Recursive Feature Elimination Based Feature Selection in Modulation Classification for MIMO Systems

ZHOU Shuai; LI Tao; LI Yongzhao

doi:10.23919/cje.2021.00.347

Volume 32 Issue 4

Jul. 2023

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2023 > 32(4): 785-792

ZHOU Shuai, LI Tao, LI Yongzhao, “Recursive Feature Elimination Based Feature Selection in Modulation Classification for MIMO Systems,” Chinese Journal of Electronics, vol. 32, no. 4, pp. 785-792, 2023, doi: 10.23919/cje.2021.00.347

Citation:

ZHOU Shuai, LI Tao, LI Yongzhao, “Recursive Feature Elimination Based Feature Selection in Modulation Classification for MIMO Systems,” Chinese Journal of Electronics, vol. 32, no. 4, pp. 785-792, 2023, doi: 10.23919/cje.2021.00.347

Citation:

PDF( 2744 KB)

Recursive Feature Elimination Based Feature Selection in Modulation Classification for MIMO Systems

doi: 10.23919/cje.2021.00.347

1.
School of Telecommunications Engineering, Xidian University, Xi’an 710071, China

Funds: This work was supported by the National Natural Science Foundation of China (62001358, 61771365), the Fundamental Research Funds for the Central Universities (JB190115, JBF180101), the National Key R&D Program of China (254), and the National Science Foundation for Post-doctoral Scientists of China (2019M663630)

More Information

Author Bio:
Shuai ZHOU received the B.S. degree from Xidian University, Xi’an, China, in 2019, where he is currently pursuing the Ph.D. degree in communication and information system. His current research interests include digital signal processing, source number estimation, and modulation classification.(Email: szhou_0319@stu.xidian.edu.cn)

Tao LI (corresponding author) received the B.S. and Ph.D. degrees in communication engineering from Xidian University, Xi’an, China, in 2012 and 2018, respectively. From September 2015 to September 2016, he worked as a Visiting Ph.D. Student, under the supervision of Prof. Leonard J. Cimini, Jr., with the University of Delaware, DE, USA. Since July 2018, he has been a Lecturer with the School of Telecommunications Engineering, Xidian University. His current research interests are in the fields of blind signal processing, random matrix theory, physical layer security, and anti-drone technique.(Email: taoli@xidian.edu.cn)

Yongzhao LI received the B.S., M.S., and Ph.D. degrees in electronic engineering from Xidian University, Xi’an, China, in 1996, 2001, and 2005, respectively. Since 1996, he joined Xidian University, where he is currently a Full Professor with the State Key Laboratory of Integrated Services Networks. As a Research Professor, he worked with the University of Delaware, DE, USA, from 2007 to 2008, and the University of Bristol, Bristol, UK, in 2011. He has published more than 70 journal articles and 30 conference papers. His research interests include wideband wireless communications, signal processing for communications, and spatial communications networks. In 2008, he received the Best Paper Award of IEEE CHINACOM 2008 International Conference. Due to his excellent contributions in education and research, in 2012, he was awarded by the Program for New Century Excellent Talents in University, Ministry of Education, China. (Email: yzhli@xidian.edu.cn)
Received Date: 2021-09-16
Accepted Date: 2022-05-26

Available Online: 2022-06-09

Publish Date: 2023-07-05

Abstract

Abstract

The feature-based (FB) algorithms are widely used in modulation classification due to their low complexity. As a prerequisite step of FB, feature selection can reduce the computational complexity without significant performance loss. In this paper, according to the linear separability of cumulant features, the hyperplane of the support vector machine is used to classify modulation types, and the contribution of different features is ranked through the weight vector. Then, cumulant features are selected using recursive feature elimination (RFE) to identify the modulation type employed at the transmitter. We compare the performance of the proposed algorithm with existing feature selection algorithms and analyze the complexity of all the mentioned algorithms. Simulation results verify that the proposed RFE algorithm can optimize the selection of the features to realize modulation recognition and improve identification efficiency.
- Multiple input multiple output,
- Modulation classification,
- Feature selection,
- Support vector machine-recursive feature elimination

1It means that the communication link or channel comprising $ N_{\rm t} $ transmitter antennas and $ N_{\rm r} $ receiver antennas that operates in a Rayleigh flat-fading environment. Each receiver antenna responds to each transmitter antenna through a statistically independent fading coefficient.
2It means that transmit independent symbols over the different antennas as well as over the different symbol times.

FullText(HTML)

References(26)

References

[1]	Y. A. Eldemerdash, O. A. Dobre, and M. Öner, “Signal identification for multiple-antenna wireless systems: achievements and challenges,” IEEE Communications Surveys & Tutorials, vol.18, no.3, pp.1524–1551, 2016. doi: 10.1109/COMST.2016.2519148
[2]	O. A. Dobre, A. Abdi, Y. Bar-Ness, et al., “Survey of automatic modulation classification techniques: classical approaches and new trends,” IET Communications, vol.1, no.2, pp.137–156, 2007. doi: 10.1049/iet-com:20050176
[3]	Z. C. Zhu and A. K. Nandi, “Automatic Modulation Classification: Principles, Algorithms, and Applications,” Wiley, Chichester, 2015.
[4]	K. Hassan, C. N. Nzéza, M. Berbineau, et al., “Blind modulation identification for MIMO systems,” in Proceedings of 2010 IEEE Global Telecommunications Conference, Miami, FL, USA, pp.1–5, 2010.
[5]	M. G. Luo, L. P. Li, and B. Tang, “A blind modulation recognition algorithm suitable for MIMO-STBC systems,” in Proceedings of the 2012 IEEE 12th International Conference on Computer and Information Technology, Chengdu, China, pp.271–276, 2012.
[6]	D. Das, P. K. Bora, and R. Bhattacharjee, “Blind modulation recognition of the lower order PSK signals under the MIMO keyhole channel,” IEEE Communications Letters, vol.22, no.9, pp.1834–1837, 2018. doi: 10.1109/LCOMM.2018.2853638
[7]	X. K. Liu, C. L. Zhao, P. B. Wang, et al., “Blind modulation classification algorithm based on machine learning for spatially correlated MIMO system,” IET Communications, vol.11, no.7, pp.1000–1007, 2017. doi: 10.1049/iet-com.2015.1222
[8]	M. S. Muhlhaus, M. Öner, O. A. Dobre, et al., “A low complexity modulation classification algorithm for MIMO systems,” IEEE Communications Letters, vol.17, no.10, pp.1881–1884, 2013. doi: 10.1109/LCOMM.2013.091113.130975
[9]	M. S. Mühlhaus, M. Öner, O. A. Dobre, et al., “Automatic modulation classification for MIMO systems using fourth-order cumulants,” in Proceedings of 2012 IEEE Vehicular Technology Conference, Quebec City, Canada, pp.1–5, 2012.
[10]	Y. Ettefagh, M. H. Moghaddam, and S. Eghbalian, “An adaptive neural network approach for automatic modulation recognition,” in Proceedings of the 2017 51st Annual Conference on Information Sciences and Systems, Baltimore, MD, USA, pp.1–5, 2017.
[11]	A. Swami and B. M. Sadler, “Hierarchical digital modulation classification using cumulants,” IEEE Transactions on Communications, vol.48, no.3, pp.416–429, 2000. doi: 10.1109/26.837045
[12]	C. S. Park, J. H. Choi, S. P. Nah, et al., “Automatic modulation recognition of digital signals using wavelet features and SVM,” in Proceedings of the 2008 10th International Conference on Advanced Communication Technology, Gangwon, Korea (South), pp.387–390, 2008.
[13]	A. Ali and Y. Y. Fan, “Automatic modulation classification using principle composition analysis based features selection,” in Proceedings of 2017 Computing Conference, London, UK, pp.294–296, 2017.
[14]	A. Ebrahimzadeh and R. Ghazalian, “Modulation classification using genetic algorithm and radial basis neural network based on the HOS,” in Proceedings of the 6th International Conference on Digital Content, Multimedia Technology and Its Applications, Seoul, Korea (South), pp.375–378, 2010.
[15]	A. K. Das, S. Das, and A. Ghosh, “Ensemble feature selection using bi-objective genetic algorithm,” Knowledge-Based Systems, vol.123, pp.116–127, 2017. doi: 10.1016/j.knosys.2017.02.013
[16]	S. Tabakhi and P. Moradi, “Relevance-redundancy feature selection based on ant colony optimization,” Pattern Recognition, vol.48, no.9, pp.2798–2811, 2015. doi: 10.1016/j.patcog.2015.03.020
[17]	E. Hancer, B. Xue, M, J. Zhang, et al., “Pareto front feature selection based on artificial bee colony optimization,” Information Sciences, vol.422, pp.462–479, 2018. doi: 10.1016/j.ins.2017.09.028
[18]	Y. Zhang, S. Cheng, Y. H. Shi, et al., “Cost-sensitive feature selection using two-archive multi-objective artificial bee colony algorithm,” Expert Systems with Applications, vol.137, pp.46–58, 2019. doi: 10.1016/j.eswa.2019.06.044
[19]	J. Kennedy and R. C. Eberhart, “A discrete binary version of the particle swarm algorithm,” in Proceedings of 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation, Orlando, FL, USA, pp.4104–4108, 1997.
[20]	A. Adeli and A. Broumandnia, “Image steganalysis using improved particle swarm optimization based feature selection,” Applied Intelligence, vol.48, no.6, pp.1609–1622, 2018. doi: 10.1007/s10489-017-0989-x
[21]	A. Tran, B. Xue, and M. J. Zhang, “A new representation in PSO for discretization-based feature selection,” IEEE Transactions on Cybernetics, vol.48, no.6, pp.1733–1746, 2018. doi: 10.1109/TCYB.2017.2714145
[22]	Y. Zhang, Y. H. Wang, D. W. Gong, et al., “Clustering-guided particle swarm feature selection algorithm for high-dimensional imbalanced data with missing values,” IEEE Transactions on Evolutionary Computation, vol.26, no.4, pp.616–630, 2022. doi: 10.1109/TEVC.2021.3106975
[23]	J. Too, A. R. Abdullah, and N. M. Saad, “A new co-evolution binary particle swarm optimization with multiple inertia weight strategy for feature selection,” Informatics, vol.6, no.2, article no.21, 2019. doi: 10.3390/informatics6020021
[24]	X. F. Song, Y. Zhang, Y. N. Guo, et al., “Variable-size cooperative coevolutionary particle swarm optimization for feature selection on high-dimensional data,” IEEE Transactions on Evolutionary Computation, vol.24, no.5, pp.882–895, 2020. doi: 10.1109/TEVC.2020.2968743
[25]	S. H. Lee, K. Y. Kim, J. H. Kim, et al., “Effective feature-based automatic modulation classification method using DNN algorithm,” in Proceedings of 2019 International Conference on Artificial Intelligence in Information and Communication, Okinawa, Japan, pp.557–559, 2019.
[26]	J. Hu and L. H. Fan, “Application of JADE to separate complex-valued sources,” in Proceedings of 2011 International Conference on Computer Science and Service System, Nanjing, China, pp.1127–1129, 2011.