Sindh Madressatul Islam University

Access to safe drinking water is a growing global challenge, with billions of people exposed to water scarcity and contamination risks. Heavy metals in drinking water are of particular concern due to their toxic effects on human health and ecosystems. This study assessed the drinking water quality of Hunza Valley, Gilgit-Baltistan, Pakistan, where no comprehensive geospatial evaluation had previously been conducted. A total of 66 water samples from springs and glaciers were analyzed for physico-chemical parameters and heavy metals (Fe, Ni, Cd, Cr-VI, As, and Pb). Statistical analysis (correlation, principal component analysis and cluster analysis), water quality indices (Water Quality Index and Synthetic Pollution Index), human health risk assessment (Hazard Quotient and Hazard Index) and geostatistical interpolation (Ordinary Kriging) were employed. Results showed that As (77

Reliable detection of railway track faults is essential for preventive maintenance and safety. We introduce RailNet, a deep learning-based convolutional architecture that uses a DenseNet121 backbone as its feature extractor together with a streamlined classification head tailored to rail imagery. RailNet is fine-tuned with a task-aware augmentation policy designed to mimic in-field conditions (viewpoint change, illumination variation, and occlusions) and includes built-in gradient-weighted class activation mapping (Grad-CAM) interpretability to highlight defect regions that drive predictions. An ablation study quantifies the contribution of key head components (batch normalisation, dropout, and layer depth) to generalisation. RailNet is evaluated on a labelled dataset of faulty and non-faulty track images; it achieves 96% accuracy with macro-averaged precision, recall, and F1-score of 0.96 on a held-out test set, indicating balanced performance across classes. Heatmap visualisations consistently localise cracks and misalignments, supporting operator trust and triage. By combining a strong backbone with domain-specific augmentation, quantified architectural choices, and built-in interpretability, RailNet provides a reliable and efficient basis for early, automated track-fault detection, enabling more proactive maintenance scheduling and contributing to reduced accident risk.

The study examines in detail how deep learning models (MobileNet, ResNet50, EfficientNetB4, InceptionV3, Xception, and DenseNet201) support the automated detection of vitiligo in medical images. Further, this research also seeks to design a solid transfer learning algorithm to get optimum results by joining DenseNet and Firefly Optimization, which is known as Firefly-Optimized DenseNet201 and it efficiently deals with classifying a range of images from the dataset. The dataset was obtained from Kaggle, which is based on two classes, i.e. vitiligo and healthy. Training the model on 3,628 skin images was accomplished, where the accuracy and loss were reviewed on the training and validation sets as each epoch finished. MobileNet reached high training accuracy quickly (93.86%), but it started overfitting after epoch 4. ResNet50, on the other hand, displayed steady validation accuracy of 87.4%. Using bio-inspired methods to tune hyperparameters, the Firefly-Optimized DenseNet201 achieved both high training accuracy (97.77%) and validation accuracy (89.58%). This model may be useful as a computer-aided tool for dermatologists, particularly in areas where there are shortages and prompt and precise vitiligo detection is crucial. The findings suggest useful ways to use deep learning in dermatology by focusing on both efficient processing and correct results.

Cervical cancer remains a major contributor to cancer-related mortality among women worldwide, with a disproportionately high burden in low- and middle-income countries. Pap smear imaging is a standard screening modality for detecting precancerous and malignant cervical abnormalities; however, manual interpretation is labor-intensive, subjective, and susceptible to interobserver variability. To mitigate these limitations, this study proposes a hybrid deep learning framework for automated cervical cell classification that integrates Vision Transformers (ViT) with Convolutional Neural Networks (CNN). The proposed framework incorporates a structured preprocessing pipeline, including image resampling and data augmentation strategies such as random horizontal flipping and controlled rotations, to enhance model generalization and mitigate overfitting. Input images are divided into fixed-size patches and processed through a ViT backbone to capture long-range contextual dependencies. Complementary CNN layers are employed to extract localized morphological features critical for cytological analysis. The extracted representations are combined through a feature fusion mechanism and passed to fully connected layers for classification. The ViT component is initialized with pretrained weights and subsequently fine-tuned on cervical cytology datasets. Experimental evaluation on the Herlev and SIPaKMeD datasets achieved classification accuracies of 97.31% and 96.62%, respectively. Ablation analysis showed that the CNN branch improves local morphological feature discrimination, while class-wise evaluation indicated stable performance across multiple cytological categories. These results support the effectiveness of the proposed CNN-ViT fusion framework for automated cervical cell classification and motivate further validation on larger and patient-indexed clinical datasets.

Accurate local rainfall prediction is vital for climate-vulnerable regions such as Sindh, Pakistan, where agriculture, water management, and flood preparedness depend on reliable forecasts under highly variable hydroclimatic regimes. This study proposes a compact physics-informed neural network that embeds an explicit relative-humidity constraint into the loss function to suppress unphysical precipitation under dry conditions, operationalized by penalizing predicted rainfall when humidity falls below 60