Data Science and Big Data Analytics in Smart Environments

✍ Scribed by Marta Chinnici (editor), Florin Pop (editor), Catalin Negru (editor)

• Publisher: CRC Press
• Year: 2021
• Tongue: English
• Leaves: 305
• Edition: 1
• Category: Library

✦ Synopsis

Most applications generate large datasets, like social networking and social influence programs, smart cities applications, smart house environments, Cloud applications, public web sites, scientific experiments and simulations, data warehouse, monitoring platforms, and e-government services. Data grows rapidly, since applications produce continuously increasing volumes of both unstructured and structured data. Large-scale interconnected systems aim to aggregate and efficiently exploit the power of widely distributed resources. In this context, major solutions for scalability, mobility, reliability, fault tolerance and security are required to achieve high performance and to create a smart environment. The impact on data processing, transfer and storage is the need to re-evaluate the approaches and solutions to better answer the user needs. A variety of solutions for specific applications and platforms exist so a thorough and systematic analysis of existing solutions for data science, data analytics, methods and algorithms used in Big Data processing and storage environments is significant in designing and implementing a smart environment.

Fundamental issues pertaining to smart environments (smart cities, ambient assisted leaving, smart houses, green houses, cyber physical systems, etc.) are reviewed. Most of the current efforts still do not adequately address the heterogeneity of different distributed systems, the interoperability between them, and the systems resilience. This book will primarily encompass practical approaches that promote research in all aspects of data processing, data analytics, data processing in different type of systems: Cluster Computing, Grid Computing, Peer-to-Peer, Cloud/Edge/Fog Computing, all involving elements of heterogeneity, having a large variety of tools and software to manage them. The main role of resource management techniques in this domain is to create the suitable frameworks for development of applications and deployment in smart environments, with respect to high performance. The book focuses on topics covering algorithms, architectures, management models, high performance computing techniques and large-scale distributed systems.

✦ Table of Contents

Cover
Title Page
Copyright Page
Preface
Contents
1. Mobility-Aware Solutions for Edge Data Center Deployment in Urban Environments
1.1 Introduction
1.2 Background and motivation
1.2.1 Related works
1.2.2 Simulation and emulation platforms for fog and edge environments
1.2.3 The impact of human mobility and scalability in realistic urban environments
1.3 Modeling human mobility in urban environments
1.3.1 The P-MOB mobility model
1.3.2 The D-MOB mobility model
1.4 The A-MOB mobility model
1.5 Modeling MEC scenario for data center deployment in urban environments
1.5.1 Modeling MEC components
1.5.1.1 Problem formulation
1.5.2 Accounting for energy consumption
1.5.2.1 Network components
1.5.2.2 EDCs
1.6 EDCs deployment policies
1.6.1 Distributed Deployment Algorithm (DDA)
1.6.2 Mobility-aware Deployment Algorithm (MDA)
1.6.3 Energy-efficient Mobility-aware Deployment Algorithm (EMDA)
1.6.4 Allocation of servers among EDCs
1.7 The simulator: CrowdEdgeSim
1.8 MEC scenario
1.9 Urban mobility
1.10 Mobile devices
1.11 Communications
1.12 MEC deployment
1.13 Simulator engine
1.14 Results
1.15 Performance evaluation
1.15.1 Evaluation settings
1.16 City layout and mobility model
1.17 MEC scenario and communications
1.18 Mobile applications
1.18.1 Synthetic applications
1.18.2 Application based on real traces
1.18.3 Results
1.19 Smart device activities and EDC deployment
1.20 Outage assessment
1.21 Energy assessment
1.22 Conclusions
2. Effective Data Assimilation with Machine Learning
2.1 Introduction
2.1.1 Related works and novelty of the presented approach
2.2 Data assimilation
2.3 Reduced space
2.4 Effective data assimilation with machine learning
2.5 Testing and results
2.6 Conclusions
3. Semantic Data Model for Energy Efficient Integration of Data Centres in Energy Grids
3.1 Introduction
3.2 Related work
3.3 Modeling assumptions
3.4 DC internal data model
3.4.1 Hardware components ontology
3.4.2 Energy efficiency actions ontology
3.4.3 Energy efficiency indicators ontology
3.5 DC external data model
3.6 Model usage in data driven operations
3.6.1 Modelling the DC infrastructure
3.6.2 Semantic annotation of monitored data
3.6.3 Assessing the DC operation efficiency
3.7 Conclusions
4. Managing the Safety in Smart Buildings using Semantically-Enriched BIM and Occupancy Data Approach
4.1 Introduction
4.2 Background
4.3 Proposed system
4.3.1 Capturing the occupancy data
4.3.2 Preprocessing the occupancy data
4.3.3 Semantic enrichment and storing the occupancy data
4.3.4 Modeling occupancy behaviors
4.3.5 Visualizing the classified occupancy behaviors
4.4 Discussion
4.5 Conclusion
5. Belief Rule-Based Adaptive Particle Swarm Optimization
5.1 Introduction
5.2 Belief Rule Based Expert System (BRBES)
5.2.1 Domain knowledge representation in BRBES
5.2.2 BRB inference procedures
5.2.2.1 Input transformation
5.2.2.2 Rule activation weight calculation
5.2.2.3 Belief update
5.2.2.4 Rule aggregation using Evidential Reasoning (ER)
5.3 Particle Swarm Optimization (PSO)
5.4 Belief Rule Based Adaptive Particle Swarm Optimization (BRBAPSO)
5.5 Results and analysis
5.6 Conclusion
6. NoSQL Environments and Big Data Analytics for Time Series
6.1 Introduction
6.2 Time series analysis
6.2.1 Understanding time series
6.2.2 Time series forecasting
6.2.2.1 Regression models
6.2.2.2 Support vector machine
6.2.2.3 Artificial neural network architectures
6.2.3 Time series outlier detection
6.2.4 Time series change point detection
6.3 NoSQL databases
6.3.1 Transaction properties
6.3.2 CAP theorem
6.3.3 Distributed database architectures
6.3.3.1 Replications methods
6.3.3.2 Data partitioning methods
6.3.4 Types of data
6.4 NoSQL time series database
6.4.1 InfluxDB
6.4.1.1 Architecture
6.4.1.2 Data model
6.4.2 Kdb+
6.4.2.1 Architecture
6.4.2.2 Data model
6.4.3 Prometheus
6.4.3.1 Architecture
6.4.3.2 Data model
6.4.4 OpenTSDB
6.4.4.1 Architecture
6.4.4.2 Data model
6.4.5 TimescaleDB
6.4.5.1 Architecture
6.4.5.2 Data model
6.4.6 Comparison
6.5 Big data environment for time series
6.6 Conclusions
7. A Territorial Intelligence-based Approach for Smart Emergency Planning
7.1 Introduction
7.2 From GeoSpatial big data to territorial intelligence
7.2.1 Geospatial big data
7.2.2 Spatial data analytics
7.2.3 GeoVisual analytics
7.2.4 Geospatial business intelligence and spatial data science
7.2.4.1 Geospatial business intelligence
7.2.4.2 Spatial data science
7.2.5 Territorial intelligence
7.3 Smart planning for risk management
7.4 A spatial decision support system for risk management
7.4.1 The emergency planning
7.4.2 A SDSS for the emergency planning
7.4.2.1 Macro-phase 1
7.4.2.2 Macro-phase 2
7.4.2.3 Macro-Phase 3
7.5 Conclusion
8. Big Data Analysis and Applications for Energy Performant Buildings and Smart Cities
8.1 Introduction
8.2 Which data are collected and integrated to guide decision making
8.3 Building data services: stakeholder engagement and value for users
8.4 Examples of integrated building data services
8.5 Towards more dynamic and automated collection of data on buildings
8.6 Conclusions
9. Selecting Suitable Plants for a Given Area using Data Analysis Approaches
9.1 Introduction
9.2 Related work
9.3 Materials and methods
9.3.1 Data collection
9.3.2 Data processing
9.3.3 Data inclusion criteria
9.3.4 Algorithms
9.3.5 Data and statistical analysis
9.4 Results
9.4.1 Area clustering
9.4.2 Selecting attributes
9.4.3 Multivariate analysis of species
9.4.4 Species clustering
9.4.5 Classification
9.4.5.1 Using full training set
9.4.5.2 Cross-validation with 10 folds
9.4.5.3 Percentage split
Section I: Title
9.5 Discussion
9.6 Conclusion
10. Ontology-Based Security Requirements Framework for Current and Future Vehicles
10.1 Introduction
10.2 Overview
10.2.1 Safety in the automotive domain
10.2.2 Autonomous vehicles
10.2.3 Cybersecurity in the automotive domain
10.3 Approach
10.4 The structure of the ontology-based security framework
10.4.1 Data digesting
10.4.2 Ontology mediator
10.4.2.1 Vocabulary
10.4.2.2 Taxonomy
10.4.2.3 Ontology
10.4.3 Model checker
10.4.4 Security validation
10.4.5 Gap analysis
10.4.6 Security enhancement
10.5 Application fields for the proposed model
10.6 Conclusions
11. Dynamic Resource Provisioning using Cognitive Intelligent Networks based on Stochastic Markov Decision Process
11.1 Introduction
11.1.1 Problem domain
11.1.2 Markov decision processes
11.2 Reward function and the optimal policy
11.3 Q-Learning technique
11.4 Multi-Objective Reinforcement Learning (MORL)
11.5 Single-policy MORL
11.6 Multi-policy MORL
11.7 Case study—communication network subject to an interference attack
11.8 Conclusions
12. Data Model for Water Resource Management
12.1 Introduction
12.2 Related work
12.2.1 Data models
12.2.2 Datasets for water management
12.2.3 Existing technologies
12.3 Proposed architecture
12.3.1 High level architecture
12.3.2 Data ingestion module
12.3.3 Data processing model
12.3.4 Data visualization
12.4 Examples of real-life utilizations
12.4.1 Flooding alerts
12.4.2 Helping water resource managers
12.5 Implementation details
12.5.1 Implementation of the data ingestion module
12.5.2 Implementation of the processing model
12.6 Experimental results
12.6.1 Analysis of experimental results
12.7 Conclusions and future work
References
Index