Schweitzer Fachinformationen
Wenn es um professionelles Wissen geht, ist Schweitzer Fachinformationen wegweisend. Kunden aus Recht und Beratung sowie Unternehmen, öffentliche Verwaltungen und Bibliotheken erhalten komplette Lösungen zum Beschaffen, Verwalten und Nutzen von digitalen und gedruckten Medien.
The book provides readers with an in-depth understanding of concepts and technologies related to the importance of analytics and deep learning in many useful real-world applications such as e-healthcare, transportation, agriculture, stock market, etc.
Advanced analytics is a mixture of machine learning, artificial intelligence, graphs, text mining, data mining, semantic analysis. It is an approach to data analysis. Beyond the traditional business intelligence, it is a semi and autonomous analysis of data by using different techniques and tools.
However, deep learning and data analysis both are high centers of data science. Almost all the private and public organizations collect heavy amounts of data, i.e., domain-specific data. Many small/large companies are exploring large amounts of data for existing and future technology. Deep learning is also exploring large amounts of unsupervised data making it beneficial and effective for big data. Deep learning can be used to deal with all kinds of problems and challenges that include collecting unlabeled and uncategorized raw data, extracting complex patterns from a large amount of data, retrieving fast information, tagging data, etc.
This book contains 16 chapters on artificial intelligence, machine learning, deep learning, and their uses in many useful sectors like stock market prediction, a recommendation system for better service selection, e-healthcare, telemedicine, transportation. There are also chapters on innovations and future opportunities with fog computing/cloud computing and artificial intelligence.
Audience
Researchers in artificial intelligence, big data, computer science, and electronic engineering, as well as industry engineers in healthcare, telemedicine, transportation, and the financial sector. The book will also be a great source for software engineers and advanced students who are beginners in the field of advanced analytics in deep learning.
Archana Mire, PhD, is an assistant professor in the Computer Engineering Department, Terna Engineering College, Navi Mumbai, India. She has published many research articles in peer-reviewed journals.
Shaveta Malik, PhD, is an associate professor in the Computer Engineering Department (NBA accredited), Terna Engineering College, Nerul, India. She has published many research articles in peer-reviewed journals.
Amit Kumar Tyagi, PhD, is an assistant professor and senior researcher at Vellore Institute of Technology (VIT), Chennai Campus, India. He received his PhD in 2018 from Pondicherry Central University, India. He has published more than 8 patents in the area of deep learning, Internet of Things, cyber-physical systems, and computer vision.
Preface xix
Part 1: Introduction to Computer Vision 1
1 Artificial Intelligence in Language Learning: Practices and Prospects 3Khushboo Kuddus
1.1 Introduction 4
1.2 Evolution of CALL 5
1.3 Defining Artificial Intelligence 7
1.4 Historical Overview of AI in Education and Language Learning 7
1.5 Implication of Artificial Intelligence in Education 8
1.5.1 Machine Translation 9
1.5.2 Chatbots 9
1.5.3 Automatic Speech Recognition Tools 9
1.5.4 Autocorrect/Automatic Text Evaluator 11
1.5.5 Vocabulary Training Applications 12
1.5.6 Google Docs Speech Recognition 12
1.5.7 Language MuseTM Activity Palette 13
1.6 Artificial Intelligence Tools Enhance the Teaching and Learning Processes 13
1.6.1 Autonomous Learning 13
1.6.2 Produce Smart Content 13
1.6.3 Task Automation 13
1.6.4 Access to Education for Students with Physical Disabilities 14
1.7 Conclusion 14
References 15
2 Real Estate Price Prediction Using Machine Learning Algorithms 19Palak Furia and Anand Khandare
2.1 Introduction 20
2.2 Literature Review 20
2.3 Proposed Work 21
2.3.1 Methodology 21
2.3.2 Work Flow 22
2.3.3 The Dataset 22
2.3.4 Data Handling 23
2.3.4.1 Missing Values and Data Cleaning 23
2.3.4.2 Feature Engineering 24
2.3.4.3 Removing Outliers 25
2.4 Algorithms 27
2.4.1 Linear Regression 27
2.4.2 LASSO Regression 27
2.4.3 Decision Tree 28
2.4.4 Support Vector Machine 28
2.4.5 Random Forest Regressor 28
2.4.6 XGBoost 29
2.5 Evaluation Metrics 29
2.6 Result of Prediction 30
References 31
3 Multi-Criteria-Based Entertainment Recommender System Using Clustering Approach 33Chandramouli Das, Abhaya Kumar Sahoo and Chittaranjan Pradhan
3.1 Introduction 34
3.2 Work Related Multi-Criteria Recommender System 35
3.3 Working Principle 38
3.3.1 Modeling Phase 39
3.3.2 Prediction Phase 39
3.3.3 Recommendation Phase 40
3.3.4 Content-Based Approach 40
3.3.5 Collaborative Filtering Approach 41
3.3.6 Knowledge-Based Filtering Approach 41
3.4 Comparison Among Different Methods 42
3.4.1 MCRS Exploiting Aspect-Based Sentiment Analysis 42
3.4.1.1 Discussion and Result 43
3.4.2 User Preference Learning in Multi-Criteria Recommendation Using Stacked Autoencoders by Tallapally et al. 46
3.4.2.1 Dataset and Evaluation Matrix 46
3.4.2.2 Training Setting 49
3.4.2.3 Result 49
3.4.3 Situation-Aware Multi-Criteria Recommender System: Using Criteria Preferences as Contexts by Zheng 49
3.4.3.1 Evaluation Setting 50
3.4.3.2 Experimental Result 50
3.4.4 Utility-Based Multi-Criteria Recommender Systems by Zheng 51
3.4.4.1 Experimental Dataset 51
3.4.4.2 Experimental Result 52
3.4.5 Multi-Criteria Clustering Approach by Wasid and Ali 53
3.4.5.1 Experimental Evaluation 53
3.4.5.2 Result and Analysis 53
3.5 Advantages of Multi-Criteria Recommender System 54
3.5.1 Revenue 57
3.5.2 Customer Satisfaction 57
3.5.3 Personalization 57
3.5.4 Discovery 58
3.5.5 Provide Reports 58
3.6 Challenges of Multi-Criteria Recommender System 58
3.6.1 Cold Start Problem 58
3.6.2 Sparsity Problem 59
3.6.3 Scalability 59
3.6.4 Over Specialization Problem 59
3.6.5 Diversity 59
3.6.6 Serendipity 59
3.6.7 Privacy 60
3.6.8 Shilling Attacks 60
3.6.9 Gray Sheep 60
3.7 Conclusion 60
References 61
4 Adoption of Machine/Deep Learning in Cloud With a Case Study on Discernment of Cervical Cancer 65Jyothi A. P., S. Usha and Archana H. R.
4.1 Introduction 66
4.2 Background Study 69
4.3 Overview of Machine Learning/Deep Learning 72
4.4 Connection Between Machine Learning/Deep Learning and Cloud Computing 74
4.5 Machine Learning/Deep Learning Algorithm 74
4.5.1 Supervised Learning 74
4.5.2 Unsupervised Learning 77
4.5.3 Reinforcement or Semi-Supervised Learning 77
4.5.3.1 Outline of ML Algorithms 77
4.6 A Project Implementation on Discernment of Cervical Cancer by Using Machine/Deep Learning in Cloud 93
4.6.1 Proposed Work 94
4.6.1.1 MRI Dataset 94
4.6.1.2 Pre Processing 95
4.6.1.3 Feature Extraction 96
4.6.2 Design Methodology and Implementation 97
4.6.3 Results 100
4.7 Applications 101
4.7.1 Cognitive Cloud 102
4.7.2 Chatbots and Smart Personal Assistants 103
4.7.3 IoT Cloud 103
4.7.4 Business Intelligence 103
4.7.5 AI-as-a-Service 104
4.8 Advantages of Adoption of Cloud in Machine Learning/ Deep Learning 104
4.9 Conclusion 105
References 106
5 Machine Learning and Internet of Things-Based Models for Healthcare Monitoring 111Shruti Kute, Amit Kumar Tyagi, Aswathy S.U. and Shaveta Malik
5.1 Introduction 112
5.2 Literature Survey 113
5.3 Interpretable Machine Learning in Healthcare 114
5.4 Opportunities in Machine Learning for Healthcare 116
5.5 Why Combining IoT and ML? 119
5.5.1 ML-IoT Models for Healthcare Monitoring 119
5.6 Applications of Machine Learning in Medical and Pharma 121
5.7 Challenges and Future Research Direction 122
5.8 Conclusion 123
References 123
6 Machine Learning-Based Disease Diagnosis and Prediction for E-Healthcare System 127Shruti Suhas Kute, Shreyas Madhav A. V., Shabnam Kumari and Aswathy S. U.
6.1 Introduction 128
6.2 Literature Survey 129
6.3 Machine Learning Applications in Biomedical Imaging 132
6.4 Brain Tumor Classification Using Machine Learning and IoT 134
6.5 Early Detection of Dementia Disease Using Machine Learning and IoT-Based Applications 135
6.6 IoT and Machine Learning-Based Diseases Prediction and Diagnosis System for EHRs 137
6.7 Machine Learning Applications for a Real-Time Monitoring of Arrhythmia Patients Using IoT 140
6.8 IoT and Machine Learning-Based System for Medical Data Mining 141
6.9 Conclusion and Future Works 143
References 144
Part 2: Introduction to Deep Learning and its Models 149
7 Deep Learning Methods for Data Science 151K. Indira, Kusumika Krori Dutta, S. Poornima and Sunny Arokia Swamy Bellary
7.1 Introduction 152
7.2 Convolutional Neural Network 152
7.2.1 Architecture 154
7.2.2 Implementation of CNN 154
7.2.3 Simulation Results 157
7.2.4 Merits and Demerits 158
7.2.5 Applications 159
7.3 Recurrent Neural Network 159
7.3.1 Architecture 160
7.3.2 Types of Recurrent Neural Networks 161
7.3.2.1 Simple Recurrent Neural Networks 161
7.3.2.2 Long Short-Term Memory Networks 162
7.3.2.3 Gated Recurrent Units (GRUs) 164
7.3.3 Merits and Demerits 167
7.3.3.1 Merits 167
7.3.3.2 Demerits 167
7.3.4 Applications 167
7.4 Denoising Autoencoder 168
7.4.1 Architecture 169
7.4.2 Merits and Demerits 169
7.4.3 Applications 170
7.5 Recursive Neural Network (RCNN) 170
7.5.1 Architecture 170
7.5.2 Merits and Demerits 172
7.5.3 Applications 172
7.6 Deep Reinforcement Learning 173
7.6.1 Architecture 174
7.6.2 Merits and Demerits 174
7.6.3 Applications 174
7.7 Deep Belief Networks (DBNS) 175
7.7.1 Architecture 176
7.7.2 Merits and Demerits 176
7.7.3 Applications 176
7.8 Conclusion 177
References 177
8 A Proposed LSTM-Based Neuromarketing Model for Consumer Emotional State Evaluation Using EEG 181Rupali Gill and Jaiteg Singh
8.1 Introduction 182
8.2 Background and Motivation 183
8.2.1 Emotion Model 183
8.2.2 Neuromarketing and BCI 184
8.2.3 EEG Signal 185
8.3 Related Work 185
8.3.1 Machine Learning 186
8.3.2 Deep Learning 191
8.3.2.1 Fast Feed Neural Networks 193
8.3.2.2 Recurrent Neural Networks 193
8.3.2.3 Convolutional Neural Networks 194
8.4 Methodology of Proposed System 195
8.4.1 DEAP Dataset 196
8.4.2 Analyzing the Dataset 196
8.4.3 Long Short-Term Memory 197
8.4.4 Experimental Setup 197
8.4.5 Data Set Collection 197
8.5 Results and Discussions 198
8.5.1 LSTM Model Training and Accuracy 198
8.6 Conclusion 199
References 199
9 An Extensive Survey of Applications of Advanced Deep Learning Algorithms on Detection of Neurodegenerative Diseases and the Tackling Procedure in Their Treatment Protocol 207Vignesh Baalaji S., Vergin Raja Sarobin M., L. Jani Anbarasi, Graceline Jasmine S. and Rukmani P.
9.1 Introduction 208
9.2 Story of Alzheimer's Disease 208
9.3 Datasets 210
9.3.1 ADNI 210
9.3.2 OASIS 210
9.4 Story of Parkinson's Disease 211
9.5 A Review on Learning Algorithms 212
9.5.1 Convolutional Neural Network (CNN) 212
9.5.2 Restricted Boltzmann Machine 213
9.5.3 Siamese Neural Networks 213
9.5.4 Residual Network (ResNet) 214
9.5.5 U-Net 214
9.5.6 LSTM 214
9.5.7 Support Vector Machine 215
9.6 A Review on Methodologies 215
9.6.1 Prediction of Alzheimer's Disease 215
9.6.2 Prediction of Parkinson's Disease 221
9.6.3 Detection of Attacks on Deep Brain Stimulation 223
9.7 Results and Discussion 224
9.8 Conclusion 224
References 227
10 Emerging Innovations in the Near Future Using Deep Learning Techniques 231Akshara Pramod, Harsh Sankar Naicker and Amit Kumar Tyagi
10.1 Introduction 232
10.2 Related Work 234
10.3 Motivation 235
10.4 Future With Deep Learning/Emerging Innovations in Near Future With Deep Learning 236
10.4.1 Deep Learning for Image Classification and Processing 237
10.4.2 Deep Learning for Medical Image Recognition 237
10.4.3 Computational Intelligence for Facial Recognition 238
10.4.4 Deep Learning for Clinical and Health Informatics 238
10.4.5 Fuzzy Logic for Medical Applications 239
10.4.6 Other Intelligent-Based Methods for Biomedical and Healthcare 239
10.4.7 Other Applications 239
10.5 Open Issues and Future Research Directions 244
10.5.1 Joint Representation Learning From User and Item Content Information 244
10.5.2 Explainable Recommendation With Deep Learning 245
10.5.3 Going Deeper for Recommendation 245
10.5.4 Machine Reasoning for Recommendation 246
10.5.5 Cross Domain Recommendation With Deep Neural Networks 246
10.5.6 Deep Multi-Task Learning for Recommendation 247
10.5.7 Scalability of Deep Neural Networks for Recommendation 247
10.5.8 Urge for a Better and Unified Evaluation 248
10.6 Deep Learning: Opportunities and Challenges 249
10.7 Argument with Machine Learning and Other Available Techniques 250
10.8 Conclusion With Future Work 251
Acknowledgement 252
References 252
11 Optimization Techniques in Deep Learning Scenarios: An Empirical Comparison 255Ajeet K. Jain, PVRD Prasad Rao and K. Venkatesh Sharma
11.1 Introduction 256
11.1.1 Background and Related Work 256
11.2 Optimization and Role of Optimizer in DL 258
11.2.1 Deep Network Architecture 259
11.2.2 Proper Initialization 260
11.2.3 Representation, Optimization, and Generalization 261
11.2.4 Optimization Issues 261
11.2.5 Stochastic GD Optimization 262
11.2.6 Stochastic Gradient Descent with Momentum 263
11.2.7 SGD With Nesterov Momentum 264
11.3 Various Optimizers in DL Practitioner Scenario 265
11.3.1 AdaGrad Optimizer 265
11.3.2 RMSProp 267
11.3.3 Adam 267
11.3.4 AdaMax 269
11.3.5 AMSGrad 269
11.4 Recent Optimizers in the Pipeline 270
11.4.1 EVE 270
11.4.2 RAdam 271
11.4.3 MAS (Mixing ADAM and SGD) 271
11.4.4 Lottery Ticket Hypothesis 272
11.5 Experiment and Results 273
11.5.1 Web Resource 273
11.5.2 Resource 277
11.6 Discussion and Conclusion 278
References 279
Part 3: Introduction to Advanced Analytics 283
12 Big Data Platforms 285Sharmila Gaikwad and Jignesh Patil
12.1 Visualization in Big Data 286
12.1.1 Introduction to Big Data 286
12.1.2 Techniques of Visualization 287
12.1.3 Case Study on Data Visualization 302
12.2 Security in Big Data 305
12.2.1 Introduction of Data Breach 305
12.2.2 Data Security Challenges 306
12.2.3 Data Breaches 307
12.2.4 Data Security Achieved 307
12.2.5 Findings: Case Study of Data Breach 309
12.3 Conclusion 309
References 309
13 Smart City Governance Using Big Data Technologies 311K. Raghava Rao and D. Sateesh Kumar
13.1 Objective 312
13.2 Introduction 312
13.3 Literature Survey 314
13.4 Smart Governance Status 314
13.4.1 International 314
13.4.2 National 316
13.5 Methodology and Implementation Approach 318
13.5.1 Data Generation 319
13.5.2 Data Acquisition 319
13.5.3 Data Analytics 319
13.6 Outcome of the Smart Governance 322
13.7 Conclusion 323
References 323
14 Big Data Analytics With Cloud, Fog, and Edge Computing 325Deepti Goyal, Amit Kumar Tyagi and Aswathy S. U.
14.1 Introduction to Cloud, Fog, and Edge Computing 326
14.2 Evolution of Computing Terms and Its Related Works 330
14.3 Motivation 332
14.4 Importance of Cloud, Fog, and Edge Computing in Various Applications 333
14.5 Requirement and Importance of Analytics (General) in Cloud, Fog, and Edge Computing 334
14.6 Existing Tools for Making a Reliable Communication and Discussion of a Use Case (with Respect to Cloud, Fog, and Edge Computing) 335
14.6.1 CloudSim 335
14.6.2 SPECI 336
14.6.3 Green Cloud 336
14.6.4 OCT (Open Cloud Testbed) 337
14.6.5 Open Cirrus 337
14.6.6 GroudSim 338
14.6.7 Network CloudSim 338
14.7 Tools Available for Advanced Analytics (for Big Data Stored in Cloud, Fog, and Edge Computing Environment) 338
14.7.1 Microsoft HDInsight 338
14.7.2 Skytree 339
14.7.3 Splice Machine 339
14.7.4 Spark 339
14.7.5 Apache SAMOA 339
14.7.6 Elastic Search 339
14.7.7 R-Programming 339
14.8 Importance of Big Data Analytics for Cyber-Security and Privacy for Cloud-IoT Systems 340
14.8.1 Risk Management 340
14.8.2 Predictive Models 340
14.8.3 Secure With Penetration Testing 340
14.8.4 Bottom Line 341
14.8.5 Others: Internet of Things-Based Intelligent Applications 341
14.9 An Use Case with Real World Applications (with Respect to Big Data Analytics) Related to Cloud, Fog, and Edge Computing 341
14.10 Issues and Challenges Faced by Big Data Analytics (in Cloud, Fog, and Edge Computing Environments) 342
14.10.1 Cloud Issues 343
14.11 Opportunities for the Future in Cloud, Fog, and Edge Computing Environments (or Research Gaps) 344
14.12 Conclusion 345
References 346
15 Big Data in Healthcare: Applications and Challenges 351V. Shyamala Susan, K. Juliana Gnana Selvi and Ir. Bambang Sugiyono Agus Purwono
15.1 Introduction 352
15.1.1 Big Data in Healthcare 352
15.1.2 The 5V's Healthcare Big Data Characteristics 353
15.1.2.1 Volume 353
15.1.2.2 Velocity 353
15.1.2.3 Variety 353
15.1.2.4 Veracity 353
15.1.2.5 Value 353
15.1.3 Various Varieties of Big Data Analytical (BDA) in Healthcare 353
15.1.4 Application of Big Data Analytics in Healthcare 354
15.1.5 Benefits of Big Data in the Health Industry 355
15.2 Analytical Techniques for Big Data in Healthcare 356
15.2.1 Platforms and Tools for Healthcare Data 357
15.3 Challenges 357
15.3.1 Storage Challenges 357
15.3.2 Cleaning 358
15.3.3 Data Quality 358
15.3.4 Data Security 358
15.3.5 Missing or Incomplete Data 358
15.3.6 Information Sharing 358
15.3.7 Overcoming the Big Data Talent and Cost Limitations 359
15.3.8 Financial Obstructions 359
15.3.9 Volume 359
15.3.10 Technology Adoption 360
15.4 What is the Eventual Fate of Big Data in Healthcare Services? 360
15.5 Conclusion 361
References 361
16 The Fog/Edge Computing: Challenges, Serious Concerns, and the Road Ahead 365Varsha. R., Siddharth M. Nair and Amit Kumar Tyagi
16.1 Introduction 366
16.1.1 Organization of the Work 368
16.2 Motivation 368
16.3 Background 369
16.4 Fog and Edge Computing-Based Applications 371
16.5 Machine Learning and Internet of Things-Based Cloud, Fog, and Edge Computing Applications 374
16.6 Threats Mitigated in Fog and Edge Computing-Based Applications 376
16.7 Critical Challenges and Serious Concerns Toward Fog/Edge Computing and Its Applications 378
16.8 Possible Countermeasures 381
16.9 Opportunities for 21st Century Toward Fog and Edge Computing 383
16.9.1 5G and Edge Computing as Vehicles for Transformation of Mobility in Smart Cities 383
16.9.2 Artificial Intelligence for Cloud Computing and Edge Computing 384
16.10 Conclusion 387
References 387
Index 391
Dateiformat: PDFKopierschutz: Adobe-DRM (Digital Rights Management)
Systemvoraussetzungen:
Das Dateiformat PDF zeigt auf jeder Hardware eine Buchseite stets identisch an. Daher ist eine PDF auch für ein komplexes Layout geeignet, wie es bei Lehr- und Fachbüchern verwendet wird (Bilder, Tabellen, Spalten, Fußnoten). Bei kleinen Displays von E-Readern oder Smartphones sind PDF leider eher nervig, weil zu viel Scrollen notwendig ist. Mit Adobe-DRM wird hier ein „harter” Kopierschutz verwendet. Wenn die notwendigen Voraussetzungen nicht vorliegen, können Sie das E-Book leider nicht öffnen. Daher müssen Sie bereits vor dem Download Ihre Lese-Hardware vorbereiten.
Bitte beachten Sie: Wir empfehlen Ihnen unbedingt nach Installation der Lese-Software diese mit Ihrer persönlichen Adobe-ID zu autorisieren!
Weitere Informationen finden Sie in unserer E-Book Hilfe.
