Page 20 - Big Data Analytics for Intelligent Healthcare Management

10 CHAPTER 1 BIO-INSPIRED ALGORITHMS FOR BIG DATA ANALYTICS

unsupervised technique, which clusters the data based on related attributes. The association technique
is used to establish a relationship among different datasets. There are five types of NoSQL database
management systems (DBMS) that are used in existing techniques: Hbase, Cassandra, MongodB,
Couchbase, and Neo4J. The two different types of mechanism for making decisions in bio-inspired
algorithms for big data analytics are: proactive (working on forward-looking decisions, which requires
forecasting or text mining) and reactive (decisions based on the requirement for data analytics).
Scalability refers to the mechanism of a computing system to scale-up or scale-down its nodes based
on the amount of transfer of data for analytics. Big data analytics techniques use a large amount of
storage space to store the information to perform the different types of analytics to extract the required
information. Fault tolerance of a system is the ability to process the user data within the required time
frame. The type of data that is requiring analytics is continually changing, so there is a need for agility-
based big data analytical models to process user data in a required format. Virtualization is a technique
that is required for cloud-based systems to create virtual machines for processing user data in a dis-
tributed manner. Execution cost is the amount of efforts that are required to perform big data analytics.
Ease of use is defined as the mechanism that explains how easily the system can be used to perform big
data analytics. Data management is discussed in Section 1.2. Table 1.1 shows the comparisons of bio-
inspired algorithms for big data analytics based on different parameters.

1.3.4 DISCUSSIONS
Table 1.1 shows the comparisons of bio-inspired algorithms for big data analytics based on different
parameters, which helps the reader to choose the most appropriate bio-inspired algorithm. In the
current scenario, cloud computing has emerged as the fifth utility of computing and has captured
the significant attention of industries and academia for big data analytics. Virtualization technology
is progressing continuously, and new models, mechanisms, and approaches are emerging for
effective management of big data using cloud infrastructure.
Fog computing uses network switches and routers, gateways, and mobile base stations to provide
cloud service with minimal possible network latency and response time. Therefore, fog or edge devices
can also perform big data analytics at the edge device instead of at a decentralized database or server.

1.4 FUTURE RESEARCH DIRECTIONS AND OPEN CHALLENGES
Bio-inspired algorithm-based big data analytics has several challenges that need to be addressed, such
as resource management, usability, data processing, elasticity, resilience, heterogeneity in intercon-
nected clouds, sustainability, energy efficiency, data security, privacy protection, edge computing,
and networking.

1.4.1 RESOURCE SCHEDULING AND USABILITY
Cloud resource management is the ability of a computing system to schedule available resources to
process user data over the Internet. The cloud uses virtual resources for big data analytics to process
user data quickly and cheaply. The virtualization technology provides effective management of cloud
resources using bio-inspired algorithms to improve user satisfaction and resource utilization. There is a