Sparse sensor array selection arises in many engineering applications, where it is imperative to obtain maximum spatial resolution from a limited number of array elements. Recent research shows that computational complexity of array selection is reduced by replacing the conventional optimization and greedy search methods with a deep learning network. However, in practice, sufficient and well-calibrated labeled training data are unavailable and, more so, for arbitrary array configurations. To address this, we adopt a deep transfer learning (TL) approach, wherein we train a deep convolutional neural network (CNN) with data of a source sensor array for which calibrated data are readily available and reuse this pre-trained CNN for a different, data-insufficient target array geometry to perform sparse array selection. Numerical experiments with uniform rectangular and circular arrays demonstrate enhanced performance of TL-CNN on the target model than the CNN trained with insufficient data from the same model. In particular, our TL framework provides approximately 20% higher sensor selection accuracy and 10% improvement in the direction-of-arrival estimation error.
Compressed Sensor Caching and Collaborative Sparse Data Recovery with Anchor Alignment
Institute of Communications Engineering, National Tsing Hua University（国立清华大学通信工程研究所）；National Central University（国立中央大学）；National Yang Ming Chiao Tung University（国立阳明交通大学）
Nonasymptotic Performance Analysis of Direct-Augmentation and Spatial-Smoothing ESPRIT for Localization of More Sources Than Sensors Using Sparse Arrays
Data-Induced Interactions of Sparse Sensors Using Statistical Physics
Department of Mechanical Engineering, University of Hawai i at M\=anoa, Honolulu, HI 96814, USA；AI Institute in Dynamic Systems, University of Washington, Seattle, WA 98195, USA；Department of Mechanical Engineering, University of Washington, Seattle, WA 98195, USA；Departments of Applied Mathematics；Computer Engineering, University of Washington, Seattle, WA 98195, USA
Spatiotemporal Reconstruction of Global Radiation from Sparse Sensor Sequences
Nuclear, Plasma & Radiological Engineering（核物理与辐射工程）；National Center for Supercomputing Applications（国家超级计算应用中心）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Civil and Urban Engineering（土木与城市工程）
本文提出了一种新的稀疏阵列结构，用于二维（方位角和仰角）波达方向（DOA）估计。所提出的阵列的几何形状是V形稀疏阵列，它是由两个线性部分，这是相互交叉。稀疏采样特性提高了稀疏阵列的自由度。在这方面，V形互质（VCA）和V形嵌套阵列（VNA）结构的开发。VCA可以同时分辨方位角和仰角，最多可以分辨MN个源，每个部分有2 M + N-1个传感器，传感器总数为4 M +2N-3。VNA可以用2N个传感器分辨O（N^2）个源。代替2-D网格搜索，所提出的方法以计算有效的方式计算用于方位角和仰角估计的1-D搜索。为了解决二维情况下的配对问题，利用两部分的互协方差矩阵进行二维配对DOA估计。所提出的方法的性能进行了评估与数值模拟，它表明，所提出的阵列几何形状VCA和VNA可以提供更少的传感器相比，传统的互质平面阵列。
Sparse Bayesian Learning-Based 3D Spectrum Environment Map Construction-Sampling Optimization, Scenario-Dependent Dictionary Construction and Sparse Recovery
