The quality of water has a direct influence on both human health and the environment. Water is utilized for a variety of purposes, including drinking, agriculture, and industrial use. The water quality index (WQI) is a critical indication for proper water management. The purpose of this work was to use machine learning techniques such as RF, NN, MLR, SVM, and BTM to categorize a dataset of water quality in various places across India. Water quality is dictated by features such as dissolved oxygen (DO), total coliform (TC), biological oxygen demand (BOD), Nitrate, pH, and electric conductivity (EC). These features are handled in five steps: data pre-processing using min-max normalization and missing data management using RF, feature correlation, applied machine learning classification, and model’s feature importance. The highest accuracy Kappa, Accuracy Lower, and Accuracy Upper findings in this research are 99.83, 99.17, 99.07, and 99.99, respectively. The finding showed that Nitrate, PH, conductivity, DO, TC, and BOD are the key qualities that contribute to the orderly classification of water quality, with Variable Importance values of 74.78, 36.805, 81.494, 105.770, 105.166, and 130.173, respectively.

Brain tumors (BTs) are one of the deadliest diseases that can significantly shorten a person’s life. In recent years, deep learning has become increasingly popular for detecting and classifying BTs. In this paper, we propose a deep neural network architecture called NeuroNet19. It utilizes VGG19 as its backbone and incorporates a novel module named the Inverted Pyramid Pooling Module (iPPM). The iPPM captures multi-scale feature maps, ensuring the extraction of both local and global image contexts. This enhances the feature maps produced by the backbone, regardless of the spatial positioning or size of the tumors. To ensure the model’s transparency and accountability, we employ Explainable AI. Specifically, we use Local Interpretable Model-Agnostic Explanations (LIME), which highlights the features or areas focused on while predicting individual images. NeuroNet19 is trained on four classes of BTs: glioma, meningioma, no tumor, and pituitary tumors. It is tested on a public dataset containing 7023 images. Our research demonstrates that NeuroNet19 achieves the highest accuracy at 99.3%, with precision, recall, and F1 scores at 99.2% and a Cohen Kappa coefficient (CKC) of 99%.

Officials in the field of public health are concerned about a new monkeypox outbreak, even though the world is now experiencing an epidemic of COVID-19. Similar to variola, cowpox, and vaccinia, an orthopoxvirus with two double-stranded strands causes monkeypox. The present pandemic has been propagated sexually on a massive scale, particularly among individuals who identify as gay or bisexual. In this instance, the speed with which monkeypox was diagnosed is the most important aspect. It is possible that the technology of machine learning could be of significant assistance in accurately diagnosing the monkeypox sickness before it can spread to more people. This study aims to determine a solution to the problem by developing a model for the diagnosis of monkeypox through machine learning and image processing methods. To accomplish this, data augmentation approaches have been applied to avoid the chances of the model’s overfitting. Then, the transfer-learning strategy was utilized to apply the preprocessed dataset to a total of six different Deep Learning (DL) models. The model with the best precision, recall, and accuracy performance matrices was selected after those three metrics were compared to one another. A model called “PoxNet22” has been proposed by performing fine-tuning the model that has performed the best. PoxNet22 outperforms other methods in its classification of monkeypox, which it does with 100% precision, recall, and accuracy. The outcomes of this study will prove to be extremely helpful to clinicians in the process of classifying and diagnosing monkeypox sickness.

Rainfall prediction plays a crucial role in raising awareness about the potential dangers associated with rain and enabling individuals to take proactive measures for their safety. This study aims to utilize machine learning algorithms to accurately predict rainfall, considering the significant impact of scarcity or extreme rainfall on both rural and urban life. The complex nature of rainfall, influenced by various atmospheric, oceanic, and geographical factors, makes it a challenging phenomenon to forecast. This research employs data preprocessing techniques, outlier analysis, correlation analysis, feature selection, and several machine learning algorithms such as Naive Bayes (NB), Decision Tree, Support Vector Machine (SVM), Random Forest, and Logistic Regression. The study focuses on developing the most accurate rainfall prediction model by utilizing machine learning and feature selection techniques. The Artificial Neural Network (ANN) achieves a maximum accuracy of 90% and 91% before and after feature selection, respectively. Furthermore, k-means clustering and Principal Component Analysis (PCA) are applied to examine regional rainfall patterns in Australia. Lastly, to make our proposed machine learning simpler and more usable for general people, we have formulated a web-based application system using Flask in our research paper. Overall, this research demonstrates the effectiveness of different machine-learning techniques in predicting rainfall using Australian weather data.

In the wake of COVID-19, rising monkeypox cases pose a potential pandemic threat. While less severe than COVID-19, its increasing spread underscores the urgency of early detection and isolation to control the disease. The main difficulty in diagnosing monkeypox arises from its prolonged diagnostic process and symptoms that are similar to those of other skin diseases, making early detection and isolation challenging. To address this, the deployment of deep learning models on edge devices presents a viable solution for the rapid and accurate detection of monkeypox. However, the resource constraints of edge devices require the use of lightweight deep learning models. The limitation of these models often involves a trade-off with accuracy, which is unacceptable in the context of medical diagnostics. Therefore, the development of optimized deep learning models that are both resource-efficient for edge computing and highly accurate becomes imperative. To this end, an attention-based MobileNetV2 model for monkeypox detection, capitalizing on the inherent lightweight design of MobileNetV2 for effective deployment on edge devices, is proposed. This model, enhanced with both spatial and channel attention mechanisms, is tailored for rapid and early-stage diagnosis of monkeypox with better accuracy. We significantly improved the Monkeypox Skin Images Dataset (MSID) by incorporating a broader range of classes for similar skin diseases, thereby substantially enriching and diversifying the training dataset. This helps better distinguish monkeypox from other similar skin diseases, particularly in its early stages or when a detailed medical examination is unavailable. To ensure transparency and interpretability, we incorporated Gradient-weighted Class Activation Mapping (Grad-CAM) and Local Interpretable Model-Agnostic Explanations (LIME) to provide clear insights into the model’s diagnostic reasoning. Finally, to comprehensively assess the performance of our model, we employed a range of evaluation metrics, including Cohen’s Kappa, Matthews Correlation Coefficient, and Youden’s J Index, alongside traditional measures like accuracy, F1-score, precision, recall, sensitivity, and specificity. The attention-based MobileNetV2 model demonstrated impressive results, outperforming the baseline models by achieving 92.28% accuracy in the extended MSID dataset, 98.19% in the original MSID dataset, and 93.33% in the Monkeypox Skin Lesion Dataset (MSLD) dataset.