Machine Learning-Based Prediction of Node Localization Accuracy in IIoT-Based MI-UWSNs and Design of a TD Coil for Omnidirectional Communication

Abstract

This study aims to realize Sustainable Development Goals (SDGs), i.e., SDG 9: Industry Innovation and Infrastructure and SDG 14: Life below Water, through the improvement of localization estimation accuracy in magneto-inductive underwater wireless sensor networks (MI-UWSNs). The accurate localization of sensor nodes in MI communication can effectively be utilized for industrial IoT applications, e.g., underwater gas and oil pipeline monitoring, and in other important underwater IoT applications, e.g., smart monitoring of sea animals, etc. The most-feasible technology for medium- and short-range communication in IIoT-based UWSNs is MI communication. To improve underwater communication, this paper presents a machine learning-based prediction of localization estimation accuracy of randomly deployed sensor Rx nodes through anchor Tx nodes in the MI-UWSNs. For the training of ML models, extensive simulations have been performed to create two separate datasets for the two configurations of excitation current provided to the Tri-directional (TD) coils, i.e., configuration1-case1_configuration2-case1 (c1c1_c2c1) and configuration1-case2_configuration2-case2 (c1c2_c2c2). Two ML models have been created for each case. The accuracies of both models lie between 95% and 97%. The prediction results have been validated by both the test dataset and verified simulation results. The other important contribution of this paper is the development of a novel assembling technique of a MI-TD coil to achieve an approximate omnidirectional magnetic flux around the communicating coils, which, in turn, will improve the localization accuracy of the Rx nodes in IIoT-based MI-UWSNs.

Machine Learning Assists IoT Localization: A Review of Current Challenges and Future Trends

“…Gang et al investigated the relationship between underwater communication IoT-based UWSNs and the united nations’ Sustainable Development Goals (SDGs) [ 63 ].…”

Applied Machine Learning for IIoT and Smart Production—Methods to Improve Production Quality, Safety and Sustainability

“…LOS/NLOS classification is shown in [ 97 ] for the less-common IEEE 802.15.4 systems, using SVM, random forests and neural networks. In [ 98 ], acoustic localization technology was employed in an IIoT underwater wireless sensor network, and linear regression was applied to predict the accuracy of node localization.…”

An Edge Computing-Based Preventive Framework With Machine Learning- Integration for Anomaly Detection and Risk Management in Maritime Wireless Communications

“…By offering a distributed computing architecture, edge computing has the ability to enhance the environment of marine communication and makes it more extensive and decentralized [24], [25], [26], [27]. In MWC, machine learning models can be implemented for risk management and anomaly detection [28], [29], [30]. Isolation Forests (IF) [1], One-Class Support Vector Machine (SVM) [31], Autoencoders [32], and LSTM [33] are some of the examples of machine learning methods that can be used for anomaly detection and risk management in MWC.…”

“…Safety and risk management in maritime environments are always challenging due to its changing situations as ships are traveling over huge, unpredictably sized stretches of oceans and seas. For communication over ocean networks and underwater wireless sensor networks (UWSN), wireless communication technology is extensively used in maritime activities [23], [29]. However, it is challenging to maintain the safety, efficient anomaly detection, timely risk mitigation, and real-time communication in maritime environments.…”