Implementing Deep Learning Techniques in 5G IoT Networks for 3D Indoor Positioning: DELTA (DeEp Learning-Based Co-operaTive Architecture).

Brahim El Boudani,Akis Kokkinis,Tasos Dagiuklas,Loizos Kanaris,Christos Chrysoulas,Michalis Kyriacou,Stavros Stavrou

doi:10.3390/s20195495

Abstract

In the near future, the fifth-generation wireless technology is expected to be rolled out, offering low latency, high bandwidth and multiple antennas deployed in a single access point. This ecosystem will help further enhance various location-based scenarios such as assets tracking in smart factories, precise smart management of hydroponic indoor vertical farms and indoor way-finding in smart hospitals. Such a system will also integrate existing technologies like the Internet of Things (IoT), WiFi and other network infrastructures. In this respect, 5G precise indoor localization using heterogeneous IoT technologies (Zigbee, Raspberry Pi, Arduino, BLE, etc.) is a challenging research area. In this work, an experimental 5G testbed has been designed integrating C-RAN and IoT networks. This testbed is used to improve both vertical and horizontal localization (3D Localization) in a 5G IoT environment. To achieve this, we propose the DEep Learning-based co-operaTive Architecture (DELTA) machine learning model implemented on a 3D multi-layered fingerprint radiomap. The DELTA begins by estimating the 2D location. Then, the output is recursively used to predict the 3D location of a mobile station. This approach is going to benefit use cases such as 3D indoor navigation in multi-floor smart factories or in large complex buildings. Finally, we have observed that the proposed model has outperformed traditional algorithms such as Support Vector Machine (SVM) and K-Nearest Neighbor (KNN).

Highlights

In the era of 5G Internet of Things (IoT) [1], real-time positioning is becoming increasingly required by context-aware applications and location-based services
With 5G paving the path for a seamless collaboration among heterogeneous wireless systems, a great opportunity has risen in the area of indoor localization in urban areas under the framework of smart cities
We propose a DEep Learning-based with Co-operative Architecture (DELTA) algorithm to enhanced 3D indoor localization

Summary

Introduction

In the era of 5G IoT [1], real-time positioning is becoming increasingly required by context-aware applications and location-based services. Cisco has predicted that 26 billion [7] of these devices will be IoT or Wireless Sensor Network (WSN) devices In this respect, technologies like Cloud Radio Access Network (C-RAN), Millimeter Wave (mm-Wave) communication, ultra dense communication [8], device-to-device (D2D) communication and Vehicle-to-everything (V2X) [9,10] and protocols like IEEE 802.11be (Extremely high Throughput WLAN) [11], IEEE 802.11az ( Generation Positioning) [12] are introduced to increase the bandwidth of communication and to offer the possibility of co-operative and precise localization. With 5G paving the path for a seamless collaboration among heterogeneous wireless systems (cellular, WiFi, WSN, IoT, etc.), a great opportunity has risen in the area of indoor localization in urban areas under the framework of smart cities Such high dense networks could be utilized to solve multi-agent positioning and offer agility and scalability for accurate positioning as a service. The contributions of this paper can be summarized as follows:

Methods

Results

Conclusion