“Single Sensor Detection and Classification of Multiple Sources by Higher-Order Spectra”
by Mithat C. Dogan and Jerry M. Mendel
June 1992
We propose a method to detect the number of non-Gaussian sources using higher-order statistics. The distinguishing feature of our method is its ability to perform detection with single sensor data unlike existing covariance-based detection algorithms that require an array of sensors. In addition, our method is blind to Gaussian observation noise. After the detection procedure, we propose an algorithm for classification of sources employing a priori knowledge of their spectra. Simulation results indicate the performance of our algorithms.