Urban Spatial Data Computing: Integration of GIS and GPS Towards Location-Based Recommendations

Urban Spatial Data Computing: Integration of GIS and GPS Towards Location-Based Recommendations

Uma V. (Pondicherry University, India) and Jayanthi Ganapathy (Anna University, India)
Copyright: © 2020 |Pages: 23
DOI: 10.4018/978-1-7998-0106-1.ch019

Abstract

Urban spatial data is the source of information in analysing risks due to natural disaster, evacuation planning, risk mapping and assessments, etc. Global positioning system (GPS) is a satellite-based technology that is used to navigate on earth. Geographical information system (GIS) is a software system that facilitates software services to mankind in various application domains such as agriculture, ecology, forestry, geomorphology analysis in earthquake and landslides, laying of underground water pipe connection and demographic studies like population migration, urban settlements, etc. Thus, spatial and temporal relations of real-time activities can be analysed to predict the future activities like predicting places of interest. Time analysis of such activities helps in personalisation of activities or development of recommendation systems, which could suggest places of interest. Thus, GPS mapping with data analytics using GIS would pave way for commercial and business development in large scale.
Chapter Preview
Top

Introduction

Urban spatial data, defines the spatial location and references of objects, people etc. They are generated from smart phones and other sources. They help in planning urban activities like disease management and control, traffic management etc. Internet of Things (IoT) is the recent advancement in information technology, electronic and telecommunication industry etc., which has led to the development of smart cities. Internetworking of devices and communication technologies has enabled wide range of applications in urban planning. Knowledge discovery on urban settlements is essential for decision making in demographic studies and urban growth (Allen, 1981 & Box et. al, 2012 & Campelo, 2013 & Claramunt and Theriault, 1995 & Rich et. al, 2009). In this view, the objective of this chapter is to present various computing methods for urban spatial data. These methods illustrate the importance of handing different data formats and utilisation of such acquired datasets in real time applications.

Data analytics and information management are intellectual property of every nation worldwide. Today, advancements in information technology have made it possible to acquire and process data efficiently. As technology advances, data storage and management becomes a fundamental issue as data is unstructured and differs in storage formats such as text, image, video. Data formats in terms of storage and computation demands high performance computing architectures (Li et. al, 2010 & Mohammady and Delavar, 2016). Today, the source of spatial data is plenty. They are multidimensional, unstructured and streaming in giga bits (Gbps). Such data differ in volume, velocity, veracity and variety and are termed as Spatial Big Data.

Machine Learning (ML) is scientific computation technology evolved from principles and concepts of Artificial Intelligence (AI). Today, ML is predominant in every domain application. Statistical method based computational models enable time series forecasting applications. Deep-learning is the recent advancement in ML using which data mining algorithms have evolved to equip parallel processing in information systems. These systems are enriched with data intensive computation using open source software frameworks. But, this chapter does not discuss about the application of machine learning for spatial data handling. This chapter actually focusses on Geographical Information System (GIS) and explains how it can be used in effective analysis of spatial data.

Raster and vector formats form the major category of spatial data. These datasets require pre-processing methods to make them useful in software systems for information retrieval and other decision support. Spatial computing algorithms are enriched with mathematical structures (Jayanthi and Uma, 2017a & Jayanthi and Uma, 2017b & Mondo et. al, 2010 & Randell, Cui, and Cohn, 1992 & Sudhira, Ramachandra, and Jagadish, 2004) . In this view, the objective of this chapter is to present various computing methods for urban spatial data. These methods illustrate the importance of handing different data formats and utilisation of such acquired datasets in real time applications.

GPS data processing using GIS helps in tracking and monitoring services. Point coordinates in the form of latitude and longitude of GPS data represents a spatial location on earth. This spatial information enables location based software service development such as travel information system, freight management, logistics and supply chain management in industries etc. An activity that has taken place in a spatial location at any given time represents temporal information.

Complete Chapter List

Search this Book:
Reset