Publication: Z. Zhao, M. C. Vuran, F. Guo and S. D. Scott, "Deep-Waveform: A Learned OFDM Receiver Based on Deep Complex-Valued Convolutional Networks," in IEEE Journal on Selected Areas in Communications, vol. 39, no. 8, pp. 2407-2420, Aug. 2021, doi: 10.1109/JSAC.2021.3087241.

The (inverse) discrete Fourier transform (DFT/IDFT) is often perceived as essential to orthogonal frequency-division multiplexing (OFDM) systems. In this paper, a deep complex-valued convolutional network (DCCN) is developed to recover bits from time-domain OFDM signals without relying on any explicit DFT/IDFT. The DCCN can exploit the cyclic prefix (CP) of OFDM waveform for increased SNR by replacing DFT with a learned linear transform, and has the advantage of combining CP-exploitation, channel estimation, and intersymbol interference (ISI) mitigation, with a complexity of O(N^2). Numerical tests show that the DCCN receiver can outperform the legacy channel estimators based on ideal and approximate linear minimum mean square error (LMMSE) estimation and a conventional CP-enhanced technique in Rayleigh fading channels with various delay spreads and mobility. The proposed approach benefits from the expressive nature of complex-valued neural networks, which, however, currently lack support from popular deep learning platforms. In response, guidelines of exact and approximate implementations of a complex-valued convolutional layer are provided for the design and analysis of convolutional networks for wireless PHY. Furthermore, a suite of novel training techniques are developed to improve the convergence and generalizability of the trained model in fading channels. This work demonstrates the capability of deep neural networks in processing OFDM waveforms and the results suggest that the FFT processor in OFDM receivers can be replaced by a hardware AI accelerator.

Please cite the publication above when using the source code. Source code for Deep Learning-Based OFDM Receiver.

• Modulation: BPSK, QPSK, 8-QAM, 16-QAM, of Gray mapping.
• SNR: -10:1:29 dB

Publication: M. M. R. Lunar, C. Stolle, R. K. Faller and M. C. Vuran, "Crashing Waves: An Empirical Vehicle-to-Barrier Communication Channel Model via Crash Tests," in Proc. IEEE International Conference on Mobile Ad Hoc and Smart Systems (MASS '21), pp. 419-427, virtual, Oct. 2021, doi: 10.1109/MASS52906.2021.00059.

Vehicle-to-barrier (V2B) communications is an emerging communication technology between vehicles and roadside barriers to mitigate run-off-road crashes, which result in more than half of the traffic-related fatalities in the United States. To ensure V2B connectivity, establishing a reliable V2B channel is necessary before a potential crash, such that real-time information from barriers can help (semi-)autonomous vehicles make informed decisions. However, the characteristics of the V2B channel are not yet well understood. Therefore, in this paper, a V2B channel model is developed with three channel metrics: received power, root mean square (RMS) delay spread, and RMS Doppler spread based on experiments during controlled vehicle crash tests. Experimentation, empirical analyses, and mathematical models are introduced to capture the impacts of antenna height, barrier type, and vehicle type in V2B channel characteristics. Vehicle-height barrier antennas experience 6.4% (540ns) less reference delay spread, while encountering 10% (13Hz) higher reference Doppler spread and 10dB more received power than the barrier-height barrier antennas. Moreover, steel barrier deployment results in a 21% (2,040ns) larger reference delay spread and 2.4% (2.35Hz) smaller reference Doppler spread than concrete barrier deployment. Finally, the impact of the crash in the communication channel is investigated with these empirical metrics. To the best of our knowledge, this is the first V2B communication channel model that captures received power, RMS delay spread, and RMS Doppler spread, validated with the most extensive set of vehicular crash tests.

Please cite the publication above when using the source code. Source code for developing models of received power, RMS delay spread, and RMS Doppler spread in Vehicle-to-Barrier communication on the single-vehicle run-off-road crash scenarios.

Publications:
F. Guo, B. Zhou and M. C. Vuran, "CFOSynt: Carrier frequency offset assisted clock syntonization for wireless sensor networks," IEEE INFOCOM 2017 - IEEE Conference on Computer Communications, pp. 1-9, 2017, doi: 10.1109/INFOCOM.2017.8057075.
B. Zhou, F. Guo and M. C. Vuran, "Demo abstract: Clock syntonization using CFO information in Wireless Sensor Networks," IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), pp. 980-981, 2017, doi: 10.1109/INFCOMW.2017.8116520.

System-level timing inconsistency and wireless communication delays are the main uncertainties of existing synchronization mechanisms for wireless sensor networks. Existing solutions mainly rely on timestamp exchanges to estimate clock offset and skew, which results in frequent synchronization, high overhead, and high energy consumption to maintain a well-synchronized network. This paper introduces a novel clock syntonization approach to estimate the differences between clock frequencies of network nodes without the need for timestamp exchanges. The carrier frequency offset (CFO) assisted syntonization (CFOSynt) utilizes the carrier information obtained from wireless packet transmission for clock skew compensation. The key idea of CFOSynt is that, in any wireless communication system, where carrier modulation is employed, carrier frequency delivers information about the transmitter RF clock. Consequently, clock frequency offset between a pair of sensor nodes will result in a carrier frequency offset detected by the receiver node. By leveraging the CFO information, CFOSynt can estimate the system clock skew based on digital counter theory. Extensive experiments and numerical analysis have been demonstrated to evaluate clock skew estimation.

Please cite the publications above when using the source code. Source Code: https://github.com/bfzhou/UNL-CPN-CFOSynt

Publication: M. M. R. Lunar, C. Stolle, R. K. Faller and M. C. Vuran, "Crashing Waves: An Empirical Vehicle-to-Barrier Communication Channel Model via Crash Tests," in Proc. IEEE International Conference on Mobile Ad Hoc and Smart Systems (MASS '21), pp. 419-427, virtual, Oct. 2021, doi: 10.1109/MASS52906.2021.00059.

Vehicle-to-barrier (V2B) communications is an emerging communication technology between vehicles and roadside barriers to mitigate run-off-road crashes, which result in more than half of the traffic-related fatalities in the United States. To ensure V2B connectivity, establishing a reliable V2B channel is necessary before a potential crash, such that real-time information from barriers can help (semi-)autonomous vehicles make informed decisions. However, the characteristics of the V2B channel are not yet well understood. Therefore, in this paper, a V2B channel model is developed with three channel metrics: received power, root mean square (RMS) delay spread, and RMS Doppler spread based on experiments during controlled vehicle crash tests. Experimentation, empirical analyses, and mathematical models are introduced to capture the impacts of antenna height, barrier type, and vehicle type in V2B channel characteristics. Vehicle-height barrier antennas experience 6.4% (540ns) less reference delay spread, while encountering 10% (13Hz) higher reference Doppler spread and 10dB more received power than the barrier-height barrier antennas. Moreover, steel barrier deployment results in a 21% (2,040ns) larger reference delay spread and 2.4% (2.35Hz) smaller reference Doppler spread than concrete barrier deployment. Finally, the impact of the crash in the communication channel is investigated with these empirical metrics. To the best of our knowledge, this is the first V2B communication channel model that captures received power, RMS delay spread, and RMS Doppler spread, validated with the most extensive set of vehicular crash tests.

Please cite the publication above when using the datasets. In the repository, data for five different crash tests are uploaded. The details about each of these crash tests are discussed in the paper. The data for each crash test are categorized according to the USRP log files, Crash test photos & videos, Crash vehicle acceleration sensor data, and Crashed barrier design & dimensions.

Publication: Shuai Nie, Mohammad M. R. Lunar, Geng Bai, Yufeng Ge, Santosh Pitla, Can Emre Koksa, Mehmet Can Vuran, "mmWave on a Farm: Channel Modeling for Wireless Agricultural Networks at Broadband Millimeter-Wave Frequency", in Proc. IEEE International Conference on Sensing, Communication, and Networking (IEEE SECON'22), Stockholm, Sweden, Sept. 2022, doi: 10.1109/SECON55815.2022.9918595.

Millimeter-wave (mmWave) spectrum with wide bandwidth provides a promising solution to enable high throughput in next-generation wireless agricultural networks, characterized by swarms of autonomous ground vehicles, unmanned aerial vehicles (UAVs), and connected agricultural machinery. However, channel models at mmWave frequencies in agricultural environments remain elusive. Moreover, agricultural field channels bear notable distinctions from urban and rural macrocellular network channels due to the dynamic crop growth behavior. In this work, a channel model is developed to characterize the large-scale path loss, coherence bandwidth, and link quality under the effect of various environmental factors based on data collected from extensive field experiments. In particular, the wind effect on signal-to-noise ratio is investigated, and the diffuse scattering of electromagnetic waves due to near-canopy propagation at different crop growth stages. Our analysis results demonstrate that (1) during the growing season, the crop canopy surface acts as a ``new ground'' that creates multipath components that result in a higher path loss exponent, which is correlated with the relative height between the crop canopy surface and the radio, (2) the wind results in a half-power drop (3-dB SNR degradation) for an increase of 4~m/s in gust speed due to beam misalignment and increasing scattering, (3) the channel coherence bandwidth increases as the water content in the crop decreases, and (4) the beam-level spatial consistency observed allows for micro-mobility support for agricultural robotic applications. It is also shown that the impacts of humidity and water vapor on the mmWave channel are insignificant in the absence of rain and irrigation. Such characteristics are fundamental for designing advanced channel estimation and signal processing algorithms in advanced agricultural Internet-of-Things solutions.

Please cite the publication above when using the dataset.