Short Communication
Appiah Prince
Abstract
The era of digital age has come with a lot of data which needs to be analyze using predictive analytic tools. In a case of exponentially increasing amount of healthcare data with Internet of Things (drone) has drawn the attention for big data analytics. The trend today in diseases surveillance epidemiological data collection is best done using drones. Hence, it comes with structured, semi-structured and unstructured data that leads to data trawling using drones. This paper proposes big data tool for appropriate machine learning technique for segregation and clustering drone data, for accurate prediction to improve the quality of healthcare. The proposed approach, aiming at overcoming data trawling using drone and provide real-time analytics of crowdsensing data. Implementation was done using Apache Spark core with machine learning algorithm for better segregation of real-time streaming from different sources from the crowds. According to the results of the conducted experiment, the concept has the potential to improve quality healthcare predictions. The result from the study clearly indicated that K-means cluster have the highest rate of controlling segregating data in real-time as compare with grid-based and density-based clustering