Automatic Digital Modulation Classification Based on Curriculum Learning

Neural network shows great potential in modulation classification because of its excellent accuracy and achievability but overfitting and memorizing data noise often happen in previous researches on automatic digital modulation classifier. To solve this problem, we utilize two neural networks, namely MentorNet and StudentNet, to construct an automatic modulation classifier, which possesses great performance on the test set with−18–20 dB signal-to-noise ratio (SNR). The MentorNet supervises the training of StudentNet according to curriculum learning, and deals with the overfitting problem in StudentNet. The proposed classifier is verified in several test sets containing additive white Gaussian noise (AWGN), Rayleigh fading, carrier frequency offset and phase offset. Experimental results reveal that the overall accuracy of this classifier for common eleven modulation types was up to 99.3% while the inter-class accuracy could be up to 100%, which was much higher than many other classifiers. Besides, in the presence of interferences, the overall accuracy of this novel classifier still could reach 90% at 10 dB SNR indicting its excellent robustness, which makes it suitable for applications like military electronic warfare.

[1]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Chao Lu,et al.  Automatic modulation format/bit-rate classification and signal-to-noise ratio estimation using asynchronous delay-tap sampling , 2015, Comput. Electr. Eng..

[3]  Jinfeng Yi,et al.  Is Robustness the Cost of Accuracy? - A Comprehensive Study on the Robustness of 18 Deep Image Classification Models , 2018, ECCV.

[4]  T. Charles Clancy,et al.  Convolutional Radio Modulation Recognition Networks , 2016, EANN.

[5]  Yonina C. Eldar,et al.  Fast Deep Learning for Automatic Modulation Classification , 2019, ArXiv.

[6]  Asoke K. Nandi,et al.  Automatic Modulation Classification Using Combination of Genetic Programming and KNN , 2012, IEEE Transactions on Wireless Communications.

[7]  Li Fei-Fei,et al.  MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels , 2017, ICML.

[8]  Ijaz Mansoor Qureshi,et al.  Classification of M-QAM and M-PSK signals using genetic programming (GP) , 2018, Neural Computing and Applications.

[9]  S. A. Alshebeili,et al.  An overview of feature-based methods for digital modulation classification , 2013, 2013 1st International Conference on Communications, Signal Processing, and their Applications (ICCSPA).

[10]  Ali Abdi,et al.  Survey of automatic modulation classification techniques: classical approaches and new trends , 2007, IET Commun..

[11]  Shiguang Shan,et al.  Self-Paced Curriculum Learning , 2015, AAAI.

[12]  William A. Gardner,et al.  Signal interception: a unifying theoretical framework for feature detection , 1988, IEEE Trans. Commun..

[13]  Octavia A. Dobre,et al.  On the likelihood-based approach to modulation classification , 2009, IEEE Transactions on Wireless Communications.

[14]  Samy Bengio,et al.  Understanding deep learning requires rethinking generalization , 2016, ICLR.

[15]  Elsayed Elsayed Azzouz,et al.  Algorithms for automatic modulation recognition of communication signals , 1998, IEEE Trans. Commun..

[16]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[17]  Asoke K. Nandi,et al.  Automatic Modulation Classification: Principles, Algorithms and Applications , 2015 .

[18]  Chao Lu,et al.  Joint modulation format/bit-rate classification and signal-to-noise ratio estimation in multipath fading channels using deep machine learning , 2016 .

[19]  Yangyu Fan,et al.  Unsupervised feature learning and automatic modulation classification using deep learning model , 2017, Phys. Commun..

[20]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Mohd Fadzli Mohd Salleh,et al.  Simultaneous Determination of Modulation Types and Signal-to-Noise Ratios Using Feature-Based Approach , 2018, IEEE Access.

[22]  Wu Dan,et al.  A new scheme of automatic modulation classification using wavelet and WSVM , 2005, 2005 2nd Asia Pacific Conference on Mobile Technology, Applications and Systems.

[23]  Timothy J. O'Shea,et al.  Deep architectures for modulation recognition , 2017, 2017 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN).

[24]  Georgios B. Giannakis,et al.  Statistical tests for presence of cyclostationarity , 1994, IEEE Trans. Signal Process..

[25]  Jerry M. Mendel,et al.  Maximum-likelihood classification for digital amplitude-phase modulations , 2000, IEEE Trans. Commun..

[26]  Andrew McCallum,et al.  Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples , 2017, NIPS.

[27]  Hongguang Li,et al.  Automatic Modulation Classification Based on Deep Learning for Unmanned Aerial Vehicles , 2018, Sensors.

[28]  Muazzam Ali Khan,et al.  Automatic Modulation Recognition of Communication Signals. , 2012 .