Role of Machine Intelligence and Big Data in Remote Sensing

Role of Machine Intelligence and Big Data in Remote Sensing

Suriya Murugan (KPR Institute of Engineering and Technology, India) and Anandakumar Haldorai (Sri Eshwar College of Engineering, India)
Copyright: © 2020 |Pages: 13
DOI: 10.4018/978-1-5225-9750-6.ch007

Abstract

Technological advances in computing, data storage, networks, and sensors have dramatically increased our ability to access, store, and process huge amounts of data. “Big data” as a term has been the biggest trends of the last few years, leading to an elevation in research, as well as industry and government applications. The problem with current big data analysis faces any one of the following challenges: heterogeneity and incompleteness, scale, timeliness, privacy, and human collaboration. It's an undeniable fact that “data” forms the basis for geospatial industry. With technological advances in the collection, distribution, management, and access of data, there is an exponential increase in the amount of geospatial information. Computational intelligence techniques such as machine learning optimization and advanced data analytics can help make faster decisions. This chapter analyses how geospatial data is driving software and services market as a “big data challenge” and how biologically inspired techniques are effective in analyzing remote sensing data.
Chapter Preview
Top

Introduction

Human knowledge competes’ technology and hence thrust to process and store voluminous data creates challenges. Researchers from various communities like Computer Intelligence, Data Intelligence, Data Mining and Data Security need to analyze emerging optimization techniques to handle growth in data processing. The process of handling big data encompasses collection, storage, transportation and exploitation of data through data analytics, which is the core of big data processing.

A sensor is used to measure the energy reflected from the earth. This information can be displayed as a digital image or as a photograph. Sensors can be mounted on a satellite orbiting the earth, or on a plane or other airborne structure. As Lary, D. J., Alavi, A. H., Gandomi, A. H., & Walker, A. L. (2016) states the amount of remote sensing and other geographic data keeps getting bigger every day, the traditional GIS (Graphical Information Systems) are often insufficient for meaningful interpretation. Mapping and analysis become further complicated with the explosion of disruptive technologies like the cloud, embedded sensors, mobile and social media. Nature provides space for every living organism in spite of its numerous growth, similarly Nature Inspired Algorithms can help compute huge amount of data through its optimization techniques. Bio Inspired Algorithms (BIAs) like Evolutionary Computation based, Swarm Intelligence based or Ecology based are increasingly becoming popular in system identification, modeling, processing, and data mining.

Figure 1.

Application of big data and machine learning tools for GIS

978-1-5225-9750-6.ch007.f01

In order to take advantage and make good use of remote sensing data, we must be able to extract meaningful information from the imagery. Geeta R. Gupta and Prof. S. M. Kamalapur, (2014) Interpretation and analysis of remote sensing imagery involve the identification and/or measurement of various targets in an image in order to extract useful information about them. Soft computing methods for this kind of big data can be used in many applications and in many modules of remote sensing systems. Fig [1] depicts the process involved in remote sensing using IS tools and the data obtained from GIS will be only of two types’ spatial or temporal data. This data is categorized as Big Data and specifies some machine learning algorithms applicable for analyzing remote sensing data efficiently.

This paper is organized as follows Section II provides an detailed review of Challenges and Myths in GIS for Bigdata; Section III the Modeling using BigData tools is described, Section IV describes the Role of Bio Inspired algorithms for GIS Data analytics, Section V provides further Discussion. Section VI concluded with further enhancement.

Complete Chapter List

Search this Book:
Reset