites absorbed water. The hybrid fillers absorbed a moderate amount of water (2%-6%), and Sample 4 absorbed the least because the filler-matrix bonding proved more effective and the void content were reduced. These results imply that teak-mahogany hybrid fillers can significantly improve the mechanical and thermal properties of glass fiber reinforced epoxy composites for lightweight semi-structural applications.

Optimizing the thickness of thermal barrier coatings is critical for achieving enhanced heat transfer performance and thermal stability under varying thermal loading conditions. In this study, a nickel–zirconia (Ni–ZrO2) composite coating was electrodeposited on mild steel and optimized using Response Surface Methodology (RSM) based on a Central Composite Design (CCD). The optimization was carried out separately for conductive and convective heat transfer conditions to identify the most effective coating thickness. For conduction-dominated heat transfer, the optimal thickness was found to be 54.36 µm, corresponding to a voltage of 164.66 V, current of 0.759 A, heat input of 51.826 W, heat flux of 3563.17 W/m2, and resulting surface temperature of 114.462 °C. Under convective heat transfer conditions, the optimized thickness was 51.499 µm, achieved at a voltage of 177.04 V, current of 4.02 A, heat input of 664.482 W, heat flux of 204,659 W/m2, air velocity of 3.381 m/s, Reynolds number of 5722.65, and surface temperature reduced to 90.573 °C. Computational fluid dynamics analysis confirmed uniform heat conduction with minimal thermal gradients and demonstrated the formation of a high-velocity boundary layer (0–3.30 m/s) that enhanced convective cooling. The wall heat transfer coefficient ranged from 20.4 to 5460 W/m2K, validating the effectiveness of the optimized coating thickness. These results establish an optimal thickness window of 50–55 µm for Ni–ZrO2 electroplated coatings, offering valuable design guidelines for thermal management applications.

ABSTRACT Geopolymer concrete is a sustainable substitute for ordinary Portland cement which minimizes carbon dioxide emissions and effectively utilizes the waste from industries. Proper predictive estimating compressive strength can assist in the mix deign optimization, structural reliability. The article presents a machine learning-based framework to predict the compressive strength of geopolymer concrete made with multiple industrial by-products as binders. This study investigated the subsequent strength of concrete when subjected to fly ash, ground granulated blast furnace slag, metakaolin, silica fume, and rice husk ash. A database was developed containing 243 experimentally prepared samples with different mix proportions. The study conducted the compressive strength prediction by implementing Artificial Neural Network (ANN) and Random Forest (RF) models in Python. The performance of model was analyzed through the coefficient of determination (R2) and mean absolute error (MAE) and root mean square error (RMSE). The RF model was found to be superior to the ANN model with R2 = 0.97, MAE = 1.9969, RMSE = 3.0586, which was an accurate result whereas ANN model was lower accurate R2 = 0.78. The results show that techniques using ensemble learning can capture complex non-linear relationships, reduce experimental efforts and assist in developing efficient and sustainable geopolymer concrete mix designs.