Data Aggregation in Healthcare Applications and BIGDATA set in a FOG based Cloud System
Suryadip Chakraborty · OhioLink ETD Center (Ohio Library and Information Network) · 2016
Wireless Body Area Sensor Network (WBASN) is a network of wearable computing devices including few medical body sensors which capture and transmit different physiological data wirelessly to a monitoring base station like laptop.They provide real time health information of a person in a non-invasive way where the person, instead of implanting the miniaturized body sensor units inside the body, puts the sensors on the body surface [8].E-Healthcare is a popular healthcare application of WBASN commonly used today [8].Applications such as monitoring of patients with movement disorders, and specially the elderly for early fall detection, monitoring the injury of the athletes, surveillance of firefighters on ground etc., are very recent and popular applications of WBASN.When a physiological sensor continuously senses and generates huge amount of data, the network might become congested due to heavy traffic and it might lead to starvation and ineffectiveness of the WBASN system.This had led to the beginning of our first problem in this research which is the use of aggregation of data so as to reduce the traffic, enhancing the network life time, and saving the network energy.This research also focuses on dealing with huge amount of healthcare data which is widely known today as 'BIGDATA'.Our research investigates the use of BIGDATA and ways to analyze them using a cloud based architecture that we have proposed as FOG Networks which improves the use of cloud architecture.During the work of data aggregation, we propose to use of a statistical measure known as the regression polynomial of the order 4, 6 and 8. Due to computation, we performed the 6 th order coefficient computation and analyzed our results with real-time patient data iii through two statistical parameters of compression ratio and correlation coefficients.We also focus on studying the energy saving scenarios using our method and investigate how the node failure scheme would be handled.The reason for using polynomial regression is that it models a relationship between two variables t and y.This makes it perfect for modeling data that take place over time since 't' is time, and 'y' is the data reading.In addition, we can change the degree of the polynomial to suite our needs.This was chosen because it is a popular way to model two values which was what we needed.So far in this research, we did not compare any other techniques to polynomial regression, because being able to create and store Beta Values was convenient for the research we were doing at the time, and other techniques simply average them out.Also, as said before, polynomial regression is convenient for modeling the relationship between two variables unlike existing schemes.While focusing on building a polynomial based data aggregation approach in the WBASN system which involves summing and aggregating of wireless body sensors data of the patient's, we noticed the problem of dealing with thousand and millions of patients data when we run a WBASN system for continuous monitoring purpose.These generated data gathered in the network if not analyzed and studied immediately, it would lead the congestion and add heavy network traffic.We could not also deal with such big amount of data in the small storage of the physiological sensors with small computation abilities of them.So, there is an immediate necessity of an architecture and tools to deal with these thousands of data commonly known today as the BIGDATA.Analyzing the BIGDATA comprising of patient's vital parameters, we propose to implement a robust cloud-based structure that uses Hadoop based map reduce system It has been a great pleasure working with the faculty, staff, and students at the University of Cincinnati, Ohio, during my tenure as a Doctoral student.This work would never have been possible if it were not for the independence I was given to pursue my own research interests, thanks in large part to the compassion and considerable mentoring provided by Professor Dr. Dharma P.