ELW-CNN: An extremely lightweight convolutional neural network for enhancing interoperability in colon and lung cancer identification using explainable AI.

Cancer is a condition in which cells in the body grow uncontrollably, often forming tumours and potentially spreading to various areas of the body. Cancer is a hazardous medical case in medical history analysis. Every year, many people die of cancer at an early stage.

E-waste recycling in an optimized way for copper recovery by leaching and a case study on E-waste generation and management in Dhaka city.

The widespread adoption of electronic devices has enhanced living standards but has also led to a surge in electronic waste (e-waste), creating serious environmental and health challenges. Although various methods exist to recover valuable metals from e-waste, each has notable drawbacks. Among these, chemical leaching with aqua regia is widely used but is both highly corrosive and hazardous.

Inverse Gini indexed averaging: A multi-leveled ensemble approach for skin lesion classification using attention-integrated customized ResNet variants.

Objective: To improve the accuracy and explainability of skin lesion detection and classification, particularly for several types of skin cancers, through a novel approach based on the convolutional neural networks with attention-integrated customized ResNet variants (CRVs) and an optimized ensemble learning (EL) strategy.

Methods: Our approach utilizes all ResNet variants combined with three attention mechanisms: channel attention, soft attention, and squeeze-excitation attention. These attention-integrated ResNet variants are aggregated through a unique multi-level EL strategy.

Phase stability, electronic, mechanical, lattice distortion, and thermal properties of complex refractory-based high entropy alloys TiVCrZrNbMoHfTaW with varying elemental ratios.

This study examines the intricate area of refractory-based high entropy alloys (RHEAs), focusing on a series of complex compositions involving nine diverse refractory elements: Ti, V, Cr, Zr, Nb, Mo, Hf, Ta, and W. We investigate the phase stability, bonding interactions, electronic structures, lattice distortions, mechanical, and thermal properties of six RHEAs with varying elemental ratios using VASP and OLCAO DFT calculations. Through comprehensive analysis, we investigate the impact of elemental variations on the electronic structure, interacting bond dynamics, lattice distortion, thermodynamic, mechanical, and thermal properties within these RHEAs, providing an insight into how these specific elemental variations in composition give rise to changes in the calculated properties in ways that would guide future experimental and computational efforts.

A single droplet dispensing system for high-throughput screening and reliable recovery of rare events.

Microfluidic droplet sorting has emerged as a powerful technique for a broad spectrum of biomedical applications ranging from single cell analysis to high-throughput drug screening, biomarker detection and tissue engineering. However, the controlled and reliable retrieval of selected droplets for further off-chip analysis and processing is a significant challenge in droplet sorting, particularly in high-throughput applications with low expected hit rates. In this study, we present a microfluidic platform capable of sorting and dispensing individual droplets with minimal loss rates.