Integrating Deep Learning Algorithms to Overcome Challenges in Big Data Analytics

Cover
Half Title
Series Page
Title Page
Copyright Page
Contents
Preface
Editors
Contributors
1. A Study on Big Data and Artificial Intelligence Techniques in Agricultural Sector
	1.1 Introduction
		1.1.1 The Life Cycle of Agriculture
	1.2 The Role of Big Data in the Agricultural Sector
		1.2.1 Overall Characteristics of Big Data Applicable to the Agricultural Sector
		1.2.2 The Processing Steps of Big Data in Agriculture
	1.3 Some Cases of the Use of Big Data on Farm
		1.3.1 To Evade Food Scarcity of the Growing Population
		1.3.2 Managing Pesticides and Farm Equipment
		1.3.3 Supply Chain Management
		1.3.4 Yield Prediction and Risk Management
	1.4 Challenges Faced by Farmers versus AI Solutions
		1.4.1 Forecasting Weather Conditions
		1.4.2 Decision-Making
		1.4.3 Diagnosing Defects in Soil and Weed Detection
		1.4.4 Nutrition Treatment
	1.5 AI Techniques in Agricultural Sector
		1.5.1 Machine Learning
			1.5.1.1 Supervised Learning
			1.5.1.2 Unsupervised Learning
		1.5.2 Neural Networks
			1.5.2.1 Working Process of Neural Network
		1.5.3 The Expert System
			1.5.3.1 Components of the Expert System
			1.5.3.2 The Working Process of the Expert System
		1.5.4 The Decision Tree
			1.5.4.1 Working Steps of the Decision Tree
		1.5.5 Support Vector Machine
		1.5.6 Random Forest
			1.5.6.1 Working Steps of an RF
	1.6 Application of AI in Agriculture
		1.6.1 Image Recognition
		1.6.2 Disease Detection
		1.6.3 Field Management
		1.6.4 Driverless Tractor
		1.6.5 Weather Forecasting
		1.6.6 AI Agricultural Bots
		1.6.7 Reduction of Pesticide Usage
	1.7 Advantages of Using AI in Agriculture
	1.8 Conclusion
	References
2. Deep Learning Models for Object Detection in Self-Driven Cars
	2.1 Introduction
	2.2 Related Work
	2.3 Self-Directed Cars
		2.3.1 Computer Vision
		2.3.2 Fusion of Sensor Data
		2.3.3 Localization
		2.3.4 Path Planning
		2.3.5 Control
	2.4 Object Detection
	2.5 Region-based Convolutional Neural Network (R-CNN)
	2.6 Fast Region-based Convolutional Neural Network (Fast R-CNN)
	2.7 Faster Region-based Convolutional Neural Network (Faster R-CNN)
	2.8 Mask Region-based Convolution Neural Network (Mask R-CNN)
	2.9 YOLO
	2.10 YOLO v1 for Self-Driven Cars
	2.11 YOLO v2 for Self-Driven Cars
	2.12 YOLO v3 for Self-Driven Cars
	2.13 Performance Analysis
	2.14 Conclusion
	References
3. Deep Learning for Analyzing the Data on Object Detection and Recognition
	3.1 Introduction
		3.1.1 Basic Concept of Deep Learning
		3.1.2 Brief History of Deep Learning
		3.1.3 Advantages of Deep Learning with Traditional Learning
		3.1.4 Convolutional Neural Networks (CNNs)
		3.1.5 Object Detection and Recognition
	3.2 Deep Learning Object Detection Models
		3.2.1 Two-Stage Methodology for Deep Object Detection
			3.2.1.1 Region-based Convolutional Neural Network (R-CNN)
			3.2.1.2 Fast Region-based Convolutional Neural Network (Fast R-CNN)
			3.2.1.3 Faster Region-based Convolutional Neural Network (Faster R-CNN)
			3.2.1.4 Mask R-CNN
		3.2.2 One-Stage Methodology for Deep Object Detection
			3.2.2.1 You Only Look Once - One-Stage Method
			3.2.2.2 Single-Shot Multi-Box Detector (SSD)
		3.2.3 The Benchmark Deep Learning's Object Detection Models
	3.3 General Datasets for Object Detection
		3.3.1 Microsoft Common Objects in Context (MS-COCO)
		3.3.2 Pattern Analysis, Statistical Modeling, and Computational Learning (PASCAL) - Visual Object Classes (VOC)
	3.4 Conclusion and Future Directions
	References
4. Emerging Applications of Deep Learning
	4.1 Introduction
		4.1.1 Machine Learning
			4.1.1.1 Machine Learning Types
			4.1.1.2 How Machine Learning Overseen Works
	4.2 Summary of Deep Learning
		4.2.1 Deep Learning Uses
		4.2.2 The Deep Learning Development
		4.2.3 Deep Learning Advantages
	4.3 Deep Learning Applications in Recent Fields
		4.3.1 Fraud Detection
		4.3.2 Autonomous Cars
		4.3.3 GoogleNet Deep Learning Algorithm for Autonomous Driving Using GoogleNet Driving
		4.3.4 Deep Learning to Self-Driving Car: Chances and Challenges
		4.3.5 Deep Learning Grokking
		4.3.6 Enabling Immersive Supercomputing at JSC, Lessons Learned
		4.3.7 Wide-Range Deep Learning on Big Scale
		4.3.8 Fast CPU Implementation
		4.3.9 Large-Scale Implementations Distributed
		4.3.10 Speech Recognition
		4.3.11 Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection
		4.3.12 Deep Learning for Computational Chemistry
		4.3.13 Deep Learning in Radiology
	4.4 Conclusion and Future Directions
	References
5. Emerging Trend and Research Issues in Deep Learning with Cloud Computing
	5.1 Introduction
		5.1.1 Cloud Computing Architecture
	5.2 Deep Learning
		5.2.1 Supervised and Unsupervised Learning
		5.2.2 Deep Learning Techniques Adopted in the Emergent Cloud Environment
	5.3 Convolutional Neural Network
	5.4 Deep Reinforcement Learning
	5.5 Recurrent Neural Network
	5.6 Deep Learning Applications in the Emerging Cloud Computing Environment
	5.7 Challenges and New Perspective for Future Direction
	5.8 Conclusion
	References
6. An Investigation of Deep Learning
	6.1 Introduction
		6.1.1 Artificial Neural Network
		6.1.2 Convolution Neural Networks
		6.1.3 Neocognitron
		6.1.4 Back Propagation
		6.1.5 Backpropagation Neural Network Architecture
	6.2 History of Machine Learning
		6.2.1 Game Checkers in Machine Learning
		6.2.2 Algorithm for Nearest Neighbors (k-NN)
		6.2.3 Forwarding Information between Layers
		6.2.4 Artificial Neural Network (ANN)
		6.2.5 Machine Learning versus Artificial Intelligence
		6.2.6 Algorithm for Boosting Machine Learning
		6.2.7 Facial Model Identification
		6.2.8 How Machine Learning Happened Today?
	6.3 Deep Learning
	6.4 Conclusion
	References
7. A Study and Comparative Analysis of Various Use Cases of NLP Using Sequential Transfer Learning Techniques
	7.1 Introduction
	7.2 Literature Review
	7.3 Empirical Study
	7.4 Sequential Transfer Learning Model for Sentiment Analysis
		7.4.1 ULMFIT
		7.4.2 RoBERTa
		7.4.3 XLNet
		7.4.4 DistilBERT
		7.4.5 Methodology
		7.4.6 Results and Discussion
			7.4.6.1 Experiment Set 1 on IMDB
			7.4.6.2 Experiment Set 2 YELP Review Dataset
	7.5 Sequential Transfer Learning Model for NER
		7.5.1 Results and Discussion
	7.6 Conclusion
	7.7 Conflict of Interest
	Acknowledgment
	References
8. Deep Learning for Medical Dataset Classification Based on Convolutional Neural Networks
	8.1 Introduction
	8.2 Deep Learning Architecture and Its Neural Networks
	8.3 CNN-Based Medical Image Classification
		8.3.1 Deep Features and Fusion with Multi-Layer Perceptron
		8.3.2 ECG Arrhythmia Classifications
		8.3.3 Classification of Tuberculosis-Related Chest X-Ray
		8.3.4 Clinical Image Classification of Infectious Keratitis
		8.3.5 Diabetic Retinopathy
		8.3.6 Tumor Stage Classification of Pulmonary Lung Nodules
		8.3.7 Classification of Alzheimer's Disease
		8.3.8 Classification of Primary Bone Tumors on Radiographs
		8.3.9 Classification of Brain Tumors
		8.3.10 Classification Methods for Diagnosis of Skin Cancer
		8.3.11 COVID-19 Detection in CT Images
		8.3.12 MRI Harmonization and Confound Removal Using Neuro-Imaging Datasets
		8.3.13 Deep Learning in Spatiotemporal Cardiac Imaging
		8.3.14 Liver Tumor Classification Using Deep Learning model
	8.4 Conclusion
	References
9. Deep Learning in Medical Image Classification
	9.1 Introduction
	9.2 Medical Image Classification
		9.2.1 What Is Medical Imaging?
		9.2.2 Why Medical Imaging So Important?
		9.2.3 Who Does It and for Whom?
		9.2.4 How It Is Done?
		9.2.5 What Is Medical Image Classification?
		9.2.6 Why Deep Learning over Conventional Methods
	9.3 Overview of Deep Learning
		9.3.1 Fundamentals of Deep Learning
			9.3.1.1 Aspects of Deep Learning
			9.3.1.2 Drivers of Deep Learning
		9.3.2 Deep Learning Architectures
			9.3.2.1 Deep Neural Networks (DNN)
			9.3.2.2 Convolutional Neural Networks
			9.3.2.3 Recurrent Neural Network (RNN)
			9.3.2.4 Deep Boltzmann Network (Also Called Restricted Boltzman Machine)
			9.3.2.5 Deep Belief Networks (DBNs)
			9.3.2.6 Deep AutoEncoder (DAE)
	9.4 Deep Learning for Medical Image Classification [Literature Review]
		9.4.1 Deep Learning for Diabetic Retinopathy
		9.4.2 Deep Learning for the Detection of Histological andMicroscopial Elements
		9.4.3 Deep Learning for Gastrointestinal Disease Detection
		9.4.4 Deep Learning for Lung Disease
		9.4.5 Deep Learning for Cardiac Disease Classification
		9.4.6 Deep Learning for Tumor Detection
		9.4.7 Deep Learning for Alzheimer's and Parkinson's Detection
	9.5 Current Progress and Limitations of Deep Learning
		9.5.1 Limited Availability of Datasets
		9.5.2 Privacy and Legal Issues
		9.5.3 Data and Model Standardization
	9.6 Conclusion
	References
10. A Comparative Review of the Role of Deep Learning in Medical Image Processing
	10.1 Introduction
		10.1.1 Challenges of Medical Image Processing
	10.2 Deep Learning
		10.2.1 Important Deep Learning Models
			10.2.1.1 Supervised Learning Models
				10.2.1.1.1 Convolutional Neural Networks (CNNs)
				10.2.1.1.2 Recurrent Neural Networks
				10.2.1.1.3 Transfer Learning
			10.2.1.2 Unsupervised Learning
				10.2.1.2.1 Autoencoders
				10.2.1.2.2 Restricted Boltzmann Machines and Deep Belief Networks
				10.2.1.2.3 Generative Adversarial Networks
	10.3 Medical Image Processing
		10.3.1 Cardiovascular Diseases
		10.3.2 Arrhythmia
		10.3.3 Coronary Artery Disease
	10.4 Parkinson's and Alzheimer's Diseases
		10.4.1 Eye Diseases
		10.4.2 Breast Cancer
		10.4.3 Gastrointestinal Diseases
		10.4.4 Skin Cancer
		10.4.5 Liver Diseases
		10.4.6 Lung Cancer
	10.5 Conclusion
	References
Index