Learning modulation filter networks for weak signal detection in noise

Abstract Weak signal detection is a challenging yet significant problem in the field of radio communication. Although hand-crafted filters are widely used in signal processing, they are challenged by the weak signal detection task with unknown background noise especially in the range of 0-5dB. In this paper, we propose the learning modulation filter networks (LMFNs) to improve the detection performance. The approach is based on a two-stage optimization scheme which addresses filter learning, attention mechanism and classification in a unified framework. Modulation filters are built to enhance the capacity of the learned filters, and the attention mechanism further characterizes the saliency properties of the input signal. LMFNs reduce the storage size of the network while achieving the state-of-the-art performance by a significant margin compared to traditional cognitive radio approaches. We establish a weak signal dataset that contains unmanned aerial vehicle (UAV) communication signals in a real-terrain environment. The source code and dataset will be made publicly available soon.

[1]  Octavia A. Dobre,et al.  Cyclostationarity-Based Robust Algorithms for QAM Signal Identification , 2012, IEEE Communications Letters.

[2]  Rongrong Ji,et al.  Generative Adversarial Learning Towards Fast Weakly Supervised Detection , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[3]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[4]  Mitchell McLaren,et al.  How to train your speaker embeddings extractor , 2018, Odyssey.

[5]  Octavia A. Dobre,et al.  Identification of SM-OFDM and AL-OFDM Signals Based on Their Second-Order Cyclostationarity , 2015, IEEE Transactions on Vehicular Technology.

[6]  Sreerama K. Murthy,et al.  Automatic Construction of Decision Trees from Data: A Multi-Disciplinary Survey , 1998, Data Mining and Knowledge Discovery.

[7]  Marios S. Pattichis,et al.  Fast Localization and Segmentation of Optic Disk in Retinal Images Using Directional Matched Filtering and Level Sets , 2012, IEEE Transactions on Information Technology in Biomedicine.

[8]  Vittorio Murino,et al.  Efficient pooling of image based CNN features for action recognition in videos , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[9]  Yangyu Fan,et al.  Automatic Modulation Classification Using Deep Learning Based on Sparse Autoencoders With Nonnegativity Constraints , 2017, IEEE Signal Processing Letters.

[10]  Chen Chen,et al.  Gabor Convolutional Networks , 2017, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[11]  Christopher Leckie,et al.  High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning , 2016, Pattern Recognit..

[12]  Vittorio Murino,et al.  Audio Tracking in Noisy Environments by Acoustic Map and Spectral Signature , 2018, IEEE Transactions on Cybernetics.

[13]  Georgios B. Giannakis,et al.  A Wavelet Approach to Wideband Spectrum Sensing for Cognitive Radios , 2006, 2006 1st International Conference on Cognitive Radio Oriented Wireless Networks and Communications.

[14]  Sofie Pollin,et al.  Distributed Deep Learning Models for Wireless Signal Classification with Low-Cost Spectrum Sensors , 2017, ArXiv.

[15]  R.W. Brodersen,et al.  Implementation issues in spectrum sensing for cognitive radios , 2004, Conference Record of the Thirty-Eighth Asilomar Conference on Signals, Systems and Computers, 2004..

[16]  Khaled Assaleh,et al.  Automatic modulation classification based on high order cumulants and hierarchical polynomial classifiers , 2016, Phys. Commun..

[17]  Kang G. Shin,et al.  In-band spectrum sensing in cognitive radio networks: energy detection or feature detection? , 2008, MobiCom '08.

[18]  Aly El Gamal,et al.  Deep neural network architectures for modulation classification , 2017, 2017 51st Asilomar Conference on Signals, Systems, and Computers.

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

[20]  Yahia A. Eldemerdash,et al.  Blind Identification of SM and Alamouti STBC-OFDM Signals , 2015, IEEE Transactions on Wireless Communications.

[21]  T. Charles Clancy,et al.  Over-the-Air Deep Learning Based Radio Signal Classification , 2017, IEEE Journal of Selected Topics in Signal Processing.

[22]  Ah Chung Tsoi,et al.  Face recognition: a convolutional neural-network approach , 1997, IEEE Trans. Neural Networks.

[23]  C. Cordeiro,et al.  Spectrum agile radios: utilization and sensing architectures , 2005, First IEEE International Symposium on New Frontiers in Dynamic Spectrum Access Networks, 2005. DySPAN 2005..

[24]  Liang Lin,et al.  Deep feature learning with relative distance comparison for person re-identification , 2015, Pattern Recognit..

[25]  Ian F. Akyildiz,et al.  NeXt generation/dynamic spectrum access/cognitive radio wireless networks: A survey , 2006, Comput. Networks.

[26]  Bernard Sklar,et al.  Digital communications , 1987 .

[27]  Brian M. Sadler,et al.  Cyclic Feature Detection With Sub-Nyquist Sampling for Wideband Spectrum Sensing , 2012, IEEE Journal of Selected Topics in Signal Processing.

[28]  William A. Gardner,et al.  Signal interception: performance advantages of cyclic-feature detectors , 1992, IEEE Trans. Commun..

[29]  Frank Y. Shih,et al.  Retinal vessels segmentation based on level set and region growing , 2014, Pattern Recognit..

[30]  Raj Rao Nadakuditi,et al.  Fundamental Limit of Sample Generalized Eigenvalue Based Detection of Signals in Noise Using Relatively Few Signal-Bearing and Noise-Only Samples , 2009, IEEE Journal of Selected Topics in Signal Processing.

[31]  H. Tang,et al.  Some physical layer issues of wide-band cognitive radio systems , 2005, First IEEE International Symposium on New Frontiers in Dynamic Spectrum Access Networks, 2005. DySPAN 2005..

[32]  Y. Bar-Ness,et al.  Higher-order cyclic cumulants for high order modulation classification , 2003, IEEE Military Communications Conference, 2003. MILCOM 2003..

[33]  Jürgen Schmidhuber,et al.  LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[34]  Lidija Paunovska,et al.  Longley-Rice model precision in case of multiple diffracting obstacles , 2015 .

[35]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[36]  Jerome M. Shapiro,et al.  Embedded image coding using zerotrees of wavelet coefficients , 1993, IEEE Trans. Signal Process..

[37]  Jakob Hoydis,et al.  An Introduction to Deep Learning for the Physical Layer , 2017, IEEE Transactions on Cognitive Communications and Networking.

[38]  Octavia A. Dobre,et al.  On the Cyclostationarity of OFDM and Single Carrier Linearly Digitally Modulated Signals in Time Dispersive Channels: Theoretical Developments and Application , 2010, IEEE Transactions on Wireless Communications.