Open Data for Sustainable Community: Glocalized Sustainable Development Goals

Foreword
Preface
Contents
Authors and Contributors
Part IEnvironment—A Fact-Based Study using Tree Census and Air Pollution Data
1 Inching Towards Sustainable Smart Cities—Literature Review and Data Preparation
	1.1 Introduction
	1.2 Literature Review
	1.3 Data Preparation: Tree Census Data
		1.3.1 Understanding the Importance of Tree Census
		1.3.2 Introduction to Tree Census Open Data
		1.3.3 Data Profiling of Tree Census Open Data
		1.3.4 Data Cleaning and Wrangling for Analysis
	1.4 Data Preparation: Air Pollution Data
		1.4.1 Understanding Air Pollution
		1.4.2 Introduction to Air Pollution Open Data
		1.4.3 Data Profiling of Air Pollution Open Data
		1.4.4 Data Cleaning and Wrangling for Analysis
	1.5 Conclusion
	References
2 Exploring Air Pollution and Green Cover Dataset—A Quantitative Approach
	2.1 Data Exploration: Tree Census
		2.1.1 Hexbin Plot Representing Tree Density
		2.1.2 Pie Chart Representing the Categories of Tree Condition
		2.1.3 Violin Plots to Study Health-Category-Wise Distribution of Girth
		2.1.4 Scatter Plot to Spot Clusters of Poor Quality and Dead Trees
		2.1.5 Mode of All Categorical Variables
		2.1.6 Top 10 Wards with Highest Number of Trees
		2.1.7 In-Depth Analysis of Tree Condition and Ownership Type
		2.1.8 Box Plot of Tree Girth and Canopy by Tree Condition and Rarity
		2.1.9 Count Plot of Trees by Their Yield Type
		2.1.10 Counts of Top 10 Most Commonly Occurring Trees in Pune Which Yield Timber Wood
		2.1.11 Counts of Balanced and Unbalanced Trees
		2.1.12 Count of Trees with Respect to the Reported Signs of Stress/Damage on the Tree
		2.1.13 Count Plot of Trees by the Rarity of Their Occurrence
		2.1.14 Count Plot of Trees by Their Phenology Category
		2.1.15 Flowering Season of the Trees
		2.1.16 Pair Plot of All the Numerical Variables
		2.1.17 K-Means Clustering
	2.2 Data Exploration: Air Pollution Data
		2.2.1 Descriptive Statistics of Pollutants for the Five Locations
		2.2.2 Visualizing Air Quality Index (AQI)
		2.2.3 Visualizing Individual Pollutant Levels
		2.2.4 Interrelationships Between AQI, SO2 and NOx (in µg/m3) Concentration
		2.2.5 Pollutant Concentration for the Months of 2018
		2.2.6 AQI Variation for the Months of 2018
	2.3 Conclusion
	References
3 Application of Statistical Analysis in Uncovering the Spatio-Temporal Relationships Between the Environmental Datasets
	3.1 Introduction
	3.2 Data Sketch for Air Pollution and Tree Census Dataset
	3.3 Methodology to Find Correlation
		3.3.1 Measuring Correlation
		3.3.2 Air Quality Index
		3.3.3 Time-Series Analysis
		3.3.4 Haversine Formula
	3.4 Analysis of Datasets to Find Correlation
		3.4.1 Exploratory Data Analysis
		3.4.2 GIS Analysis
		3.4.3 Time-Series Analysis
		3.4.4 Statistical Analysis
	3.5 Results
	3.6 Conclusion and Future Work
	References
Part IIResilient Agriculture—A War Against Hunger
4 Farmer Call Centre Literature Review and Data Preparation
	4.1 Introduction
	4.2 Literature Review
	4.3 Understanding the Operations of Kisan Call Centre
	4.4 Data Preparation: Kisan Call Centre Queries
		4.4.1 Data of Kisan Call Centre Queries
		4.4.2 Preparation of Kisan Call Centre Queries
		4.4.3 Pre-processing of Kisan Call Centre Queries
	4.5 Conclusion
	References
5 Analysis and Visualization of Farmer Call Center Data
	5.1 Introduction
	5.2 Material Methods Used for Analysis
		5.2.1 Check and Confirm the Pre-processed Data
		5.2.2 Form an Objective and Acquire Domain Knowledge
		5.2.3 Data Visualization Criteria
		5.2.4 Libraries Used for Visualization
		5.2.5 Visualization Charts Used
	5.3 Data Exploration and Visualization
		5.3.1 Donut Pie Chart Presenting Overview of Query Types
		5.3.2 Radar Chart and Stacked Bar Graph to Analyse District-Wise Query Type
		5.3.3 Radar Chart to Present Queries According to Seasons
		5.3.4 Radar Chart and Plot Chart to Present Category-Wise Query Type
	5.4 Conclusion and Future Scope
	References
6 An Approach for Exploring New Frontiers for Optimizing Query Volume for Farmer Call Centre—KCC Query Pattern
	6.1 Introduction
	6.2 Different Approaches for Query Text to Query Type Classification
		6.2.1 Text Similarity and Clustering
		6.2.2 Word-Based Encodings
		6.2.3 Text to Sequences
		6.2.4 Out of Vocabulary (OOVs)
		6.2.5 Padding
		6.2.6 Visualization
	6.3 Conclusions
	References
Part IIIDemand and Supply Study of Healthcare Human Resource and Infrastructure—Through the Lens of COVID 19
7 Sustainable Healthcare in COVID-19 Pandemic—Literature Survey and Data Lifting
	7.1 Introduction
	7.2 Literature Review
	7.3 Data Preparation: COVID-19, Infrastructure, Human Resource, State Population Data
		7.3.1 Data Source Identification and Data Acquisition
		7.3.2 Data Profiling: COVID-19, Infrastructure, Human Resource, State Population Data
		7.3.3 Data Cleaning and Wrangling for Analysis
	7.4 Exploratory Data Analysis (EDA)
	7.5 Conclusion
	References
8 COVID-19 and Indian Healthcare System—A Race Against Time
	8.1 Introduction
	8.2 Material Methods Used for Analysis
	8.3 Data Analysis and Visualization
		8.3.1 Progression of COVID-19 in India
		8.3.2 Healthcare Infrastructure in India
		8.3.3 Healthcare Human Resource in India
	8.4 Conclusion
	References
9 Estimating Cases for COVID-19 in India
	9.1 Introduction
	9.2 Methodology
		9.2.1 The Database
		9.2.2 The Models
	9.3 Polynomial Regression
		9.3.1 Why Polynomial Regression Model?
		9.3.2 Polynomial Regression—Model A
		9.3.3 Polynomial Regression—Model B
	9.4 Long Short-Term Memory (LSTM)
		9.4.1 Why LSTM?
		9.4.2 LSTM Model
	9.5 Autoregressive Integrated Moving Average (ARIMA)
		9.5.1 Why Is ARIMA Preferred to Exponential Smoothing?
		9.5.2 ARIMA Model A
		9.5.3 ARIMA Model B
		9.5.4 ARIMA Model C
		9.5.5 ARIMA Model D
		9.5.6 Validation of Models B, C and D
	9.6 Prophet
		9.6.1 Why Prophet?
		9.6.2 Prophet Model
	9.7 Conclusions
	References
10 Multifacet Impact of Pandemic on Society
	10.1 Introduction
	10.2 Literature Review
	10.3 Economy During the Time of Pandemic
		10.3.1 Impact of Lockdown on Banking Sector and Insurers
		10.3.2 Layoffs in Various Industries
		10.3.3 Migration and Livelihood
		10.3.4 Reverse Migration
	10.4 Supply Chain Management
		10.4.1 Demand of Essential Commodities
		10.4.2 What Are Decentralized Supply Chains?
		10.4.3 Framework of Decentralized Supply Chain
		10.4.4 Technologies Used
		10.4.5 Quality Assurance
		10.4.6 Salient Features
	10.5 Conclusion
	References