Page 11 - Big Data Analytics for Intelligent Healthcare Management

CHAPTER

BIO-INSPIRED ALGORITHMS FOR

BIG DATA ANALYTICS: A SURVEY, 1

TAXONOMY, AND OPEN

CHALLENGES

Sukhpal Singh Gill, Rajkumar Buyya
Cloud Computing and Distributed Systems (CLOUDS) Laboratory, School of Computing and Information Systems,
The University of Melbourne, Parkville, VIC, Australia

1.1 INTRODUCTION
Cloud computing is now the spine of the modern economy, which offers on-demand services to cloud
customers through the Internet. To improve the performance and effectiveness of cloud computing sys-
tems, new technologies, such as internet of things (IoT) applications (healthcare services, smart cities
etc.) and big data, are emerging, which further requires effective data processing to process data [1].
However, there are two problems in existing big data processing approaches, which degrade the per-
formance of computing systems such as large response time and delay due to data being transferred
twice [2]: (1) computing systems to cloud and (2) cloud to IoT applications. Presently, IoT devices
collect data with a huge amount of volume (big data) and variety and these systems are growing with
the velocity of 500MB/seconds or more [3].
For IoT based smart cities, the transfer of data is used to make effective decisions for big data an-
alytics. Data is stored and processed on cloud servers after collection and aggregation of data from
smart devices on IoT networks. Further, to process the large volume of data, there is a need for auto-
matic highly scalable cloud technology, which can further improve the performance of the systems [4].
Literature reported that existing cloud-based data processing systems are not able to satisfy the perfor-
mance requirements of IoT applications when a low response time and latency is needed. Moreover,
other reasons for a large response time and latency are: geographical distribution of data and commu-
nication failures during transfer of data [5]. Cloud computing systems become bottlenecked due to con-
tinually receiving raw data from IoT devices [6]. Therefore, a bio-inspired algorithm based big data
analytics is an alternative paradigm that provides a platform between computing systems and IoT de-
vices to process user data in an efficient manner [7].

1
Big Data Analytics for Intelligent Healthcare Management. https://doi.org/10.1016/B978-0-12-818146-1.00001-5
# 2019 Elsevier Inc. All rights reserved.