Muutke küpsiste eelistusi

GIS and Machine Learning for Small Area Classifications in Developing Countries [Kõva köide]

  • Formaat: Hardback, 246 pages, kõrgus x laius: 234x156 mm, kaal: 453 g, 33 Tables, black and white; 7 Illustrations, color; 61 Illustrations, black and white
  • Ilmumisaeg: 30-Dec-2020
  • Kirjastus: CRC Press
  • ISBN-10: 0367322447
  • ISBN-13: 9780367322441
Teised raamatud teemal:
GIS and Machine Learning for Small Area Classifications in Developing CountriesSuurem pilt
  • Formaat: Hardback, 246 pages, kõrgus x laius: 234x156 mm, kaal: 453 g, 33 Tables, black and white; 7 Illustrations, color; 61 Illustrations, black and white
  • Ilmumisaeg: 30-Dec-2020
  • Kirjastus: CRC Press
  • ISBN-10: 0367322447
  • ISBN-13: 9780367322441
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9780367322441.html
Märksõnad:
Since the emergence of contemporary area classifications, population geography has witnessed a renaissance in the area of policy related spatial analysis. Area classifications subsume geodemographic systems which often use data mining techniques and machine learning algorithms to simplify large and complex bodies of information about people and the places in which they live, work and undertake other social activities. Outputs developed from the grouping of small geographical areas on the basis of multi- dimensional data have proved beneficial particularly for decision-making in the commercial sectors of a vast number of countries in the northern hemisphere. This book argues that small area classifications offer countries in the Global South a distinct opportunity to address human population policy related challenges in novel ways using area-based initiatives and evidence-based methods.

This book exposes researchers, practitioners, and students to small area segmentation techniques for understanding, interpreting, and visualizing the configuration, dynamics, and correlates of development policy challenges at small spatial scales. It presents strategic and operational responses to these challenges in cost effective ways. Using two developing countries as case studies, the book connects new transdisciplinary ways of thinking about social and spatial inequalities from a scientific perspective with GIS and Data Science. This offers all stakeholders a framework for engaging in practical dialogue on development policy within urban and rural settings, based on real-world examples.

Features:











The first book to address the huge potential of small area segmentation for sustainable development, combining explanations of concepts, a range of techniques, and current applications.





Includes case studies focused on core challenges that confront developing countries and provides thorough analytical appraisal of issues that resonate with audiences from the Global South.





Combines GIS and machine learning methods for studying interrelated disciplines such as Demography, Urban Science, Sociology, Statistics, Sustainable Development and Public Policy.





Uses a multi-method approach and analytical techniques of primary and secondary data.





Embraces a balanced, chronological, and well sequenced presentation of information, which is very practical for readers.

Arvustused

A very comprehensive, powerful and insightful contribution to the field of Geoinformatics in the Social Sciences. Highly novel both in terms of the study regions it focuses on and in the state-of-the-art methods it engages with and applies.

Dimitris Ballas, Professor of Economic Geography, University of Groningen. The Netherlands

This book represents a clearly written and highly inventive attempt to enrich public policy analysis in developing countries by applying GIS and machine learning for small area classification. It offers both a technical introduction to the topic and a wide range of contemporary illustrative applications from both Nigeria and the Philippines. The book should be of interest to development scholars, methodologists and to human geographers interested in the application of new spatial technologies to Global South contexts.

Roger Burrows, Professor of Cities, School of Architecture, Planning, and Landscape, Newcastle University, UK

Foreword xi
Preface xv
Acknowledgements xvii
Author Biography xix
Abbreviations xxi
Part 1 Background, Concepts, and Definitions
1 Introduction
3(24)
1.1 Global South or Developing World?
3(4)
1.2 Demographic Shifts across the Developing World
7(2)
1.3 The Demographic Payoff: A Myth or Reality?
9(4)
1.4 Public Policy Challenges Arising from Shifting Demographic Patterns
13(5)
1.5 Critical Review of Global and National Policy Responses
18(3)
1.6 Why This Book Was Written
21(6)
2 Origins and Concept of Social Area Classification
27(18)
2.1 Conceptual Clarifications
27(1)
2.2 Pre-1980s History of Area Classifications
28(5)
2.3 Area Classifications in the 1980s and 1990s
33(1)
2.4 Post-2000 Area Classifications
34(2)
2.5 Criticisms Levied against the Social Sorting of People in Small Geographic Areas
36(5)
2.6 Conclusion
41(4)
3 Public Policy Prospects of Small Area Classifications for Developing Countries
45(18)
3.1 Unmasking Subnational Population Disparities
45(2)
3.2 Evidence-Based Decision-Making
47(2)
3.3 Transparent Resource Allocation
49(2)
3.4 Targeting of Policy Interventions
51(1)
3.5 Monitoring the Impacts of National Policies
52(1)
3.6 Public Sector Social Marketing
53(2)
3.7 Differential Communication Strategies
55(2)
3.8 Geographic Forecasting of Social and Economic Futures
57(1)
3.9 Conclusion
58(5)
4 Reasons for Slow Proliferation of Area Classification across Developing Countries
63(22)
4.1 Lack of Publicity of the Benefits of Area Classifications
63(2)
4.2 Institutional and Organizational Weaknesses
65(1)
4.3 Cultural Constraints
65(1)
4.4 Physical Infrastructure versus Spatial Data Infrastructure
66(2)
4.5 Analytical Capacity and Costs
68(1)
4.6 Local Security and Safety Conditions
69(1)
4.7 Existence of Data
70(1)
4.8 Access to Data
71(1)
4.9 Quality of Data
72(1)
4.10 Mitigating Barriers
72(5)
4.11 Conclusion
77(8)
Part 2 Underlying Techniques and Deployment Approaches
5 Building Blocks: Spatial Data Preparation
85(24)
5.1 Clarifying and Defining the Purpose of Classification
85(2)
5.2 Principles for Selecting Initial Input Variables
87(5)
5.3 Quality Control and Reduction of Initial Variables
92(7)
5.4 Dealing with Outliers and the Problem of Different Measurement Units
99(5)
5.5 Weighting Techniques
104(1)
5.6 Conclusion
105(4)
6 Machine Learning Methods for Building Small Area Classifications
109(22)
6.1 Machine Learning, Artificial Intelligence, and GIS
109(2)
6.2 Algorithms for Grouping Data
111(8)
6.3 Determining the Ideal Number of Groups
119(3)
6.4 Sensitivity Analysis
122(3)
6.5 Naming and Describing Groups
125(1)
6.6 Conclusion
126(5)
7 Visualizing Small Area Geodemographic Data and Information Products
131(16)
7.1 Goals of Visualization
131(2)
7.2 Radial Plots
133(2)
7.3 Node-Link Trees
135(2)
7.4 Bar and Column Plots
137(1)
7.5 Area Cartograms
138(1)
7.6 Online and Offline Interactive Visualizations
139(2)
7.7 Conclusion
141(6)
Part 3 Illustrative Applications and Conclusion
8 The Grouping of Nigerian Local Government Areas
147(26)
8.1 Nigeria: Structure of Administrative, Census, and Electoral Geographies
147(4)
8.2 Data and Input Variables
151(12)
8.3 The Clustering Process
163(3)
8.4 Labeling, Cluster Profiles, and Visualizations
166(3)
8.5 Conclusion
169(4)
9 Combining Continuous and Categorical Data to Segment Philippines Barangays
173(24)
9.1 Administrative Divisions of the Philippines
173(2)
9.2 Social Aspects
175(1)
9.3 Data Source - The 2000 Census of the Philippines
176(1)
9.4 Evaluating Categorical and Continuous Data for Small Areas
177(8)
9.5 Grouping Barangays Based on Demographic and Housing Characteristics
185(1)
9.6 Profiles, Pen Portraits, and Mapping
186(6)
9.7 Conclusion
192(5)
10 Modeling Temporal Distribution and Seasonality of Infectious Diseases with Area Classifications
197(20)
10.1 The Burden of Infectious Diseases
197(3)
10.2 Importance of Surveillance
200(1)
10.3 Data Modeling Approach
201(3)
10.4 Community-Based Distribution of Measles and Meteorological Factors
204(2)
10.5 Spatial Targeting of Resources Based on Seasonal Disease Load
206(9)
10.6 Conclusion
215(2)
11 Segmenting Gender Gaps in Levels of Educational Attainment
217(12)
11.1 Educational Attainment and Gender Parity
217(2)
11.2 Data Sets
219(1)
11.3 Methodological Approach
219(2)
11.4 Gendered Differences in Neighborhood Patterns of Educational Attainment
221(2)
11.5 The Scale of Spatial Inequalities in Educational Attainment
223(4)
11.6 Conclusion
227(2)
12 Conclusion
229(8)
12.1 Geodemographics for the Developing World
229(2)
12.2 Some Lessons to Take Home
231(1)
12.3 Issues with Crowdsourcing Data
232(1)
12.4 Coupling Official Face-to-Face Surveys with Emerging Forms of Data
233(4)
Index 237
Dr. Adegbola Ojo is Director of Teaching and Learning, Programme Leader, and Senior Lecturer in Urban Geography and Applications of Big Data at the School of Geography, University of Lincoln, UK. He received his PhD in Quantitative Human Geography from the University of Sheffield, his MSc in Geographic Information Science from the University College London, and his BSc in Geography and Planning Sciences from the University of Ado-Ekiti, Nigeria. His research interests are focused in understanding and representing social and spatial dynamics and intricacies of population behavior within a framework of Interdisciplinary Studies, Population Geography, Quantitative Social Science, and Computer Modeling. His research activities are grouped around the development and application of small area classifications, geographic information systems and geographic information science for informing public policy. Dr. Ojo has published many monographs and research articles with reputable journals. He has designed and delivered lectures, workshops, seminars, tutorials, practical labs, and assessments to a range of undergraduate and graduate students and working professionals.