Joint signal-to-noise ratio and source number estimation based on hierarchical artificial intelligence units. (3rd August 2018)

• Record Type: Journal Article
• Authors: Yun, Wu; Xiukun, Li; Zhimin, Cao; Jian, Han; Haiwei, Mu; Zhentao, Wang
• Is Part Of: Measurement science & technology. Volume 29:Number 9(2018:Sep.)
• Publication Date: 2018-08-03
• Subjects: direction of arrival (DOA) -- SNR -- source number -- uniform linear array (ULA) -- neural networks (NN) -- SVM; Physical measurements -- Periodicals; Scientific apparatus and instruments -- Periodicals; Equipment and Supplies -- Periodicals; Science -- instrumentation -- Periodicals; Technology -- instrumentation -- Periodicals; Mesures physiques -- Périodiques; Physical measurements; Scientific apparatus and instruments; Periodicals; 502.87
• DOI: 10.1088/1361-6501/aad12a
• Languages: English
• ISSNs: 0957-0233

Abstract

Abstract: Accurately measuring the direction of arrival (DOA) is one of the most important issues in multiple sensor/antenna array monitoring scenarios. However, as a necessary parameter of almost all state-of-the-art DOA estimation methods, the source number is always hard to be determined by using the traditional Akaike information criterion (AIC) or minimum description length (MDL) methods, especially in low or very low signal-to-noise ratio (SNR) conditions. In this paper, we propose to sequentially estimate the SNR and source number in a novel data-driven manner by employing artificial intelligence (AI) techniques. Specifically, a simulated uniform linear array (ULA) dataset with different source numbers and different SNRs is first generated. With this dataset, the artificial neural network (ANN) regression unit for SNR prediction is built. Then, a hierarchical support vector machine (SVM) classification unit is constructed to estimate the source number. Finally, with these hierarchical AI units, the SNR and source number were estimated simultaneously in an iterative way. Experimental results illustrated that the proposed method can estimate the source number stably and reliably even in the low SNR condition.