Explainable Machine Learning Models and Architectures

Cover
Title Page
Copyright Page
Contents
Preface
Acknowledgements
Chapter 1 A Comprehensive Review of Various Machine Learning Techniques
1.1 Introduction
1.1.1 Random Forest
1.1.2 Decision Tree
1.1.3 Support Vector Machine
1.1.4 Naive Bayes
1.1.5 K-Means Clustering
1.1.6 Principal Component Analysis
1.1.7 Linear Regression
1.1.8 Logistic Regression
1.1.9 Semi-Supervised Learning
1.1.10 Transductive SVM
1.1.11 Generative Models
1.1.12 Self-Training
1.1.13 Relearning
1.2 Conclusions
References
Chapter 2 Artificial Intelligence and Image Recognition Algorithms
2.1 Introduction
2.2 Traditional Image Recognition Algorithms
2.2.1 Harris Corner Detector (1988)
2.2.2 SIFT (2004)
2.2.3 ASIFT
2.2.4 SURF (2006)
2.3 Neural Network–Based Algorithms
2.4 Convolutional Neural Network Architecture
2.5 Various CNN Architectures
2.5.1 LeNet-5 (1998)
2.5.2 AlexNet (2012)
2.5.3 VGGNet (2014)
2.5.4 GoogleNet (2015)
Conclusion
References
Chapter 3 Efficient Architectures and Trade-Offs for FPGA-Based Real-Time Systems
3.1 Overview of FPGA-Based Real-Time System
3.1.1 Key Elements of Real-Time System
3.1.2 Real-Time System and its Computation
3.1.3 FPGA Functionality and Applications
3.1.4 FPGA Applications
3.1.5 FPGA Architecture
3.1.6 Reconfigurable Architectures
3.2 Hybrid FPGA Configurations and its Algorithms
3.2.1 Hybrid FPGA
3.2.2 Hybrid FPGA Architecture
3.2.3 Hybrid FPGA Configuration
3.3 Hybrid FPGA Algorithms
3.3.1 Relevance of Hardware-Accelerated Architecture to FPGA Software Implementation
3.4 CNN Hardware Accelerator Architecture Overview
3.5 Summary
References
Chapter 4 A Low-Power Audio Processing Using Machine Learning Module on FPGA and Applications
4.1 Introduction
4.2 Existing Machine Learning Modules and Audio Classifiers
4.3 Audio Processing Module Using Machine Learning
4.4 Application of Proposed FPGA-Based ML Models
4.5 Implementation of a Microphone on FPGA
4.6 Conclusion
4.7 Future Scope
References
Chapter 5 Synthesis and Time Analysis of FPGA-Based DIT-FFT Module for Efficient VLSI Signal Processing Applications
5.1 Introduction
5.2 Implementation of DIT-FFT Algorithm
5.2.1 A Quick Overview of DIT-FFT
5.2.2 Algorithmic Representation with Example
5.2.3 Simulated Output Waveform
5.3 Synthesis of Designed Circuit
5.4 Static Timing Analysis of Designed Circuit
5.5 Result and Discussion
5.6 Conclusion
References
Chapter 6 Artificial Intelligence–Based Active Virtual Voice Assistant
6.1 Introduction
6.2 Literature Survey
6.3 System Functions
6.4 Model Training
6.5 Discussion
6.5.1 Furnishing Movie Recommendations
6.5.2 KNN Algorithm Book Recommendation
6.6 Results
6.7 Conclusion
References
Chapter 7 Image Forgery Detection: An Approach with Machine Learning
7.1 Introduction
7.2 Historical Background
7.3 CNN Architecture
7.4 Analysis of Error Level of Image
7.5 Proposed Model of Image Forgery Detection, Results and Discussion
7.6 Conclusion
7.7 Future Research Directions
References
Chapter 8 Applications of Artificial Neural Networks in Optical Performance Monitoring
8.1 Introduction
8.2 Algorithms Employed for Performance Monitoring
8.2.1 Artificial Neural Networks
8.2.2 Deep Neural Networks
8.2.3 Convolutional Neural Networks
8.2.3.1 Convolutional Layer
8.2.3.2 Non-Linear Layer
8.2.3.3 Pooling Layer
8.2.3.4 Fully Connected Layer
8.2.4 Support Vector Regression (SVR)
8.2.5 Support Vector Machine (SVM)
8.2.6 Kernel Ridge Regression (KRR)
8.2.7 Long Short-Term Memory (LSTM)
8.3 Artificial Intelligence (AI) Methods, Performance Monitoring and Applications in Optical Networks
8.3.1 Performance Monitoring
8.3.2 Applications of AI in Optical Networking
8.4 Optical Impairments and Fault Management
8.4.1 Noise
8.4.2 Distortion
8.4.3 Timing
8.4.4 Component Faults
8.4.5 Transmission Impairments
8.4.6 Fault Management in Optical Network
8.5 Conclusion
References
Chapter 9 Website Development with Django Web Framework
9.1 Introduction
9.2 Salient Features of Django
9.2.1 Complete
9.2.2 Versatile
9.2.3 Secure
9.2.4 Scalable
9.2.5 Maintainable
9.2.6 Portable
9.3 UI Design
9.3.1 HTML
9.3.2 CSS
9.3.3 Bootstrap
9.4 Methodology
9.5 UI Design
9.6 Backend Development
9.6.1 Login Page
9.6.2 Registration Page
9.6.3 User Tracking
9.7 Ouputs
9.8 Conclusion
References
Chapter 10 Revenue Forecasting Using Machine Learning Models
10.1 Introduction
10.2 Types of Forecasting
10.2.1 Qualitative Forecasting
10.2.1.1 Industries That Use Qualitative Forecasting
10.2.1.2 Qualitative Forecasting Methods
10.2.2 Quantitative Forecasting
10.2.2.1 Quantitative Forecasting Methods
10.2.3 Artificial Intelligence Forecasting
10.2.3.1 Artificial Neural Network (ANN)
10.2.3.2 Support Vector Machine (SVM)
10.3 Types of ML Models Used in Finance
10.3.1 Linear Regression
10.3.1.1 Simple Linear Regression
10.3.1.2 Multiple Linear Regression
10.3.2 Ridge Regression
10.3.3 Decision Tree
10.3.3.1 Prediction of Continuous Variables
10.3.3.2 Prediction of Categorical Variables
10.3.4 Random Forest Regressor
10.3.5 Gradient Boosting Regression
10.3.5.1 Advantages of Gradient Boosting
10.4 Model Performance
10.4.1 R-Squared Method
10.4.2 Mean Squared Error (MSE)
10.4.3 Root Mean Square Error (RMSE)
10.5 Conclusion
References
Chapter 11 Application of Machine Learning Optimization Techniques in Wind Resource Assessment
11.1 Introduction
11.2 Wind Data Analysis Methods
11.2.1 Wind Characteristics Parameters
11.2.2 Wind Speed Distribution Methods
11.2.3 Weibull Method
11.2.4 Goodness of Fit
11.3 Wind Site and Measurement Details
11.3.1 Seasonal Wind Periods
11.3.2 Machine Learning and Optimization Techniques
11.3.2.1 Moth Flame Optimization (MFO) Method
11.4 Results and Discussions
11.4.1 Wind Characteristics
11.4.1.1 Kayathar Station (Onshore)
11.4.1.2 Gulf of Khambhat (Gujarat Offshore) Station
11.4.1.3 Jafrabad (Gujarat-Nearshore)
11.4.2 Wind Distribution Fitting
11.4.2.1 Kayathar Station (Onshore)
11.4.2.2 Bimodal Behaviour
11.4.2.3 Gulf of Khambhat (Offshore) Wind Distribution
11.4.2.4 Jafrabad Station (Nearshore) Distribution Fitting
11.4.3 Optimization Methods for Parameter Estimation
11.4.3.1 Optimization Parameters Comparison
11.4.4 Wind Power Density Analysis (WPD)
11.4.4.1 Comparison of Wind Power Density
11.5 Research Summary
11.6 Conclusions
References
Chapter 12 IoT to Scale-Up Smart Infrastructure in Indian Cities: A New Paradigm
12.1 Introduction
12.2 Technological Progress: A Brief History
12.3 What is the Internet of Things (IoT)?
12.4 Economic Effects of Internet of Things
12.5 Infrastructure and Smart Infrastructure: The Difference
12.5.1 What is Smart Infrastructure?
12.5.2 What are the Principles of Smart Infrastructure?
12.5.3 Components of IoT-Based Smart City Project
12.6 Architecture for Smart Cities
12.6.1 Networking Technologies
12.6.2 Network Topologies
12.6.3 Network Architectures
12.6.3.1 Home Area Networks (HANs)
12.6.3.2 Field/Neighborhood Area Networks (FANs/NANs)
12.6.3.3 Wide Area Networks (WANs)
12.6.3.4 Network Protocols
12.7 IoT Technology in India’s Smart Cities: The Current Scenario
12.8 Challenges in IoT-Based Smart City Projects
12.8.1 Technological Challenges
12.8.1.1 Privacy and Security
12.8.1.2 Smart Sensors and Infrastructure Essentials
12.8.1.3 Networking in IoT Systems
12.8.1.4 Big Data Analytics
12.8.2 Financial - Economic Challenges
12.9 Role of Explainable AI
12.10 Conclusion and Future Scope
References
Index
EULA