Machine Learning Modeling for IoUT Networks: Internet of Underwater Things (SpringerBriefs in Computer Science)

✍ Scribed by Ahmad A. Aziz El-Banna, Kaishun Wu

• Publisher: Springer
• Year: 2021
• Tongue: English
• Leaves: 71
• Category: Library

✦ Synopsis

This book discusses how machine learning and the Internet of Things (IoT) are playing a part in smart control of underwater environments, known as Internet of Underwater Things (IoUT). The authors first present seawater’s key physical variables and go on to discuss opportunistic transmission, localization and positioning, machine learning modeling for underwater communication, and ongoing challenges in the field. In addition, the authors present applications of machine learning techniques for opportunistic communication and underwater localization. They also discuss the current challenges of machine learning modeling of underwater communication from two communication engineering and data science perspectives.

✦ Table of Contents

Preface
Contents
Acronyms
1 Introduction to Underwater Communication and IoUT Networks
1.1 Underwater Communication
1.2 IoUT Network and Node Structure
1.2.1 Network Architecture
1.2.2 Sensor Node Architecture
1.3 Machine Learning Modeling for Underwater Communication
References
2 Seawater's Key Physical Variables
2.1 Key Physical Variables (KPVs)
2.1.1 Temperature
2.1.2 Salinity
2.1.3 Pressure
2.1.4 Density
2.1.5 pH
2.1.6 Internal Waves
2.1.7 Conductivity
2.1.8 KPV Interrelationships
References
3 Opportunistic Transmission in IoUT Networks
3.1 Underwater Communication
3.1.1 Channel Model
3.1.2 Transmission System Analysis
3.2 Confidence Metric
3.2.1 Derivations of the Confidence Metric
3.2.2 TPL Control and Adaptive Modulation
3.2.3 Employing the Confidence Metric in the Transmission Framework
3.3 Performance Analysis
References
4 Localization and Positioning for Underwater Networks
4.1 Introduction
4.2 System Modeling Using TDoA
4.3 TDoA-Based Positioning Approach
4.4 System Modeling Using RSS Method
4.5 RSS Positioning Approach
References
5 ML: Modeling for Underwater Communication in IoUT Systems
5.1 Classification for Transmission Methods
5.2 Dynamic Modeling Using Neural Networks for Position Prediction
5.3 Performance Evaluation
5.3.1 Dataset and Preprocessing
5.3.2 Training and Evaluating the DyNets
References
6 Open Challenges for IoUT Networks
6.1 Communication Challenges
6.1.1 Media Characteristics
6.1.2 Underwater Channel Modeling
6.1.3 Complexity of the Hardware and Other Combined Technologies
6.2 ML Challenges
6.2.1 Datasets Availability
6.2.2 Problem Formulation and Model Selection
6.2.3 Feasibility of Online Learning
6.2.4 Reduced Computational Complexity Models
References
Index