Al-Turjman Smart Cities Performability, Cognition, & Security

1. Auflage 2019
ISBN: 978-3-030-14718-1
Verlag: Springer International Publishing
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 248 Seiten

Reihe: EAI/Springer Innovations in Communication and Computing

This book provides knowledge into the intelligence and security areas of smart-city paradigms. It focuses on connected computing devices, mechanical and digital machines, objects, and/or people that are provided with unique identifiers. The authors discuss the ability to transmit data over a wireless network without requiring human-to-human or human-to-computer interaction via secure/intelligent methods. The authors also provide a strong foundation for researchers to advance further in the assessment domain of these topics in the IoT era. The aim of this book is hence to focus on both the design and implementation aspects of the intelligence and security approaches in smart city applications that are enabled and supported by the IoT paradigms. Presents research related to cognitive computing and secured telecommunication paradigms;Discusses development of intelligent outdoor monitoring systems via wireless sensing technologies;
With contributions from researchers, scientists, engineers and practitioners in telecommunication and smart cities.



Prof. Dr. FADI AL-TURJMAN received his Ph.D. degree in computer science from Queen's University, Canada, in 2011. He is a Professor with Antalya Bilim University, Turkey. He is a leading authority in the areas of smart/cognitive, wireless and mobile networks' architectures, protocols, deployments, and performance evaluation. His record spans over 180 publications in journals, conferences, patents, books, and book chapters, in addition to numerous keynotes and plenary talks at flagship venues. He has authored/edited more than 10 books about cognition, security, and wireless sensor networks' deployments in smart environments with Taylor & Francis, and the Springer (Top tier publishers in the area). He was a recipient of several recognitions and best papers' awards at top international conferences. He led a number of international symposia and workshops in flag-ship ComSoc conferences. He is serving as the Lead Guest Editor in several journals, including the IET Wireless Sensor Systems and Sensors (MDPI and Wiley). He is also the Publication Chair for the IEEE International Conference on Local Computer Networks.

Autoren/Hrsg.

Al-Turjman, Fadi

Inhaltsverzeichnis

1;Preface;7
2;Contents;8
3;About the Editor;10
4;1 An Effective Design for Polar Codes over Multipath Fading Channels;11
4.1;1.1 Introduction;11
4.2;1.2 System Model and Preliminaries;14
4.3;1.3 Proposed Transceiver Design;17
4.4;1.4 Simulation Results;19
4.5;1.5 Conclusion;23
4.6;References;24
5;2 LearningCity: Knowledge Generation for Smart Cities;26
5.1;2.1 Introduction;26
5.2;2.2 Previous Work;29
5.3;2.3 Data Annotation in Smart Cities: Challenges;31
5.3.1;2.3.1 Use Cases;33
5.4;2.4 Architecture;34
5.5;2.5 Implementation;35
5.5.1;2.5.1 Communication and Frameworks Used;36
5.5.2;2.5.2 Machine-Learning Frameworks;36
5.5.3;2.5.3 Knowledge Warehouse;37
5.5.4;2.5.4 End-User Interfaces and Integration with Existing Tools;38
5.6;2.6 Results and Discussion;41
5.7;2.7 Conclusions and Future Work;47
5.8;References;48
6;3 Deep Reinforcement Learning Paradigm for Dense Wireless Networks in Smart Cities;51
6.1;3.1 Introduction;51
6.1.1;3.1.1 Motivation;51
6.1.2;3.1.2 Scope of the Chapter;52
6.1.3;3.1.3 Contributions of the Chapter;53
6.2;3.2 Preliminaries;53
6.2.1;3.2.1 IEEE 802.11ax High Efficiency WLAN (HEW);54
6.2.2;3.2.2 MAC Layer Resource Allocation in IEEE 802.11 Wireless Networks;55
6.2.2.1;3.2.2.1 MAC Layer Coordination Functions;56
6.2.3;3.2.3 Problem Statement;58
6.3;3.3 Deep Reinforcement Learning Paradigm;60
6.3.1;3.3.1 Deep Reinforcement Learning;60
6.3.2;3.3.2 Q-Learning as a MAC-RA Paradigm;62
6.3.2.1;3.3.2.1 Q-Learning Algorithm;62
6.3.2.2;3.3.2.2 Scope and Limitations of QL;64
6.4;3.4 Intelligent Q-Learning-Based Resource Allocation (iQRA);64
6.4.1;3.4.1 Channel Observation-Based Scaled Backoff (COSB) Mechanism;65
6.4.2;3.4.2 *10pt;67
6.5;3.5 Performance Evaluation;70
6.5.1;3.5.1 Simulation Scenarios and Parameters;70
6.5.2;3.5.2 Throughput;72
6.5.3;3.5.3 Average Channel Access Delay;72
6.5.4;3.5.4 Fairness;73
6.5.5;3.5.5 Network Dynamicity;74
6.5.6;3.5.6 Distance-Based Rate Adaptation Models;75
6.6;3.6 Conclusion;76
6.7;Appendix: SCI/SCIE Journal Publications Related to the Chapter;77
6.8;References;77
7;4 Energy Demand Forecasting Using Deep Learning;79
7.1;Introduction to Machine Learning;79
7.2;Artificial Neural Network;83
7.2.1;Learning Process in ANN;86
7.2.2;Deep ANN;90
7.2.3;Recurrent Neural Network;90
7.2.4;Deep LSTM RNN;94
7.3;Modeling Time Series Events;95
7.3.1;Time Series Decomposition Procedure;96
7.3.2;Energy Demand Analysis by Time Series Decomposition;97
7.3.3;Energy Demand Forecasting Using Decomposed Series;100
7.4;LSTM Deep Learning Model for Energy Demand Prediction;101
7.4.1;Autoencoder Deep Neural Network;104
7.4.2;Training Process of LSTM Deep Learning Model;104
7.4.3;Evaluation Process of the LSTM Deep Learning Model;106
7.4.4;Testing Process of the LSTM Deep Learning Model;107
7.4.5;Deep Learning Model as a Cloud Solution for Smart Cities;108
7.5;References;110
8;5 RETRACTED CHAPTER: Context-Aware Location Recommendations for Smart Cities;113
8.1;Abbreviations;113
8.2;Introduction;113
8.3;Existing Frameworks;115
8.4;Proposed Work;116
8.5;Discussion;120
8.6;Conclusion;120
8.7;References;121
9;6 Fractional Derivatives for Edge Detection: Application to Road Obstacles;123
9.1;Introduction;123
9.2;Overview of the Fractional Calculus;125
9.3;Edge Detection Techniques;126
9.3.1;Conventional Methods;127
9.3.2;Fractional Methods Implementation;129
9.4;Road Obstacle Detection;136
9.5;Results Discussion;139
9.6;Applications;141
9.7;Conclusion and Future Work;142
9.8;References;142
10;7 Machine Learning Parameter Estimation in a Smart-City Paradigm for the Medical Field;146
10.1;Introduction;146
10.2;Methodology;148
10.3;Gaussian Mixture Model;149
10.3.1;Maximum Likelihood Parameter Estimation;149
10.3.2;Expectation Maximization Algorithm;150
10.4;Support Vector Machine;152
10.5;Results and Discussion;152
10.5.1;Classifier Performance;152
10.5.2;Contingency Table;153
10.6;Conclusion;156
10.7;References;156
11;8 Open Source Tools for Machine Learning with Big Data in Smart Cities;159
11.1;Introduction;159
11.2;Big Data;160
11.3;Machine Learning in Big Data;161
11.3.1;Supervised Learning Algorithms;162
11.3.2;Unsupervised Learning Algorithms;162
11.3.3;Semi-supervised Learning Algorithms;162
11.3.4;Data Availability;163
11.3.5;Batch Learning;163
11.3.6;Online Learning;163
11.4;Open Source Tools for Big Data;164
11.4.1;Hadoop Ecosystem;164
11.4.1.1;Storage Layer;165
11.4.1.2;Processing Layer;166
11.4.1.3;Management Layer;169
11.4.2;Machine Learning Toolkits;169
11.4.2.1;Mahout;170
11.4.2.2;MLLib;170
11.4.2.3;H2O;170
11.4.2.4;Samoa;170
11.4.3;Data Movement and Integration Tools;171
11.4.3.1;Kafka;171
11.4.3.2;Flume;171
11.4.3.3;Sqoop;171
11.4.3.4;Hive;171
11.5;Open Research Issues;172
11.6;Conclusion;173
11.7;References;173
12;9 Identity Verification Using Biometrics in Smart-Cities;175
12.1;Acronyms;175
12.2;Introduction;175
12.3;Highlights of the Current Approach;177
12.3.1;Potential Benefits of Utilizing Periocular Region as a Useful Biometric Trait;177
12.3.2;Potential Periocular Sub-Region;178
12.3.3;Computationally Efficient Variation of LBP;180
12.3.4;Bit-Plane Representation of the Original Image;180
12.4;Feature Extraction Using Dominant Bit-Plane LBP;181
12.4.1;Segmentation of LCPR;181
12.4.2;Construction of Dominant Bit-Plane;184
12.4.2.1;Bit-Plane 5 Selection Justification Using Structural Similarity Index;186
12.4.2.2;Bit-Plane 5 Selection Justification Using Texture Information;187
12.4.3;Dominant Bit-Plane LBP Feature Extraction Using Radial Filters;189
12.4.4;Determination of Dominant Bit-Plane LBP Feature Vectors;192
12.5;Experiments;195
12.5.1;Experimental Datasets;195
12.5.1.1;UBIRISv2 Dataset;196
12.5.1.2;High Resolution Images;196
12.5.1.3;Low Resolution Images;197
12.5.2;Results and Discussion;198
12.5.2.1;Experimental Validation of Dominant Bit-Plane;198
12.5.2.2;Authentication Accuracies;199
12.5.2.3;Comparison of Entire Face, Periocular Region, and LCPR Using DB-LBP;201
12.6;Conclusion;203
12.7;References;203
13;10 Network Analysis of Dark Web Traffic Through the Geo-Location of South African IP Address Space;206
13.1;Introduction;206
13.2;Related Research;207
13.2.1;Step 1: Finding the Anonymity Set;208
13.3;Anonymous Network Communication Systems;209
13.4;The Deep and Dark Web Defined;210
13.5;Accessing and Navigating the Dark Web;211
13.6;What Are the Uses of the Dark Web?;212
13.7;The Impact of Anonymous Communication Networks on Cyber Security in Smart Cities;212
13.8;Research Methodology;213
13.9;Research Question;213
13.10;Research Taxonomy;213
13.11;Experiment Design;214
13.11.1;Configuration of a Private TOR Network;216
13.11.2;Network Layout;216
13.12;TOR Configuration;216
13.13;Data Collection Methodology;217
13.14;Results;217
13.14.1;TOR Usage;217
13.15;Final Observation;218
13.16;Conclusion;222
13.17;References;223
14;11 LBCLCT: Location Based Cross Language Cipher Technique;225
14.1;Nomenclature;225
14.2;Introduction;226
14.2.1;Infrastructure as a Service;226
14.2.2;Platform as a Service;226
14.2.3;Software as a Service;226
14.2.4;Deployment Models for Cloud Architecture Solution;227
14.2.4.1;Private Cloud;227
14.2.4.2;Community Cloud;227
14.2.4.3;Public Cloud;227
14.2.4.4;Hybrid Cloud;227
14.2.5;Cryptography;228
14.3;Literature Survey;228
14.4;Methodology Adopted;230
14.4.1;Encryption Using Affine Cipher;230
14.4.2;Encryption Using Rail Fence Cipher;230
14.4.3;Translation Mapping;231
14.4.4;Proposed Algorithms/Pseudocode;231
14.5;Simulation and Result;234
14.6;Conclusion and Future Scope;236
14.7;References;237
15;Retraction Note to: Context-Aware Location Recommendations for Smart Cities;239
16;Index;240