IoT and AI in Agriculture: Smart Automation Systems for increasing Agricultural Productivity to Achieve SDGs and Society 5.0

Preface
Acknowledgments
Contents
Chapter 1: Digital Innovations in Agrifood Systems to Achieve the SDGs and Society 5.0
	1.1 Introduction
	1.2 Digital Innovations in Agrifood Systems
		1.2.1 Big Data Analytics
		1.2.2 Internet of Things (IoT) and 5G Wireless Networks
		1.2.3 Artificial Intelligence in Digital Agrifood Systems
		1.2.4 Robotics and Drone Technology
		1.2.5 3D Printing Technology: Changing the Manufacturing in Agriculture
		1.2.6 Edge Computing
		1.2.7 Digital Twins and Cross Reality (XR) in Precision Farming
		1.2.8 Digital-Twin-Driven Smart Supply Chain
	1.3 Achieving SDGs through Digital Innovations in Agrifood Systems
	1.4 Achieving Society 5.0 through Digital Innovations in Agrifood Systems
	1.5 Conclusion
	References
Chapter 2: Strategic Short Note: Appropriate Integration of Precision Agriculture Technology, IoT, and AI for Enhancing Southeast Asian Agriculture
	2.1 Introduction
	2.2 Research and Development for Appropriate Solutions
	2.3 Conclusions
	References
Chapter 3: Strategic Short Note: Climate Smart Technology for Corn Production in Rizal, Kalinga, Philippines
	3.1 Introduction
	3.2 Biophysical Sensitivity and Technological Adaptations for Yellow Hybrid Corn
	3.3 Conclusions
	References
Chapter 4: Appropriate Scale of Mechanization and Automation for Agriculture in Southeast Asia
	4.1 Introduction
	4.2 Current Scale of Agricultural Mechanization in Southeast Asia
	4.3 Transformation of Agricultural Mechanization in Southeast Asia
	4.4 Level of Automation in Agricultural Machinery
	4.5 Level of Machinery for Agricultural Practices
		4.5.1 Tillage Practices
			4.5.1.1 Transformation of Partial Automation
			4.5.1.2 Hydrostatic Transmission (HST)
			4.5.1.3 Transformation of Conditional Automation
		4.5.2 Seeding Practices
		4.5.3 Transplanting
		4.5.4 Spraying Practices
		4.5.5 Harvesting Practices
	4.6 Appropriate Scale of Mechanization in Southeast Asia
	4.7 Discussion
	4.8 Conclusion
	References
Chapter 5: Design of Navigation System for Transportation Mobile Robot for Agricultural Farms
	5.1 Introduction
	5.2 Materials and Methods
		5.2.1 Hardware System
		5.2.2 Software System
		5.2.3 Design for Localization System
			5.2.3.1 Setting for Base Station and Rover
			5.2.3.2 GNSS Data Acquisition
			5.2.3.3 Coordinates Transform for GNSS
		5.2.4 Process for IMU
		5.2.5 Sensor Fusion for GNSS/IMU
			5.2.5.1 Coordinate System Specification
			5.2.5.2 Kalman Filter for GNSS/INS System
		5.2.6 Design for Obstacles Avoidance System
			5.2.6.1 Process for LiDAR
			5.2.6.2 Obstacles Avoidance Strategy
		5.2.7 Design for Navigation System
		5.2.8 Robot Tracking
			5.2.8.1 Fuzzy Control Strategies
			5.2.8.2 Fuzzy Control System Design
	5.3 Results
		5.3.1 Experiment for the Automatic Driving
		5.3.2 Experiment for Obstacles Avoidance
	5.4 Discussion
	5.5 Conclusion
	References
Chapter 6: Automatic Navigation of Pesticide Spraying Vehicle for Orchard Tree Trunk Detection
	6.1 Introduction
	6.2 Materials and Methods
		6.2.1 Experimental Prototype Vehicles
		6.2.2 Installation of Sensors
		6.2.3 System Structure
		6.2.4 Path Planning Algorithm
		6.2.5 Graphical User Interface (GUI)
	6.3 Results
		6.3.1 Planning Path Calibration on a Concrete Road
		6.3.2 Field Test in a Facilitated Artificial-Tree-Based Orchard
	6.4 Discussion
	6.5 Conclusions
	References
Chapter 7: Driver Safety System for Agricultural Machinery Operations Using Deep Learning Algorithm
	7.1 Introduction
	7.2 Materials and Methods
		7.2.1 The Overall Framework of the Model
		7.2.2 Dataset Introduction
			7.2.2.1 Data Collection Part
			7.2.2.2 Data Processing
		7.2.3 Model Introduction
			7.2.3.1 MoViNet
			7.2.3.2 Model Module
			7.2.3.3 Loss Function
	7.3 Results and Discussion
		7.3.1 Environment for Training and Evaluating
		7.3.2 Evaluation Metrix
		7.3.3 Model Results
		7.3.4 Online Model Realization and Result Display
		7.3.5 Discussion
	7.4 Conclusions
	References
Chapter 8: Navigation System for Autonomous Agricultural Vehicles for Indoor Farms
	8.1 Introduction
	8.2 Navigation System
	8.3 Coordinates Calculation
		8.3.1 Cloud Map Generation Using ORB_SLAM2
		8.3.2 OctoMap
		8.3.3 CostMap
		8.3.4 System Data Structure Based on ROS
	8.4 Path Planning and Path tracking for Tiny Agricultural Vehicles
		8.4.1 Design of Navigation System Based on move_base Repository
		8.4.2 Pure-Pursuit Path tracking Algorithm
		8.4.3 Instruction of DWA
	8.5 Results and Discussion
	8.6 Conclusions
	References
Chapter 9: Strategic Short Note: Integration of Multiomics Approaches for Sustainable Crop Improvement
	9.1 Introduction
	9.2 Integrated Multiomics Approaches for Crop Improvement
	9.3 Concluding Remarks
	References
Chapter 10: Strategic Short Note: Artificial Intelligence in Food Quality Assessments
	10.1 Introduction
	10.2 Application of AI Techniques in Food Quality Detection
	10.3 Challenges and Future Direction
	References
Chapter 11: High-Throughput Plant Phenotyping Techniques in Controlled Environments
	11.1 Introduction
		11.1.1 Plant Morphological Characteristics
		11.1.2 Plant Physiology
	11.2 High-throughput Plant Phenotyping
		11.2.1 2D Image-Based Phenotyping
			11.2.1.1 RGB Imaging System
			11.2.1.2 Fluorescence Imaging System
			11.2.1.3 Hyperspectral Imaging System
			11.2.1.4 Thermal Imaging System
		11.2.2 3D Image-Based Phenotyping
			11.2.2.1 LiDAR
			11.2.2.2 Depth Camera
	11.3 High-throughput Plant Phenotyping Platforms
		11.3.1 Conveyor-Type
		11.3.2 Benchtop-Type
		11.3.3 Gantry-Type
		11.3.4 Mobile Type
	11.4 Deep Learning Applications in Plant Phenotyping
		11.4.1 DL-Based HTPP in the Germination and Early Growth Stages
		11.4.2 DL-Based HTPP in Vegetative Growth and Development
		11.4.3 DL-Based HTPP in the Flowering and Reproductive Stages
		11.4.4 DL-Based HTPP in Harvest and Yield Prediction
	11.5 Conclusions and Prospects
	References
Chapter 12: Revolutionizing Agriculture: Embracing Modern Strategies for the Management of Coffee Leaf Rust Disease
	12.1 Overview of Coffee Leaf Rust
		12.1.1 Coffee Leaf Rust
		12.1.2 History of Coffee Leaf Rust
		12.1.3 Economic and Ecological Consequences of Coffee Leaf Rust
	12.2 The Need to Shift to Modern Management Methods for Coffee Leaf Rust
		12.2.1 Why Modern Management?
		12.2.2 Deep Learning as Modern Approaches for Coffee Leaf Rust
	12.3 Challenges and Limitations of Using Deep Learning for Coffee Leaf Rust Management
		12.3.1 Challenges and Limitations
		12.3.2 Solutions
	12.4 Conclusion
	References
Chapter 13: Digital Transformation of Horticultural Crop Production Systems Toward Sustainable Agricultural Productivity
	13.1 Introduction
	13.2 Transforming the Horticulture Production System
	13.3 Digital Technologies in Horticultural Production
		13.3.1 Digital Transformation of Horticultural Production Environment
			13.3.1.1 Smart Greenhouse Production
			13.3.1.2 Plant Factory Revolution
		13.3.2 Digital Transformation of Horticultural Production Operations
			13.3.2.1 Pest Management
			13.3.2.2 Water Management
			13.3.2.3 Nutrient Management
			13.3.2.4 Harvesting
			13.3.2.5 Postharvest
	13.4 Challenges and Opportunities in Digital Horticulture Production and Management
		13.4.1 Challenges
			13.4.1.1 Technical Challenge
			13.4.1.2 Financial Challenge
			13.4.1.3 Social Challenges
			13.4.1.4 Behavioral Challenges
		13.4.2 Opportunities
			13.4.2.1 Socioeconomic Opportunities
			13.4.2.2 Digital Literacy
			13.4.2.3 Achieving the Sustainable Development Goals
			13.4.2.4 Environmental and Health Benefits
	13.5 Conclusion
	References
Chapter 14: Challenges in Orchard Weed Management: Perspectives on the Use of 3D Cameras and LiDAR to Develop a Low-Cost Small-Scale Robotic Weeder
	14.1 Introduction
	14.2 Characteristics of Orchard Environments for Robotic Weeding Operations
	14.3 The Use of 3D Cameras and LiDAR in Robotics-Based Weed Control
		14.3.1 Machine Vision Using a 3D Camera
		14.3.2 LiDAR
	14.4 Weeding Operations Using a 3D Camera and LiDAR for Orchards
		14.4.1 Current Orchard Weeding Operations Using Autonomous Robots
		14.4.2 Weed Cutter that Moves Around Tree Trunks for Small-Robot Intrarow Weeding
		14.4.3 Path Planning and Weed Management Strategy
	14.5 Conclusions
	References
Chapter 15: Investigating the Pesticide Spraying Characteristics of Plant Protection UAV and Designing a Variable Spraying System for Improving the Spraying Uniformity
	15.1 Introduction
	15.2 Materials and Methods
		15.2.1 Analyzing the Effect of Downwash Airflow of Plant Protection UAV Using the Computational Fluid Dynamics (CFD)
			15.2.1.1 Calculation of the Change State of Rotation Speed
			15.2.1.2 3D Modeling
			15.2.1.3 Downwash Airflow Simulation
			15.2.1.4 Data Analysis
		15.2.2 Development of an Efficient Variable Spraying System (VSS) for Plant Protection UAV Based on Pulse Width Modulation
			15.2.2.1 PWM Modulation Principle
			15.2.2.2 Variable Spraying System (VSS) Control Principle
			15.2.2.3 The Main Program of Variable Spraying Control System Based on PWM
			15.2.2.4 System Composition
			15.2.2.5 Calculating the Relationship Between the Spray Flow Rate and Duty Cycle
			15.2.2.6 Comparison of Theoretical Pesticide Consumption Between Variable Spraying System and Non-variable Spraying System
	15.3 Results and Discussion
		15.3.1 Effect of Downwash Airflow of Plant Protection UAV
			15.3.1.1 Change of Rotor Rotation Speed in Hover
			15.3.1.2 Analysis of the Movement of Droplets
		15.3.2 Variable Spraying System (VSS) for Plant Protection UAV Based on Pulse Width Modulation
			15.3.2.1 The Relationship Between Flight Speed and Pulse Width Modulation (PWM) Duty Cycle
			15.3.2.2 Amount of Spraying for Reference Area by Variable Spraying System and Non-variable Spraying System
	15.4 Conclusions
	References
Chapter 16: Strategic Short Note: Myanmar Climate-Smart Agriculture
	16.1 Introduction
	16.2 Role of Agricultural Sector in Myanmar
	16.3 Climate Change Adaptation Option for Agriculture Sector
	16.4 Climate Change Mitigation Option for Agriculture Sector
	16.5 Policy Related to Climate Change from MOALI
		16.5.1 Collaboration with Others
	16.6 Summary
	References
Chapter 17: Strategic Short Note: Enhancing Postharvest Operations Through Centralized Data Processing and Analysis
	17.1 Introduction
Chapter 18: Optimization of Soil-Based Irrigation Scheduling Through the Integration of Machine Learning, Remote Sensing, and Soil Moisture Sensor Technology
	18.1 Introduction
	18.2 Soil Moisture and Irrigation Management
		18.2.1 Significance of Soil Moisture in Agriculture
		18.2.2 Soil Moisture as a Base for Irrigation Decision-Making
	18.3 Remote Sensing in Irrigation Scheduling
		18.3.1 Remote Sensing Technologies
		18.3.2 Remote Sensing Applications in Irrigation
			18.3.2.1 Active Remote Sensing Techniques
			18.3.2.2 Passive Remote Sensing Techniques
			18.3.2.3 Combination of Passive and Active Remote Sensing Techniques
	18.4 Soil Moisture Sensing in Irrigation Scheduling
		18.4.1 Types of Soil Moisture Sensors
		18.4.2 Installation and Calibration of Sensors
		18.4.3 Benefits of Soil Moisture Sensor
	18.5 Machine Learning in Irrigation Scheduling
		18.5.1 Introduction to Machine Learning
		18.5.2 Benefits of Machine Learning
	18.6 Discussion
		18.6.1 Irrigation Scheduling Based on Soil Moisture Sensor Data
		18.6.2 Irrigation Scheduling Based on Remote Sensing Data
		18.6.3 Machine Learning in Soil-Based Irrigation Scheduling
		18.6.4 Integration of Soil Moisture Sensors, Remote Sensing, and Machine Learning Techniques
	18.7 Future Directions and Concluding Remarks
		18.7.1 Emerging Trends in Irrigation Technology
		18.7.2 Conclusion and Practical Recommendations
	References
Chapter 19: AI-Based IoT Greenhouse Control System for Environmental Parameters
	19.1 Introduction
	19.2 Materials and Methods
		19.2.1 IoT-Based Greenhouse System
		19.2.2 YOLOv3 Object Detection Model
		19.2.3 CenterNet Object Detection Model
		19.2.4 Evaluation Metrics for Object Detection Model
		19.2.5 Fuzzy PID Control Algorithm
	19.3 Results
		19.3.1 System Architecture
			19.3.1.1 Embedded System Design
		19.3.2 Monitoring Web Pages of IoT System
		19.3.3 Object Detection Experiment Results
			19.3.3.1 Object Detection System Design
			19.3.3.2 Images Results of Growth Stage Detection
			19.3.3.3 Performance Comparison
		19.3.4 Control Experiment Results
			19.3.4.1 Humidity Control Experiment Results
			19.3.4.2 Light Intensity Control Experiment Results
			19.3.4.3 Soil Moisture Control Experiment Results
	19.4 Conclusions
	References
Chapter 20: Enhancement of Cottage Mushroom Cultivation in Tropical and Subtropical Regions with IoT and AI Applications
	20.1 Introduction
	20.2 Oyster Mushroom Production Process at Cottage Level
	20.3 Mechanization and Automation of the Substrate Preparation
		20.3.1 Enabling Seamless Continuity by Integrating the Three Operations
	20.4 Application of IoT Technology in Disinfection of Substrate
		20.4.1 Controlling the Biomass Supply to the Burner
	20.5 Controlling the Environment in a Mushroom House/Shed
		20.5.1 Controlling the Temperature and Humidity of a Mushroom House with IoT
	20.6 Conclusion
	References
Chapter 21: Approaches for Improving Fruit Detection and Gripping Mechanisms in Orchard Robotic Fruit Harvesting
	21.1 Introduction
	21.2 Occlusions Caused by Plant Parts and Challenges for Robotic Operations
		21.2.1 Challenges for the Vision System
		21.2.2 Challenges for Robotic Arm Manipulation
	21.3 Light Variation, Wind, Shadows, and Vision System Challenges
	21.4 Recent Trends of Harvesting Robots
		21.4.1 Kinematic Examples for Basic Robotic Arm Design
	21.5 Discussion
	21.6 Conclusion
	References
Chapter 22: Smart Automation for End-Effectors in the Development of Horticultural Robots
	22.1 Introduction
	22.2 Types of End-Effectors for Automation in Horticulture
		22.2.1 Gripper End-Effectors
		22.2.2 Cutting End-Effectors
		22.2.3 Spraying End-Effectors
	22.3 Sensing and Perception Technologies for End-Effector Automation in Horticulture
		22.3.1 Computer Vision
		22.3.2 Lidar Sensing Technology
		22.3.3 Thermal Imaging Technology
	22.4 Actuation and Control Mechanisms for Smart End-Effectors
		22.4.1 Actuation Technologies
		22.4.2 Control Mechanisms
	22.5 Applications of Deep Learning for End-Effector Automation in Horticultural Robots
		22.5.1 Object Classification and Detection
		22.5.2 Yield Estimation and Quality Assessment
		22.5.3 Pest and Disease Detection
		22.5.4 Weed Detection and Management
	22.6 Case Studies About Design of a Three-Finger Flexible Gripper for Orchard
		22.6.1 The Three-Finger Flexible Gripper
		22.6.2 Flexible Finger
		22.6.3 Connecting Rod Structure
		22.6.4 Stepper Motor Drive and Lead Screw Transmission
	22.7 Conclusion
	References
Chapter 23: Strategic Short Note: Spatially Factorized Spectroscopy—Focusing on a Single Component in a Mixed Sample
	References
Chapter 24: Strategic Short Note: Reviving Local Resources for Healthier Foods in Indonesia
	24.1 Introduction
	24.2 Repositioning Local Food Resources
	References
Chapter 25: Development of IoT-Based Platform for Biomass Utilization Toward Low-Carbon Economic Society: Case of Oil Palm Residue
	25.1 Introduction
		25.1.1 Trend on IoT and Application for Agriculture
		25.1.2 Potential of Agriculture Residue Utilization to Replace Fossil Fuel
		25.1.3 Existing IoT Platform for Oil Palm Production System
	25.2 Methods for Developing the Prototype
		25.2.1 Identifying Relevant Stakeholders
		25.2.2 Developing Biomass Utilization Flow
		25.2.3 Identifying GHG Calculation Methods
		25.2.4 Constructing the Tool
		25.2.5 Testing and Validation
		25.2.6 Writing Guideline
	25.3 Integrating the Tool Toward IoT Platform of Low-Carbon Economic Society
	25.4 The Role of AI in Biomass Utilization Platform
	25.5 Estimating the Cost and Potential Benefits
	25.6 Conclusion
	References
Chapter 26: A Web-Based IoT Monitoring and Service System for Agricultural Applications
	26.1 Introduction
	26.2 Materials and Methods
		26.2.1 Web-Based IoT Monitoring System
	26.3 Hardware Configuration for Sensor Node for an IoT System Prototype in Universiti Putra Malaysia (UPM)
	26.4 Dash Plotly Framework Design
		26.4.1 Dash Layout
		26.4.2 Interactive Dash Components
		26.4.3 Launch of the Dash Application
	26.5 Web-Based Dashboard Deployment and Experiment Setup
		26.5.1 Soil Moisture, Humidity, and Temperature Measurement Test in the Tenth College (K10), UPM
		26.5.2 Outdoor Environmental Measurement in Taiwan
	26.6 Assessment of Web-Based IoT Platform
		26.6.1 Web Application’s Overall Performance
			26.6.1.1 The Performance Scores Under Different Types of Internet Connections
			26.6.1.2 The Google Lighthouse and PageSpeed Insights Performance Is Based on Different Time Zones
	26.7 Results and Discussion
		26.7.1 The Overall Performance of the Web Applications
		26.7.2 Web Application for National Ilan University, Taiwan’s Weather Station
			26.7.2.1 Overall Performance of the Web Applications
			26.7.2.2 The T-Test of Web Application Performance Based on Internet Connection
			26.7.2.3 The Comparison Between Google Lighthouse and PageSpeed Insights Performance Based on Different Time Zones
		26.7.3 Impact of the WebBased IoT Monitoring and Service System for Agricultural Applications to Society, Safety, and Health
	26.8 Conclusions
	References
Chapter 27: Strategic Short Note: Application of Smart Machine Vision in Aquaculture and Animal Husbandry
	27.1 Introduction
	27.2 Overview of Smart Machine Vision in Aquaculture and Animal Husbandry
	27.3 Examples of Smart Machine Vision in Aquaculture and Animal Husbandry
	27.4 Conclusion
	References
Chapter 28: Deep Learning Algorithms for Postharvest Quality Assessment: A New Sensing Methodology for Quail Eggs Freshness Estimation and Shelf-Life Revalidation
	28.1 Introduction
	28.2 Materials and Methods
		28.2.1 Experimental Environment
		28.2.2 Thermal Imaging
		28.2.3 Dataset Collection
		28.2.4 Air Cell Assessment Methodology
		28.2.5 Deep Learning-Based Object Detection Algorithms
			28.2.5.1 Data Labeling
			28.2.5.2 Training Parameters
			28.2.5.3 Evaluation Metrics
	28.3 Results
		28.3.1 Correlation Test
		28.3.2 Computer Vision Model Prediction
			28.3.2.1 Training Results
			28.3.2.2 Revalidation of the Expiration Date
	28.4 Discussion
	28.5 Conclusions
	References
Chapter 29: AI × IoT: Increasing Agricultural Productivity of Crops, Orchards, and Livestock Management Using Smart Agricultural Space for Achieving SDGs
	29.1 Introduction
	29.2 Smart Outdoor Systems for Agricultural Production
	29.3 Smart Indoor Production Systems
	29.4 Smart Orchard Management for Increasing Productivity
	29.5 Smart Management of Poultry and Livestock
	29.6 Postharvest Management and Nondestructive Quality Measurements
	29.7 Conclusion
	References
Index