AI Solutions for the United Nations Sustainable Development Goals (Un SDGs): A Practical Approach Using JavaScript

Learn the United Nations Sustainable Development Goals (UN SDGs) and see how machine learning can significantly contribute to their realization. This book imparts both theoretical knowledge and hands-on experience in comprehending and constructing machine learning-based applications for addressing multiple UN SDGs using JavaScript. The reading begins with a delineation of diverse UN SDG targets, providing an overview of previous successful applications of machine learning in solving realistic problems aligned with these targets. It thoroughly explains fundamental concepts of machine learning algorithms for prediction and classification, coupled with their implementation in JavaScript and HTML programming. Detailed case studies examine challenges related to renewable energy, agriculture, food production, health, environment, climate change, water quality, air quality, and telecommunications, corresponding to various UN SDGs. Each case study includes related works, datasets, machine learning algorithms, programming concepts, and comprehensive explanations of JavaScript and HTML codes used for web-based machine learning applications. The results obtained are meticulously analyzed and discussed, showcasing the pivotal role of machine learning in advancing the relevant SDGs. By the end of this book, you'll have a firm understanding of SDG fundamentals and the practical application of machine learning to address diverse challenges associated with these goals. What You'll Learn Understand the fundamental concepts of the UN SDGs, AI, and machine learning algorithms. Employ the correct machine learning algorithms to address challenges on the United Nations Sustainable Development Goals (UN SDGs)? Develop web-based machine learning applications for the UN SDGs using Javascript, and HTML. Analyze the impact of a machine learning-based solution on a specific UN SDG. Who This Book Is For Data scientists, machine learning engineers, software professionals, researchers, and graduate students. About the Authors About the Contributors Chapter 2 Chapter 3 Chapter 4 Chapter 5 Chapter 6 Chapter 3: A Crop Recommendation System Using Machine Learning Algorithms for Achieving SDGs 2, 9, and 12 3.1 Introduction 3.2 AI Use Cases for SDGs 2, 9, and 12 3.3 Data Processing and Application Design 3.3.1 Data Collection Process and Description of the Datasets 3.3.2 Data Preprocessing Steps 3.3.3 Program Structure 3.3.4 Layout of Web Application 3.4 Application Testing and Analysis 3.4.1 Application Testing 3.4.2 K-NN Classification Results 3.4.3 Decision Trees Classification Results 3.4.4 Random Forest 3.4.5 Multilayer Perceptron 3.4.6 Discussion 3.5 Summary Chapter 4: Aligning Manufacturing Emissions with SDGs 9 and 13 Using Machine Learning Algorithms 4.1 Introduction 4.2 Use Cases for SDGs 9 and 13 4.3 Data Processing and Application Design 4.3.1 Data Collection Process and Description of Datasets 4.3.2 Data Preprocessing Steps Stages of Data Preprocessing Feature Selection and Removal of Attributes 4.4 Program Structure for Analysis 4.4.1 Simple Linear Regression (SLR) 4.4.2 Multiple Linear Regression (MLR) 4.4.3 k-Nearest Neighbor (k-NN) 4.5 Application Testing and Analysis 4.5.1 Simple Linear Regression (SLR) 4.5.2 Multiple Linear Regression (MLR) 4.5.3 k-Nearest Neighbors (k-NN) 4.5.4 Discussion 4.6 Recommendations 4.7 Improvements 4.8 Summary 4.9 Appendix 4.9.1 Dataset Chapter 5: Potability Analysis of Water Using Machine Learning 5.1 Introduction 5.2 AI Use Cases for SDGs 3, 6, and 12 5.3 Data Processing and Application Design 5.3.1 Data Collection Process and Description of the Datasets 5.3.2 Data Preprocessing Steps 5.3.3 General Layout of Web Application 5.3.4 Water Potability System 5.3.5 Machine Learning Algorithms k-NN Decision Tree and Random Forest Naïve Bayes 5.4 Application Testing and Analysis 5.4.1 Application Testing 5.4.2 k-NN 5.4.3 Decision Tree 5.4.4 Random Forest 5.4.5 Naïve Bayes 5.5 Summary Chapter 6: Air Quality Monitoring: A Case Study for the Application of Machine Learning in Meeting SDGs 3 and 13 6.1 Introduction 6.2 AI Use Cases for SDGs 3 and 13 6.2.1 SDG 3: Good Health and Well-Being 6.2.2 SDG 13: Climate Action 6.3 Data Processing and Application Design 6.3.1 Data Collection Process and Dataset Description 6.3.2 Program Structure 6.3.3 Layout of Website 6.3.4 Implementation of Linear Regression 6.3.5 Implementation of Polynomial Regression 6.3.6 Implementation of LSTM/MLP 6.3.7 Displaying Regression Graphs 6.3.8 AQI Classification 6.4 Application Testing and Analysis 6.4.1 Testing of Web Application 6.4.2 Performance of Regression Algorithms 6.4.3 Performance of SLR 6.4.4 Performance of PR 6.4.5 Performance of MLP 6.4.6 Performance of LSTM 6.4.7 Performance of Classification Algorithms 6.5 Summary