The hazards associated with cyber security attacks have increased due to our increasing reliance on digital technologies. We suggest an ensemble strategy employing multiple models of machine learning to get over these restrictions. Our suggested approach detects an extra 141 dangerous URLs, outperforming the single model that is currently in use by 6%. We gathered a collection of malicious and benign URLs for this investigation. Applying Principal Component Analysis (PCA) to feature extraction. Subsequently advantageous features are selected and categorised using the Social Spider optimised Densely-connected Convolutional Caps net (SSO-DCN). The most effective detection frameworks and automated methods for identifying rogue web pages, including those distribute malicious malware, are included in the proposed technology. When comparing the proposed method to the existing approaches, the improvements are in mean accuracy (96.30%), precision (96.90%), F1-Measure (97.20%), recall (96.90%), FPR (3.50%) and FNR (3.90%).

Precision agriculture relies heavily on crop selection to improve sustainability and increase productivity. The increasing problems of soil erosion, climate change, and water shortages have made it crucial to optimize crop selection through cutting-edge methods to increase farm yields and enhance resource efficiency. This research attempts to develop machine learning (ML) models, such as logistic regression (LR), Gaussian Naive Bayes (GNB), support vector classifier (SVC), K-nearest neighbors (KNN) classifier, decision tree (DT) classifier, extra tree (ET) classifier, random forest (RF) classifier, and bagging classifier, to optimize crop selection for precision agricultural systems. A large dataset comprising information on crop recommendations, weather patterns, and soil characteristics was used in this research. The data is preprocessed using the interquartile range (IQR) method to remove outliers and ensure that all features contribute equally to the model. Linear discriminant analysis (LDA) is used to extract the important features for feature extraction. The RF classifier was determined to be the most effective method for raising the precision of crop selection forecasts. This framework is designed to provide actionable insights for selecting optimal crops based on environmental conditions and resource availability. The suggested model is a valuable tool for crop selection optimization in precision agriculture, as preliminary results show that it outperforms traditional ML models in terms of F1-score, precision, accuracy, and recall at 99.88% (all measures). According to the research, modern ML algorithms can revolutionize agricultural practices and provide a sustainable solution to increase crop output while reducing resource wastage. Received: 29 April 2025 | Revised: 13 August 2025 | Accepted: 19 August 2025 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The Crop Recommendation datasets that support the findings of this study are openly available in Kaggle at https://www.kaggle.com/datasets/atharvaingle/crop-recommendation-dataset. The data that support the findings of this study are openly available in Kaggle at https://www.kaggle.com/datasets/shekharyada/crop-soilcsv. Author Contribution Statement Rajesh Natarajan: Conceptualization, Methodology, Validation, Writing – original draft, Writing – review & editing, Funding acquisition. Sujatha Krishna: Validation, Formal analysis, Writing – original draft, Writing – review & editing. Pradeepa Ganesan: Software, Formal analysis, Visualization. Amna Al Kaabi: Writing – review & editing, Supervision. Rajesh Kala: Resources, Data curation. Anthony Mendoza Madlambayan: Resources, Data curation, Visualization.

Purpose: The purpose of this paper is to improve the privacy in healthcare datasets that hold sensitive information. Putting a stop to privacy divulgence and bestowing relevant information to legitimate users are at the same time said to be of differing goals. Also, the swift evolution of big data has put forward considerable ease to all chores of life. As far as the big data era is concerned, propagation and information sharing are said to be the two main facets. Despite several research works performed on these aspects, with the incremental nature of data, the likelihood of privacy leakage is also substantially expanded through various benefits availed of big data. Hence, safeguarding data privacy in a complicated environment has become a major setback.Design/methodology/approach: In this study, a method called deep restricted additive homomorphic ElGamal privacy preservation (DR-AHEPP) to preserve the privacy of data even in case of incremental data is proposed. An entropy-based differential privacy quasi identification and DR-AHEPP algorithms are designed, respectively, for obtaining privacy-preserved minimum falsified quasi-identifier set and computationally efficient privacy-preserved data.Findings: Analysis results using Diabetes 130-US hospitals illustrate that the proposed DR-AHEPP method is more significant in preserving privacy on incremental data than existing methods. A comparative analysis of state-of-the-art works with the objective to minimize information loss, false positive rate and execution time with higher accuracy is calibrated.Originality/value: The paper provides better performance using Diabetes 130-US hospitals for achieving high accuracy, low information loss and false positive rate. The result illustrates that the proposed method increases the accuracy by 4% and reduces the false positive rate and information loss by 25 and 35%, respectively, as compared to state-of-the-art works.

Agriculture is the backbone of national food security and sustainable economic development, which requires performance analysis of the correct crop choice based on soil nutrients and environmental conditions. However, traditional crop selection heavily depends on farmers' experience and is not necessarily data driven. To tackle this issue, this study proposes an intelligent decision support system for crop recommendation based on deep learning techniques. Factors such as nitrogen, phosphorus, potassium, soil power of hydrogen, rainfall, and temperature were used to predict suitable crop selection. Several architectures—such as convolutional neural networks-1D, long short-term memory, residual deep multilayer perceptron, Wide and Deep, and ResNet-1D—were evaluated and compared. Among them, the highest performance was achieved by ResNet-1D, with 93.61% accuracy and very high precision, recall, and F1-score values. The system supports precision agriculture by leveraging local data to improve decision making and has been implemented as a Streamlit-based web application that allows real-time recommendations for crops.

Artificial intelligence (AI) enables data‐driven modeling and forecasting for smart city environmental monitoring. Government agencies and the public are becoming more concerned about air quality, which impacts several aspects of the human environment and development. Through careful analysis of environmental and pollution data, the research identified key factors that influence air pollution monitoring. Traditional air pollution forecasting methods often show limited predictive accuracy due to simplified modeling assumptions and the absence of heuristic optimization strategies for model parameter tuning. This research aimed to develop intelligent ecosystem models for smart cities using a battle royal optimized multilevel artificial neural network (BRO‐MLANN). The Global Air Pollution dataset from Kaggle, which includes air quality observations from multiple towns, is used to assess the suggested model. The goal of this endeavor is to improve air quality prediction in smart cities by using an intelligent ecosystem model based on BRO‐MLANN. The results show how well the framework supports air quality monitoring and decision‐making in smart city environments, even if the dataset encompasses a variety of urban areas and does not represent all worldwide regions. Prior to model training, Z ‐score normalization was used to standardize the data. The stacked autoencoder (SAE) used a feature extraction technique to predict air quality to plan intelligent environment design for smart cities. In developing intelligent ecosystem methods for smart cities, the BRO‐MLANN is utilized. The results show that the BRO‐MLANN method achieves higher performance scores for prediction rate, MAE, RMSE, MAPE, and accuracy compared to other competing techniques.