A Highly Controllable Cooperative Automatic Modulation Classification

• Published in: Wireless personal communications Vol. 131; no. 3; pp. 2081 - 2092
• Main Authors: Rahim, V. C. Abdul, Prema, S. Chris
• Format: Journal Article
• Language: English
• Published: New York Springer US 01-08-2023; Springer Nature B.V
• Subjects: Classification; Communications Engineering; Computer Communication Networks; Controllability; Cooperative control; Engineering; Error reduction; Fading; Modulation; Networks; Nodes; Random noise; Signal classification; Signal to noise ratio; Signal,Image and Speech Processing; Statistical analysis; Weight reduction; Controllability factor; Cognitive radio; Weight vector; Sensor nodes; Cumulants; Cooperative AMC
• ISSN: 0929-6212; 1572-834X
• DOI: 10.1007/s11277-023-10533-x

In this paper, we propose a novel highly controllable cooperative automatic modulation classification using higher order cumulants as features to increase the probability of correct classification in lower signal to noise ratios (SNR). In a cooperative framework, spatially separated sensor nodes provides a better statistical representation. Initially at the sensor nodes, higher order cumulants of the received signal are calculated and weight vector is estimated at the fusion center. Then the controllability factor is selected deterministically from the weights of the highest order cumulant in the weight vector to reduce the error in classification in lower SNRs. A soft decision fusion approach is considered in the fusion center. The Monte Carlo simulations conducted in additive white Gaussian noise and flat fading Rayleigh channels show that the proposed scheme performs better than the state-of-the-art methods for modulation classification using higher order statistics in lower SNRs. The analysis of simulation result with four modulation schemes BPSK, 4QAM, 8PSK and 16QAM in the Rayleigh flat fading channel, revealed that the proposed method achieved a 15
%
improvement in classification accuracy compared to existing approaches at SNR=
-
 10  dB.