MCKV Institute of Engineering

Lung cancer accounts for the highest number of deaths due to cancer in the world. Precise and prompt identification on the basis of histopathology pictures is vital in enhancing survival outcomes. This study proposes to create a fast and intelligible CNN with high accuracy and an easy-to-use CBQA model that can be deployed in the clinical setting. To do this, we created a bespoke model of CNN with four convolutional layers, group normalisation, dropout and SoftMax output. A small balanced dataset of 15,000 histopathology images (5000 adenocarcinoma, 5000 squamous cell carcinoma, 5000 benign) out of Kaggle dataset of Lung Cancer Histopathological Images was adopted with a 70–15–15

This work investigates the thermoelastic free vibration behavior of functionally graded porous (FGP) sandwich plates with bi-directional thickness variations using the finite element method (FEM) under various boundary conditions. The sandwich configuration comprises a porous ceramic core and two porous sigmoid functionally graded facesheets. The kinematic relations and thermoelastic constitutive equations are formulated within higher-order shear deformation theory (HSDT), and Lagrange’s equation is used to derive the governing equations, including geometric stiffness to capture thermal nonlinearity. The study presents the natural frequencies of FGP sandwich tapered plates considering the combined effects of sandwich scheme, material gradation, porosity distribution, taper ratio, boundary conditions, and temperature rise. Results show that under cantilever conditions, the fundamental frequency decreases with increasing spanwise taper and increases with chordwise taper, while for simply supported and clamped plates, frequencies increase with both taper types across all sandwich configurations. The novelty of this work lies in formulating a free vibration model for porous sigmoid functionally graded material (S-FGM) sandwich tapered plates with a porous ceramic core under arbitrary boundary conditions operating in thermal environments. The scientific contribution is the reliable prediction of thermally influenced vibration characteristics, offering guidance for designing lightweight, high-temperature aerospace, energy, and automotive structures.

This correlative investigation presents a comparative performance analysis on machining characteristics by wire-cut electrical discharge machining (WEDM) outcomes when processing a titanium matrix composite (TMC) under diversifying input parameters. Experimental investigation focuses on metrics such as material removal rate (MRR), surface roughness (SR), kerf width (KW), and overcut (OC). An innovative multi-objective optimization (MOO) algorithm like desirable ant colony optimization (DACO) is proposed here, which is correlated with desirable particle swarm optimization (DPSO). DACO achieved a combined desirability score of 0.804, which rose to 0.813 with the implementation of DPSO. Comparing these two algorithms, DPSO outperformed DACO by approximately 1.119

High-dimensional gene expression data pose substantial challenges for predictive modeling due to noise, redundancy, and the curse of dimensionality. This work introduces a hybrid machine learning framework that integrates a Variational Autoencoder (VAE) for nonlinear dimensionality reduction with an Explainable Boosting Machine (EBM) for transparent multiclass cancer classification. The VAE compresses over 20,000 transcriptomic features into a 64-dimensional latent space while preserving biologically meaningful structure, yielding improved separability across tumor types. These latent representations are then classified using an EBM, enabling inherently interpretable predictions supported by global feature importance and SHAPbased local explanations. Experiments on the TCGA Pan-Cancer dataset demonstrate the effectiveness of the proposed pipeline, achieving 0.98 accuracy, 0.99 macro-precision, 0.97 macro-recall, and 0.98 macro-F1, with per-class F1-scores ranging from 0.95 to 1.00. The results highlight that the VAE-EBM framework provides both high predictive performance and clinical interpretability, offering a promising direction for precision oncology.

Purpose The simultaneous maximization of a MEMS pressure sensor diaphragm’s deflection and resonance frequency are two essential but entirely contradictory objectives for maximum performance. Selection of proper material which has optimum diaphragm deflection and resonating frequency by using Ashby’s technology is the main objective of this paper. By using Ashby’s technique three materials are found which shows optimum performance for diaphragm deflection and resonating frequency. They are Single crystal Silicon, Polycrystalline Silicon and Silicon carbon Nitride. After selecting the material, a piezoresistive pressure sensor is designed and the performances are analyzed for Single crystal Silicon, Polycrystalline Silicon type piezoresistor material and Single crystal Silicon, Polycrystalline Silicon and Silicon carbon Nitride diaphragm material. The purpose of this study is to select optimized material for piezoresistive pressure sensor diaphragm and piezoresistor material to achieve maximum output voltage. Design/methodology/approach A diaphragm of size 3,000 um * 2,400 um * 50 um is constructed using different ceramic materials and it is simulated for deflection and resonance frequency determination using COMSOL Multiphysics software. As per Ashby’s method the deflection ratio of different material to standard material (Silicon) and Eigen frequency ratio of different material to standard material is calculated and a graph is plotted. Three material lies in the first quadrant of the graph which become optimum for pressure sensor material. They are Single crystal Silicon, Polycrystalline Silicon and Silicon carbon Nitride. Then a pressure sensor is designed by using these materials and the performances are compared. The performance and sensitivity of the piezoresistive pressure sensor can be improved by using a < 110> piezoresistor on a < 100> diaphragm. But Polycrystalline Silicon is a cheap and abundant material. In this proposed model, the performance of the pressure sensor is improved by using polycrystalline silicon as a piezoresistor on a single-crystal N-silicon diaphragm. Findings By applying Ashby’s material selection technique three materials (Single crystal Silicon, Polycrystalline Silicon and Silicon carbon Nitride) are found suitable for pressure sensor design which has optimum diaphragm deflection and resonating frequency. Then a piezoresistive pressure sensor is designed and the performance like output voltage, diaphragm deflection and maximum Von Misses stress is analyzed and compared for two piezoresistor material (Single crystal Silicon, Polycrystalline Silicon) and the same parameters are analyzed and compared for three different types of diaphragm material (Single crystal Silicon, Polycrystalline Silicon, Silicon Carbon Nitride). Originality/value In this work at first by Ashby’s material selection technology proper material for piezoresistor and sensor diaphragm is selected. Then a MEMS pressure sensor is designed using those selected materials. The performance of the sensor for different material is analyzed and compared. It is clear from the proposed work that the output voltage response of the sensor can be improved by using Polysilicon piezoresistor and Silicon Carbon Nitride diaphragm. The sensor is suitable in harsh condition also for using Silicon Carbon Nitride diaphragm and it will be cost effective also for the use of polysilicon.