
Artificial Intelligence and Robotics
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
This book explores advanced mathematical computational algorithms in artificial intelligence and robotics, with a focus on areas such as machine learning, optimization, and digital simulations. Key topics include the mathematical foundations of AI, robotics control systems, computational geometry for image processing, and their applications in real-world problem-solving, such as autonomous systems and smart manufacturing.
More details
Other editions
Additional editions


Persons
Dr. Suresh Kumar Krishnadhas is an academician and researcher specializing in Artificial Intelligence, Machine Learning, Deep Learning, NLP, IoT, Blockchain, Networking, and Cybersecurity. He obtained his Ph.D. in Information and Communication Engineering from Anna University, M.Tech. from Manonmaniam Sundaranar University, and B.E. from Anna University. With over 16 years of teaching experience, he currently serves as Assistant Professor at Sri Eshwar College of Engineering (Autonomous), Coimbatore. He has published extensively in SCI/Scopus-indexed journals, conferences, and book chapters, with research interests in AI-driven healthcare, smart cities, image analysis, and quantum machine learning. He holds patents and copyrights, is a Red Hat Certified System Administrator, and is a member of IEEE, ISTE, SDIWC, IRED, and IAENG.
Dr. Ananth Kumar Tamilarasan is an Associate Professor and Research Head at IFET College of Engineering (Autonomous), India. He earned his Ph.D. in VLSI Design from Manonmaniam Sundaranar University, Tirunelveli, and completed his Master's and Bachelor's degrees from Anna University, Chennai. He has published research papers in national and international journals and conferences. His research interests include Networks-on-Chip, Computer Architecture, and ASIC Design. He has received several honors, including the Young Innovator Award, Young Researcher Award, Class A Award from IIT Bombay, and Best Paper Award at INCODS 2017. He holds multiple patents, is a life member of IEEE and ISTE, has edited six books, authored numerous book chapters with Springer, IET Press, and Taylor & Francis, and authored the book Evolutionary Intelligence for Healthcare Applications published by Taylor & Francis.
Dr. Pramod Singh Rathore is working in the Department of Computer and Communication Engineering, Manipal University Jaipur, Jaipur, India. He has completed his Ph. D. in Computer Science & Engineering from the University of Engineering and Management, Jaipur (UEM) and done M. Tech in Computer Sci. & Engineering from the Government Engineering College Ajmer, Rajasthan Technical University, Kota, India. With over 15 years of academic teaching experience, he has published more than 95 papers in reputable, peer-reviewed national and international journals, books, and conferences, including Wiley, IGI GLOBAL, Taylor & Francis, Springer, Elsevier Science Direct, Annals of Computer Science, and IEEE. He has co-authored and edited numerous books with well-known publishers such as Wiley, CRC Press, and USA. His research interests include computer networks, machine learning, and DBMS. He is a senior member of IEEE.
Dr. Abhishek Kumar is currently working as an Assistant Director and Professor in the Department of Computer Science & Engineering at Chandigarh University, Mohali, Punjab, India, and as a Senior Researcher at Ingeniot Lab, Universidad de Castilla-La Mancha (UCLM), Spain, since August 2025. He completed his Post-Doctoral Fellowship from the Ingenium Research Group Lab, Universidad de Castilla-La Mancha, Spain. With over 15 years of teaching and research experience, he has published more than 200 papers in reputed national and international journals, books, and conferences .
Content
- Intro
- Preface
- Contents
- List of Contributors
- 1 Mathematical and Statistical Techniques in Artificial Intelligence Designing AI Systems Grounded in Math and Statistics
- 1.1 Introduction to Mathematical and Statistical Techniques
- 1.2 Fundamentals of Probability and Statistics
- 1.2.1 Probability: The Foundation of Uncertainty
- 1.2.1.1 Probability of Events
- 1.2.1.2 Axioms of Probability
- 1.2.1.3 Joint, Conditional Probability, and Independence
- 1.2.2 Random Variables and Probability Distributions
- 1.2.2.1 Discrete Random Variables
- 1.2.2.2 Continuous Random Variables
- 1.2.2.3 Probabilistic Models in AI
- 1.2.2.4 AI Optimization Techniques
- 1.3 Optimization by the Gradient
- 1.3.1 Variants
- 1.3.2 Extensions
- 1.4 Optimization Through Heuristics
- 1.4.1 Convex Optimization
- 1.4.2 Optimization Using Combinatorial Methods
- 1.4.3 Optimization via Bayesian
- 1.4.4 Heuristic Search Methods
- 1.5 Heuristic Functions
- 1.5.1 Popular Heuristic Search Algorithms
- 1.5.2 Application in Optimization Problems
- 1.5.3 Handling Uncertainty and Probabilistic Heuristics
- 1.5.4 Continuous and High-Dimensional Spaces
- 1.6 Statistical Techniques in Machine Learning
- 1.6.1 Machine Learning Techniques
- 1.6.2 Optimization and Regularization
- 1.6.3 Applications of Mathematical and Statistical Techniques in AI
- 1.7 Advanced ML Techniques
- 1.7.1 Neural Networks and Deep Learning
- 1.7.2 Kernel Methods and Support Vector Machines (SVMs)
- 1.7.3 Ensemble Methods
- 1.7.4 Graphical Models Based on Probabilities
- 1.7.5 Reinforcement Learning (RL)
- 1.8 Reinforcement Learning: Concepts and Applications
- 1.8.1 Core Concepts of RL
- 1.8.1.1 The Environment and the Agent
- 1.8.1.2 State, Action, and Rewards
- 1.8.1.3 Policy (p)
- 1.8.2 Q-Function (Q) and Value Function (V)
- 1.8.3 Investigating as Opposed to Exploiting
- 1.8.4 Algorithms for Learning
- 1.8.5 Applications of Reinforcement Learning in AI and Statistics
- 1.8.6 Risk and Finance Management
- 1.9 Statistical Learning and Inference in AI
- 1.9.1 Core Concepts in Statistical Learning
- 1.9.1.1 Statistical Models and Probabilistic Assumptions
- 1.9.1.2 Supervised and Unsupervised Learning
- 1.9.1.3 Parameter Estimation
- 1.9.1.4 Regularization and Complexity Control
- 1.9.1.5 Model Evaluation and Selection
- 1.9.2 AI Statistical Inference
- 1.9.2.1 Hypothesis Testing and Significance Testing
- 1.9.2.2 Quantification of Uncertainty and Confidence Intervals
- 1.9.2.3 Bayesian Inference
- 1.9.2.4 Resampling and Bootstrapping
- 1.9.3 Applications of Statistical Learning in AI
- Outline placeholder
- Forecasting and Predictive Modeling
- NLP
- Computer Vision
- Identifying Anomalies
- Recommendation Systems
- 1.9.4 High-Level Statistical Techniques of AI
- Outline placeholder
- Models of Hierarchies
- Bayesian Networks and Graphical Models with Probabilities
- State-Space Models and HMMs
- Gaussian Processes (GPs)
- Causal Inference
- 1.10 Case Studies of Quantitative AI Applications
- 1.10.1 Predictive Maintenance in Manufacturing
- 1.10.2 Fraud Detection in Financial Services
- 1.10.3 Optimizing Supply Chain and Logistics with Predictive Analytics
- 1.10.4 Personalized Healthcare and Treatment Optimization
- 1.10.5 Credit Scoring and Risk Assessment in Banking
- 1.10.6 E-Commerce Dynamic Pricing Optimization
- 1.10.7 Predicting and Improving Energy Use in Smart Grids
- 1.11 Future Directions in Mathematical and Statistical AI
- 1.12 Conclusion
- References
- 2 Linear Algebra in AI and Robotics
- 2.1 Introduction
- 2.2 Data Representation Technique Using Linear Algebra
- 2.3 Optimization and Machine Learning
- 2.3.1 Data Preprocessing and Noise Reduction
- 2.3.2 Feature Extraction
- 2.3.3 Visualization
- 2.3.4 Improving Model Efficiency
- 2.3.5 Pattern Recognition and Anomaly Detection
- 2.3.6 Compression in Image and Signal Processing
- 2.4 Neural Networks and Deep Learning
- 2.5 Control Systems in Robotics
- 2.6 Conclusion
- References
- 3 Advanced Statistical Tools for Data Science
- 3.1 Introduction
- 3.1.1 Advanced Statistical Tools and its Application in Data Science
- 3.1.2 Advanced Statistical Tools in Robotics
- 3.2 Markov Chain Monte Carlo methods
- 3.3 Canonical Correlation Analysis (CCA)
- 3.4 Discriminant Analysis (LDA and QDA)
- 3.5 Multivariate ANOVA (MANOVA)
- 3.6 Mixed-Effects Models (Hierarchical Models)
- 3.6.1 The Structure of a Mixed-Effects Model
- 3.7 Linear Mixed-Effects Model Fit by ML
- 3.8 Survival and Hazard Models
- 3.9 Causal Inference
- 3.9.1 Fundamental Problem of Causal Inference, Confounding Variables, and Selection Bias, Along with Expanded Examples and Implications
- 3.9.2 Structural Causal Models (SCMs)
- 3.9.3 Do-Calculus: Mathematical Framework for Causal Inference
- 3.10 High-Dimensional Statistics
- 3.10.1 Lasso and Elastic Net Regression
- 3.10.2 Random Forests
- 3.10.3 Gradient Boosting Machines
- 3.11 Time Series Analysis
- 3.11.1 Autoregressive Integrated Moving Average (ARIMA) and Seasonal Autoregressive Integrated Moving Average (SARIMA)
- 3.11.2 Long Short-Term Memory (LSTM) Networks
- 3.12 Nonparametric Methods
- 3.12.1 Kernel Density Estimation
- 3.12.2 Spline Regression
- References
- 4 The Heartbeat of Innovation: Investigating the Essential Role of Differential Equations in the Evolution of Digital Technologies
- 4.1 Introduction
- 4.1.1 Historical Context of Differential Equations
- 4.1.2 Evolution of Digital Technologies
- 4.1.3 Literature Survey
- 4.2 The Mathematical Foundations of Differential Equations
- 4.2.1 Types of Differential Equations
- 4.2.1.1 Ordinary Differential Equations (ODEs)
- 4.2.1.2 Partial Differential Equations (PDEs)
- 4.2.1.3 Linear Versus Nonlinear Differential Equations
- 4.2.1.4 Homogeneous Versus Nonhomogeneous Differential Equations
- 4.2.2 Methods of Solution and Analysis
- 4.2.2.1 Analytical Methods
- 4.2.2.2 Numerical Methods
- 4.3 Applications in Digital Technologies
- 4.3.1 Signal Processing and Communication Systems
- 4.3.1.1 Signal Representation and Filtering
- 4.3.1.2 System Dynamics and Response Analysis
- 4.3.1.3 Modulation and Demodulation Techniques
- 4.3.1.4 Signal Reconstruction and Sampling Theory
- 4.3.1.5 Adaptive Filtering and Machine Learning Applications
- 4.3.2 Control Systems and Robotics
- 4.3.2.1 Modeling Dynamic Systems
- 4.3.2.2 Control Design Techniques
- 4.3.2.3 Stability Analysis
- 4.3.2.4 Robotics and Kinematic Modeling
- 4.3.2.5 Path Planning and Motion Control
- 4.3.2.6 Adaptive and Intelligent Control
- 4.3.3 Machine Learning and Data Science
- 4.3.3.1 Dynamic Systems and State-Space Models
- 4.3.3.2 Learning Dynamics through Differential Equations
- 4.3.3.3 Neural Networks and Differential Equations
- 4.3.3.4 Regularization and Differential Equations
- 4.3.3.5 Partial Differential Equations in Data Analysis
- 4.3.3.6 Bayesian Inference and Stochastic Differential Equations (SDEs)
- 4.3.3.6.1 Stochastic Processes and Noise in Machine Learning
- 4.4 Case Studies
- 4.4.1 Differential Equations in Engineering Applications
- 4.4.1.1 Mechanical Vibrations
- 4.4.1.1.1 Case Study: Spring-Mass-Damper System
- 4.4.1.2 Electrical Circuit Analysis
- 4.4.1.2.1 Case Study: RLC Circuit
- 4.4.1.3 Structural Analysis
- 4.4.1.3.1 Case Study: Beam Bending
- 4.4.1.4 Fluid Dynamics
- 4.4.1.4.1 Case Study: Navier-Stokes Equations
- 4.4.1.5 Control Systems in Robotics
- 4.4.1.5.1 Case Study: Inverted Pendulum
- 4.4.2 Real-World Examples in Computer Science
- 4.4.2.1 Image Processing
- 4.4.2.1.1 Example: Image Denoising
- 4.4.2.2 Neural Networks and Deep Learning
- 4.4.2.2.1 Example: Neural Ordinary Differential Equations (ODEs)
- 4.4.2.3 Robotics and Path Planning
- 4.4.2.3.1 Example: Optimal Control in Robotic Arms
- 4.4.2.4 Network Theory and Graph Algorithms
- 4.4.2.4.1 Example: Epidemic Modeling on Networks
- 4.4.2.5 Computational Fluid Dynamics (CFD)
- 4.4.2.5.1 Example: Simulating Airflow Around Objects
- 4.5 Challenges and Limitations
- 4.5.1 Numerical Methods and Computational Complexity
- 4.5.1.1 Numerical Solution of Differential Equations
- 4.5.1.2 Stiffness in Differential Equations
- 4.5.1.3 Computational Complexity
- 4.5.1.4 Resource Requirements
- 4.5.1.5 Error Propagation and Stability
- 4.5.2 Addressing Nonlinear Dynamics
- 4.5.2.1 Nature of Nonlinear Dynamics
- 4.5.2.2 Challenges of Nonlinear Dynamics
- 4.5.2.3 Approaches to Address Nonlinear Dynamics
- 4.5.2.3.1 Numerical Methods
- 4.5.2.3.2 Approximation Techniques
- 4.5.2.3.3 Bifurcation Analysis
- 4.5.2.3.4 Machine Learning and Data-Driven Approaches
- 4.5.2.3.5 Lyapunov Stability Theory
- 4.6 Future Trends and Innovations
- 4.6.1 Emerging Applications in AI and Big Data
- 4.6.1.1 Enhanced Machine Learning Models
- 4.6.1.2 Predictive Analytics and Time Series Forecasting
- 4.6.1.3 Optimization and Control in Smart Systems
- 4.6.1.4 Data-Driven Discovery of Dynamics
- 4.6.1.5 Computational Efficiency and Scalability
- 4.6.2 The Role of Differential Equations in Next-Generation Technologies
- 4.6.2.1 Quantum Computing
- 4.6.2.2 Biotechnology and Systems Biology
- 4.6.2.3 Advanced Materials and Manufacturing
- 4.6.2.4 Environmental Modeling and Climate Science
- 4.6.2.5 Robotics and Autonomous Systems
- 4.7 Ethical Implications of Mathematical Models in Digital Technologies
- 4.7.1 Ethical Challenges Raised through Mathematical Models
- 4.7.2 Using Mathematical Models to Mitigate Ethical Problems
- 4.8 Conclusion
- 4.8.1 Summary of Key Insights
- 4.8.2 The Continued Relevance of Differential Equations in Digital Evolution
- References
- 5 Mathematical Tools for Digital Signal Processing
- 5.1 Introduction
- 5.2 Comprehending Signal Analysis
- 5.2.1 Complex Analysis Function in Signal Processing
- 5.2.2 The Delta Function in Signal Analysis
- 5.2.3 Fourier Series with Half-Range Expansions and Fourier Series in Signal Analysis
- 5.2.4 Fourier and Alternative Integral Transforms in Signal Analysis
- 5.3 Computational Linear Algebra in Digital Signal Analysis
- 5.3.1 Matrix Theory and Algebra in DSP
- 5.3.2 Direct Approaches to Resolution in Digital Signal Analysis
- 5.3.3 Vector and Matrix Standards in Digital Signal Analysis
- 5.3.4 Digital Signal Analysis Iterative Methods of Solution
- 5.3.5 Wavelets and Iterative Methods in Quantitative AI
- 5.4 Software Engineering and Programming in DSP and Analysis
- 5.4.1 Software Engineering in DSP
- 5.4.2 Enhancement of DSP Algorithms
- 5.4.3 Software Tools and Frameworks for DSP
- 5.4.4 Utilization of DSP in Practical Systems
- 5.5 DSP: Techniques, Algorithms, and Library Development in Signal Analysis
- 5.5.1 An Overview of DSP
- 5.5.2 Algorithms in DSP
- 5.5.3 Constructing a DSP Library: Procedures and Elements
- 5.5.4 Utilization of DSP Libraries
- 5.5.5 Comparative Analysis: DSP Techniques and Algorithms
- 5.5.6 DSP-AI Real-Time Applications and Future Research Directions
- 5.6 Conclusion
- References
- 6 The Role of Differential Equation in Digital Technologies
- 6.1 Overview of Differential Equations
- 6.1.1 Historical Evolution and Relevance in Digital Systems
- 6.1.2 Chapter Objectives and Scope
- 6.2 Fundamentals of Differential Equations
- 6.2.1 Initial and Boundary Conditions
- Common Solution Methods
- Linear Versus Nonlinear Equations
- 6.3 Modeling Digital Technologies with Differential Equations
- 6.3.1 Signal Processing and Filter Design
- 6.3.2 Circuit Analysis and RLC Networks
- 6.3.3 Control Systems in Automation
- 6.4 Application in Digital Communication Systems
- 6.4.1 Wave Propagation and Transmission Lines
- 6.4.2 Modulation Techniques and Channel Modeling
- 6.4.3 Error Prediction and Correction Dynamics
- 6.5 Differential Equations in Computer Graphics and Vision
- 6.5.1 Image Processing and Edge Detection
- 6.5.2 Heat Equation for Denoising
- 6.5.3 Shape Deformation and Morphing Techniques
- 6.6 Use in Machine Learning and AI
- 6.6.1 Neural Differential Equations
- 6.6.2 Gradient Dynamics and Optimization
- 6.6.3 Reinforcement Learning Models
- 6.7 Simulation Tools and Computational Techniques
- 6.7.1 Finite Difference and Finite Element Methods
- 6.7.1.1 Finite Difference Method
- 6.7.1.2 Finite Element Method (FEM)
- 6.7.2 MATLAB, Simulink, and Python Libraries
- 6.7.2.1 MATLAB
- 6.7.2.2 Simulink
- Python Libraries
- 6.7.3 Stability and Convergence Analysis
- 6.7.3.1 Convergence
- 6.8 Case Studies and Practical Implementations
- 6.8.1 Smart Sensors and IoT Devices
- 6.8.2 Real-Time Systems Modeling
- 6.8.3 Biomedical Signal Analysis
- Example: ECG Signal Filtering (Denoising)
- Example: Glucose-Level Prediction in Diabetes
- 6.9 Challenges and Future Trends
- 6.9.1 Computational Complexity and Real-Time Constraints
- 6.9.1.1 Problem 1: High Computational Load
- 6.9.1.2 Problem 2: Real-Time Response Constraint
- 6.9.2 Hybrid Modeling Approaches
- 6.9.3 Integration with Quantum and Edge Computing
- 6.9.3.1 Quantum Computing
- 6.9.3.2 Edge Computing
- 6.10 Conclusion
- References
- 7 Disease Prediction with Decision Trees Optimized by MapReduce Algorithm
- 7.1 Introduction
- 7.1.1 Predicting Diseases with MapReduce's Algorithm
- 7.1.2 MapReduce's Benefits for Disease Prediction
- 7.1.3 Applications in Healthcare
- 7.2 Learning Algorithm about Disease Prediction
- 7.2.1 Real-Time Disease Prediction with Decision Trees and MapReduce
- 7.2.2 Using Streaming Data for Real-Time Disease Prediction
- 7.2.3 Disease Prediction Using a MapReduce-Optimized Decision Tree Algorithm
- 7.3 Working of Disease Prediction
- 7.4 Implementation
- 7.5 Conclusion
- References
- 8 AI-Assisted Predator-Prey Framework for Understanding COVID-19 Transmission Dynamics
- 8.1 Introduction
- 8.2 Model Formulation
- 8.3 Boundedness and Positivity of the Theorem
- 8.4 Analysis of Nonlinear Systems and Stability
- 8.4.1 Critical Point
- 8.4.2 Analysis of equilibrium point's existence and stability
- 8.5 Numerica1 Results
- 8.6 Discussions and Conclusions
- References
- 9 Predicting Mathematics Achievement in Secondary Education Using Regression Analysis
- 9.1 Introduction
- 9.2 Literature Survey
- 9.3 Proposed Methodology
- 9.3.1 Data Collection
- 9.3.1.1 Null Hypothesis
- 9.3.1.2 Preprocessing
- 9.3.2 Feature Selection
- 9.3.3 Prediction
- 9.3.3.1 Linear Regression
- 9.3.3.2 Logistic Regression (LogR)
- 9.3.3.3 Support Vector Regression
- 9.3.3.4 Decision Tree Regression (DTR)
- 9.3.3.5 Random Forest Regression (RFR)
- 9.4 Experimental Results
- 9.4.1 Correlation Analysis of Learning Behavior and Mathematics Achievement
- 9.4.2 Mathematics Achievement Prediction
- 9.5 Conclusion
- References
- 10 Performance Enhancement of Artificial Intelligence Models Utilizing Hybrid Optimization Techniques
- 10.1 Introduction
- 10.2 Challenges in Single Optimization Techniques
- 10.2.1 High Dimensionality
- 10.2.2 Noise
- 10.2.3 Scalability
- 10.2.4 Convergence
- 10.2.5 Computational Cost
- 10.2.6 Hyperparameter Tuning
- 10.2.7 Data Efficiency
- 10.2.8 Unreliable Results
- 10.2.9 Limited Memory
- 10.2.10 Overfitting
- 10.2.11 Outliers
- 10.3 Distinct Hybrid Optimization Techniques
- 10.3.1 Genetic Algorithm and Simulated Annealing (GA-SA)
- 10.3.2 Particle Swarm Optimization and Genetic Algorithm (PSO-GA)
- 10.3.3 Differential Evolution and Particle Swarm Optimization (DE-PSO)
- 10.3.4 Genetic Algorithm and Neural Networks (GA-NN)
- 10.3.5 Ant Colony Optimization and Particle Swarm Optimization (ACO-PSO)
- 10.3.6 Simulated Annealing and Tabu Search (SA-TS)
- 10.3.7 Memetic Algorithms (MAs)
- 10.3.8 Genetic Algorithm and Ant Colony Optimization (GA-ACO)
- 10.3.9 Differential Evolution and Simulated Annealing (DE-SA)
- 10.3.10 Harmony Search and Particle Swarm Optimization (HS-PSO)
- 10.3.11 Artificial Bee Colony and Genetic Algorithm (ABC-GA)
- 10.3.12 Whale Optimization Algorithm and Genetic Algorithm (WOA-GA)
- 10.4 Applications of Hybrid Optimization Techniques
- 10.4.1 Scheduling Flights
- 10.4.2 Supply Chain Management
- 10.4.3 Energy Distribution
- 10.4.4 Manufacturing Processes
- 10.4.5 Healthcare Scheduling
- 10.4.6 Telecommunication Networks
- 10.4.7 Urban Planning
- 10.4.8 Agricultural Planning
- 10.4.9 Water Resource Management
- 10.4.10 Traffic Management
- 10.4.11 Disaster Response
- 10.4.12 Network Design
- 10.4.13 Vehicle Design
- 10.4.14 Drug Discovery
- 10.5 Background Studies in Hybrid Optimization Techniques
- 10.6 Conclusion and Future Scope
- References
- 11 Smart Fuzzy Logic in AI Systems for Accurate Medical Diagnostics
- 11.1 Introduction
- 11.1.1 Contribution
- 11.2 Proposed Methodology
- 11.2.1 Data Layer
- 11.2.1.1 Patient ID Description
- 11.2.1.2 Heart Rate (bpm)
- 11.2.1.3 SpO2 (%) Measurement
- 11.2.1.4 Temperature (°C) Description
- 11.2.1.5 Blood Pressure (mmHg)
- 11.2.2 Neuro-Fuzzy Layer
- 11.2.2.1 Feature Extraction in Neuro-Fuzzy Systems
- 11.2.2.2 Feature Transformation Using Membership Functions and Fuzzy Sets
- 11.2.2.3 Neural Network Architecture and Training
- 11.2.2.4 Combining Features and Assessing Rules
- 11.2.2.5 Neural Network Optimization for Learning and Adaptation
- 11.2.2.6 Mathematical Model for Neural Fuzzy System
- 11.2.3 AI Layer
- 11.2.4 Practical Deployment of the Proposed System in a Real World
- 11.3 Experimental Results and Discussion
- 11.3.1 Classification of Data in This Dataset
- 11.3.1.1 Patients in the Low Category (Patients 1, 2, and 3)
- 11.3.1.2 Patients Within the Normal Range (Patients 4, 5, 8, 9, and 11)
- 11.3.1.3 Patients in High Range (Patients 6, 7, 10, 12, and 13)
- 11.3.1.4 t-Test and ANOVA Test
- 11.4 Conclusion
- References
- 12 2-Domination in Fuzzy Digraphs and Its Applications in Digital Systems
- 12.1 Introduction
- 12.2 Preliminaries
- 12.3 Main Results
- 12.4 Application of 2-Domination Fuzzy Digraph on Digital System
- 12.4.1 Algorithms to Find 2-Dominating Set in Fuzzy Digraph
- 12.4.2 Seven-Robot Coordination Network Using 2-Domination in Fuzzy Digraph
- 12.4.2.1 Illustration
- 12.4.3 Benefits
- 12.4.4 AI-Driven 2-Domination in Traffic Management for Smart Cities
- 12.4.4.1 Illustration
- 12.5 Conclusion
- References
- 13 Optimizing Machine Learning and Robotics for Precision in Cancer Prediction and Treatment
- 13.1 Introduction
- 13.2 Related Works
- 13.3 Proposed Work for Cancer Prediction and Treatment Optimization
- 13.3.1 Cancer Prediction as a Classification Task
- 13.3.2 Treatment Optimization as a Decision-Making Problem
- 13.3.3 Mathematical Models
- 13.3.3.1 Cancer Prediction Using Transformer Models
- 13.3.3.2 Real-Time Robotic Treatment Planning with Reinforcement Learning
- 13.3.3.3 Cross-Domain Attention Mechanism
- 13.4 Experimental Setup
- 13.5 Simulation Framework
- 13.5.1 Dataset
- 13.5.2 Simulation Setup
- 13.5.3 Evaluation Metrics
- 13.5.4 Performance of Cancer Prediction Models
- 13.6 Conclusion
- References
- 14 Applications of Split Divisor Equitable Domination in Fuzzy Graphs to Network Theory
- 14.1 Introduction
- 14.2 Preliminaries
- 14.3 Main Results
- 14.4 Split Equitable Domination in Computer Networks
- 14.4.1 Illustration
- 14.5 Conclusion
- References
- 15 Optimizing Image Preprocessing Methods for Crop Disease Detection in Precision Agriculture
- 15.1 Introduction
- 15.2 Literature Review
- 15.3 Overview of Deep Learning for Crop Disease Detection
- 15.4 Understanding Image Processing Algorithms in the Context of Deep Learning
- 15.4.1 Hough Transform
- 15.4.1.1 Challenges in Edge Linking
- 15.4.1.2 Line Detection Algorithm
- 15.4.2 Otsu Adaptive Thresholding
- 15.4.3 NDVI
- 15.4.4 Histogram Equalization
- 15.4.5 SLIC: Simple Linear Iterative Clustering
- 15.4.6 Gaussian Blur
- 15.5 ResNet-50
- 15.5.1 Introduction
- 15.5.2 What Are Convolution, Pooling, and Relu?
- 15.5.3 Pooling
- 15.5.4 Batch Normalization
- 15.5.5 RELU
- 15.5.6 Need for ResNet-50
- 15.5.7 Architecture and Internal Implementation
- 15.6 Experimentation and Evaluation
- 15.7 Analyzing the Challenges in Image Preprocessing and Deep Learning for Precision Agriculture
- 15.8 Conclusion
- 15.9 Future Directions in Preprocessing and Deep Learning for Precision Agriculture
- References
- 16 AI-Powered Web Application for Early Detection of Heart Disease Using Computational Algorithms
- 16.1 Introduction
- 16.2 Survey on Cardiac Disease Forecasting by Using Ml Algorithms
- 16.3 Materials and Method
- 16.4 Results and Discussion
- 16.5 Conclusion
- References
- 17 Analytical Optimization on a Two-Echelon Supply Chain with Fuzzy Production Rate and Environmental Effects
- 17.1 Introduction
- 17.2 Symbols and Hypotheses
- 17.2.1 Symbols and Descriptions
- 17.2.2 Hypotheses
- 17.3 Mathematical Formulation
- 17.3.1 Integrated SC Model
- 17.3.2 Fuzzy to Crisp Conversion
- 17.3.3 Solution Procedure
- 17.4 Numerical Analysis
- 17.4.1 Examples
- 17.4.2 Numerical Results and Discussion
- 17.5 Managerial Insights
- 17.6 Conclusion and Possible Extensions
- References
- 18 Verdcure: Automatic Identification of Plant Diseases Using Convolutional Neural Networks
- 18.1 Introduction
- 18.1.1 Survey on Automatic Identification of Plant Diseases
- 18.2 Materials and Methods
- 18.2.1 Workflow
- 18.2.2 Data Normalization and Activation Functions
- 18.2.3 Feature Extraction and Model Building with CNN Using PyTorch
- 18.2.4 Training the Model
- 18.3 Results and Discussion
- 18.4 Conclusion
- References
- 19 Lightweight Deep Learning Models for Crab Species Recognition
- 19.1 Introduction
- 19.2 Literature Survey
- 19.3 Proposed Method
- 19.3.1 CNN-Based Crab Species Classification
- 19.3.1.1 Convolutional Layer
- 19.3.1.2 Activation Functions
- 19.3.1.3 Batch Normalization
- 19.3.1.4 Pooling Layer
- 19.3.1.5 Flatten Layer
- 19.3.1.6 Fully Connected (Dense) Layer
- 19.3.1.7 Dropout Layer
- 19.3.2 VGG-16-based Crab Species Classification
- 19.3.3 EfficientNet-B0
- Compound Scaling Equation
- 19.3.4 ShuffleNetV2
- 19.3.5 SqueezeNet
- 19.4 Results and Discussion
- 19.4.1 Dataset Details
- 19.4.2 Evaluation Metrics on CNN-Based Model
- 19.4.3 Performance Evaluation on Lightweight Models
- 19.5 Conclusion
- References
- 20 Ethical and Social Implications of Mathematical Models in AI and Robotics
- 20.1 Introduction
- 20.2 Literature Survey
- 20.3 Ethical and Social Implications of Mathematical Models in AI
- 20.3.1 Ethical Considerations in AI Development
- 20.3.2 Ethical and Social Implications of Mathematical Models in Robotics
- 20.4 Conclusion
- References
- 21 Efficient Trade Optimization Using Artificial Intelligence and Amazon Web Service Platform
- 21.1 Introduction
- 21.1.1 Amazon Web Service
- 21.1.2 Online Trading Strategies
- 21.1.3 Background
- 21.2 Related Works
- 21.3 Proposed Methodology
- 21.3.1 Dataset
- 21.3.2 Preprocessing
- 21.3.3 Train and Test Split-Up
- 21.3.4 Feature Selection
- 21.3.5 Classification
- 21.3.6 Prediction
- 21.4 Results and Discussion
- 21.5 Conclusion
- References
- 22 AI Bias and Fairness: Unveiling Solutions for Ethical Algorithmic Practices
- 22.1 Introduction
- 22.1.1 Training Data and Bias
- 22.2 Types of Bias
- 22.2.1 Algorithmic Bias
- 22.2.2 Contextual Bias
- 22.2.3 Transparency Bias
- 22.2.4 Application Bias
- 22.2.5 In-Group Bias
- 22.2.6 Financial Bias
- 22.2.7 Confirmation Bias
- 22.2.8 Data Bias
- 22.2.9 Demographic Bias
- 22.2.10 Cognitive Bias
- 22.2.11 Social Bias
- 22.2.12 Temporal Bias
- 22.2.13 Interpretation Bias
- 22.2.14 Power Imbalance Bias
- 22.2.15 Availability Bias
- 22.3 Bias in AI: Key Relationships
- 22.3.1 Bias and Discrimination
- 22.3.2 Bias and Variance
- 22.3.3 Bias and F1 Score
- 22.4 Bias in Emerging AI Techniques
- 22.4.1 Bias and Retrieval-Augmented Generation
- 22.4.2 Bias Amplification in Deep Models
- 22.4.3 Bias in Transfer Learning
- 22.4.4 Bias and Algorithmic Oppression
- 22.5 Measuring and Quantifying Bias
- 22.5.1 Measuring Bias
- 22.6 Impact of Bias in AI: Real-World Consequences
- 22.6.1 Case Study 1
- 22.6.2 Case Study 2
- 22.6.3 Case Study 3
- 22.6.4 Case Study 4
- 22.6.5 Case Study 5
- 22.6.6 Case Study 6
- 22.6.7 Technology Leaders
- 22.6.8 Facial Recognition Technology:
- 22.7 Feedback Loops: How Algorithms Can Influence Algorithms?
- 22.8 Challenges and Limitations Encountered
- 22.9 Recommendations for Fixing Algorithmic Bias
- 22.9.1 Accountability and Transparency
- 22.9.2 Race-aware Algorithm (RCA)
- 22.9.3 Algorithmic Greenlining (AGL)
- 22.9.4 Data Preprocessing Techniques
- 22.9.5 Algorithmic Adjustments
- 22.9.6 Explainable AI Approaches (EAA)
- 22.9.7 Differential Privacy Techniques
- 22.9.8 Federated Learning Techniques (FLT)
- 22.9.9 Counterfactual Fairness
- 22.9.10 Causal Inference Techniques (CIT)
- 22.9.11 Contextual Bandit Algorithms (CBA)
- 22.9.12 Bias Auditing Frameworks
- 22.9.13 Human-in-the-Loop Approaches
- 22.9.14 SMOTE: Synthetic Minority Over Sampling Technique
- 22.10 Need for Global Regulation Frameworks and Guidelines
- 22.11 Existing Initiatives in Fairness Frameworks and Guidelines
- 22.12 The Ethical Implications of Mathematical Models in the Digital Age
- 22.13 Conclusion: Charting a Course Toward Algorithmic Equity: A Multifarious Approach
- References
- 23 Image Steganography and Attacks Analysis for Secured Data Communication
- 23.1 Introduction
- 23.1.1 Steganography Techniques
- 23.2 Related Works
- 23.3 The Proposed LSB-Based Steganography Strategy
- 23.3.1 Encoding the Secret Message Using LSB-Based Steganography
- 23.3.2 Decoding of Secret Message Using the LSB-Based Steganography
- 23.4 Experimental Setup and Results
- 23.5 Conclusions and Future Work
- References
- 24 Real-World Intelligence: Applications of Fuzzy Logic in Modern AI Systems
- 24.1 Introduction to Fuzzy Logic
- 24.1.1 Origin and Evolution
- 24.1.2 Comparison with Classical Logic
- 24.1.3 Importance in Soft Computing
- 24.2 Mathematical Foundations of Fuzzy Sets)
- 24.2.1 Fuzzy Sets and Membership Functions
- 24.2.2 Operations on Fuzzy Sets
- 24.2.3 Fuzzy Relations and Their Properties
- 24.2.4 Fuzzy Logic in Machine Learning
- 24.3 Fuzzy Decision Trees
- 24.3.1 Fuzzy Clustering (Fuzzy C-Means) (Fuzzy Clustering: FCM Algorithm)
- 24.3.2 Neuro-Fuzzy Systems
- 24.3.3 Fuzzy Logic and Deep Learning
- 24.4 Fuzzy Layers in Neural Networks
- 24.4.1 Interpretability in Deep Models Using Fuzzy Concepts
- 24.4.2 Case Studies with Fuzzy CNN/RNN Architectures
- 24.4.3 Fuzzy Logic in Expert Systems
- 24.5 Knowledge Representation
- 24.5.1 Rule Generation and Uncertainty Handling
- 24.5.2 Fuzzy-Based Medical and Legal Expert Systems
- 24.5.3 Fuzzy Logic in Robotics and Automation
- 24.6 Motion Control and Navigation
- 24.6.1 Fuzzy Controllers for Dynamic Environments
- 24.6.2 Human-Robot Interaction Using Fuzzy Models
- 24.6.3 Use of Fuzzy Systems in Natural Language Processing (NLP)
- 24.7 Sentiment and Emotion Analysis (Using Fuzzy Logic in Sentiment Analysis)
- 24.7.1 Fuzzy Ontologies for Semantic Understanding
- 24.8 Fuzzy Logic in Computer Vision
- 24.8.1 Image Segmentation and Enhancement
- 24.8.2 Object Detection with Fuzzy Classifiers
- 24.8.3 Fuzzy Logic in Surveillance Systems
- 24.9 Fuzzy Control Systems in Industry
- 24.9.1 Applications in Manufacturing and Process Control
- 24.9.2 Adaptive Control in Smart Grids and IoT
- 24.9.3 Case Studies from Industrial Automation
- 24.10 Challenges and Opportunities in Fuzzy-AI Integration
- 24.10.1 Scalability and Computation Cost
- 24.10.2 Standardization and Benchmarking
- 24.10.3 Future Research Directions
- References
- 25 Trustworthy Stock Market Forecasting: Time Series Modeling Under Generative AI Manipulation Risks
- 25.1 Introduction
- 25.2 Literature Survey
- 25.3 Methodology
- 25.3.1 Data Collection
- 25.3.2 Data Preprocessing
- 25.3.3 Dataset Creation for LSTM
- 25.3.4 Reshaping Data for LSTM
- 25.3.5 LSTM Model Creation
- 25.3.6 Model Training
- 25.3.7 Prediction
- 25.3.8 Implementation of Prophet Model
- 25.3.9 Hybrid Model Approach Methodology
- 25.3.10 Evaluation Metrics
- 25.3.11 Visualization
- 25.4 Results and Discussion
- 25.4.1 LSTM Model
- 25.4.2 Hybrid Model
- 25.5 Conclusion
- References
- Index
- Mathematical Methods in the Digital Age
System requirements
File format: PDF
Copy protection: Watermark-DRM (Digital Rights Management)
System requirements:
- Computer (Windows; MacOS X; Linux): Use the free software Adobe Reader, Adobe Digital Editions, or any other PDF viewer of your choice (see eBook Help).
- Tablet/Smartphone (Android; iOS): Install the free app Adobe Digital Editions or another reading app for eBooks, e.g., PocketBook (see eBook Help).
- E-reader: Bookeen, Kobo, Pocketbook, Sony, Tolino and many more (only limited: Kindle).
The file format PDF always displays a book page identically on any hardware. This makes PDF suitable for complex layouts such as those used in textbooks and reference books (images, tables, columns, footnotes). Unfortunately, on the small screens of e-readers or smartphones, PDFs are rather annoying, requiring too much scrolling.
This eBook uses Watermark-DRM, a „soft” copy protection. This means that there are no technical restrictions to prevent illegal distribution. However, there is a personalised watermark embedded in the eBook that can be used to identify the purchaser of the eBook in the event of misuse and to provide evidence for legal purposes.
For more information, see our eBook Help page.