Preface
Objective of the Book
Contents
Editors and Contributors
Chapter 1: The Contribution of Artificial Intelligence to Drug Discovery: Current Progress and Prospects for the Future
1.1 Introduction
1.2 Historical Evolution of Drug Discovery
1.3 Fundamentals of Artificial Intelligence in Drug Discovery
1.4 Data-centric Approaches in Artificial Intelligence for the Field of Drug Discovery
1.5 Data-driven Approaches in AI for Drug Discovery
1.6 Hurdles and Prospects in Artificial Intelligence for the Field of Drug Discovery
1.6.1 Navigating Challenges and Embracing Prospects in AI-driven Drug Discovery
1.6.2 Pinpointing Bottlenecks in Traditional Drug Discovery
1.6.3 Untangling AI Implementation Challenges
1.6.4 Glimmers of Possibilities Unleashed by AI
1.6.5 A New Dawn in Drug Discovery
1.7 Case Study: AlphaFold´s Acceleration in Drug Discovery
1.7.1 Significance of AlphaFold
1.7.1.1 Mathematical Mastery Behind AlphaFold´s Prognostic Abilities
1.7.2 Elevating Drug Discovery: The AlphaFold Impact on CDK20 Inhibitor Discovery
1.7.3 AlphaFold´s Multi-dimensional Drug Discovery Impact
1.7.4 Navigating Challenges and Seizing Opportunities
1.7.5 The Eclipsing Horizon
1.8 AI in the Era of Pandemics: Case of COVID-19
1.8.1 Overview of the COVID-19 Pandemic
1.8.2 AI´s Crucial Role in Drug Discovery and Vaccine Development
1.8.3 Leveraging Mathematical Models for Drug Prediction
1.8.4 A Glimpse into the Future
1.9 Deep Learning in Antibiotic Discovery
1.10 AI Techniques in Antibiotic and Antiviral Development
1.11 Applications of AI in Drug Discovery
1.11.1 Target Identification and Validation
1.11.2 Compound Screening and Design
1.11.3 Clinical Trial Optimization
1.11.4 Concrete Examples of AI´s Impact
1.12 The Future of AI in Drug Discovery
1.12.1 Emerging AI Techniques in Drug Discovery
1.12.2 The Potential of Personalized Medicine via AI
1.12.3 Predictive Mathematical Models Shaping Drug Discovery´s Future
1.13 Conclusion
1.13.1 Revolutionizing Microbial Drug Discovery with Artificial Intelligence
1.13.2 Anticipating Future Trends and Breakthroughs
1.13.3 Potential Breakthroughs Envisioned by AI
References
Chapter 2: Prediction of Plant Disease Using Artificial Intelligence
2.1 Introduction
2.2 Fundamentals of Plant Disease Diagnosis
2.2.1 Plant Disease Types
2.2.2 Symptoms and Signs
2.2.3 Conventional Diagnostic Techniques
2.2.4 Limitations of Traditional Methods
2.2.5 Need for AI-driven Innovative Methods
2.3 Role of Artificial Intelligence in Plant Disease Diagnosis
2.3.1 AI: Changing the Diagnosis of Plant Disease
2.3.2 Disease Diagnosis Based on Images
2.3.3 Sensor Data and Disease Forecasting
2.4 AI´s Advantages in Plant Disease Diagnosis
2.4.1 Early Disease Detection and Prevention
2.4.2 Accuracy and Scalability
2.4.3 Reduced Dependence on Chemicals
2.4.4 Improved Decision-making Capability
2.5 Barriers to Implementing AI Techniques in Plant Disease Diagnosis
2.5.1 Data Accuracy
2.5.2 Model Interpretability
2.5.3 Infrastructure and Accessibility
2.6 Current Trends in AI Involvement in Plant Disease Diagnostics
2.7 Data Collection and Pre-processing
2.8 The Significance of Data Quality
2.9 Data Sources
2.10 Techniques for Pre-processing Data
2.10.1 Data Augmentation
2.10.2 Standardization and Normalization
2.10.3 Feature Extraction
2.10.4 Balancing Classes
2.11 Data Collection and Pre-processing Challenges
2.11.1 Labeling Complexity
2.11.2 Imbalanced Data
2.11.3 Data Access and Privacy
2.11.4 Environmental Variability
2.12 Building and Training AI Models
2.12.1 Comparative Analysis of Choosing Appropriate AI Algorithms for Plant Disease Diagnosis
2.12.2 Convolutional Neural Networks (CNN)
2.12.3 Random Forests
2.12.4 Factors Affecting Algorithm Selection
2.12.4.1 Data Accessibility
2.12.4.2 Interpretability
2.12.4.3 Computing Power
2.12.4.4 Real-time Requirements
2.13 Image-based Plant Disease Diagnosis
2.13.1 Data Pre-processing and Training AI Models
2.13.2 Systematic Algorithm for Image-based Disease Diagnosis
2.14 Model Evaluation
2.15 Sensor Data-based Disease Diagnosis
2.16 Future Directions and Innovations
2.16.1 Explicit AI for Interpretability
2.16.2 Fusion of Multi-modal Data
2.16.3 Limited Transfer Learning with Data
2.16.4 Active Learning Techniques
2.16.5 Distributed Learning for Decentralized Data
2.17 Integration of AI for Plant Disease Diagnosis Using Robotics, Drones, and Automated Farm Equipment
2.17.1 Robotics for Precision Plant Inspection
2.17.2 Aerial Surveillance Using Drones
2.17.3 Autonomous Farm Machinery for Personalized Care
2.17.4 Analyzing Real-time Data
2.17.5 Improved Disease Surveillance
2.18 AI Revolutionizing Sustainable Farming Methods and Precision Agriculture
2.19 Conclusion
References
Chapter 3: Computer Vision-based Remote Care of Microbiological Data Analysis
3.1 Introduction
3.2 The Role of Computer Vision
3.2.1 Automatization of Microorganism Identification
3.2.2 Classification and Taxonomy
3.2.3 Quantification
3.2.4 Tracking and Behavior Analysis
3.2.5 Presence/Absence Detection
3.2.6 High-throughput Screening
3.2.7 Integration with Other Technologies
3.2.8 Remote Monitoring
3.2.9 Applications
3.3 Steps Required to Implement
3.4 Microbiological Data
3.5 Different Algorithms to Implement Computer Vision
3.6 Challenges and Future Directions
3.7 Conclusion
References
Chapter 4: A Comparative Study of Various Machine Learning (ML) Approaches for Fake News Detection in Web-based Applications
4.1 Introduction
4.1.1 Logistic Regression
4.1.2 Decision Tree Classifier
4.1.3 Random Forest Classifier
4.1.4 Linear Support Vector Classifier (SVC)
4.1.5 Multinomial Naive Bayes (NB)
4.1.5.1 Naive Bayes Equation
4.2 Related Work
4.3 Work Done
4.4 Result Discussion
4.5 Conclusions and Future Direction
References
Chapter 5: Analytics and Decision-making Model Using Machine Learning for Internet of Things-based Greenhouse Precision Manage...
5.1 Introduction
5.2 Related Work
5.3 Development of IoT-based Smart Farming System
5.4 Experimental Results and Discussion
5.5 Conclusion
References
Chapter 6: DistilBERT-based Text Classification for Automated Diagnosis of Mental Health Conditions
6.1 Introduction
6.2 Related work
6.3 Dataset and Prepossessing
6.3.1 Dataset
6.3.2 Prepossessing
6.4 Methodology
6.4.1 Batch Training
6.4.2 Hyperparameter Tuning
6.4.3 Algorithm
6.4.4 Evaluation Standards
6.5 Simulation Results and Discussion
6.5.1 Model Training
6.5.2 Text Data Distribution Analysis
6.5.3 Confusion Matrix
6.5.4 Visualizing Word Clouds
6.6 Conclusion
References
Chapter 7: An Optimized Hybrid ARIMA-LSTM Model for Time Series Forecasting of Agricultural Production in India
7.1 Introduction
7.2 Materials and Methods
7.2.1 Data
7.2.2 Stationary Test
7.2.3 Autoregressive Integrated Moving Average (ARIMA)
7.2.4 Long Short-term Memory (LSTM)
7.2.5 Optimized Hybrid ARIMA-LSTM
7.3 Results and Discussion
7.4 Conclusion
References
Chapter 8: An Exploratory Analysis of Machine Intelligence-enabled Plant Diseases Assessment
8.1 Introduction
8.2 Literature Review
8.3 Working Methodology and Datasets
8.4 Advantages and Constraints
8.5 Challenging Issues of the Framework
8.6 Conclusion
References
Chapter 9: Synergizing Smart Farming and Human Bioinformatics Through IoT and Sensor Devices
9.1 Introduction
9.2 Smart Farming and IoT: Enhancing Agricultural Productivity
9.2.1 IoT in Agriculture
9.2.2 Precision Agriculture
9.2.3 Predictive Analytics
9.2.4 Resource Optimization
9.3 Benefits of IoT and Sensor Technologies in Agriculture
9.4 Human Bioinformatics and IoT: Revolutionizing Healthcare
9.4.1 IoT in Healthcare
9.4.2 Personalized Health Insights
9.4.3 Disease Management
9.4.4 Healthcare Accessibility
9.5 Synergy Between Smart Farming and Human Bioinformatics
9.5.1 Environment-Health Nexus
9.5.2 Shared Data Analytics
9.5.3 Nutritional Sustainability
9.5.4 Early Warning Systems
9.6 Benefits of Combining Insights
9.6.1 Holistic Approach
9.6.2 Cross-Domain Findings
9.6.3 Enhanced Resource Management
9.6.4 Impact on Public Health
9.7 Challenges, Limitations, and Ethical Considerations
9.7.1 Data Security and Privacy
9.7.2 Data Accuracy and Quality
9.7.3 Interoperability and Standardization
9.7.4 Technology Access and Literacy
9.7.5 Environmental Impact
9.8 Future Possibilities, Innovations, and Research Areas
9.8.1 Predictive Public Health Models
9.8.2 Data-Driven Nutritional Sustainability
9.8.3 Environmentally Friendly Precision Agriculture
9.8.4 Solutions for Personalized Agri-Health
9.8.5 Ethical Data Governance
9.8.6 Cross-Disciplinary Training
9.8.7 Climate-Health Resilience
9.9 Conclusion
References
Chapter 10: Deep Learning-Assisted Techniques for Detection and Prediction of Colorectal Cancer From Medical Images and Microb...
10.1 Introduction
10.2 Deep Neural Networks for Image Analysis
10.2.1 Convolutional Neural Networks
10.2.2 Transfer Learning Models
10.2.3 Ensemble Learning Models
10.2.4 Object Detection Models
10.2.5 Image Segmentation Models
10.2.6 Network Pruning
10.2.7 Deep Belief Networks (DBNs)
10.2.8 Generative Adversarial Networks (GANs)
10.2.9 Transformers
10.3 Deep Learning for Classification, Segmentation, Detection, and Prediction of CRC From Different Modalities
10.3.1 CRC Detection and Prediction Using Endoscopic Images and Videos
10.3.2 CRC Detection and Prediction Using Tissue Images (Biopsy Samples)
10.3.3 CRC Detection Using Omic Data
10.3.4 CRC Detection From MRI, (FDG)-PET, and CT Scan Data
10.3.5 Deep Learning for Detecting Colorectal Cancer Using Microbial Data
10.4 Methodology
10.4.1 Dataset
10.4.2 Model Selection for CRC Classification
10.4.3 Tools
10.4.4 Model Evaluation
10.5 Results and Discussion
10.5.1 Model Implementation
10.5.2 Model Performance on Datasets
10.6 Conclusion
References
Chapter 11: Smart Farming and Human Bioinformatics System Based on Context-Aware Computing Systems
11.1 Introduction
11.1.1 Motivation
11.1.2 Contributions of This Chapter
11.2 State-of-the-Art
11.3 Data Analytics in Agriculture
11.4 Proposed HDFS Recommendation System
11.4.1 System Model
11.4.2 Phase 1: Data Polishing
11.4.2.1 Phase 2: Feature Extraction and Similarity Matching
11.4.3 Phase 3: Dual Analysis
11.4.4 Phase 4: Data Clustering
11.5 Conclusion
References
Chapter 12: Plant Diseases Diagnosis with Artificial Intelligence (AI)
12.1 Introduction
12.1 Supervised Learning
12.1 Unsupervised Learning
12.1 Semi-supervised Learning
12.1 Reinforcement Learning
12.1 Techniques and Tools
12.1 Crop Diagnosis
12.1 Plantix App
12.1 Saillog Agrio
12.1 Future Directions
References
Chapter 13: Analyzing the Frontier of AI-Based Plant Disease Detection: Insights and Perspectives
13.1 Introduction
13.2 Related Work
13.3 Steps in the Detection of Plant Diseases
13.4 Disease Detection AI Methods and Type of Crops
13.5 Impact of Plant Diseases on Human Life and Environment
13.6 Challenges
13.7 Open Issues
13.8 Conclusion
References
Chapter 14: Fuzzy and Data Mining Methods for Enhancing Plant Productivity and Sustainability
14.1 Introduction
14.2 The Imperative of Sustainable Agriculture
14.2.1 Fuzzy Logic
14.2.2 Data Mining: Unearthing Insights from Agricultural Data
14.2.3 The Synergy: Fuzzy Logic and Data Mining.
14.2.4 Fuzzy Logic: A Foundation for Uncertainty Handling.
14.3 Data Mining Techniques for Agricultural Insights
14.3.1 Classification and Clustering
14.3.2 Regression
14.4 Integration of Fuzzy Logic and Data Mining
14.5 Case Studies
14.6 Challenges and Future Directions
14.6.1 Challenges
14.7 Role of Data Mining in Addressing Resource Constraints
14.8 Challenges and Considerations
14.9 Future Directions
14.10 Conclusion
References
Chapter 15: Plant Disease Diagnosis with Artificial Intelligence (AI)
15.1 Introduction
15.1.1 AI Technologies in Plant Diseases Diagnosis
15.1.1.1 Deep Learning and Neural Network
15.1.2 Convolutional Neural Network (CNN)
15.2 Machine Learning Method
15.2.1 Disease Detection System for General Plant
15.2.2 Data Acquisition
15.2.3 Dataset Annotation
15.2.4 Data Processing
15.2.5 Feature Extraction
15.3 Classification Techniques
15.3.1 Support Vector Machine (SVM) Classifier
15.3.2 Artificial Neural Network Classifier
15.3.3 Fizzy Classifier
15.4 Advantages and Challenges
15.4.1 Early Detection of Plant Diseases
15.4.2 Rapid Diagnosis
15.4.3 Accurate Estimations
15.4.4 Cost-Effectiveness
15.4.5 Global Collaboration and Accessibility
15.4.6 Continuous Monitoring
15.4.7 Improved Yield and Crop Quality
15.4.8 Data-Driven Insights
15.4.9 Robotics in Agriculture
15.4.10 Integration with IoT
15.4.11 Challenges and Limitations
15.4.12 Data Quality and Quantity
15.4.13 Scalability
15.4.14 Ethical Considerations
15.4.15 Complexity of Plant Diseases
15.5 Future Prospects and Implications
15.5.1 Fusion of AI Techniques
15.5.2 Robotics and Drones
15.6 Conclusion
References
Chapter 16: Sustainable AI-Driven Applications for Plant Care and Treatment
16.1 Introduction
16.1.1 Role of AI in Optimizing Farming Practices Through Precision Agriculture
16.1.2 Agriculture Satellite Imagery: A Technological Revolution for Sustainable Farming
16.1.3 Use of Sensors and Data Analytics
16.2 Drones in Agriculture: Planting the Seeds of a High-Tech Future
16.2.1 Precision Farming
16.2.2 Crop Monitoring and Management
16.2.3 Mapping and Surveying
16.2.4 Yield Prediction and Assessment
16.2.5 Environmental Stewardship
16.2.6 Internet of Things (IoT) in Agriculture: Real-Time Data Collection for Better Farming
16.2.7 Weather Monitoring and Forecasting
16.2.8 Livestock Management
16.3 Predictive Modeling for Yield Optimization
16.3.1 DSSAT AI Growth Models
16.3.2 Crop Enhancement Through Predictive Modeling
16.4 Disease Detection and Treatment
16.4.1 Machine Learning for Crop Disease Management
16.4.2 Deep Learning Models to Extract Features
16.4.3 Two-Stage Detection Network (Faster R-CNN)
16.4.4 AI and Remote Sensing Applications for Plant Health Monitoring and Treatment
16.4.4.1 Plantix Application
16.4.4.2 Stress Detection
16.4.4.3 Yield Prediction
16.4.4.4 Weed Control
16.4.4.5 Nutrient Management
16.4.4.6 Smart Irrigation
16.4.4.7 Climate Resilience
16.5 Conclusion
References
Chapter 17: Use Cases and Future Aspects of Intelligent Techniques in Microbial Data Analysis
17.1 Introduction
17.1.1 Role of Intelligent Techniques
17.2 Microbial Data Analysis
17.2.1 Using AI for Public Health Surveillance
17.2.2 Microbial Networks: Nature´s Intelligent Systems
17.2.3 Microbial Data Analysis for Disease Association
17.2.4 AI-Powered Antibiotic Susceptibility Testing
17.3 Use Cases of Intelligent Techniques
17.3.1 Microbiome Studies
17.3.1.1 Predicting Disease Risk Through Gut Microbiome Analysis
17.3.1.2 Microbial Biomarkers for Disease Prediction
17.3.1.3 Targeted Microbiome Interventions
17.3.1.4 Discovering Novel Microbial Functions
17.3.1.5 Functional Metagenomics in Environmental Microbiomes
17.3.1.6 Recognition of Fungi with Convolutional Neural Networks (CNN)
17.3.1.7 Combined Application of Microbial Genome Sequencing and Machine Learning
17.3.1.8 AI and Skin Diseases in the Context of the Gut-Skin Axis
17.3.2 Antibiotic Resistance Prediction
17.3.2.1 Genomic Analysis of Antibiotic Resistance in Pathogens
17.3.2.2 Real-Time Antibiotic Resistance Prediction
17.3.2.3 Tracking Resistance Trends
17.3.3 Environmental Microbiology
17.3.3.1 Machine Learning Empowers Microbial Community Analysis in Soil Ecosystems
17.3.3.2 Advancements in Predicting Nutrient Cycling in Aquatic Environments
17.3.3.3 Machine Learning and AI Revolutionize Bioremediation of Contaminated Sites
17.3.4 Biotechnology and Bioprocess Optimization
17.3.4.1 Optimization of Bioethanol Fermentation
17.3.4.2 Accelerating Drug Discovery Through Metabolic Engineering
17.4 Challenges in Microbial Data Analysis
17.4.1 Data Quality and Quantity
17.4.2 Interpretability
17.4.3 Ethical and Privacy Concerns
17.4.4 Validation and Generalization
17.5 Future Aspects and Trends
17.5.1 Integration of Omics Data
17.5.2 Explainable AI in Microbial Data Analysis
17.5.3 Personalized Microbiome Analysis
17.5.4 Ethical and Regulatory Frameworks
17.5.5 Collaborative Research and Data Sharing
17.6 Conclusion
References
Chapter 18: Early Crop Disease Identification Using Multi-fork Tree Networks and Microbial Data Intelligence
18.1 Introduction
18.2 Crop Disease Data and Disease Recognition Methods
18.2.1 Experimental Data
18.2.2 Disease Recognition Methods
18.2.2.1 Improved Attention Module (SMLP)
18.2.2.2 Improved Residual Network Structure (SMLP_ResNet)
18.2.2.3 Disease Recognition Model Based on Multi-branch SMLP_ResNet
18.3 Experiment
18.3.1 Experimental Dataset and Parameter Settings
18.3.2 Disease Identification Experiment Based on SMLP_ResNet
18.3.3 Early Disease Recognition Experiment Based on Multi-branch SMLP_ResNet
18.4 Conclusion
References
Chapter 19: Guarding Maize: Vigilance Against Pathogens Early Identification, Detection, and Prevention
19.1 Introduction
19.1.1 Key Features of Maize
19.1.2 A Closer Look at World Maize Harvesting
19.1.3 Determining Corn Leaf Stages
19.1.3.1 Leaf Collar Method
19.1.3.2 Droopy Leaf Method
19.1.3.3 Leaf Tip Method
19.1.3.4 Corn Height Method
19.1.4 The Growth Cycle of the Maize Plant
19.2 Overview of Maize Crop Diseases
19.2.1 Fungi Diseases
19.2.1.1 Brown Spot
19.2.1.2 Downy Mildew
Tar Spot
Maize Rusts
Common Rust
Polysora Rust
Bacterial Disease in Maize
19.2.2 Maize Virus and Mollicute Diseases
19.2.2.1 Corn Stunt
19.3 Conclusion
References
Chapter 20: Comprehensive Analysis of Deep Learning Models for Plant Disease Prediction
20.1 Introduction
20.2 History
20.3 Research Methodology
20.4 Deep Learning for Wheat Leaf Disease Detection
20.5 Transfer Learning for Wheat Leaf Disease Detection
20.5.1 Identify Transfer Learning Base Model
20.5.2 Create a New Neural Network
20.5.3 Perform Fine-Tuning on Created New Neural Networks
20.6 Hybrid Approach
20.6.1 MobileNet
20.6.2 XceptionNet
20.6.3 VGG16
20.6.4 ResNet
20.6.5 Extraction of Features Using VGG and Capsule Network Layers
20.6.6 Classification Layers
20.6.7 Spatial Transformer Layers
20.6.8 Implementation Steps Involved
20.7 Result and Discussion
20.8 Conclusion
References
Chapter 21: Enhancing Single-Cell Trajectory Inference and Microbial Data Intelligence
21.1 Introduction
21.2 iterTIPD
21.2.1 TIPD Algorithms
21.2.2 Iterative Feature Selection of iterTIPD Algorithm
21.3 Experiment
21.3.1 Data Set Description
21.3.2 Evaluation Index
21.3.3 Confirmation of iterTIPD Iteration Parameters
21.3.4 Analysis of the Effectiveness of iterTIPD
21.3.4.1 Accuracy Analysis
21.3.4.2 Robustness Analysis
21.3.4.3 Analysis of the Ability to Detect Gold Standard Genes
21.3.5 Analysis of Results
21.4 Application of iterTIPD in Neural Stem Cell Differentiation
21.4.1 Adult Stem Cell Lineage
21.4.2 Data Sets and Preprocessing
21.4.3 Neural Stem Cell Differentiation Trajectory Constructed by iterTIPD Analysis
21.4.3.1 iterTIPD Reconstructs the Differentiation Trajectory of Neural Stem Cells
21.4.3.2 Analysis to Identify Intermediate States of aNSC Populations
21.4.3.3 Analyse and Discover Markers That Define the Intermediate State of aNSC
21.5 Conclusion
References
Chapter 22: AI-Assisted Methods for Protein Structure Prediction and Analysis
22.1 Introduction
22.1.1 Overview of Protein Structure Prediction and Analysis
22.1.2 Role of AI in Advancing Protein Structure Research
22.2 Fundamentals of Protein Structure
22.3 Machine Learning Basics for Protein Structure Analysis
22.3.1 Supervised, Unsupervised, and Reinforcement Learning
22.3.1.1 Supervised Learning Algorithms
Regression Algorithms and Distance Prediction
Classification Algorithms and Secondary Structure Prediction
Solvent Accessibility Prediction with Classification Algorithms
22.3.1.2 Unsupervised Learning Algorithms
Clustering
Principal Component Analysis
Application in Protein Structure Prediction
22.3.1.3 Reinforced Learning
22.4 AI-Assisted Secondary Structure Prediction
22.4.1 Traditional Methods
22.4.2 Deep Learning Models for Secondary Structure Prediction
22.4.2.1 Convolutional Neural Networks (CNNs)
22.4.2.2 Recurrent Neural Networks (RNNs)
22.4.3 Case Studies
22.5 Predicting Tertiary Structure with AI
22.5.1 Homology Modeling and Comparative Protein Structure Prediction
22.5.2 Template-Based Structure Prediction
22.5.3 Threading or Fold Recognition-Based Methods
22.5.4 Ab Initio Modeling
22.5.5 Knowledge-Based Energy Function
22.5.6 AI-Driven De Novo Protein Structure Prediction
22.5.7 Deep Learning Models for Tertiary Structure Prediction
22.5.8 AlphaFold2
22.5.9 Applications of AlphaFold2
22.6 Conclusion and Future Scope
References