Machine Learning Methods for Signal, Image and Speech Processing

Front Cover
Machine Learning Methods for Signal, Image and Speech Processing
Contents
Preface
List of Figures
List of Tables
List of Contributors
List of Abbreviations
1 Evaluation of Adaptive Algorithms for Recognition of Cavities in Dentistry
	1.1 Introduction
	1.2 Related Work
	1.3 Proposed Model for Cavities Detection
		1.3.1 Pre-processing
		1.3.2 Contrast Enhancement
	1.4 Feature Extraction using MPCA and MLDA
		1.4.1 MPCA
		1.4.2 MLDA
	1.5 Classification
		1.5.1 Classification
		1.5.2 Nonlinear Programming Optimization
	1.6 Proposed Artificial Dragonfly Algorithm
	1.7 Results and Discussion
	1.8 Result Interpretation
	1.9 Performance Analysis by Varying Learning Percentage
	1.10 Conclusion
	References
2 Lung Cancer Prediction using Feature Selection and Recurrent Residual Convolutional Neural Network (RRCNN)
	2.1 Introduction
	2.2 Related Work
	2.3 Methodology
	2.4 Experimental Analysis
	2.5 Cross Validation
	2.6 Conclusion
	References
3 Machine Learning Application for Detecting Leaf Diseases with Image Processing Schemes
	3.1 Introduction
	3.2 Existing Work on Machine Learning with Image Processing
	3.3 Present Work of Image Recognition Using Machine
	3.4 Conclusion
	References
4 COVID-19 Forecasting Using Deep Learning Models
	4.1 Introduction
	4.2 Deep Learning Against Covid-19
		4.2.1 Medical Image Processing
		4.2.2 Forecasting COVID-19 Series
		4.2.3 Deep Learning and IoT
		4.2.4 NLP and Deep Learning Tools
		4.2.5 Deep Learning in Computational Biology and Medicine
	4.3 Population Attributes – Covid-19
	4.4 Various Deep Learning Model
		4.4.1 LSTM Model
		4.4.2 Bidirectional LSTM
	4.5 Conclusion
	4.6 Acknowledgement
	4.7 Figures and Tables Caption List
	References
5 3D Smartlearning Using Machine Learning Technique
	5.1 Introduction
		5.1.1 Literature Survey
			5.1.1.1 Machine learning basics
				5.1.1.1.1 Supervised learning
				5.1.1.1.2 Unsupervised Learning
				5.1.1.1.3 Semi supervised learning
				5.1.1.1.4 Reinforcement learning
	5.2 Methodology
		5.2.1 Problem Definition
		5.2.2 Block Diagram of Proposed System
			5.2.2.1 myDAQ
			5.2.2.2 Speaker
			5.2.2.3 Camera
		5.2.3 Optical Character Recognition
			5.2.3.1 Acquisition
			5.2.3.2 Segmentation
			5.2.3.3 Pre-Processing
			5.2.3.4 Feature Extraction
			5.2.3.5 Recognition
			5.2.3.6 Post-Processing
		5.2.4 K-Nearest Neighbors Algorithm
		5.2.5 Proposed Approach
		5.2.6 Discussion of Proposed System
			5.2.6.1 Flow Chart
			5.2.6.2 Algorithm
	5.3 Results and Discussion
	5.4 Conclusion and Future Scope
	References
6 Signal Processing for OFDM Spectrum Sensing Approaches in Cognitive Networks
	6.1 Introduction
		6.1.1 Spectrum Sensing in CRNs
		6.1.2 Multiple Input Multiple Output OFDM Cognitive Radio Network Technique (MIMO–OFDMCRN)
		6.1.3 Improved Sensing of Cognitive Radio for MB pectrum using Wavelet Filtering
			6.1.3.1 MB-Spectrum Sensing Method
				6.1.3.1.1 Estimation of PSD
				6.1.3.1.2 Edge detection (a)
				6.1.3.1.3 Edge detection (b)
				6.1.3.1.4 Edge classifier
				6.1.3.1.5 Correction of errors
				6.1.3.1.6 Generation of spectral mask
				6.1.3.1.7 Sensing of OFDM signals
		6.1.4 OFDM-Based Blind Sensing of Spectrum in Cognitive Networks
			6.1.4.1 Model of the Proposed System
			6.1.4.2 Constrained GLRT Algorithm
			6.1.4.3 A Multipath Correlation Coefficient Test
			6.1.4.4 Probability Calculation
		6.1.5 Comparative Analysis
	6.2 Conclusion
	References
7 A Machine Learning Algorithm for Biomedical Signal Processing Application
	7.1 Introduction
		7.1.1 Introduction to Signal Processing
			7.1.1.1 ECG Signal
	7.2 Related Work
		7.2.1 Signal Processing Based on Traditional Methods
		7.2.2 Signal Processing Based on Artificial Intelligence
		7.2.3 Problem Context
	7.3 Results and Discussion Based on Recent Work
	7.4 Real-Time Applications
	7.5 Conclusion
	References
8 Reversible Image Data Hiding Based on Prediction-Error of Prediction Error Histogram (PPEH)
	8.1 Introduction
	8.2 Existing Methodology
		8.2.1 Histogram-Based RDH
		8.2.2 PEH-Based RDH
	8.3 Proposed Method
	8.4 Results and Discussions
	8.5 Conclusion
	References
9 Object Detection using Deep Convolutional Neural Network
	9.1 Introduction
	9.2 Related and Background Work
	9.3 Object Detection Techniques
		9.3.1 Histogram of Oriented Gradients (HOG)
		9.3.2 Speeded-up Robust Features (SURF)
		9.3.3 Local Binary Pattern (LBP)
		9.3.4 Single Shot MultiBox Detector (SSD)
		9.3.5 You Only Look Once (YOLO)
		9.3.6 YOLOv1
		9.3.7 YOLOv2
		9.3.8 YOLOv3
		9.3.9 Regions with CNN (RCNN)
		9.3.10 Fast RCNN
		9.3.11 Faster RCNN
	9.4 Datasets for Object Detection
	9.5 Conclusion
	References
10 An Intelligent Patient Health Monitoring System Based on A Multi-Scale Convolutional Neural Network (MCCN) and Raspberry Pi
	10.1 Introduction to Signal Processing
		10.1.1 Cases of Implanted Frameworks
		10.1.2 Features of Embedded Systems
		10.1.3 Domain Applications
	10.2 Background of the Medical Signal Processing
		10.2.1 Literature Review
		10.2.2 Problem Identification
	10.3 Real-Time Monitoring Device
		10.3.1 Hardware Design Approach
		10.3.2 Multi-Scale Convolutional Neural Networks
		10.3.3 Raspberry Pi
		10.3.4 162 Liquid Crystal Display (LCD)
		10.3.5 Ubidots
		10.3.6 Blood Pressure Module
		10.3.7 Temperature Sensor (TMP103)
		10.3.8 Respiratory Devices
		10.3.9 Updation of Data Using MCNN and MATLAB
	10.4 Outcome and Discussion
	10.5 Conclusion
	10.6 Future Work
	References
Index
About the Editors
Back Cover