Big Data and Cloud Paradigm for Health Care Reports Monitoring and Performance Analysis

Abstract

Big data has real time data-intensive processing that runs on high performance clusters. Big data computing and information sharing are carried out effectively using data pre-processing model in cloud environment. The noise and inconsistent present in the data obtained from various sources are removed with help of pre-processing which minimizes the time taken for computation and improves the rate of information sharing. Therefore, big data involves the process of collecting and sharing the information with better memory consumption. Health care information is provided with certain conditions that make fastest communication using big data for sharing medical data. For the distribution of medical information and data allocation in cloud environment with big data approach, an efficient PSM-PBC model is proposed. Cloud computing presents a cost-effective approach of providing facilities for computation and big data processing. The sharing of information about medical records presented with different management according to the proposed PSM-PBC model includes three processes. Initially, tridiagonal symmetric matrix is constructed in parallel on distributed patients’ records with the help of big data applications.The size or complexity of the big data includes transaction and interaction of datasets that exceed regular technical capability in capturing, managing and processing data within reasonable cost. DSV-CP model is proposed for classifying the medical data to offer better communication in cloud environment. This model provides an efficient computation on big data applications and allocation of information in cloud computing environment. Initially, pre-processing based on IED is performed in DSV-CP model that helps to remove the noise and inconsistent medical data that are obtained from various sources. After performing the data pre-processing task, DSV-CP model uses support vector prediction classifier to effectively classify big data in cloud.A framework named as parallel LFR-CM is proposed for big data classification and distribution of medical data in cloud environment. At the same time, several numbers of medical data are processed for sharing specific information and for providing more security. Initially, parallel processing mechanism ensures minimum runtime of medical data among different organizers by using linguistic fuzzy rules based on the MapReduce parallel programming model. While reducing the runtime of medical data, a large number of data can be processed within a stipulated time that ensures various aspects in medical field. Then canopy shuffle algorithm is applied to the resultant linguistic fuzzy rules to train a different sample set that accelerates classification accuracy. Similarly, the convergence rate of canopy fuzzy MapReduce algorithm is accelerated. Finally, a hybrid classification model is developed to improve the classification time and search accuracy in parallel manner based on fuzzy knowledge and canopy fuzzy MapReduce algorithm.