A new method is proposed for identifying outliers in the direction-of-arrival (DOA) data of a source observed from a linear array sonar. Suppose a source moves uniformly along a straight line. The method for identifyi...A new method is proposed for identifying outliers in the direction-of-arrival (DOA) data of a source observed from a linear array sonar. Suppose a source moves uniformly along a straight line. The method for identifying outliers consists of three steps, (i) Divide the data into groups, each with four sample points, and delete certain two sample points from every group by means of a robust method pesented in this paper. When the percentage of the outliers is less than 50%, there exists at least one group in which the remaining two sample points are 'good' . (ii) Estimate the DOA and its Change rate, (θ0 , θ0 ), using the remaining two simple points of every group, and computethe objective functions of M-etsimator using the resulting estimates of all groups respectively. A 'good' estimate of (θ0 , θ0 ), which minmizes the objective function is then obtained, (iii) Iterate the M-estimator with the 'good' estimate of (θ0 , θ0 ) as the initial value, obtain an accurate estimate of (θ0 , θ0),and identify outliers in the observed data using the residuals calculated from the accurate estimate of (θ0 , θ0 ). The breakdown point of the method is 50%. Thesimulation examples given in the paper verify the reliability of the method.展开更多
基金The project is supported by National Natural Science Foundation of China
文摘A new method is proposed for identifying outliers in the direction-of-arrival (DOA) data of a source observed from a linear array sonar. Suppose a source moves uniformly along a straight line. The method for identifying outliers consists of three steps, (i) Divide the data into groups, each with four sample points, and delete certain two sample points from every group by means of a robust method pesented in this paper. When the percentage of the outliers is less than 50%, there exists at least one group in which the remaining two sample points are 'good' . (ii) Estimate the DOA and its Change rate, (θ0 , θ0 ), using the remaining two simple points of every group, and computethe objective functions of M-etsimator using the resulting estimates of all groups respectively. A 'good' estimate of (θ0 , θ0 ), which minmizes the objective function is then obtained, (iii) Iterate the M-estimator with the 'good' estimate of (θ0 , θ0 ) as the initial value, obtain an accurate estimate of (θ0 , θ0),and identify outliers in the observed data using the residuals calculated from the accurate estimate of (θ0 , θ0 ). The breakdown point of the method is 50%. Thesimulation examples given in the paper verify the reliability of the method.
