An experimental study on RSS-based wireless localization with software defined radio

Vasudeva, Karthik; Çiftler, Bekir Sait; Altamar, Armando; Güvenç, İsmail

doi:10.1109/wamicon.2014.6857806

Cited by 15 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is the well-known trilateration problem. There are many sources providing potential solutions as in [10], [12], [25], [26]. For the sake of completeness of this study, we present the detailed solution as follows: representing the system in matrix form (A. m = b) as [25]:…”

Section: A Multilateration Solution For 3 Base Stationsmentioning

confidence: 99%

RSSI-Based Localization Using LoRaWAN Technology

Kwasme

Ekin

2019

IEEE Access

View full text Add to dashboard Cite

The Internet of Things (IoT) is increasing in size by having more devices connected to it as they are becoming low-cost to manufacture and easier to connect to the internet. New use cases are being created by the need for it and feasibility to provide it, with low-cost solutions. As a key enabler of the IoT, Long Range Wide Area Network (LoRaWAN) is gaining great attention in research and industry. It provides a desirable solution for applications that require hundreds or thousands of actively connected devices to monitor a process or an environment or to assist in controlling a certain process. Some of these IoT use cases require having the location information of the IoT devices. In some cases, localization can be the intrinsic purpose of deployment. In this regard, the received signal strength indicator (RSSI)-based localization offers a feasible and affordable solution. Since LoRaWAN has only been there for only a few years, research on utilizing LoRaWAN RSSI for localization purposes is in early stages and is scarce. In this paper, we study LoRaWAN RSSI-based localization and evaluate its accuracy, impairments, and prospects. In addition, we employ the use of software-defined radios (SDR) into our work for the purpose of path-loss characterization. The experimental results revealed the fact that a high variance of RSSI due to frequency hopping feature of LoRaWAN could severely impact the localization performance. Potential solutions are developed and presented to reduce this negative impact, hence improve the performance.

show abstract

Section: A Multilateration Solution For 3 Base Stationsmentioning

confidence: 99%

RSSI-Based Localization Using LoRaWAN Technology

Kwasme

Ekin

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The corresponding loss function of the mirror layer decoded by the second hidden layer in (14) is then employed to converge the weights of the second layer of the denoising autoencoder, such that the second layer loss function is defined as:…”

Section: Deep Learning and Denoising Autoencodermentioning

confidence: 99%

“…The results documented localization performance of sub-0.5 m in an undocumented environment. Finally, the most recent research expressed in [14] demonstrated one of the first machine learning based WiFi localizing SDR platforms. The SDR leveraged simultaneous RSS and CSI in a LabVIEW aided system cascaded with a convolutional neural network to achieve approximately 1 m of localization error.…”

Section: Introductionmentioning

confidence: 99%

“…This work proposes an SDR based localization procedure that can rapidly extract 3D multipath CSI and perform indoor localization via PkNN and deep learning at rates relative to the link's time-bandwidth product. In the case of this work, a bandwidth of 5 MHz is used with a BPSK beacon frame of 2 ms realizing 10,000 times improvement in packet realization rates when compared to the approach in [14]. The selected bandwidth and digital modulation are not required as the designed approach implements a matched filter methodology that is agnostic to frequency, bandwidth, and transmitted waveform so long as the SDR can tolerate such characteristics.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

SDR Based Indoor Beacon Localization Using 3D Probabilistic Multipath Exploitation and Deep Learning

2019

View full text Add to dashboard Cite

Wireless indoor positioning systems (IPS) are ever-growing as traditional global positioning systems (GPS) are ineffective due to non-line-of-sight (NLoS) signal propagation. In this paper, we present a novel approach to learning three-dimensional (3D) multipath channel characteristics in a probabilistic manner for providing high performance indoor localization of wireless beacons. The proposed system employs a single triad dipole vector sensor (TDVS) for polarization diversity, a deep learning model deemed the denoising autoencoder to extract unique fingerprints from 3D multipath channel information, and a probabilistic k-nearest-neighbor (PkNN) to exploit the 3D multipath characteristics. The proposed system is the first to exploit 3D multipath channel characteristics for indoor wireless beacon localization via vector sensing methodologies, a software defined radio (SDR) platform, and multipath channel estimation.

show abstract

“…SDR has many applications in various fields, such as spectrum monitoring [ 19 ], RF transmitter identification [ 25 ], and other areas. For example, it was used as a receiver to estimate a mobile station’s location through received signal strength [ 26 ]. Bonoir et al applied SDR to remote wireless tomography in their experiment [ 27 ].…”

Section: Introductionmentioning

confidence: 99%

Human Occupancy Detection via Passive Cognitive Radio

Liu

Vakil

et al. 2020

Sensors

View full text Add to dashboard Cite

Human occupancy detection (HOD) in an enclosed space, such as indoors or inside of a vehicle, via passive cognitive radio (CR) is a new and challenging research area. Part of the difficulty arises from the fact that a human subject cannot easily be detected due to spectrum variation. In this paper, we present an advanced HOD system that dynamically reconfigures a CR to collect passive radio frequency (RF) signals at different places of interest. Principal component analysis (PCA) and recursive feature elimination with logistic regression (RFE-LR) algorithms are applied to find the frequency bands sensitive to human occupancy when the baseline spectrum changes with locations. With the dynamically collected passive RF signals, four machine learning (ML) classifiers are applied to detect human occupancy, including support vector machine (SVM), k-nearest neighbors (KNN), decision tree (DT), and linear SVM with stochastic gradient descent (SGD) training. The experimental results show that the proposed system can accurately detect human subjects—not only in residential rooms—but also in commercial vehicles, demonstrating that passive CR is a viable technique for HOD. More specifically, the RFE-LR with SGD achieves the best results with a limited number of frequency bands. The proposed adaptive spectrum sensing method has not only enabled robust detection performance in various environments, but also improved the efficiency of the CR system in terms of speed and power consumption.

show abstract

An experimental study on RSS-based wireless localization with software defined radio

Cited by 15 publications

References 8 publications

RSSI-Based Localization Using LoRaWAN Technology

RSSI-Based Localization Using LoRaWAN Technology

SDR Based Indoor Beacon Localization Using 3D Probabilistic Multipath Exploitation and Deep Learning

Human Occupancy Detection via Passive Cognitive Radio

Contact Info

Product

Resources

About