Adaptive Screening Approach of Training Data with an Unknown Number of Outliers

In multichannel adaptive radar target detection, diverse nonhomogeneous background factors can cause considerable outlier interference, making it challenging to meet the requirements of independent and identically distributed training data. Current methods for screening training data rely on prior knowledge of the number of outliers, often leading to poor performance in real-world scenarios where this number is usually unknown. This paper addresses these issues by focusing on adaptive training data screening when the number of outliers is unknown. First, the outlier set is estimated using maximum likelihood estimation, assuming known covariance matrices of clutter and noise. In particular, the training data is initially ranked based on the generalized inner product of each range cell data, approximately transforming the maximum likelihood estimation of the outlier set to the estimation of the number of outliers. Second, a fast maximum likelihood estimation algorithm is employed to calculate the unknown covariance matrix, and an adaptive screening approach is designed for scenarios with an unspecified number of outliers. Furthermore, to address the adverse effects of outliers on ranking performance, a normalized generalized inner product form is devised utilizing the normalized sampling covariance matrix. This form is subsequently incorporated into an iterative estimation procedure to improve the adaptive screening accuracy of training data. Simulation results demonstrate that the screening accuracy of the normalized generalized inner product exceeds that of the generalized inner product. Moreover, through even a small number of reiterations, maintaining a consistent enhancement in terms of the Normalized Signal-to-Interference Ratio (NSIR) is still possible. Compared with existing methods, the proposed algorithm considerably improves screening performance, especially when the number of outliers is unknown.