Abstract:
Currently, scientific research on healthcare demand to develop an interactive solution
to provide healthy life facility with earlier disease detection to the user. In the recent
time, healthcare industries are generating lots of unstructured or semi-structured
data which needs to be analyzed and processed in real time. In this paper, we have
designed a healthcare system to deal with patients biological, and emotional condition
as well as the previous health history with genetical data. The data generated by the
patient and the hospital are gathered in High-Performance Computer server, and the
medical history, as well as genetical data, are collected from the cloud synchronization.
We proposed a probabilistic data acquisition scheme to analyze the data and apply
MapReduce algorithm in HPC to make structure database. The system holds a data
warehouse which provides a two-way interaction between HPC and cloud for interactive
information gathering. In this research, we present a prediction algorithm which is
performed in cloud server to predict a patients disease. We apply Random Forest, SVM,
C5.0, Naive Bayes and Arti cial Neural Network for prediction analysis and shows the
side by side comparison on those algorithms.
i
Description:
This thesis submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering of East West University, Dhaka, Bangladesh.