Abhishek Narayan Sarkar’s research while affiliated with National Institute of Technology Durgapur and other places

Radio wave propagation in an intra-vehicular (IV) environment is markedly different from other well-studied indoor scenarios, such as an office or a factory floor. While millimetre wave (mmWave)-based intra-vehicular communications promise large bandwidth and can achieve ultra-high data rates with lower latency, exploiting the advantages of mmWave communications largely relies on adequately characterising the propagation channel. Channel characterisation is most accurately done through an extensive channel sounding, but due to hardware and environmental constraints, it is impractical to test channel conditions for all possible transmitter and receiver locations. Artificial neural network (ANN)-based channel sounding can overcome this impediment by learning and estimating the channel parameters from the channel environment. We estimate the power delay profile in intra-vehicular public and private vehicle scenarios with a high accuracy using a simple feedforward multi-layer perception-based ANN model. Such artificially generated models can help extrapolate other relevant scenarios for which measurement data are unavailable. The proposed model efficiently matches the taped delay line samples obtained from real-world data, as shown by goodness-of-fit parameters and confusion matrices.

Radio wave propagation in an intra-vehicular environment is markedly different from other well studied indoor scenarios such as an office or a factory oor. Millimeter Wave (mmWave) based intra-vehicular communications promises large bandwidth and can achieve ultra-high data rate with lower latency. However, exploiting the advantages of mmWave communications largely relies on proper characterization of the propagation channel. Channel characterization is most accurately done through an extensive channel sounding, but due to hardware and environmental constraints, it is impractical to test channel condition for all possible transmitter and receiver locations. In this paper, we use artificial neural network to aid channel sounding. Based on some real-world sounding data we show that it is possible to accurately estimate channel transfer function (CTF) and power delay profile (PDP) in an intra-bus scenario. Such artificially generated models can help in extrapolation in other relevant scenarios for which measurement data is unavailable. The proposed model can also be used for tapped delay line based bit-error-simulations as well.

In this article we have utilized deep learning (DL) for channel sounding application in the millimeter wave (mmWave) band. Using data from a channel sounding campaign for studying intra-vehicle wireless channels operating over the 55-65 GHz mmWave band, we have trained an artificial neural network (ANN) model, which is used to simulate power-delay-profile (PDP) trends. The required simulation inputs form a minimal set, only comprising the frequency points, the transmitter-receiver distance and the presence of passengers inside car. The simulated PDP trend shows good match with the measured PDP and can be used for constructing tapped-delay-line (TDL) based channel models.