In dermatological diagnosis, accurately and appropriately classifying skin diseases is crucial for timely treatment, thereby improving patient outcomes. Our goal is to develop transfer learning models that can detect skin disease from images. We performed our study in the “Skin Cancer: MNIST HAM10000” dataset. This dataset has seven categories, including melanocytic nevi, melanoma, benign keratosis (solar lentigo/seborrheic keratosis), basal cell carcinoma, actinic keratoses, intraepithelial carcinoma (Bowen’s disease), vascular lesions, and more. To leverage pre-trained feature extraction, we use five available models—ResNet50, InceptionV3, VGG16, VGG19, and MobileNetV2. Overall results from these models show that ResNet50 is the least time-intensive and has the best accuracy (99%) in comparison to other classification performances. Interestingly, with a notable accuracy of 97.5%, MobileNetV2 also seems to be adequate in scenarios with less computational power than ResNet50. Finally, to interpret our black box model, we have used LIME as an explainable AI technique (XAI) to identify how the model is classifying the disease. The results emphasize the utility of transfer learning for optimizing diagnostic accuracy in skin disease classification, blending performance and resource efficiency as desired. The findings from this study may contribute to the development of automated tools for dermatological diagnosis and enable clinicians to reduce skin conditions in a timely manner.

Purpose: This article provides a theoretical analysis and numerical simulation of bio-magnetic non-Newtonian pulsatile blood flow through a bifurcated artery with both stenosis and aneurysm, incorporating nanoparticles (Au). Blood flow is taken into account to be unsteady, incompressible, biomagnetic and non-Newtonian.Design/methodology/approach: These flow processes are modeled mathematically by use of the continuity, momentum and energy partial differential equations. The finite element method (FEM) is then accustomed to numerically resolve the dimensionless governing equations.Findings: The average Nusselt number ( N u ¯ ), local Nusselt number (Nu), local wall shear stress (WSS), isotherm and velocity profile are among the important blood flow parameters that are the primary concern of the study. These characteristics are thoroughly investigated and found to be largely consistent with existing literature. The results, presented graphically, include velocity profiles, isotherms, local Nu, local WSS and average Nu for a range of magnetic numbers (M_nf = 0.0, 0.1, 0.2, 0.3), Reynolds numbers (Re = 50, 100, 150, 200, 250, 300), power law indices (n = 0.8, 0.9, 1.0) and nanoparticle volume fraction coefficients (Φ = 0, 0.02, 0.04, 0.06). The Prandtl number for the biofluid (blood) is assumed constant at Pr = 21. The findings suggest that the magnetic field, nanoparticle volume fraction, power law index and Reynolds number significantly influence the isotherms, velocity, heat transfer coefficients and WSS in pulsatile blood circulation across an artery that is bifurcated and has aneurysm and stenosis.Research limitations/implications: One limitation of this study is that fluid–structure interaction was not taken into account. Additionally, we modeled the computational domain in 2D rather than 3D. While we assumed a homogeneous distribution of nanoparticles, this is not always accurate.Originality/value: The investigation of the non-Newtonian biomagnetic fluid flow of blood with gold nanoparticles in arterial stenosis and aneurysm is novel. The present numerical method is validated for the nanofluids in an aneurysm-shaped computational domain which confirmed the results accuracy.

Urban pollutant dispersion is governed by highly nonlinear interactions between flow structures, turbulence characteristics, and scalar transport processes, making accurate prediction computationally demanding. The present study investigates pollutant dispersion behaviour within an idealised urban configuration using a combined computational fluid dynamics (CFD) and surrogate machine learning. Reynolds-averaged Navier–Stokes simulations were performed to analyse the effects of Reynolds number, Schmidt number, turbulence kinetic energy, concentration transport, velocity distribution, and injection ratio on flow symmetry and pollutant redistribution. The numerical results showed that variations in Reynolds number and injection ratio modified the spatial organisation and relative symmetry of the computed vorticity and concentration fields, together with the corresponding centreline concentration, velocity, and turbulent kinetic energy responses. To complement the CFD analysis, an Extreme Gradient Boosting (XGBoost) model was trained to predict concentration, velocity, and turbulence kinetic energy using CFD-generated datasets. Feature importance analysis further revealed physically meaningful relationships among the governing transport variables, with Reynolds number dominating velocity and turbulence kinetic energy behaviour, while concentration transport remained strongly influenced by injection ratio.

In this research, we explored the improvement in terms of multi-class disease classification via pre-trained language models over Medical-Abstracts-TC-Corpus that spans five medical conditions. We excluded non-cancer conditions and examined four specific diseases. We assessed four LLMs, BioBERT, XLNet, and BERT, as well as a novel base model (Last-BERT). BioBERT, which was pre-trained on medical data, demonstrated superior performance in medical text classification (97% accuracy). Surprisingly, XLNet followed closely (96% accuracy), demonstrating its generalizability across domains even though it was not pre-trained on medical data. LastBERT, a custom model based on the lighter version of BERT, also proved competitive with 87.10% accuracy (just under BERT's 89.33%). Our findings confirm the importance of specialized models such as BioBERT and also support impressions around more general solutions like XLNet and well-tuned transformer architectures with fewer parameters (in this case, LastBERT) in medical domain tasks.

An application of software known as an Intrusion Detection System (IDS) employs machine algorithms to identify network intrusions. Selective logging, safeguarding privacy, reputation-based defense against numerous attacks, and dynamic response to threats are a few of the problems that intrusion identification is used to solve. The biological system known as IoT has seen a rapid increase in high dimensionality and information traffic. Self-protective mechanisms like intrusion detection systems (IDSs) are essential for defending against a variety of attacks. On the other hand, the functional and physical diversity of IoT IDS systems causes significant issues. These attributes make it troublesome and unrealistic to completely use all IoT elements and properties for IDS self-security. For peculiarity-based IDS, this study proposes and implements a novel component selection and extraction strategy (our strategy). A five-ML algorithm model-based IDS for machine learning-based networks with proper hyperparamater tuning is presented in this paper by examining how the most popular feature selection methods and classifiers are combined, such as K-Nearest Neighbors (KNN) Classifier, Decision Tree (DT) Classifier, Random Forest (RF) Classifier, Gradient Boosting Classifier, and Ada Boost Classifier. The Random Forest (RF) classifier had the highest accuracy of 99.39%. The K-Nearest Neighbor (KNN) classifier exhibited the lowest performance among the evaluated models, achieving an accuracy of 94.84%. This study's models have a significantly higher performance rate than those used in previous studies, indicating that they are more reliable.