收稿日期: 2016-05-09
修回日期: 2016-11-18
网络出版日期: 2017-11-30
基金资助
国家自然科学基金（No.61171085，No.61401266）；上海市教委创新项目基金（No.14ZZ096）资助
SVM Spectrum Sensing Based on Data Pre-processing with Log Function
Received date: 2016-05-09
Revised date: 2016-11-18
Online published: 2017-11-30
翟旭平, 孟田, 王涛 . 采用对数预处理的SVM频谱感知方法[J]. 应用科学学报, 2017 , 35(6) : 726 -734 . DOI: 10.3969/j.issn.0255-8297.2017.06.006
To improve probability of detection and reduce training time, this paper proposes a method of support vector machine (SVM) spectrum sensing based on data preprocessing with a log function. A minimum size of training set is selected, which is applicable with good performance in spectrum sensing. The sample sets are generated with laboratory instruments. The obtained sample sets are pre-processed with a log function to increase the mean difference between sample sets with and without primary users (PU). Experimental results show that, after pre-processing, performance of spectrum sensing is significantly improved under low SNR conditions with detection accuracy 90% or better.
[1] Tripathi P, Chandra A, Kumar A, Sridhara K. Dynamic spectrum hole management in cognitive radio[C]//4th IFIP International Conference on New Technologies, Mobility and Security (NTMS), Paris, France. 2011:1-4.
[2] 潘建国,翟旭平. 基于能量检测的频谱感知方法[J]. 上海大学学报(自然科学版),2009, 15(1):54-59. Pan J G, Zhai X P. Spectrum sensing in cognitive radio based on energy detection[J]. Journal of Shanghai University (Natural Science Edition), 2009, 15(1):54-59. (in Chinese)
[3] Saberali S A, Beaulieu N C. Matched-filter detection of the presence of MPSK signals[C]//2014 International Symposium on Information Theory and its Applications (ISITA), Melbourne, VIC, Australia. 2014:85-89.
[4] 翟旭平,韩延坤,刘祥震. 信号循环谱在衰落与多普勒信道中的特性[J]. 上海大学学报(自然科学版),2010, 16(1):5-9. Zhai X P, Han Y K, Liu X Z. Cyclic feature of signals in fading doppler channels[J]. Journal of Shanghai University (Natural Science Edition),2010, 16(1):5-9. (in Chinese)
[5] Zhai X P, He H G, Zheng G X. Optimization of threshold for local spectrum sensing with energy detector[J]. Journal of Shanghai University (English Edition), 2011, 15:132-136.
[6] Jia M X, Du J Q, Cheng T. An improved detection algorithm of face with combining adaBoost and SVM[C]//25th Chinese Control and Decision Conference, IEEE, Guilin, China, 2013:2459-2463.
[7] Chamasemani F F, Singh Y P. Multi-class support vector machine (SVM) classifiers-an application in hypothyroid detection and classification[C]//International Conference on Bio-inspired Computing:Theories and Applications, 2011:351-356.
[8] Zhang D D, Zhai X P. SVM-based spectrum sensing in cognitive radio[C]//International Conference on Wireless Communications, Networking and Mobile Computing. IEEE, Wuhan, China. 2011, 15(1):1-4.
[9] Zhang D D, Zhai X P. SVM-based spectrum sensing in cognitive radio[C]//7th International Conference on Wireless Communications, Networking and Mobile Computing, 2011:1-4.
[10] Zhai X P, Wang X P. A new SVM-based spectrum sensing method[C]//WIT Transactions on Information and Communication Technologies, 2014:113-120.
[11] Zhai X P, Liu Q M. A SVM-based spectrum sensing method[C]//Proceedings of the 2014 International Conference on Multimedia, Communication and Computing Application, Xiamen, China, 2014, CRC Press, 2015:285-289.
[12] Yang H L, Xie X Z, Wang R Y. SOM-GA-SVM detection based spectrum sensing in cognitive radio[C]//2012 International Conference on Wireless Communications, Networking and Mobile Computing, Shanghai, China. 2012:1-7.
/
| 〈 |
|
〉 |
