Big data analytics for sensor-network collected intelligence / edited by Hui-Huang Hsu, Chuan-Yu Chang, and Ching-Hsien Hsu.
Series: Intelligent data centric systemsPublisher: London, United Kingdom : Academic Press, an imprint of Elsevier, [2017]Copyright date: ©2017Description: xx, 306 pages : illustrations ; 24 cmISBN:- 9780128093931
- 0128093935
- 23 005.7 BIG
Item type | Current library | Call number | Copy number | Status | Date due | Barcode |
---|---|---|---|---|---|---|
Book Closed Access | Engineering Library | 005.7 BIG 1 (Browse shelf(Opens below)) | 1 | Available | BUML24010363 |
CONTENTS
Part. I BIG DATA ARCHITECTURE AND PLATFORM
Chapter 1 Big Data: A Classification of Acquisition and Generation Methods
1.Big Data: A Classification
1.1.Characteristics of Big Data
2.Big Data Generation Methods
2.1.Data Sources
2.2.Data Types
3.Big Data: Data Acquisition Methods
3.1.Interface Methods
3.2.Interface Devices
4.Big Data: Data Management
4.1.Data Representation and Organization
4.2.Databases
4.3.Data Fusion and Data Integration
5.Summary
Chapter. 2 Cloud Computing Infrastructure for Data Intensive Applications
1.Introduction
2.Big Data Nature and Definition
2.1.Big Data in Science and Industry
2.2.Big Data and Social Network/Data
2.3.Big Data Technology Definition: From 6V to 5 Parts
3.Big Data and Paradigm Change
3.1.Big Data Ecosystem
3.2.New Features of the BDI
3.3.Moving to Data-Centric Models and Technologies
4.Big Data Architecture Framework and Components
4.1.Defining the Big Data Architecture Framework
4.2.Data Management and Big Data Lifecycle
4.3.Data Structures and Data Models for Big Data
4.4.NIST Big Data Reference Architecture
4.5.General Big Data System Requirements
5.Big Data Infrastructure
5.1.BDI Components
5.2.Big Data Stack Components and Technologies
5.3.Example of Cloud-Based Infrastructure for Distributed Data Processing
5.4.Benefits of Cloud Platforms for Big Data Applications
6.Case Study: Bioinformatics Applications Deployment on Cloud
6.1.Overall Description
6.2.UC1 -- Securing Human Biomedical Data
6.3.UC2 -- Cloud Virtual Pipeline for Microbial Genomes Analysis
6.4.Implementation of Use Cases and CYCLONE Infrastructure Components
7.CYCLONE Platform for Cloud Applications Deployment and Management
7.1.General Architecture for Intercloud and Multicloud Applications Deployment
7.2.Ensuring Consistent Security Services in Cloud-Based Applications
7.3.Dynamic Access Control Infrastructure
8.Cloud Powered Big Data Applications Development and Deployment Automation
8.1.Demand for Automated Big Data Applications Provisioning
8.2.Cloud Automation Tools for Intercloud Application and Network Infrastructure Provisioning
8.3.Slipstream: Cloud Application Management Platform
9.Big Data Service and Platform Providers
9.1.Amazon Web Services and Elastic MapReduce
9.2.Microsoft Azure Analytics Platform System and HDInsight
9.3.IBM Big Data Analytics and Information Management
9.4.Cloudera
9.5.Pentaho
9.6.LexisNexis HPCC Systems as an Integrated Open Source Platform for Big Data Analytics
10.Conclusion
Chapter. 3 Open Source Private Cloud Platforms for Big Data
1.Cloud Computing and Big Data as a Service
1.1.Public Cloud Infrastructure
1.2.Advantages of the Cloud for Big Data
2.On-Premise Private Clouds for Big Data
2.1.Security of Cloud Computing Systems
2.2.Advantages of On-Premise Private Clouds
3.Introduction to Selected Open Source Cloud Environments
3.1.OpenNebula
3.2.Eucalyptus
3.3.Apache CloudStack
3.4.OpenStack
4.Heterogeneous Computing in the Cloud
4.1.Exclusive Mode
4.2.Sharing Mode
5.Case Study: The EMS, an On-Premise Private Cloud
6.Conclusion Part . II BIG DATA PROCESSING AND MANAGEMENT
Chapter . 4 Efficient Nonlinear Regression-Based Compression of Big Sensing Data on Cloud
1.Introduction
1.1.Motivation
1.2.Organization of the Chapter
2.Related Work and Problem Analysis
2.1.Related Work
2.2.Problem Analysis: Real-World Requirements for Nonlinear Regression
3.Temporal Compression Model Based on Nonlinear Regression
3.1.Nonlinear Regression Prediction Model
4.Algorithms
4.1.Algorithm for Nonlinear Regression
4.2.Nonlinear Regression Compression Algorithm Based on MapReduce
5.Experiments
5.1.Experiment Environment and Process
5.2.Experiment for the Compression With Nonlinear Regression
5.3.Experiment for Data Loss and Accuracy
6.Conclusions and Future Work
Chapter. 5 Big Data Management on Wireless Sensor Networks
1.Introduction
2.Data Management on WSNs
2.1.Storage
2.2.Query Processing
2.3.Data Collection
3.Big Data Tools
3.1.File System
3.2.Batch Processing
3.3.Streaming Data Processing
4.Put It Together: Big Data Management Architecture
4.1.Batch Layer
4.2.Serving Layer
4.3.Speed Layer
5.Big Data Management on WSNs
5.1.In-Network Aggregation Techniques and Data Integration Components
5.2.Exploiting Big Data Systems as Data Centers
6.Conclusion -- References -- Glossary
Chapter . 6 Extreme Learning Machine and Its Applications in Big Data Processing
1.Introduction
1.1.Background
1.2.Artificial Neural Networks
1.3.Era of Big Data
1.4.Organization
2.Extreme Learning Machine
2.1.Traditional Approaches to Train ANNs
2.2.Theories of the Extreme Learning Machine
2.3.Classical ELM
2.4.ELM for Classification and Regression
2.5.ELM for Unsupervised Learning
3.Improved Extreme Learning Machine With Big Data
3.1.Shortcomings of the Extreme Learning Machine for Processing Big Data
3.2.Optimization Strategies for the Traditional Extreme Learning Machine
3.3.Efficiency Improvement for Big Data
3.4.Parallel Extreme Learning Machine Based on MapReduce
3.5.Parallel Extreme Learning Machine Based on Apache Spark
4.Applications
4.1.ELM in Predicting Protein Structure
4.2.ELM in Image Processing
4.3.ELM in Cancer Diagnosis
4.4.ELM in Big Data Security and Privacy
5.Conclusion -- References -- Glossary
Part . III BIG DATA ANALYTICS AND SERVICES
Chapter. 7 Spatial Big Data Analytics for Cellular Communication Systems
1.Introduction
2.Cellular Communications and Generated Data
3.Spatial Big Data Analytics
3.1.Statistical Foundation for Spatial Big Data Analytics
3.2.Spatial Pattern Mining From Spatial Big Data Analytics
4.Typical Applications
4.1.BS Behavior Understanding Through Spatial Big Data Analytics
4.2.User Behavior Understanding Through Spatial Big Data Analytics
5.Conclusion and Future Challenging Issues -- Acknowledgments -- References -- Glossary
Chapter . 8 Cognitive Applications and Their Supporting Architecture for Smart Cities
1.Introduction
2.CSE for Smart City Applications
2.1.Architecture Specification
2.2.Big Data Analysis and Management
3.Anomaly Detection in Smart City Management
3.1.Related Work to Anomaly Detection
3.2.Challenges and Benefits of Anomaly Detection in Smart Cities
4.Functional Region and Socio-Demographic Regional Patterns Detection in Cities
4.1.Discovering Functional Regions
4.2.Deep Learning and Regional Pattern Detections
5.Summary -- References -- Glossary
Chapter. 9 Deep Learning for Human Activity Recognition
1.Introduction
2.Motivations and Related Work
3.Convolutional Neural Networks in HAR
1.Temporal Convolution and Pooling
3.2.Architecture -- 3.3.Analysis
4.Experiments, Results, and Discussion
4.1.Experiment on OAR Dataset
4.2.Experiment on Hand Gesture Dataset
4.3.Experiment on REALDISP Dataset
4.4.Computational Requirements
4.5.Future Directions
5.Conclusion -- References -- Glossary
Chapter. 10 Neonatal Cry Analysis and Categorization System Via Directed Acyclic Graph Support Vector Machine
1.Introduction
2.Neonatal Cry Analysis and Categorization System
2.1.Cry Signal Preprocessing
2.2.Feature Extraction -- Essential Features
2.3.Selection of Features
2.4.Categorization and Validation
3.Experimental Results and Discussion
3.1.Environment of the Experiments
3.2.Experiment 1: Neonatal Cry Analysis and Categorization -- Employing 15 Extracted Features
3.3.Experiment 2: Neonatal Cry Analysis and Categorization -- Deploying the Selected Four Features
3.4.Experiment 3: Comparison of Neonatal Cry Analysis and Categorization Between Male and Female Babies
3.5.Experiment 4: Comparison of Proposed System With Y. Abdulaziz's Approach
4.Conclusion -- Acknowledgment -- References
Part . IV BIG DATA INTELLIGENCE AND INFORMATION SYSTEMS
Chapter. 11 Smart Building Applications and Information System Hardware Co-Design
1.Smart Building Applications
1.1.The Ever-Increasing Need for Smart Buildings
1.2.Smart Building Applications
2.Emerging Information System Hardware
2.1.Overview
2.2.Examples
3.Big Data Application and Information Hardware Co-Design
3.1.Motivation and Challenge
3.2.Case Study and Discussion
Chapter. 12 Smart Sensor Networks for Building Safety
1.Introduction
2.Related Works
3.Background: Modal Analysis
3.1.Modal Parameters
3.2.The ERA
4.Distributed Modal Analysis
4.1.Stage 1: Try to Distribute the Initial Stage of Modal Analysis Algorithms
4.2.Stage 2: Divide and Conquer
5.A Multiscale SHM Using Cloud
6.Conclusion -- Acknowledgments
Chapter. 13 The Internet of Things and Its Applications
1.Introduction
2.Collection of Big Data From IoT
2.1.MQ Telemetry Transport
2.2.Constrained Application Protocol
2.3.MQTT vs. CoAP
3.IoT Analytics 3
3.1.Related Works
3.2.Outlier Detection for Big Data
3.3.Island-Based Cloud GA
4.Examples of IoT Applications
4.1.Applications on Intelligent Transportation Systems
4.2.Applications on Intelligent Manufacturing Systems
5.Conclusions
Chapter. 14 Smart Railway Based on the Internet of Things
1.Introduction
2.Architecture of the Smart Railway
2.1.Overview
2.2.Perception and Action Layer
2.3.Transfer Layer
2.4.Data Engine Layer
2.5.Application Layer
3.IRIS for Smart Railways
3.1.Rail Defects
3.2.The State-of-the-Art for Rail Inspection
Includes bibliographical references and index P. 299-306
There are no comments on this title.