Abstract
Aiming at the limitations of traditional communication modulation recognition algorithms, a novel recognition algorithm based on deep learning network far communication signal features is proposed in this paper. By introducing the two different computation mechanisms of STFT, two unsupervised feature-learning networks based on Restrict Boltzmann Machine (RBM) are respectively adopted for communication signal, where the network based on RBM is greatly improved in computing performance compared to the network based on convolutional Restrict Boltzmann Machine (CRBM), and greatly reduces the requirement for high-performance hardware in deep learning networks. In addition, as for signal modulation recognition and signal detection problems in communications, two modulation recognition networks are constructed by using the learning-to-STFT networks and the Back Propagation Neural Network (BPNN) classifier. Compared with the traditional modulation algorithms, our proposed algorithm in the paper can obtain better performance in the recognition accuracy, especially under the condition of low SNR.
Similar content being viewed by others
References
Karra K, Kuzdeba S, Petersen J. Modulation recognition using hierarchical deep neural networks[C]// IEEE international symposium on dynamic Spectrum access networks. 2017
Yuan L, Xinyu DA, Jialiang WU et al (2018) WFRFT modulation recognition based on HOC and optimal order searching algorithm[J]. Systems Engineering and Electronic Technology (English edition)
Mohamed B, Hua W, Lakhdari MEH (2018) Automatic digital modulation recognition based on stacked sparse AutoEncoder[C]// IEEE international conference on communication technology. IEEE
Li R, Li L, Yang S et al (2018) Robust automated VHF modulation recognition based on deep convolutional neural networks[J]. IEEE Commun Lett:1–1
Kumar Y, Amit S, Prasanna C A learnable distortion correction module for modulation recognition[J]. IEEE Wireless Commun Lett 2018:1–1
Wang H, Guo L, Dou Z, Lin Y (2018) A new method of cognitive signal recognition based on hybrid information entropy and D-S evidence theory[J]. Mobile Networks and Applications 23:677–685
Almohamad TA, Salleh MFM, Mahmud MN et al (2018) Simultaneous determination of modulation types and signal-to-noise ratios using feature-based approach[J]. IEEE Access:1–1
Kulin M, Kazaz T, Moerman I, de Poorter E (2018) End-to-end learning from Spectrum data: a deep learning approach for wireless signal identification in Spectrum monitoring applications[J]. IEEE Access 6:18484–18501
Bin Z , Morgan M E , Van d K H J G , et al (2018). Corrigendum Transcriptional modulation of pattern recognition receptors in chronic colitis in mice is accompanied with Th1 and Th17 response[J]. Biochemistry and Biophysics Reports, (13):147–148
Saylor Z, Maier R (2018) Helicobacter pylori nickel storage proteins: recognition and modulation of diverse metabolic targets[J]. Microbiology 164:1059–1068
Wang H, Cui J, Arshad A, Xu S, Wang L (2018) A visual photothermal paper sensor for H2S recognition through rational modulation LSPR wavelength of plasmonics[J]. SCIENCE CHINA Chem 61(3):368–374
Cristina MC, Leonardo S, Silvina CL et al (2018) Helminth infections: recognition and modulation of the immune response by innate immune cells[J]. Front Immunol 9:664
Ren W, Ji D, Xu X et al (2018) Metal cofactor modulated folding and target recognition of HIV-1 NCp7[J]. PLoS One 13(5)
Bijlstra G, Holland RW, Dotsch R et al (2018) Stereotypes and prejudice affect the recognition of emotional body postures[J]. Emotion
Cheng X, Liu Y, Shu Y, Tao DD, Wang B, Yuan Y, Galvin JJ III, Fu QJ, Chen B (2018) Music training can improve music and speech perception in pediatric mandarin-speaking Cochlear implant users[J]. Trends in Hearing 22:233121651875921
Liu T, Guan Y, Lin Y (2017) Research on modulation recognition with ensemble learning[J]. EURASIP J Wirel Commun Netw 2017(1):179
Spooner CM, Mody AN, Chuang J et al (2017) Modulation recognition using second- and higher-order cyclostationarity[C]// IEEE international symposium on dynamic Spectrum access networks. IEEE
Chao YW, Quan YX (2017) Modulation recognition of double satellite signals in alpha-stable distribution noise[J]. J Appl Sci 35(3):309–316
Xie L, Wan Q (2017) Cyclic feature based modulation recognition using compressive sensing[J]. IEEE Wireless Commun Lett:1–1
Zhang Y, Yang M, Liu X (2017) Artificial-neural-network-based automatic modulation recognition in satellite communication[C]// international conference on Machine Learning & Intelligent Communications. Springer, Cham
Hazar MA, Odabasioglu N, Ensari T et al Performance analysis and improvement of machine learning algorithms for automatic modulation recognition over Rayleigh fading channels[J]. Neural Comput Applic 2017(12):1–10
Jin S, Lin Y, Wang H . Automatic modulation recognition of digital signals based on Fisherface[C]// IEEE international conference on software quality. IEEE, 2017
Kumar H L P, Shrinivasan L . Automatic digital modulation recognition system using feature extraction[J]. 2017
Xie J (2017) Robust intra-pulse modulation recognition via sparse representation[C]// Cie international conference on radar. IEEE
Khosraviani M, Kalbkhani H, Shayesteh MG (2017) Digital modulation recognition in MIMO systems based on segmentation of received data[C]// electrical engineering. IEEE
Xie L, Wan Q (2017, PP) Automatic modulation recognition for phase shift keying signals with compressive measurements[J]. IEEE Wireless Commun Lett:99):1–99):1
Benedetto F, Tedeschi A, Giunta G (2017) Automatic blind modulation recognition of analog and digital signals in cognitive radios[C]// vehicular technology conference. IEEE
Xu Y, Mcsally J, Andricioaei I et al (2018) Modulation of Hoogsteen dynamics on DNA recognition[J]. Nat Commun 9(1):1473
Arumugam KSK, Kadampot IA, Tahmasbi M et al (2017) Modulation recognition using side information and hybrid learning[C]// IEEE international symposium on dynamic Spectrum access networks. IEEE
West N E, O'Shea T J . Deep architectures for modulation recognition[J]. 2017
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This article is part of the Topical Collection: Special Issue on Fog/Edge Networking for Multimedia Applications
Guest Editors: Yong Jin, Hang Shen, Daniele D'Agostino, Nadjib Achir, and James Nightingale
Rights and permissions
About this article
Cite this article
Wu, S. Communication modulation recognition algorithm based on STFT mechanism in combination with unsupervised feature-learning network. Peer-to-Peer Netw. Appl. 12, 1615–1623 (2019). https://doi.org/10.1007/s12083-019-00807-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12083-019-00807-2