PROJECT TITLE :
Asynchronous Linear Modulation Classification With Multiple Sensors via Generalized EM Algorithm
In this paper, we tend to contemplate the problem of automatic modulation classification with multiple sensors in the presence of unknown time offset, section offset and received signal amplitude. We have a tendency to develop a novel hybrid maximum likelihood (HML) classification theme based on a generalized expectation maximization (GEM) algorithm. GEM is capable of finding ML estimates numerically that are extraordinarily onerous to obtain otherwise. Assuming a good initialization technique is on the market for GEM, we show that the classification performance (in terms of the chance of error) will be greatly improved with multiple sensors compared to that with one sensor, especially when the signal-to-noise ratio (SNR) is low. We tend to further demonstrate the superior performance of our approach when simulated annealing (SA) with uniform plus nonuniform grids is employed for initialization of GEM in low SNR regions. The proposed GEM based approach employs only a little range of samples (in the order of hundreds) at a given sensor node to perform both time and part synchronization, signal power estimation, followed by modulation classification. We give simulation results to show the efficiency and effectiveness of the proposed algorithm.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here