A dynamic frame of signal sorting based on data stream clustering

In order to solve the contradiction between the accuracy and the real-time in signal sorting, a dynamic signal sorting frame based on data stream clustering was proposed. The frame can be divided into two parts: on-line part and off-line part. In on-line part, the reconnaissance data was transformed and saved as grid frame; in off-line part, the grid frame was sorted with the algorithm of grid-based clustering. Experimental results show that the proposed frame can sort the high density and complex reconnaissance data stream without any prior knowledge, and is not sensitive to the influence of noise. The requirement of accuracy and real-time in signal sorting can be satisfied with this frame.