Today, sensors generate vast amounts of data in different fields such as hospitals, the transport sector, social media, and so on. In hospitals, the use of sensors that are installed in the patient’s body to monitor the pulse rate, heartbeats, head movement, eyes, and other body parts. Every day, these collected data are stored in local data servers and database servers by various sensors that require effective handling of these data. Sensors are primarily used in most of the IoT applications in everyday life from which smart city plays a crucial role. The aim of the work is to address the application of big data in healthcare and life science, including different types of data that involve special attention in processing. This work focuses on the use of large-data analytical techniques to process medical data. A large volume of unstructured cancer database is considered to identify and predict different types of cancer such as breast cancer, lung cancer, blood cancer, and so forth. This research involves the segmentation of thousands of records on cancer forms in a broad cancer database into various segmented databases. Using KNN algorithm this segmentation, classification and prediction will be achieved.

Increasing of humanity and development of Internet resources, storage size is growing with each day, whereby digital records are accessible in clouds of an exploratory format. The immediate future of Big Data is coming shortly for almost all other sectors. Big data can aid in the metamorphosis of significant company operations by offering a recommended and reliable overview of available data. Big data has also figured prominently in the detection of violence. Present framework for designing Big data implementations is capable of processing vast quantities of data through Big data analytics using collections of computing devices together to execute complex processing. Furthermore, existing technologies have not been built to fulfil the specifications of time-critical application areas and are far more oriented on real applications than on time-critical ones. This paper proposes the lightweight architecture called Yet Another Resource Negotiator (YARN), which focuses on the concept of a time-critical big-data system from the perspective of specifications and analyses the essential principles of several common big-data implementations. YARN as the normal computational framework to help MapReduce and another application instances within that Hadoop cluster. YARN requires multiple programs to execute concurrently on a constitutive common server and assent programs to delegate services depending on need. The final evaluation is accompanied by problems stemming from infrastructure and services that serve applications, recommend frameworkand provide preliminary efficiency behaviours that often contribute system impacts to implementation reliability.

No abstract