Low probability of intercept (LPI) radars using linear frequency-modulated continuous waveforms (LFMCWs) is rapidly proliferating in the military domain and posing a serious challenge to conventional electronic support receivers (ESRs). In this article, we provide a practical approach that can be used in digital ESR systems for real-time LFMCW radar signal detection and parameter extraction under challenging SNR levels. We proposed a modified version of the Wigner-Ville distribution (WVD), namely, short-time Wigner distribution (STWD), postprocessing steps, e.g., column-based thresholding of STWD combined with the Hough transform (HT), and a field-programmable gate array (FPGA) design as an embedded solution with low computational complexity. The performance of the proposed system is tested with MATLAB and hardware simulations using a signal database generated with different signal-to-noise ratio (SNR) levels. The system is then embedded into a Virtex-7 FPGA where the performance evaluations showed satisfactory detection results down to -6-dB SNR level, and parameter extraction results down to -8-dB SNR level.

In this brief, conic section function neural network (CSFNN) circuitry was designed for offline signature recognition. CSFNN is a unified framework for multilayer perceptron (MLP) and radial basis function (RBF) networks to make simultaneous use of advantages of both. The CSFNN circuitry architecture was developed using a mixed mode circuit implementation. The designed circuit system is problem independent. Hence, the general purpose neural network circuit system could be applied to various pattern recognition problems with different network sizes on condition with the maximum network size of 16-16-8. In this brief, CSFNN circuitry system has been applied to two different signature recognition problems. CSFNN circuitry was trained with chip-in-the-loop learning technique in order to compensate typical analog process variations. CSFNN hardware achieved highly comparable computational performances with CSFNN software for nonlinear signature recognition problems.

In this study, an iterative reduction based heuristic algorithm (IRHA) based closed loop control and space vector PWM (SVPWM) control of the Z-source inverter are implemented in hardware. The third harmonic addition method is used to realize the SVPWM structure in programmable embedded environment. The control parameters are optimally determined by IRHA to overcome the problem of instability. The controllers are implemented in single Field-Programmable Gate Array (FPGA) chip using hardware description language without help of any IP core units which increases speed, accuracy, compactness and cost efficiency. Furthermore, power consumption of the controllers is lower than a conventional ones which is prominent advantage of employing FPGAs. The effectiveness and accuracy of the control structure are verified by experimental results.

A novel method to reconstruct the energy of hadronic showers in the CMS High Granularity Calorimeter (HGCAL) is presented. The HGCAL is a sampling calorimeter with very fine transverse and longitudinal granularity. The active media are silicon sensors and scintillator tiles readout by SiPMs and the absorbers are a combination of lead and Cu/CuW in the electromagnetic section, and steel in the hadronic section. The shower reconstruction method is based on graph neural networks and it makes use of a dynamic reduction network architecture. It is shown that the algorithm is able to capture and mitigate the main effects that normally hinder the reconstruction of hadronic showers using classical reconstruction methods, by compensating for fluctuations in the multiplicity, energy, and spatial distributions of the shower's constituents. The performance of the algorithm is evaluated using test beam data collected in 2018 prototype of the CMS HGCAL accompanied by a section of the CALICE AHCAL prototype. The capability of the method to mitigate the impact of energy leakage from the calorimeter is also demonstrated.