Engineering Commons^™

Deep Learning Based Localization Of Zigbee Interference Sources Using Channel State Information, Dylan Kensler

All Theses

As the field of Internet of Things (IoT) continues to grow, a variety of wireless signals fill the ambient wireless environment. These signals are used for communication, however, recently wireless sensing has been studied, in which these signals can be used to gather information about the surrounding space. With the development of 802.11n, a newer standard of WiFi, more complex information is available about the environment a signal propagates through. This information called Channel State Information (CSI) can be used in wireless sensing. With the help of Deep Learning, this work attempts to generate a fingerprinting technique for localizing a …

Convolutional Neural Network Architecture Study For Aerial Visual Localization, Jedediah M. Berhold

Theses and Dissertations

In unmanned aerial navigation the ability to determine the aircraft's location is essential for safe flight. The Global Positioning System (GPS) is the default modern application used for geospatial location determination. GPS is extremely robust, very accurate, and has essentially solved aerial localization. Unfortunately, the signals from all Global Navigation Satellite Systems (GNSS) to include GPS can be jammed or spoofed. To this response it is essential to develop alternative systems that could be used to supplement navigation systems, in the event of a lost GNSS signal. Public and governmental satellites have provided large amounts of high-resolution satellite imagery. These …

Collaborative Appearance-Based Place Recognition And Improving Place Recognition Using Detection Of Dynamic Objects, Juan Pablo Munoz

Dissertations, Theses, and Capstone Projects

This dissertation makes contributions to the problem of Long-Term Appearance-Based Place Recognition. We present a framework for place recognition in a collaborative scheme and a method to reduce the impact of dynamic objects on place representations. We demonstrate our findings using a state-of-the-art place recognition approach.

We begin in Part I by describing the general problem of place recognition and its importance in applications where accurate localization is crucial. We discuss feature detection and description and also explain the functioning of several place recognition frameworks.

In Part II, we present a novel framework for collaboration between agents from a pure …

Node Localization In Underwater Sensor Networks (Uwsn), Huai Huang

Doctoral Dissertations

"This dissertation focuses on node localization in underwater wireless sensor networks (UWSNs) where anchor nodes have knowledge of their own locations and communicate with sensor nodes in acoustic or magnetic induction (MI) means. The sensor nodes utilize the communication signals and the locations of anchor nodes to locate themselves and propagate their locations through the network.

For UWSN using MI communications, this dissertation proposes two localization methods: rotation matrix (RM)-based method and the distance-based method. Both methods require only two anchor nodes with arbitrarily oriented tri-directional coils to locate one sensor node in the 3-D space, thus having advantages in …

A Novel Low Latency, High Resolution And Low Cost Time Synchronization, Ali Aghdaei

Dissertations, Master's Theses and Master's Reports

This report presents a new low latency, high resolution and low cost timing synchro- nization technique for digital receivers. Traditional timing synchronization employs Matched filter to perform cross-correlation operation and estimate Time-of-Arrival (TOA) of the signal. Decreasing the latency of the traditional method through over- sampling leads to a higher complexity and it is not viable. Furthermore, to obtain a high-resolution TOA, an extensive bandwidth is required, which results in high system complexity. The proposed method uses single bit quantization to employ XNOR blocks instead of multiplier and accumulator (MAC) blocks in the traditional method. This substantially decreases complexity incorporating …

Uwb Precise Indoor Localization System Performance, Limitations And Its Integration, Essam Abdelkadir Elkhouly

Doctoral Dissertations

An indoor localization system that was built at University of Tennessee is extensively studied and improved. The goal of the system is to achieve mm down to sub-mm accuracy/precision.

Sub-sampling is used to alleviate the high sampling rate required for UWB signals. Current commercial direct sampling systems are still too slow or prohibitively expensive for UWB applications. We developed two different sub-sampling techniques, but the two systems suffer numerous shortcomings: low throughput, non-robustness, non-linearity. A third system is introduced that achieve both high accuracy and high through-put. Changes in the detection algorithm and the frame synchronization are developed to accommodate …

Multi-Tag Access For A High Precision Ultra-Wideband Localization System, Nathan Carl Rowe

Masters Theses

Ultra-Wideband (UWB) wireless positioning systems have many advantages for track- ing and locating items in indoor environments. Surgical navigation and industrial process control are potential applications for high accuracy UWB localization systems with millimeter or sub-millimeter accuracy. I present improvements made to an existing high accuracy, multi-tag, UWB localization system. The goal of this thesis was to improve the multi-tag performance of this system while maintaining the high localization accuracy, and to utilize the UWB system for digital communications allowing the existing narrowband 2.4 GHz transceiver to be eliminated.

This thesis presents a proof-of-concept for a multi-tag, UWB localization system …

Underwater Localization And Tracking Of Physical Systems, Patrick E. Carroll

Master's Theses

In this paper, we investigate the problem of localizing an underwater sensor node basedon message broadcasting from multiple surface nodes. With the time-of-arrival measurementsfrom a DSP-based multicarrier modem, each sensor node localizes itself based on the traveltime differences among multiple senders to the receiver. Using one-way message passing, such asolution can scale to accommodate a large number of nodes in a network. We consider the issuefrom not only the physical layer, but also at the node processing layer by incorporating a trackingsolution. We present simulation results as well as preliminary testing results in a swimming poolwith both stationary and moving …