Chronic kidney disease (CKD) is a global healthcare issue that highlights the need for early identification for better quality of life for patients. This study evaluates various machine learning (ML) classifiers on datasets from UCI and self-collected sources in search of the best methods for CKD classification. This review examines commonly used ML models like support vector machine, K-nearest neighbor, naïve Bayes, decision trees, random forest, logistic regression and boosting-based ensemble methods. The results demonstrated the highest performance of ensemble methods. Despite these promising results, challenges related to model integration and interpretability still exist. Transparent models that are reliable and efficient are suitable for enhancement of clinical application(s). By overcoming these challenges, the work highlights importance of ML for CKD detection and treatment paving the way for artificial intelligence (AI)-driven healthcare solutions that are both effective and trustworthy.

Sentiment Analysis (SA) has achieved significant growth in recent decades among the evolving applications, including social networks and decision-support systems. Recently, the proliferation of data volumes for Dravidian languages has made SA a significant task to retrieve useful information. The prevailing works are focused more on the monolingual analysis and lack a complete study of the recent trends. The research presents a survey on the evolving landscape of SA in Indian languages with a specific emphasis on Dravidian languages. An overview of SA, emphasizing the levels and the purpose of the analysis is presented. Moreover, the generic process is explained with the major advancements of pre-trained architectures applied in recent works. Along with the various classification methodologies, this study analyzes the strengths conforming to the various training databases and languages, mainly focused on sentiment classification. Furthermore, an exhaustive view of the existing challenges and the applications is provided, offering unique linguistic guidance in the field of SA.

In order to enable users to extract useful insights on demand, this paper presents a unique approach for secure and privacy-preserving ranked search in cloud environments. There is a rising need for strong systems that strike a balance between data utility and individual privacy as cloud-based data processing and storage become more and more prevalent. Our suggested methodology makes use of sophisticated multi-keyword operators and encryption methods to offer a safe and effective solution for cloud-based ranked search that protects privacy. Our methodology's essential component is the combination of a safe encryption technique and sophisticated multi-keyword search operators. With this combination, users can do ranked searches on encrypted data while maintaining the privacy of the underlying data. Our approach leverages strong cryptography protocols and an advanced indexing mechanism to provide rapid retrieval of relevant results while protecting confidential information from unauthorized individuals. Secure query processing techniques and encryption are added for added privacy protection. This guarantees that throughout the ranking search operations, the decrypted data cannot be accessed by the cloud service provider or any other parties participating in the data processing pipeline. Users don't have to compromise the privacy of their stored data or expose the exact text of their queries to obtain ranked results based on several keywords. Our technology is especially useful in situations when customers need instantaneous insights from data stored in the cloud without compromising privacy. Our technology protects the secrecy of the underlying datasets while enabling customers to obtain secure insights on demand in a variety of sensitive sectors, including financial analysis and medical research. The suggested method offers a strong and adaptable way to achieve privacy-preserving ranked search in cloud environments. Through the incorporation of sophisticated multi-keyword operators and encryption strategies, our approach guarantees users may effectively obtain pertinent data while maintaining personal privacy. With its ability to provide safe, anytime access to insights stored in cloud-based data repositories, this breakthrough has enormous potential for a variety of applications.