Investigation on secured task scheduling and service quality for crowdsource in healthcare using deep learning with big data

Abstract

Computer technology has a wide application as well as medical newlinedata is also increasing, and Big data analysis of medical record induce to newlinereduce time in addition securely providing support for intelligent detection of newlinemedical health data. The crowdsourcing approach is essential to handle newlinecomplex data management problems such as missing values, schema newlinematching, and data linkage. In the proposed system, Deep learning newlineaugmented decision-making (DLADM) algorithm is used to share resources newlinebased on the multiple user requests through leverage scheduling algorithms newlineto optimize the execution of a task with various types of tasks run newlineconcurrently. newlineand#61623; Secure priority-wise task scheduling using deep learning by crowdsource newlinedata in a medical environment newlineand#61623; QoS analysis for crowdsourcing data using deep learning in medical field newlineand#61623; Multi-tenant crowdsourcing jobs different scheduling tasks assigned and newlineseveral requesters in the platform priority wise assigning, bandwidth and newlinetask duration as input scheduling using DLADM algorithm of deep newlinelearning. newlineCrowdsourced security is essential to avoid a third-party attack newlinewhile scheduling the task by all the requester have to get registered first with newlinethe SECurity-As-A- Service (SECaaS) contributor and crowd user share newlinesome of their resources for computation and security assessment. newline