Deep reinforcement learning-based precise prediction model for Smart M-Health system

The use of Android mobile phones and other wireless technology in the field of healthcare infers to mHealth (mobile health). Modern Science and technological developments have paved way for better and more sophisticated solutions towards Smart mHealth systems and preventive Smart Healthcare services for disease-treatment, surveillance, management of chronic disease and tracking epidemic outbreaks. Thus, the mHealth data can be collected from various end users, deposited in repository, perform analysis and suitable Smart Healthcare services can be made accessible to end users, anytime, anywhere, over the internet. This can be achieved by incorporating the methodologies of advanced Soft Computing methodologies, data communication, cloud storage and cloud computing, big data analysis, artificial intelligence, computer communication/networking and other engineering techniques. However, the analysis of such huge volumes of data and to provide precise Smart Healthcare services is a million-dollar question. This research article exposes a Deep Reinforcement Learning model for precisely predicting the disease and offer precise Smart m-Healthcare services to the end users. This research provides an intensive experimental analysis and investigation using synthetic health parameters that were simulated using various mHealth sensors. The dataset includes 15 varieties of mHealth metrics with a total dataset size of 285.