通过数据集成和人工智能评估亚太区的贫困现状.docxVIP

Contents Foreword v Highlights vii Introduction 1 Estimating Poverty Using Conventional Data Sources 3 Using Big Data to Enhance Development Statistics 5 Predicting Poverty Using Geospatial Data 6 Using Neural Networks to Develop an Algorithm 10 Understanding Convolutional Neural Networks 12 Outlining Data Requirements for the Feasibility Study 13 Daytime satellite imagery 13 Data on night lights 15 Poverty statistics 17 Applying a Convolutional Neural Network to Poverty Prediction 18 Extracting Features from the Convolutional Neural Network 20 Predicting Poverty from Features Using Ridge Regression Models 21 Outlining the Key Findings of the Feasibility Study 22 Preparing National Statistics Offices for the Use of Big Data 29 Access to nontraditional data 33 Technological requirements 33 Capabilities 34 Data privacy 34 Ecosystem 34 Institutional strengthening 35 Summary and Conclusion 35 References 37 Appendixes Appendix 1: A Primer on Deep Learning Concepts 40 Appendix 2: Sources of Satellite Imagery 43 Tables, Figures, and Boxes Tables Select Countries in Asia and the Pacific that Use the World Bank’s Poverty Mapping Methodology 5 Summary of Poverty Prediction Results using Confusion Matrixes, Thailand 22 Summary of Poverty Prediction Results using Confusion Matrixes, Philippines 22 Appendix Tables A1.1 Sample of a Typical Confusion Matrix 41 A1.2 Comparison of Popular Deep-Learning Software Communities 43 A2.1 Uses of Landsat 8 Spectral Bands 44 Figures Illustration of a Computer Vision Task 8 Illustration of a Neural Network 11 Neural Network Filters to Detect Vertical and Horizontal Lines 12 Road Map of Methodology for Predicting Poverty Using Satellite Imagery 14 Pansharpening Images to Improve Their Resolution 15 Night Light Image Tiles for the Philippines and Thailand 16 Distribution of Poverty Rates in the Philippines and Thailand 18 Image Co