Computational Intelligence in Robotics and Automation

Cover
Half Title
Title Page
Copyright Page
Table of Contents
Preface
Acknowledgments
Editors
Contributors
Chapter 1: Automatic Detection of Dental Age Assessment Using an Efficient Elman Neural Network with Dragonfly Optimization
1.1 Introduction
1.2 Background
1.2.1 Dental Age Assessment
1.2.2 Antiquity of Age Assessment
1.2.2.1 Necessity for Age Assessment
1.2.3 Methods of Age Estimation in Adults
1.2.3.1 Histological Methods
1.2.3.1.1 Dentinal Translucency
1.2.3.1.2 Incremental Lines of Cementum
1.2.3.1.3 Typical Age of Erosion
1.2.3.1.4 Newborn Line in Enamel and Dentin
1.2.3.1.5 Racemization Method
1.2.3.2 Biochemical Methods
1.2.3.2.1 Amino Acid Racemization
1.2.3.3 Radiological Method
1.2.3.3.1 Schour and Masseler Method
1.2.3.3.2 Demirjian, Goldstein and Tanner Method
1.3 Proposed Methodology
1.3.1 System Overview
1.3.2 Dataset Description
1.3.3 Pre-Processing Stage
1.3.4 Teeth Segmentation Using IABC
1.3.4.1 Fitness Value Approximation
1.3.5 Feature Extraction
1.3.6 Dental Age Classification
1.3.7 Optimal Weight of ENN Selection Using DO
1.3.7.1 Threshold Determination
1.4 Outcomes and Disclosure
1.5 Conclusion and Future Work
Bibliography
Chapter 2: Robotic Assistants from Personalized Care to Disease Diagnosis and Treatment Plans in Healthcare Applications
2.1 Introduction
2.2 Robotic Assistance in Healthcare
2.2.1 OneRemission
2.2.2 Youper
2.2.3 Babylon Health
2.2.4 Florence
2.2.5 Healthily
2.3 Usage of AI in Improving Healthcare System
2.4 Nanorobots in Cancer Medication
2.5 Personalized Treatment Procedures in Cancer Patients Using Nanoautomation Techniques
2.6 Isolating Cells Autonomously in Cancer Medications
2.7 Data Analysis
2.8 Conclusion
References
Chapter 3: A Novel Model for Weather Forecasting Using Deep Learning
3.1 Introduction
3.2 Literature Review
3.3 Proposed System
3.3.1 Long Short-Term Memory
3.3.2 Architecture of LSTM
3.3.3 Additional Hyper-Parameters
3.4 Results and Discussion
3.4.1 Overview of Dataset
3.4.2 Results and Discussion
3.5 Conclusion and Future Work
References
Chapter 4: Application of Artificial Intelligence Algorithms for Robot Development
4.1 Artificial Intelligence
4.1.1 Use Cases of Artificial Intelligence
4.1.1.1 Infectious Disease Diagnosis Using Machine Learning
4.1.1.2 Surgical Robots with Intelligence
4.1.1.3 Healthcare Applications
4.1.1.4 Fraud Detection
4.1.1.5 Investment Prediction
4.1.2 AI Applications in Manufacturing Sectors
4.1.3 AI Applications in Quality Control and Automotive Insurance
4.1.3.1 Personalized Learning and Smart Learning
4.1.3.2 Reducing Admin/Staff Work and Increased Accessibility
4.1.3.3 Product Pricing and Advertising
4.1.3.4 Surveillance and Logistics
4.1.3.5 Client Sentiment Analysis
4.1.3.6 Search Optimization
4.2 Robotics
4.2.1 Types of Robot
4.2.2 Robotic Applications
4.3 Robotic Process Automation (RPA)
4.3.1 RPA in Banking Sector
4.3.2 AI and Robotics in Healthcare
4.3.3 AI-Based Industrial Robots
4.3.4 AI and Robotics in Smart Cities Development
4.3.5 Distinction between AI and Robotics
4.4 Machine Learning Algorithms for Robotic Applications
4.4.1 Machine Learning in Business Processes
4.4.2 Robotic Use Cases with Machine Learning
4.4.2.1 Indoor Navigations
4.4.2.2 Manufacturing Environment
4.4.2.3 Unmanned Aerial Vehicles
4.4.3 Modern Arenas of Artificial Intelligence in Robotics
4.4.3.1 Statistical Learning
4.4.3.2 Fuzzy Logic
4.4.3.3 Deep Learning
4.4.3.4 Evolutionary Computing
4.4.3.5 Neural Networks
4.4.3.6 Reinforcement Learning
4.4.3.7 Logic-Based AI
4.5 Societal Impact of Artificial Intelligence
4.5.1 AI: Positive Impacts
4.5.2 AI: Negative Impacts
4.5.2.1 Change in Human Experience
4.5.2.2 Stimulated Hacking
4.5.2.3 Loss of Jobs
4.5.2.4 Laws and Regulations
4.5.2.5 Bias
4.5.2.6 Terrorism
4.5.3 Challenges of AI for Robotics
4.5.3.1 Challenge 1: Volume of Training Data
4.5.3.2 Challenge 2: Time Taken to Train
4.5.3.3 Challenge 3: Estimating Uncertainty
4.5.3.4 Challenge 4: Unknown’s Identification
4.5.3.5 Challenge 5: Continuous Learning
4.6 Conclusion
References
Chapter 5: Robotic Process Automation in COVID-19
5.1 Introduction
5.2 What is RPA?
5.3 What Advantages Does RPA Bring to a COVID-19 Environment?
5.4 Analyzing the Pros and Cons of Robotic Process Automation
5.4.1 Pandemic Drives a Move Toward Increased Automation
5.4.2 Potential Strengths
5.4.3 Potential Weaknesses
5.4.4 Potential Opportunities
5.5 The Meaning of RPA in Healthcare Industry
5.5.1 Why Is RPA Significant in Medical Care?
5.5.2 Use Cases of RPA in Medical Care
5.5.2.1 Patient Scheduling
5.5.2.2 Guarantee Administration
5.5.2.3 Regulatory Compliance
5.5.2.4 Resettling/Relocation
5.5.2.5 Use Cases of Skeptic Industry
5.6 What Are the Benefits of RPA in Healthcare?
5.7 Real-World Application of RPA in Healthcare
5.7.1 Hit the High Spots of Patients’ Booking
5.7.2 More Viable Administration of Supply Measures (Claims and Charging)
5.7.3 Further Develop Income Cycle Capacities (New Understanding Arrangement Demands, Patient Pre-Appearance and Appearance, Guarantee Disavowals, Charging)
5.7.4 Support Large-Scale Implementation of Health Plans
5.7.5 Improvement of the Consideration Cycle
5.7.6 Advanced Administrative Consistence
5.8 How Is the Pandemic Accelerating RPA Adoption?
5.8.1 Some Healthcare Organizations are Still Cautious
5.8.2 Improving on Claim Processing
5.8.3 The State of Arizona Employs RPA Solutions
5.8.4 Extricating Patient Data while Remaining Compliant
5.9 How Is the Pandemic Accelerating RPA Adoption?
5.9.1 Some Healthcare Organizations are Still Cautious
5.9.2 Simplifying Claim Processing
5.9.3 Automation in the Clinical Business Can Fix This Issue. This Is What RPA Bots Can Do
5.9.4 The State of Arizona Employs RPA Solutions
5.9.5 Extricating Patient Data While Remaining Compliant
5.10 Robotic Cycle Automation (RPA) In Healthcare
5.10.1 Data Management
5.10.2 Appointment Scheduling
5.10.3 Managing Claims
5.10.4 Optimal Care Delivery
5.10.5 Hospital Management
5.11 Advantages of RPA in Healthcare
5.11.1 Further Developing the Medical Services Cycle
5.11.2 An Outline of RPA in Medical Services
5.11.3 Settling COVID-Explicit Difficulties
5.11.4 Moderate Appropriation, Up to This Point
5.12 Conclusion
Bibliography
Chapter 6: Newfangled Immaculate IoT-Based Smart Farming and Irrigation System
6.1 Introduction
6.1.1 The Need for Agricultural Computational Intelligence
6.1.1.1 Use of Robotic Applications in Agriculture
6.1.2 Challenges for Implementing IoT in Agriculture
6.1.2.1 Weak Farm Internet Connectivity
6.1.2.2 Elevated Prices for Hardware
6.1.2.3 Disrupted Cloud Access
6.1.3 Smart Agriculture Practices
6.1.4 Benefits of Adopting New Technology in Agriculture
6.1.4.1 Adoption of Technology in Agriculture
6.1.4.2 Technology Use of Agriculture
6.1.4.2.1 Farm Robots
6.1.4.2.2 Sensors for Crops
6.1.4.2.3 Application of GPS in Field Documentation
6.1.4.2.4 Biotechnology
6.1.5 State of IoT in Agriculture
6.1.5.1 Data Collection and Processing
6.1.5.2 Control over Risks
6.1.5.3 Business Automation
6.1.5.4 Quality Improvements
6.2 Impact of Intelligence
6.2.1 Role of Intelligence in Agriculture in the Modern Era
6.2.1.1 Effects of Artificial Intelligence in Agriculture
6.2.1.1.1 Weather Data Forecast
6.2.1.1.2 Crop and Soil Quality Monitoring
6.2.1.1.3 Decrease Pesticide Usage
6.2.1.1.4 AI Agriculture Bots
6.2.2 Scope of Internet of Things in Agriculture
6.2.3 Importance of Intelligence in Agriculture Process
6.2.4 Benefits of Computational Intelligence
6.3 Overview on Smart Farming
6.3.1 Various Steps in the Farming Process
6.3.1.1 Crop Selection
6.3.1.2 Preparation of Land
6.3.1.2.1 Land Preparation Method—Tillage Practices
6.3.1.2.2 Seed Preparation
6.3.1.2.3 Sowing Seed
6.3.1.2.4 Irrigation
6.3.1.2.5 Increase in Crops
6.3.1.2.6 Crop Fertilizing
6.3.1.2.7 Harvest
6.3.2 Using Modern Sensors in a Farming Environment
6.3.2.1 Benefits of Agriculture Sensors
6.3.2.2 Drawbacks of Sensors for Agriculture
6.3.3 Role of Automation in Agriculture and Its Advantages Over Traditional Method
6.3.4 Applications of IoT in Agriculture
6.3.4.1 Climate Conditions
6.3.4.2 Precision Farming
6.3.4.3 Smart Greenhouse
6.3.4.4 Data Analytics
6.3.4.5 Agricultural Drones
6.4 Process Involved in Irrigation
6.4.1 Introduction about Irrigation and Its Importance
6.4.1.1 Irrigation Types
6.4.1.2 Irrigation Methods
6.4.1.3 Traditional Irrigation Method
6.4.1.4 Modern Irrigation Method
6.4.1.5 System of Sprinklers
6.4.1.6 Drip System
6.4.1.7 The Need for Automation in Irrigation
6.4.2 Role of Robotics in the Irrigation Process
6.4.3 Irrigation Deployment in Smart Farming
6.4.3.1 Details for Land
6.4.3.2 Data on the Weather
6.4.3.3 Moisture Level of Soil
6.4.3.4 Recourse to Water
6.5 Security Aspects in Smart Agriculture
6.5.1 Security for Using AI in Agriculture
6.6 Future Trends in Smart Agriculture
6.7 Conclusion
References
Chapter 7: A Review on Haze Removal Methods in Image and Video for Object Detection and Tracking
7.1 Introduction
7.1.1 Background Subtraction Method
7.1.2 Weather Condition-Based Method
7.2 Polarization Filter-Based Method
7.2.1 Depth-Based Method
7.2.2 Independent Component Analysis
7.2.3 DCP (Dark Channel Prior) Method
7.2.4 CLAHE/Mix-CLAHE
7.3 Literature
7.3.1 Analysis from Literature
7.3.2 Findings from Literature
7.4 Challenges
7.5 Application and Benefits
7.6 Research Gap Identification
7.7 Conclusion
7.8 Future Scope
References
Chapter 8: Cyber ML-Based Cyberattack Prediction Framework in Healthcare Cyber-Physical Systems
8.1 Introduction
8.2 CPS in Medical Healthcare – An Overview
8.3 Background Work
8.4 Cyber Machine Learning Frameworks with Intrusion Detection System
8.4.1 Real-World Prediction
8.4.2 Detection of Anomalies
8.5 Results and Discussion
8.5.1 Attack Determination Ratio
8.5.2 Attack Determination Accuracy
8.5.3 Delay Ratio
References
Chapter 9: IoT-Based Smart Irrigation and Monitoring System for Agriculture
9.1 Introduction
9.1.1 Farming in India
9.1.2 Smart Farming
9.1.2.1 Precision Farming
9.1.2.2 Smart Greenhouse
9.1.2.3 Future of Farming
9.1.3 Differences between Traditional and Smart Farming
9.2 Literature Survey
9.3 Methods of Irrigation
9.3.1 Channel Irrigation
9.3.2 Sprinkler Irrigation
9.3.3 Drip Irrigation
9.4 Comparative Study
9.5 WSN-Based IoT System
9.5.1 WSNs
9.5.1.1 Function of Nodes
9.5.2 Internet of Things
9.6 Hardware Description
9.6.1 Soil Moisture Sensor
9.6.2 LDR Sensor
9.6.2.1 Working of LDR
9.6.3 PH Sensor
9.6.4 Humidity and Temperature Sensor
9.6.5 Modules
9.6.5.1 Arduino Mega 2560
9.6.5.2 ESP 8266
9.6.5.3 Breadboard BB400
9.6.5.4 Breadboard Power Supply
9.7 Proposed System
9.7.1 Smart Agriculture
9.7.2 Difficulties in Smart Farming
9.8 Conclusion
9.9 Challenges and Future Scope
References
Chapter 10: Applications in Automobile Industries: Warehouse, Logistics and Delivery Systems, Mobile Robots
10.1 Introduction
10.2 Literature Review
10.3 Industrial Application of Mobile Robotics
10.3.1 History
10.3.2 Industrial Applications
10.3.2.1 Arc Welding
10.3.2.2 Materials Handling
10.3.2.3 Machine Tending
10.3.2.4 Painting
10.3.2.5 Picking and Packing
10.3.2.6 Assembly
10.3.2.7 Mechanical Cutting and Grinding
10.3.2.8 Gluing and Sealing
10.4 Autonomous Mobile Robots
10.4.1 So What Are Autonomous Robots?
10.4.2 Control Scheme of Autonomous Mobile Robots (AMRs)
10.4.3 Comparison between AGVs and AMRs
10.4.3.1 Direction Identification
10.4.3.2 Tractability
10.4.3.3 Ease of Access
10.4.4 Types of Autonomous Mobile Robots
10.4.4.1 Automated Goods Picking Machine
10.4.4.2 Automated Driving Forklifts
10.4.4.3 Automated Inventory Robots
10.4.4.4 Unmanned Autonomous Vehicles
10.4.5 Path Planning in Autonomous Mobile Robots
10.4.6 Applications of AMRs
10.4.6.1 AMRs in Distribution Centres
10.4.6.2 AMRs as Disinfectants
10.4.6.3 Autonomous Security Robots (ASR)
10.4.6.4 Autonomous Robots in Healthcare
10.4.6.5 Autonomous Mobile Robots in Grocery Stores
10.4.6.6 AMRs for Hospitality
10.5 Usage of Drones in Warehouse-Based Applications
10.5.1 Drones
10.5.2 Drones in Warehouse-Based Applications
10.5.3 Inventory Management
10.5.4 Intra-Logistics
10.5.5 Inspection and Surveillance
10.6 Automated Guided Vehicles
10.6.1 Advantages of an Automated Guided Vehicle System
10.6.2 Different Types of AGVs
10.6.2.1 Fork Lifts
10.6.2.2 Tow/Tugger
10.6.2.3 Unit Load
10.6.3 Guidance Methods
10.6.3.1 Wire – Embedded in Floor
10.6.3.2 Guide Tape (Magnetic or Coloured)
10.6.3.3 Inertial (Gyroscopic) Navigation
10.6.3.4 Laser – Triangulation from Reflective Target
10.6.4 Path Decision
10.6.4.1 Frequency Select Mode
10.6.4.2 Path Select Mode
10.6.4.3 Magnetic Tape Mode
10.6.5 Application
10.6.5.1 Industries Application
10.6.5.2 Common Applications
10.7 Planning and Control of Autonomous Vehicles
10.7.1 Integrated Planning
10.7.2 System Architecture of Planning and Decision Making in Autonomous Vehicles
10.7.3 Deep Neural Networks (DNN) in Object Detection and Classification
10.8 Conclusion
References
Chapter 11: Drones in Agriculture: Multispectral Analysis
11.1 Introduction
11.1.1 Drones
11.1.2 Multispectral Camera
11.1.2.1 Capturing the Multispectral Data
11.1.3 Discussion (Literature Survey)
11.1.3.1 Difference between Multispectral Data Obtained from Satellite and Drone
11.1.3.2 Using Data with Plant Indices
11.1.3.3 Farmers Need Solutions from Data
11.1.4 Algorithmic Analysis
11.1.4.1 Plant Indices
11.1.4.2 Uses
11.1.4.3 Description
11.1.4.4 Uses
11.1.4.5 Description
11.1.4.6 Uses
11.1.4.7 Description
11.1.4.8 Chlorophyll Map
11.1.4.9 Uses
11.1.4.10 Description
11.1.4.11 Uses
11.1.4.12 Explanation
11.1.4.13 Explanation
11.1.4.14 Uses
11.1.5 Real-World Results
11.1.5.1 Stress Management
11.1.5.2 Nitrogen Recommendation Methodology
11.1.5.3 Analyzing the Effects of Fertilizers in Plant Chlorophyll Levels
11.1.5.4 Detection of Disease Using the Red Edge Band
11.1.5.5 Analyzing the Effects of Various Fungicides on Disease Management
11.1.5.6 Detection of Weeds
11.2 Results
11.3 Conclusion
References
Index