A Novel Modulation Classification Approach Using Gabor Filter Network

Algorithm 1

(Training of Gabor filter Network for Modulation Classification).

Step  1. Initialization of Gabor atom parameters (shift parameter 𝑐_𝑖, scale parameter 𝜎_𝑖 and modulation parameter 𝑓_𝑖)

   and weights of Gabor filter (𝑤_𝑖).

Step  2. Calculate the Gabor atom using (4) and using (20), compute all Gabor atom nodes.

Step  3. The Gabor atoms node (𝜑_𝑖) are now input to the Adaptive filter, and adjust the weights of the adaptive filter

   using LMS (28)–(32).

Step  4. Evaluate error which is defined in (7). If error is less than chosen threshold, then training of algorithm is stopped

   and save Gabor atom parameters (𝑐_𝑖,𝜎_𝑖,𝑓_𝑖) and Gabor filter weights (𝑤_𝑖).

Step  5. If error is not less than threshold, repeat Step  3 by using the error calculated in Step  4.

Step  6. Tune the Gabor atom parameters (𝑐_𝑖,𝜎_𝑖,𝑓_𝑖) using (8), (23), (25) and (27).

Step  7. Save Gabor atom parameters (𝑐_𝑖,𝜎_𝑖,𝑓_𝑖) and Gabor filter weights (𝑤_𝑖).