Part 1: Big Data, Clouds and Internet of Things
Chapter 1 Big Data Science and Machine Intelligence
1.1 Enabling Technologies for Big Data Computing
1.1.1 Data Science and Related Disciplines
1.1.2 Emerging Technologies in The Next Decade
1.1.3 Interactive SMACT Technologies
1.2 Social-Media, Mobile Networks and Cloud Computing
1.2.1 Social Networks and Web Service Sites
1.2.2 Mobile Cellular Core Networks
1.2.3 Mobile Devices and Internet Edge Networks
1.2.4 Mobile Cloud Computing Infrastructure
1.3 Big Data Acquisition and Analytics Evolution
1.3.1 Big Data Value Chain Extracted from Massive Data
1.3.2 Data Quality Control, Representation and Database Models
1.3.3 Data Acquisition and Preprocessing
1.3.4 Evolving Data Analytics over The Clouds
1.4 Machine Intelligence and Big Data Applications
1.4.1 Data Mining and Machine Learning
1.4.2 Big Data Applications – An Overview
1.4.3 Cognitive Computing – An Introduction
1.5 Conclusions, References and Exercises
Chapter 2 Smart Clouds, Virtualization and Mashup Services
2.1 Cloud Computing Models and Services
2.1.1 Cloud Taxonomy based on Services Provided
2.1.2 Layered Development Cloud Service Platforms
2.1.3 Cloud Models for Big Data Storage and Processing
2.1.4 Cloud Resources for Supporting Big Data Analytics
2.2 Creation of Virtual Machines and Docker Containers
2.2.1 Virtualization of Machine Resources
2.2.2 Hypervisors and Virtual Machines
2.2.3 Docker Engine and Application Containers
2.2.4 Deployment Opportunity of VMs/Containers
2.3 Cloud Architectures and Resources Management
2.3.1 Cloud Platform Architectures
2.3.2 VM Management and Disaster Recovery
2.3.3 Container Scheduling and Orchestration
2.3.4 OpenStack for Private Cloud Construction
2.3.5 VMWare Packages for Building Hybrid Clouds
2.4 Case Studies of IaaS, PaaS and SaaS Clouds
2.4.1 AWS Architecture over Distributed Datacenters
2.4.2 AWS Cloud Service Offerings
2.4.3 Platform PaaS Clouds – Google App Engine
2.4.4 Application SaaS Clouds – The Salesforce Clouds
2.5 Mobile Clouds and Multi-Cloud Mashup Services
2.5.1 Mobile Clouds and Cloudlet Mesh
2.5.2 Inter-Cloud Mashup Services
2.5.3 Skyline Discovery of Mashup Services
2.5.4 Dynamic Composition of Mashup Services
2.6 Conclusions, References and Home Work
Chapter 3 IoT Sensing, Mobile and Cognitive Systems
3.1 Sensing Technologies for Internet of Things
3.1.1 Enabling Technologies and Evolution of IoT
3.1.2 Introducing RFID and Sensor Technologies
3.1.3 IoT Architecture and Wireless Support
3.2 IoT Interactions with GPS, Clouds and Smart Machines
3.2.1 Local vs. Global Positioning Technologies
3.2.2 Standalone vs. Cloud-Centric IoT applications
3.2.3 IoT Interaction Frameworks with Environments
3.3 Radio Frequency Identification (RFID)
3.3.1 RFID Technology and Tagging Devices
3.3.2 RFID System Architecture
3.3.3 IoT Support of Supply Chain Management
3.4 Sensors, Wireless Sensor Networks and GPS Systems
3.4.1 Sensor Hardware and Operating Systems
3.4.2 Sensing Through Smart Phones
3.4.3 Wireless Sensor Networks and Body Area Networks
3.4.4 Global Positioning Systems
3.5 Cognitive Computing Technologies and Systems
3.5.1 Cognitive Science and Neuroinformatics
3.5.2 Brain-Inspired Computing Chips and Systems
3.5.3 Google’s Brain Team Projects
3.5.4 IoT Contexts for Cognitive Services
3.5.5 Augmented and Virtual Reality Applications
3.6 Conclusions, References and Exercises
Part 2: Machine Learning and Deep Learning Algorithms
Chapter 4 Supervised Machine Learning Algorithms
4.1 Taxonomy of Machine Learning Algorithms
4.1.1 Machine Learning based on Learning Styles
4.1.2 Machine Learning based on similarity Testing
4.1.3 Supervised Machine Learning Algorithms
4.1.4 Unsupervised Machine Learning Algorithms
4.2 Regression Methods for Machine Learning
4.2.1 Basic Concept of Regression Analysis
4.2.2 Linear Regression for Prediction or Forecasting
4.2.3 Logistic Regression for Classification
4.3 Supervised Classification Methods
4.3.1 Decision Trees for Machine Learning
4.3.2 Rule-based Classification
4.3.3 Nearest Neighbor Classifier
4.3.4 Support Vector Machines
4.4 Bayesian Network and Ensemble Methods
4.4.1 Bayesian Classifiers
4.4.2 Bayesian Belief Network
4.4.3 Random Forests and Ensemble Methods
4.5 Conclusions, References and Exercises
Chapter 5 Unsupervised Machine Learning Algorithms
5.1 Introduction and Association Analysis
5.1.1 Introduction To Unsupervised Machine Learning
5.1.2 Association Analysis and Apriori Principle
5.1.3 Association Rule Generation
5.1.4 Case Study of Association Analysis
5.2 Clustering Methods without Labels
5.2.1 Cluster Analysis for Prediction and Forecasting
5.2.2 K-means Clustering for Classification
5.2.3 Agglomerative Hierarchical Clustering
5.2.4 Density-based Clustering
5.3 Dimensionality Reduction and Other Algorithms
5.3.1 Reduce Dimensionality Reduction Methods
5.3.2 Principal Component Analysis (PCA)
5.3.3 Semi-Supervised Machine Learning Methods
5.4 How To Choose Machine Learning Algorithms?
5.4.1 Performance Metrics and Model Fitting
5.4 2 Methods To Reduce Model Overfitting
5.4.3 Methods To Avoid Model Underfitting
5.4.4 Effects of Using Different Loss Functions
5.5 Conclusions, References and Exercises
Chapter 6 Deep Learning with Artificial Neural Networks
6.1 Introduction
6.1.1 Deep Learning Mimics Human Senses
6.1.2 Biological versus Artificial Neurons
6.1.3 Deep Learning versus Shallow Learning
6.2 Artificial Neural Networks
6.2.1 Single Layer Artificial Neural Networks
6.2.2 Multilayer Artificial Neural Network (ANN)
6.2.3 Forward Propagation and Back Propagation in ANN
6.3 Stacked Auto-Encoder and Deep Belief Networks
6.3.1 Auto-Encoder
6.3.2 Stacked Auto-Encoder
6.3.3 Restricted Boltzmann Machine
6.3.4 Deep Belief Networks
6.4 Convolutional Neural Networks (CNN) and Extensions
6.4.1 Convolution in CNN
6.4.2 Pooling in CNN
6.4.3 Deep Convolutional Neural Networks
6.4.4 Other Deep Learning Networks
6.5 Conclusions, References and Exercise
Part 3: Cloud Programming and Analytics Applications
Chapter 7 Programming with Hadoop, Spark and TensorFlow
7.1 Evolution of Scalable Parallel Computing
7.1.1 Characteristic of Scalable Parallel Computing
7.1.2 From MapReduce to Hadoop and Spark
7.1.3 Software Libraries for Big-Data Cloud Applications
7.2 Hadoop Programming with YARN and HDFS
7.2.1 The MapReduce Computing Engine
7.2.2 MapReduce for Parallel Matrix Multiplication
7.2.3 Hadoop Architecture and Recent Extensions
7.2.4 Hadoop Distributed File System (HDFS)
7.2.5 Hadoop YARN for Resource Management
7.3 Spark Core and Resilient Distributed Datasets
7.3.1 Spark Core for General-Purpose Applications
7.3.2 In-Memory Computation and Language Support
7.3.3 Spark Resilient Distributed Datasets (RDDs)
7.4 Spark SQL, Streaming, Machine Learning and GraphX
7.4.1 Spark SQL with Structured Data
7.4.2 Spark Streaming for Live Stream of Data
7.4.3 Spark MLlib for Machine Learning
7.4.4 Spark GraphX for Graph Processing
7.5 TensorFlow for Programming Neural Networks
7.5.1 Google’s TensorFlow Software Platform
7.5.2 Graph Programming Model in TensorFlow Operations
7.5.3 Development Steps of TensorFlow Applications
7.5.4 Image Understanding System on TensorFlow Platform
7.6 Conclusions, References and Exercises
Chapter 8 Machine Learning over Big Data in Healthcare Applications
8.1 Healthcare Problems and Machine Learning Tools
8.1.1 Healthcare and Chronic Disease Problems
8.1.2 Software Libraries for Machine Learning Applications
8.2 IoT-based Healthcare Systems and Applications
8.2.1 IoT Sensing for Body Signals
8.2.2 Healthcare Monitoring System
8.2.3 Physical Exercise Promotion and Smart Clothing
8.2.4 Healthcare Robotics and Mobile Heath Cloud
8.3 Big Data Analytics for Healthcare Applications
8.3.1 Healthcare Big Data Preprocessing
8.3.2 Predictive Analytics for Disease Detection
8.3.3 Performance of 5 Disease Prediction Methods
8.3.4 Mobile Big Data for Disease Control
8.4 Emotion-Control Healthcare Applications
8.4.1 Mental Healthcare System
8.4.2 Emotion-Control Computing and Services
8.4.3 Emotion Interaction through IoT and Clouds
8.4.4 Emotion-Control via Robotics Technologies
8.4.5 A 5G Cloud-Centric Healthcare System
8.5 Conclusions, References and Exercise
Chapter 9 Reinforcement Deep Learning and Social Media Analytics
9.1 Deep Learning Systems and Social Media Industry
9.1.1 Deep Learning Systems and Software Support
9.1.2 Reinforcement Learning Principles
9.1.3 Social Media Industry and Global Impact
9.2 Text and Image Recognition using ANN and CNN
9.2.1 Numeral Recognition using TensorFlow for ANN
9.2.2 Numeral Recognition Using Convolutional Neural Network
9.2.3 Convolutional Neural Networks for Face Recognition
9.2.4 Medical Text Analytics by Convolutional Neural Networks
9.3 DeepMind with Reinforcement Deep Learning
9.3.1 Google DeepMind AI Programs
9.3.2 Reinforcement Deep Learning Algorithms
9.3.3 Google AlphaGo Game Competition
9.3.4 Flappybird Game Using Reinforcement Learning
9.4 Data Analytics for Social-Media Applications
9.4.1 Big data in Social-Media Applications
9.4.2 Social Networks and Graph Analytics
9.4.3 Predictive Analytics Software Tools
9.4.4 Community Detection in Social Networks
9.5 Conclusions, References and Exercise
Subject Index