No abstract

Implementing line-of-sight (LOS) and none-line-ofsight (NLOS) identification in ultra-wideband (UWB) systems is crucial. Convolutional neural network (CNN) based identification methods can extract higher-level features automatically, but they are based on channel impulse response (CIR)-turned image ingested features that impose calculation complexity and do not make use of manual features due to the data inundation risk. In this letter, we propose a novel multilayer perceptron (MLP)based LOS/NLOS identification algorithm that can utilize both manually extracted features and feature from CNN based on raw CIR inputs with only 7.39% calculation complexity as compared to the traditional image-based CNN. Three experiments, at a teaching building, an office, and an underground mine, were conducted to verify the proposed method's performance. Our proposed features are conducive to LOS/NLOS identification, especially the proposed raw CIR-based feature from the CNN, achieving 26.9% improvement over existing manual features. Furthermore, the proposed method outperformed the traditional image-based CNN with an improvement of 44.16%.

Ultra-wideband (UWB) sensor technology is known to achieve high-precision indoor localization accuracy in line-of-sight (LOS) environments, but its localization accuracy and stability suffer detrimentally in non-line-of-sight (NLOS) conditions. Current NLOS/LOS identification based on channel impulse response's (CIR) characteristic parameters (CCP) improves location accuracy, but most CIR-based identification approaches did not sufficiently exploit the CIR information and are environment specific. This paper derives three new CCPs and proposes a novel two-step identification/classification methodology with dynamic threshold comparison (DTC) and the fuzzy credibilitybased support vector machine (FC-SVM). The proposed SVM based classification methodology leverages on the derived CCPs obtained from the waveform and its channel analysis, which are more robust to environment and obstacles dynamic. This is achieved in two-step with a coarse-grained NLOS/LOS identification with the DTC strategy followed by FC-SVM to give the fine-grained result. Finally, based on the obtained identification results, a real-time ranging error mitigation strategy is then designed to improve the ranging and localization accuracy. Extensive experimental campaigns are conducted in different LOS/NLOS scenarios to evaluate the proposed methodology. The results show that the mean LOS/NLOS identification accuracy in various testing scenarios is 93.27 %, and the LOS and NLOS recalls are 94.27 % and 92.57 %, respectively. The ranging errors in LOS(NLOS) conditions are reduced from 0.106 m(1.442 m) to 0.065 m(0.739 m), demonstrating an improvement of 38.85 %(48.74 %) with 0.041 m(0.703 m) error reduction. On the other hand, the average positioning accuracy is also reduced from 0.250 m to 0.091 m with an improvement of 63.49 %(0.159 m), which outperforms the state-of-the-art approaches of the Least-squares support vector machine (LS-SVM) and K-Nearest Neighbor (KNN) algorithms.

Cs2LiYCl6: Ce3+ (CLYC) is a dual-mode gamma-neutron scintillator with a medium gamma-ray resolution and pulse-shape discrimination (PSD) capability. The PSD performance of CLYC is greatly weakened when coupled with silicon photomultipliers (SiPMs) because of SiPMs’ low detection efficiency for the ultrafast Core-Valence-Luminescence (CVL) component under gamma excitation. In our previous work, the PSD Figure-of-Merit (FoM) value was optimized to 2.45 at the gamma-equivalent energy region of the thermal neutron by using the charge comparison method. However, this value was reduced to 1.37 at the lower gamma-equivalent energy region of more than 325 keV, and neutrons were difficult to distinguish from gamma rays. Hence, new algorithms should be studied to improve the PSD performance at low gamma-equivalent energy regions. Convolutional Neural Networks (CNNs) have excellent image recognition capabilities, and thus, neutron and gamma-ray waveforms can be discriminated by their characteristics through a known training set. In this study, neutron and gamma-ray waveforms were measured with a 137Cs source and moderated 252Cf source via an SiPM array-coupled CLYC detector and divided into two groups: training and PSD testing. The CNN training set comprised 137Cs characteristic gamma-ray waveforms and thermal neutron waveforms that were discriminated by the charge comparison method from the training group. A CNN with two convolution-pooling layers was designed to accomplish PSD with the test group. The PSD FoM value of the CNN method was calculated to be 37.20 at the gamma-equivalent energy region of more than 325 keV. This result was much higher than that of the charge comparison method, indicating that neutrons and gamma rays could be better distinguished with the CNN method, especially at low gamma-equivalent energy regions.

No abstract