An efficient data science technique for IoT assisted healthcare monitoring system using cloud computing

In this era of smart healthcare system, patient expects better healthcare support with low cost which satisfy through the innovative process such as Internet of Things (IoT), cloud computing and data science techniques. Meantime, the healthcare industry faces many problems including the data collection and storage for further progress. For healthcare monitoring system, the data collection and data analytics plays important role to screening the patient health. Therefore, data science techniques and cloud computing are heart for the healthcare system to resists several problems in terms of technical aspects. For further enhancement, efficient data science technique is proposed for IoT assisted healthcare monitoring (DST-HM) system using cloud computing, which improves the data processing efficiency, data accessibility in cloud. The several IoT sensors are used in a person corpse to collect the real clinical data. The composed data are then maintained in cloud for added data science processing. In DST-HM system, we first introduce a modified data science technique that is, improved pigeon optimization (IPO) algorithm for grouping the cloud stored data which enhances the prediction rate. Second, we illustrate the optimal feature selection technique for feature extraction and selection.