The advent of Internet of Things (IoT) revolutionizes the healthcare sector by altering how medical equipment and humans interact while providing healthcare solutions. Applications of IoT in healthcare are advantageous to patients, their families, physicians, hospitals, and insurance companies. Before the IoT, patients could only speak with doctors physically, over the phone, or by text. There wasn’t a practical way for medical staff or facilities to continuously assess patients' health and provide guidance. Remote monitoring in the healthcare industry is made possible by utilizing sensor devices that help physicians to deliver superlative care to their patients. Sensor devices play a crucial role in the remote monitoring of patients. However, the failure of network or sensor devices may result in data with missing values. This incomplete data cannot be utilized to diagnose a patient or to make effective predictions of the disease in early diagnosis. To ensure the effective diagnosis and predict the risk of diseases in the patient, this paper proposed a novel ReMiss (Removing Missingness in medical datasets) algorithm to impute the missing values present in incomplete medical datasets. The proposed ReMiss algorithm is a data-partitioning based missing values imputation technique that partitions the datasets into complete and incomplete subsets to predict the missing values efficiently. The adjusted coefficient of determination, RMSEs and classification accuracy are the performance metrics used to evaluate the performance of the proposed ReMiss algorithm with the existing imputation techniques. The proposed ReMiss algorithm obtained an average classification accuracy of 93.53%.
15 September 2025 in International Journal of Multidisciplinary Research and Explorer
Integration of renewable energy systems, into the electrical grid has been investigated in the present research, with a special focus on the use of machine learning (ML) techniques in power system operations. In the framework of renewable energy, it critically investigates the applications of machine learning (ML) in forecasting, efficiency improvement, problem detection, and system optimization. The paper also discusses the primary challenges to implementing AI-driven solutions in contemporary power systems, including the need for quick decisions, cybersecurity risks, limitations on data availability and quality, and the difficulties of integrating with current grid infrastructure. This paper aims to provide an in-depth understanding of how intelligent algorithms are transforming the future of the electrical sector by highlighting both the revolutionary potential and the implementation challenges of AI technology in energy systems.