ArticlePDF Available

Neural Networks Application for Processing of the Data from the FMICW Radars

Authors:
Lubos Rejfek at University of Pardubice
Lubos Rejfek
Nguyen Nhat Tan at Ton Duc Thang University
Nguyen Nhat Tan
Pavel Chmelar at University of Pardubice
Pavel Chmelar
Ladislav Beran at University of Pardubice
Ladislav Beran
Show all 5 authorsHide
Download full-text PDFDownload full-text PDF
Read full-text
Download citation

Abstract

In this paper the results of the Neural Networks and machine learning applications for radar signal processing are presented. The radar output from the primary radar signal processing is represented as a 2D image composed from echoes of the targets and noise background. The Frequency Modulated Interrupted Continuous Wave (FMICW) radar PCDR35 (Portable Cloud Doppler Radar at the frequency 35.4 GHz) was used. Presently, the processing is realized via a National Instruments industrial computer. The neural network of the proposed system is using four or five (optional for the user) signal processing steps. These steps are 2D spectrum filtration, thresholding, unification of the target, target area transforming to the rectangular shape (optional step), and target board line detection. The proposed neural network was tested with sets of four cases (100 tests for every case). This neural network provides image processing of the 2D spectrum. The results obtained from this new system are much better than the results of our previous algorithm.
symmetry-11-013
08.pdf
Content uploaded by Nguyen Nhat Tan
Author content
All content in this area was uploaded by Nguyen Nhat Tan on Oct 22, 2019
Content may be subject to copyright.
Neural Networks Application for Processing of the Data from the FMICW Rada
rs.pdf
Available via license: CC BY
Content may be subject to copyright.
A preview of the PDF is not available
... At present, the neural networks for the signal processingare very often used. In this paper, we are aiming at the classification of output data from the neural network for target marking, which was described in [1]. This processing isrealized by the simple neurons and they can be simply implemented into the FPGA. ...
... III. SYSTEM FOR AUTOMATIC MARKING OF ECHOES Our system described in [1] processes the measured signals after 2D FFT. We can choose whether the marking will be rectangular, or the target shape will be included. ...
... We also derived data in our work described in [8], where we did it without the neural networks, but with worse results. The result comparison of both methodswas shown in [1]. The first aim of the neural network extension is derivation of the number of incoming, outgoing and static targets. ...
View
View
AMTI Filter Design for Radar with Variable Pulse Repetition Period
Article
Full-text available
  • Apr 2016
This paper presents a design of a Doppler AMTI filter, for a radar with a variable pulse repetition period (stagger). The filter can suppress ground and volume clutter echoes simultaneously. The maximum filter impulse response length is limited to 5 coefficients due to a limited radar system stability and a radar antenna movement.
View
Automatic Analysis of the Signals from the FMICW Radars
Conference Paper
  • Apr 2019
In this paper, FMICW radars and processing of the signals from these systems are described. Main part of the paper is a system for automatic analysis of the signals. An algorithm is applied on the two-dimensional Fast Fourier Transform. In paper, the complication caused by the signal processing and their removal are described.
View
An Interference Mitigation Technique for FMCW Radar Using Beat-Frequencies Interpolation in the STFT Domain
Article
  • Nov 2018
A frequency-modulated continuous-wave (FMCW) radar interference mitigation technique using the interpolation of beat frequencies in the short-time Fourier transform (STFT) domain, phase matching, and reconfigurable linear prediction coefficients estimation for Coherent Processing Interval processing is proposed. The technique is noniterative and does not rely on algorithm convergence. It allows the usage of the fast Fourier transform (FFT) as the radar's beat-frequency estimation tool, for reasons such as real-time implementation, noise linearity after the FFT, and compatibility with legacy receiver architectures. Verification is done in range and in range-Doppler using radar experimental data in two ways: first by removing interferences from interference-contaminated data and second by using interference-free data as the reference data, and processing it--as if it had interferences--using the proposed technique, inverse cosine windowing and zeroing for comparison. We found that processing with the proposed technique closely matches the reference-data and outperforms the inverse cosine windowing and zeroing techniques in 2-D cross correlation, amplitude, and phase average errors and phase root-mean-square error. It is expected that the proposed technique will be operationally deployed on the TU Delft simultaneous-polarimetric PARSAX radar. IEEE
View
A Stochastic Computational Multi-Layer Perceptron with Backward Propagation
Article
  • Mar 2018
Stochastic computation has recently been proposed for implementing artificial neural networks with reduced hardware and power consumption, but at a decreased accuracy and processing speed. Most existing implementations are based on pre-training such that the weights are predetermined for neurons at different layers, thus these implementations lack the ability to update the values of the network parameters. In this paper, a stochastic computational multi-layer perceptron (SC-MLP) is proposed by implementing the backward propagation algorithm for updating the layer weights. Using extended stochastic logic (ESL), a reconfigurable stochastic computational activation unit (SCAU) is designed to implement different types of activation functions such as the tanh and the rectifier function. A triple modular redundancy (TMR) technique is employed for reducing the random fluctuations in stochastic computation. A probability estimator (PE) and a divider based on the TMR and a binary search algorithm are further proposed with progressive precision for reducing the required stochastic sequence length. Therefore, the latency and energy consumption of the SC-MLP are significantly reduced. The simulation results show that the proposed design is capable of implementing both the training and inference processes. For the classification of nonlinearly separable patterns, at a slight loss of accuracy by 1.32%−1.34%1.32\%-1.34\% , the proposed design requires only 28.5%−30.1%28.5\%-30.1\% of the area and 18.9%−23.9%18.9\%-23.9\% of the energy consumption incurred by a design using floating point arithmetic. Compared to a fixed-point implementation, the SC-MLP consumes a smaller area ( 40.7%−45.5%40.7\%-45.5\% ) and a lower energy consumption ( 38.0%−51.0%38.0\%-51.0\% ) with a similar processing speed and a slight drop of accuracy by 0.15%−0.33%0.15\%-0.33\% . The area and the energy consumption of the proposed design is from 80.7%−87.1%80.7\%-87.1\% and from 71.9%−93.1%71.9\%-93.1\% , respectively, of a binarized neural network (BNN), with a similar accuracy.
View
View
View
View
View
View