This book is a detailed reference guide on deep learning and its applications. It aims to provide a basic understanding of deep learning and its different architectures that are applied to process images, speech, and natural language. It explains basic concepts and many modern use cases through fifteen chapters contributed by computer science academics and researchers. By the end of the book, the reader will become familiar with different deep learning approaches and models, and understand how to implement various deep learning algorithms using multiple frameworks and libraries. This book is divided into three parts. The first part explains the basic operating understanding, history, evolution, and challenges associated with deep learning. The basic concepts of mathematics and the hardware requirements for deep learning implementation, and some of its popular frameworks for medical applications are also covered. The second part is dedicated to sentiment analysis using deep learning and machine learning techniques. This book section covers the experimentation and application of deep learning techniques and architectures in real-world applications. It details the salient approaches, issues, and challenges in building ethically aligned machines. An approach inspired by traditional Eastern thought and wisdom is also presented. The final part covers artificial intelligence approaches used to explain the machine learning models that enhance transparency for the benefit of users. A review and detailed description of the use of knowledge graphs in generating explanations for black-box recommender systems and a review of ethical system design and a model for sustainable education is included in this section. An additional chapter demonstrates how a semi-supervised machine learning technique can be used for cryptocurrency portfolio management. The book is a timely reference for academicians, professionals, researchers and students at engineering and medical institutions working on artificial intelligence applications.
Author(s): Gyanendra Verma, Rajesh Doriya
Publisher: Bentham Science Publishers
Year: 2023
Language: English
Pages: 270
Cover
Title
Copyright
End User License Agreement
Contents
Foreword
Preface
List of Contributors
Deep Learning: History and Evolution
Application of Artificial Intelligence in Medical Imaging
Sampurna Panda1, Rakesh Kumar Dhaka1 and Babita Panda2,*
INTRODUCTION
MACHINE-LEARNING
Supervised Learning
Unsupervised Learning
Semi-supervised Learning
Active Learning
Reinforcement Learning
Evolutionary Learning
Introduction to Deep Learning
APPLICATION OF ML IN MEDICAL IMAGING
DEEP LEARNING IN MEDICAL IMAGING
Image Classification
Object Classification
Organ or Region Detection
Data Mining
The Sign-up Process
Other Imaging Applications
CONCLUSION
CONSENT FOR PUBLICATION
CONFLICT OF INTEREST
ACKNOWLEDGEMENT
REFERENCES
Classification Tool to Predict the Presence of Colon Cancer Using Histopathology Images
Saleena Thorayanpilackal Sulaiman1,*, Muhamed Ilyas Poovankavil2 and Abdul Jabbar Perumbalath3
INTRODUCTION
METHODS AND PREPARATION
Dataset Preparation
Related Works
METHODOLOGY
Convolutional Neural Network (CNN)
ResNet50
RESULTS
CONCLUSION
CONSENT FOR PUBLICATION
CONFLICT OF INTEREST
ACKNOWLEDGEMENT
REFERENCES
Deep Learning For Lung Cancer Detection
Sushila Ratre1,*, Nehha Seetharaman1 and Aqib Ali Sayed1
INTRODUCTION
RELATED WORKS
METHODOLOGY
VGG16 ARCHITECTURE
RESNET50 ARCHITECTURE
FLOWCHART OF THE METHODOLOGY
EXPERIMENTAL RESULTS
CONCLUDING REMARKS
ACKNOWLEDGEMENTS
REFERENCES
Exploration of Medical Image Super-Resolution in terms of Features and Adaptive Optimization
Jayalakshmi Ramachandran Nair1,*, Sumathy Pichai Pillai2 and Rajkumar Narayanan3
INTRODUCTION
LITERATURE REVIEW
METHODOLOGIES
Pre-Upsampling Super Resolution
Very Deep Super-Resolution Models
Post Upsampling Super Resolution
Residual Networks
Multi-stage Residual Networks (MDSR)
Balanced Two-Stage Residual Networks
Recursive Networks
Deep Recursive Convolution Network (DRCN)
Progressive Reconstruction Networks
Attention-Based Network
Pixel Loss
Perceptual Loss
Adversarial Loss
SYSTEM TOOLS
FINDINGS
CONCLUSION
ACKNOWLEDGEMENTS
REFERENCES
Analyzing the Performances of Different ML Algorithms on the WBCD Dataset
Trupthi Muralidharr1,*, Prajwal Sethu Madhav1, Priyanka Prashanth Kumar1 and Harshawardhan Tiwari1
INTRODUCTION
LITERATURE REVIEW
DATASET DESCRIPTION
PRE-PROCESSING OF DATA
Exploratory Data Analysis(EDA)
Model Accuracy: Receiver Operating Characteristic (ROC) curve:
RESULTS
CONCLUSION
ACKNOWLEDGEMENTS
REFERENCES
Application and Evaluation of Machine LearningAlgorithms in Classifying Cardiotocography(CTG) Signals
Deep SLRT: The Development of Deep Learning based Multilingual and Multimodal Sign Language Recognition and Translation Framework
Natarajan Balasubramanian1 and Elakkiya Rajasekar1,*
INTRODUCTION
RELATED WORKS
Subunit Modelling and Extraction of Manual Features and Non-manual Features
Challenges and Deep Learning Methods for SLRT Research
THE PROPOSED MODEL
Algorithm: 2 NMT-GAN based Deep SLRT Video Generation (Backward)
Training Details
EXPERIMENTAL RESULTS
CONCLUSION
ACKNOWLEDGEMENTS
REFERENCES
Hybrid Convolutional Recurrent Neural Network for Isolated Indian Sign Language Recognition
Rajasekar Elakkiya1, Archana Mathiazhagan1 and Elakkiya Rajalakshmi1,*
INTRODUCTION
RELATED WORK
METHODOLOGY
Proposed H-CRNN Framework
Data Acquisition, Preprocessing, and Augmentation
Proposed H-CRNN Architecture
Experiments and Results
CONCLUSION AND FUTURE WORK
ACKNOWLEDGEMENTS
REFERENCES
A Proposal of an Android Mobile Application for Senior Citizen Community with Multi-lingual Sentiment Analysis Chatbot
Harshee Pitroda1,*, Manisha Tiwari1 and Ishani Saha1
INTRODUCTION
LITERATURE REVIEW
Twitter data
PROPOSED FRAMEWORK
IMPLEMENTATION OVERVIEW
Exploratory Data Analysis (EDA)
Feature Extraction
Classification
Support Vector Machine
Decision Tree
Random Forest
Implementation
Pickling the Model
Translation
Integrating with the Android App
Code Snippets
Support Vector Machine
Decision Tree
Random Forest
RESULTS AND CONCLUSION
Results
Feature Extraction
Classification
CONCLUSION
CONSENT FOR PUBLICATION
CONFLICT OF INTEREST
ACKNOWLEDGEMENT
REFERENCES
Technology Inspired-Elaborative Education Model (TI-EEM): A futuristic need for a Sustainable Education Ecosystem
Anil Verma1, Aman Singh1,*, Divya Anand1 and Rishika Vij2
INTRODUCTION
BACKGROUND
METHODOLOGY
RESULT AND DISCUSSION
CONCLUSION
CONSENT FOR PUBLICATION
CONFLICT OF INTEREST
ACKNOWLEDGEMENT
REFERENCES
Knowledge Graphs for Explaination of Black-Box Recommender System
Mayank Gupta1 and Poonam Saini1,*
INTRODUCTION
Introduction to Recommender System
Introduction to Knowledge Graphs
RECOMMENDER SYSTEMS
Types of Recommender Systems
KNOWLEDGE GRAPHS
Knowledge Graphs for Providing Recommendations
Knowledge Graphs for Generating Explanations
GENERATING EXPLANATIONS FOR BLACK-BOX RECOMME-NDER SYSTEMS
PROPOSED CASE STUDY
MovieLens Dataset
Modules
Knowledge Graph Generation
The Proposed Approach for Case Study
Results
Graph Visualisation
CONCLUSION
REFERENCES
Universal Price Tag Reader for Retail Supermarket
Jay Prajapati1,* and Siba Panda1
INTRODUCTION
LITERATURE REVIEW
METHODOLOGY
Image Pre-processing and Cropping
Optical Character Recognition
Price of the product
Name of the product
Discounted Price
RESULTS AND FUTURE SCOPE
CONCLUDING REMARKS
ACKNOWLEDGEMENTS
REFERENCES
The Value Alignment Problem: Building Ethically Aligned Machines
Sukrati Chaturvedi1,*, Chellapilla Vasantha Lakshmi1 and Patvardhan Chellapilla1
INTRODUCTION
Value Alignment Problem
Approaches for Solving AI-VAP
Top-Down Approach
Limitations, Issues, and Challenges of Extant Approaches
Eastern Perspectives of Intelligence for Solving AI-VAP
Proposed Approach
CONCLUSION
REFERENCES
Cryptocurrency Portfolio Management Using Reinforcement Learning
Vatsal Khandor1,*, Sanay Shah1, Parth Kalkotwar1, Saurav Tiwari1 and Sindhu Nair1
INTRODUCTION
RELATED WORK
DATASET PRE-PROCESSING
Simple Moving Average
Moving Average Convergence/Divergence
Parabolic Stop and Reverse
Relative Strength Index
MODELING AND EVALUATION
Convolutional Neural Networks (CNN)
Dense Neural Network Model
CONCLUSION AND FUTURE SCOPE
REFERENCES
Subject Index
Back Cover
