Effective Feature Selection Using Hybrid GA-EHO for Classifying Big Data SIoT

Effective Feature Selection Using Hybrid GA-EHO for Classifying Big Data SIoT

Iyapparaja M (Vellore Institute of Technology, Vellore, India) and Deva Arul S (Vellore Institute of Technology, Vellore, India)
Copyright: © 2020 |Pages: 14
DOI: 10.4018/IJWP.2020010102

Abstract

Several novel applications and services of networking for the IoT are supported by the Social Internet of Things (SIoT) in a more productive and powerful way. SIoTs are the recent hot topics rather than other extensions of IoTs. In this research, the authors have extracted the Big Data SIoT using the well-known model named MapReduce framework. Moreover, the unwanted data and noise from the database are reduced using the Gabor filter, and the big databases are mapped and reduced using the Hadoop MapReduce (HMR) technique for improving the efficiency of the proposed GA-EHO. Furthermore, the feature selection using GA-EHO is processed on the filtered dataset. The implementation of the proposed system is done by using some machine learning classifiers for classifying the data and the efficiency is predicted for the proposed work. From the simulation results, the specificity, maximum accuracy, and sensitivity of the proposed GA-EHO are produced about 87.88%, 99.1%, and 81%. Also, the results are compared with other existing techniques.
Article Preview
Top

1. Introduction

In this modern era, the development of solutions and technologies based on IoT are becoming a crucial challenge. Moreover, the IoT technology is the collection of pervasive data and its sharing for obtaining a certain goal. The data in IoT refers the integer values or variables of certain attributes for a condition to be reached. A predefined interface is used for carrying the certain functions that allowed by IoT services (Lopez, Rios, Bao, & Wang, 2017; Ahmad, Rathore, Paul, & Rho, 2016). Several researchers are giving interest in finding the security issues that are arising during the integration and discovery of data within IoT. Moreover, the SIoT is the combination of large social networks that are connection of people and objects, people-to-people, and objects-to-objects. For this reason, data processing faces various challenges for improving storage and cleaning, data collection, and performing real-time analysis (Yim et al., 2017; Song et al., 2019; Nagarajan & Gandhi, 2019). Furthermore, in the field of Big Data, several platforms and standards have introduced by the vendors of relational database which can be used for data analysis and data aggregation (Ochoa, Fortino, & Fatta, 2017; Wasi-ur-Rahman et al., 2013).

The SIoT and big data are perfect characterization of social systems and human progression is represented by IoT. Several feature selection algorithms are proposed that are mainly classified into two main categories; wrapper-approaches, and filter-approaches. In filter-based approach, the process of filtration is analyzed before classification because of the independent usage nature of classification-algorithms (Ahmed et al., 2017; Iyapparaja & Bhanupriya 2017; Rathore, Ahmad, & Paul, 2016). Several machine learning algorithms are used for classifying the data collected from the SIoT. These approaches have various benefits of resolving nonlinear, little specimen, and pattern recognition of high dimensional. In addition, advanced things cannot be applied to SIoT as it has huge amount of data processed along with a high bandwidth (Iyapparaja et.al., 2012; Iyapparaja & Tiwari, 2017).

  • The main endowment of this research is to ensure the system of SIoT structure with big data on classification model for helping features.

  • For analyzing the process, some social network databases are used and classification model is finally performed. Moreover, the systems performance is improved using the classifiers based on the optimal features which are used in this approach.

  • This proposed work helps SIoT systems and provide guidance for the researchers to analyze the SIoT big data.

The rest of this research is described as follows, segment 2 describes the literature review of the existing works, segment 3 presents the proposed GA-EHO algorithm, and segment 4 defines the simulation results of the proposed system and comparison of various classifiers with previous works are processed and finally the conclusion of the research work is given with future enhancement.

Top

Hasan and Al-Turjman (2018) has proposed embedded sensors for SIoT for exchange and gather information of individuals or protests associated with the developing system. The authors proposed Particle Multi-Swarm Enhancement (PMSO) which is a bio-inspired for calculating directly to recoup, select and build disjoint ways that disappoints the endure while fulfilling the parameters of Quality of Service (QoS). The optimal directions are decided by multi-swarm technique for choosing the directed multipath and trading of messages at the same time from all position of the systems. The qualities utilized from all the individuals best data that demonstrated from the results which is substantial technique which is a motivation for the enhancement of the PMSO execution.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 12: 2 Issues (2020): 1 Released, 1 Forthcoming
Volume 11: 2 Issues (2019)
Volume 10: 2 Issues (2018)
Volume 9: 2 Issues (2017)
Volume 8: 1 Issue (2016)
Volume 7: 2 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing