Drone Data Analytics in Aerial Computing (Transactions on Computer Systems and Networks)

✍ Scribed by P. Karthikeyan (editor), Sathish Kumar (editor), V. Anbarasu (editor)

• Publisher: Springer
• Year: 2023
• Tongue: English
• Leaves: 282
• Edition: 1st ed. 2023
• Category: Library

✦ Table of Contents

Preface
Acknowledgments
Contents
Editors and Contributors
Abbreviations
1 Introduction to Drone Data Analytics in Aerial Computing
1.1 Introduction
1.2 Literature Survey
1.3 Data Analytics
1.4 Drone Data Analytics
1.5 Working Principle of Drone and Essential Principles of Data Analytics
1.6 Aerial Computing
1.7 Fundamental Elements of Data Analytics
1.8 Reasons for Using AI in Data Analytics
1.9 Drone Technology Using AI
1.10 Challenges in Drone Data Analytics
1.11 Future Research Direction of Drone Data Analytics
1.12 Conclusion
References
2 A Study in Federated Learning Analytics for UAV
2.1 Introduction
2.2 Federated Learning Architecture for UAV
2.2.1 Original FL (Google)
2.2.2 Collaborative FL
2.2.3 Multihop FL
2.2.4 Fog Learning
2.3 A Decentralized FL for UAV Network
2.3.1 Advantages
2.3.2 Future Research Directions in DFL-UN
2.4 A Simple Federated Learning in UAV Networks
2.5 Federated Applications in UAV-Enabled Networks
2.5.1 Federated Learning in UAV for 6G Cellular Networks
2.5.2 Federated UAV Ad-Hoc Networks
2.5.3 Federated UAV for IOT Networks
2.5.4 Federated Learning in UAVs in Edge Computing
2.6 The Future of Federated Learning
References
3 Analysis of Geospatial Data Collected by Drones as Part of Aerial Computing
3.1 Introduction
3.2 Related Work
3.2.1 Unmanned Aerial Vehicles (UAVs)
3.2.2 High Altitude Platforms (HAPs)
3.2.3 Mobile Edge Computing (MEC)
3.2.4 Geographic Information System (GIS)
3.2.5 Space Air-Ground Integrated Network (SAGIN)
3.2.6 Offloading of Calculations in Satellite Networks
3.2.7 Using Machine Learning to Offload Computation
3.3 Drones
3.3.1 History of Drones
3.3.2 Key Features of a Drone
3.3.3 Classification of Drones
3.3.4 Software’s for Drones
3.4 Aerial Computing
3.4.1 Features
3.4.2 Network Design
3.4.3 Enabling Technologies
3.4.4 Domain Applications
3.4.5 Challenges
3.5 Geospatial Data Analysis
3.5.1 Definition of Geospatial Data
3.5.2 Types of Geospatial Data
3.5.3 Geospatial Big Data Challenges
3.5.4 Geospatial Data Collection and Management
3.5.5 Benefits of Using Geospatial Data
3.5.6 Photogrammetry
3.6 Conclusion
References
4 Beach Wrack Identification on Unmanned Aerial Vehicles Dataset Using Artificial Intelligence for Coastal Environmental Management
4.1 Introduction
4.2 Related Review About Beach Wrack
4.3 Material and Methods
4.3.1 Working Procedure of BPWCNN
4.3.2 Working Procedure of KNN
4.3.3 Working Procedure of RF
4.4 Results on Beach Wrack
4.4.1 Comparison of Beach Wrack Identification Between BPWCNN and KNN
4.4.2 Comparison of Beach Wrack Identification Between BPWCNN and RF
4.5 Discussion with Similar and Opposite Finding
4.6 Conclusion and Future Direction About Detection of Beach Wrack
References
5 Environmental Drones for Autonomous Air Pollution Investigation, Detection, and Remediation
5.1 Introduction
5.2 The Materials and Procedures
5.2.1 Materials
5.3 Methods
5.3.1 Unmanned Aerial Vehicles and Analytical Equipment
5.3.2 Measurement of the Quality of Air in Urban Areas
5.4 Discussion
5.5 Conclusion
References
6 Detection of Pathogens in Plant Leaves Using Drone-Based Deep Learning Approach
6.1 Introduction
6.2 Impact of Drones in the Precise Agriculture Industry
6.2.1 Agricultural Drones
6.2.2 Why I Choose Leaf Other Than Root or Branch?
6.3 Plant Diseases
6.3.1 Non-infectious Disease
6.3.2 Infectious Disease
6.4 Key Issues and Challenges in the Field of Disease Analysis
6.5 Methodology
6.6 Conclusion
References
7 Artificial Intelligence Based Drones for Plant Disease Detection
7.1 Introduction
7.2 Proposed Work
7.3 Diseases and Description
7.3.1 Powdery Mildew
7.3.2 Downy Mildew
7.3.3 Black Spot
7.3.4 Fusarium Wilt
7.4 Results and Conclusion
7.5 Future Scope
References
8 Machine Vision in UAV Data Analytics for Precision Agriculture
8.1 Introduction
8.2 Machine Vision for Precision Farming
8.2.1 Utilization of Machine Vision in Precision Farming
8.2.2 Phenotyping for Crop Management
8.3 UAV for Precision Agriculture Using Machine Vision
8.3.1 Significance of ML and DL for Machine Vision in Precision Agriculture
8.4 Proposed Crop Classification Model Using Machine Vision
8.4.1 Proposed Algorithm for Crop Classification Model
8.4.2 Data Selection
8.4.3 Pre-processing Data
8.4.4 ML for Classification
8.5 Result and Discussion
8.6 Conclusion
References
9 Smart IoT Drone-Rover for Sustainable Crop Prediction Based on Mutual Subset Feature Selection Using U-Net CNN for Sustainable Crop Recommendation
9.1 Introduction
9.1.1 Contribution of This Paper
9.2 Related Work
9.3 Proposed Implementation
9.3.1 IoT Drone Environment Preliminaries
9.3.2 Successive Weather/Crop Influence Rate (SWF)
9.3.3 Spatial Weather Information Data Rate (SCIDR)
9.3.4 Contemporary Forecasting Rate (CFR)
9.3.5 Mutual Subset Intensive Cluster Feature Selection (MSIFS)
9.3.6 U-Net CNN
9.3.7 Sustainable Crop Recommendation
9.4 Result and Discussion
9.5 Conclusion
References
10 IoT-Based Automatic Drip Irrigation Control Using Intelligent Agriculture
10.1 Introduction
10.2 Identification of Chlorophyll
10.2.1 Methods of Measurement of Chlorophyll
10.3 Image Capturing and Processing
10.3.1 Drones and Its Functions
10.3.2 Rice Leaf Image Pre-processing and Segmentation
10.3.3 Proposed Method
10.4 Irrigation Control
10.5 Conclusion
References
11 IOT-Based Innovative Agriculture Farming System Based on Rover-Drone Surveillance Sensing Unit Using Feature Selection and Classification Techniques
11.1 Introduction
11.2 Related Work
11.3 Proposed Solution
11.3.1 Drone and IoT Sensing Approach
11.3.2 Data Preprocessing
11.3.3 Harvest Impact Rate (HIR)
11.3.4 Farming Intensity Feature Margin Rate (FIFMR)
11.3.5 Fuzzy Intensive Feature Selection (FIFS)
11.3.6 Multi-perception Neural Network
11.3.7 Prediction and Recommendation
11.4 Result and Discussion
11.5 Conclusion
References
12 Village Mapping for Micro-level Planning Using UAV Technology
12.1 Introduction
12.2 Applications of UAV
12.3 Accuracy of Drone Survey
12.4 Processing Drone Survey Data
12.4.1 Importing Images in to Photogrammetry Software
12.5 Applications of UAV-RS in NE Region
12.5.1 Mapping of Landslide-Affected Areas
12.5.2 Infested Crop Damage Assessment
12.5.3 Town Mapping of Nongpoh–Meghalaya
12.5.4 3-D Terrain Modeling
12.6 Operational Challenges and Issues
12.7 Case Study
12.7.1 The Development Planning Scenario
12.7.2 Use of Satellite Imagery for Developmental Planning
12.8 Survey of India’s Latest Initiative
12.9 Conclusion
References
13 An In-Sight Analysis of Cyber-Security Protocols and the Vulnerabilities in the Drone Communication
13.1 Introduction
13.2 UAV Systems
13.3 Security Protocols Used in UAV System
13.3.1 Symmetric Cryptography Security Protocols
13.3.2 Asymmetric Cryptography Security Protocols
13.3.3 Lightweight Security Protocols
13.4 Related Works
13.5 Attacks on UAV Security Systems
13.5.1 Confidentiality and Privacy Attacks (Data Interception)
13.5.2 Integrity Attacks (Data Modification)
13.5.3 Availability Attacks (Communication Interruption)
13.5.4 Authenticity Attacks (Data Fabrication)
13.6 Conclusion
References
14 Introspecting the Impact of Selected Macro-economic Variables and Policy Interventions in Unmanned Aerial Vehicle (UAV) Sector: The Case of India
14.1 Introduction
14.2 Review of Literature
14.3 Methodology
14.4 Results and Discussions
14.5 Stability Test
14.6 Managerial Implications
14.7 Conclusions and Future Directions
References