Search Results (4)

Skin cancer is a major global health concern and one of the deadliest forms of cancer. Early and accurate detection significantly increases the chances of survival. However, traditional visual inspection methods are time-consuming and prone to errors due to artifacts and noise in dermoscopic images. To address these challenges, this paper proposes an innovative deep learning-based framework that integrates an ensemble of two pre-trained convolutional neural networks (CNNs), SqueezeNet and InceptionResNet-V2, combined with an improved Whale Optimization Algorithm (WOA) for feature selection. The deep features extracted from both models are fused to create a comprehensive feature set, which is then optimized using the proposed enhanced WOA that employs a quadratic decay function for dynamic parameter tuning and an advanced mutation mechanism to prevent premature convergence. The optimized features are fed into machine learning classifiers to achieve robust classification performance. The effectiveness of the framework is evaluated on two benchmark datasets, PH2 and Med-Node, achieving state-of-the-art classification accuracies of 95.48% and 98.59%, respectively. Comparative analysis with existing optimization algorithms and skin cancer classification approaches demonstrates the superiority of the proposed method in terms of accuracy, robustness, and computational efficiency. Our method outperforms the genetic algorithm (GA), Particle Swarm Optimization (PSO), and the slime mould algorithm (SMA), as well as deep learning-based skin cancer classification models, which have reported accuracies of 87% to 94% in previous studies. A more effective feature selection methodology improves accuracy and reduces computational overhead while maintaining robust performance. Our enhanced deep learning ensemble and feature selection technique can improve early-stage skin cancer diagnosis, as shown by these data. Full article

Protein-based fish adhesives have historically been used in various bonding applications; however, due to the protein’s high affinity for water absorption, these adhesives become destabilized in high-moisture environments, resulting in reduced bondline strength and early failure. This limitation makes them unsuitable for industrial applications with higher demands. To address this issue, water-insoluble raw powder materials such as iron, copper, or zeolite were incorporated into natural fish adhesives. In this study, the hygroscopicity, dry matter content, thermal analysis (TGA/DSC), FT-IR spectroscopy, surface tension measurements, vapour permeability, and scanning electron microscope (SEM) of the modified adhesives were determined. In addition, the bonding properties of the modified adhesives were evaluated by the tensile shear strength of the lap joints, and mould growth was visually inspected. The resulting modified protein-based adhesives demonstrated improved stability in high humidity environments. Enhancing the hygroscopic properties of protein-based fish adhesives has the potential to unlock new opportunities and applications, providing a healthier and more environmentally sustainable alternative to petroleum-based adhesives. Full article

This paper presents the results of research focused on increasing the lifespan of HPDC moulds for casting aluminium alloys by applying duplex PVD coatings in combination with laser texturing the base material before the coatings’ deposition. This article describes the HPDC process and the degradation mechanisms of the moulds that arose during this process. The PVD nanostructured coatings utilised, the methods of their deposition, and the evaluation of their wear resistance are defined in this paper. The surface texturing process is described alongside the description of the analysis of the wear of the functional parts of the mould after decommissioning, which was carried out by visual inspection and optical and light microscopy. Three types of PVD duplex coatings were analysed during our study. The coatings were deposited using the LARC technology method (lateral rotating cathode). Subsequently, the procedure of laser texturing in the form of dimple textures using a laser was proposed. The quality of the coatings was evaluated under tribological conditions by means of the “Ball on disc” method. Based on the experimental results, recommendations for practice are established. Full article

The relationship between the use of unflued gas heaters (UGH, N = 14) and heat pump heaters (HP, N = 12) located in the living rooms, and mould growth on the living room and bedroom walls, of 26 New Zealand (NZ) occupied homes was investigated during winter. Two methods were employed to evaluate the potential of mould growth on walls: (i) measurement of daily hyphal growth rate using a fungal detector (encapsulated fungal spores); and (ii) estimation of fungal contamination based on a four level scale visual inspection. The average wall psychrometric conditions were significantly different between the two heater type groups, in both the living rooms and the bedrooms with the UGH user homes being colder and damper than HP user homes. The UGHs were found to be a significant additional source of moisture in the living rooms which dramatically increased the capacity for fungi to grow on wall surfaces. The average daily hyphal growth rates were 4 and 16 times higher in the living rooms and in the bedrooms of the UGH user homes, respectively. Results from both mould detection methods gave good agreement, showing that the use of a fungal detector was an efficient method to predict the potential of mould growth on the inside of the external walls in NZ homes. Full article