No prior recognition method of modulation mode by partition-fractal and SVM learning method

Shanshan Li; Qi Zhang; Xiangjun Xin; Ran Gao; Sitong Zhou; Ying Tao; Yufei Shen; Huan Chang; Qinghua Tian; Feng Tian; Yongjun Wang; Leijing Yang

doi:10.3788/COL202018.111404

Chinese Optics Letters, Volume. 18, Issue 11, 111404(2020)

No prior recognition method of modulation mode by partition-fractal and SVM learning method

Shanshan Li¹, Qi Zhang^1,2,3、*, Xiangjun Xin^1,2,3, Ran Gao⁴, Sitong Zhou¹, Ying Tao⁵, Yufei Shen⁶, Huan Chang⁷, Qinghua Tian^1,2,3, Feng Tian^1,2,3, Yongjun Wang^1,2,3, and Leijing Yang^1,2,3

Author Affiliations

¹School of Electronic Engineering, Beijing University of Posts and Telecommunications (BUPT), Beijing 100876, China

²Beijing Key Laboratory of Space-round Interconnection and Convergence, BUPT, Beijing 100876, China

³State Key Laboratory of Information Photonics and Optical Communications, BUPT, Beijing 100876, China

⁴The Advanced Research Institute of Multidisciplinary Science, Beijing Institute of Technology, Beijing 100081, China

⁵China Academy of Space Technology, Beijing 100094, China

⁶China Satellite Communication Co., Ltd., Beijing 100048, China

⁷School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China

show less

Figures & Tables(7)

Fig. 1. System scheme of AMC implementation in satellite communication system.

Download full size

View in Article

$Description of the partition-fractal method.$

Fig. 2. Description of the partition-fractal method.

Download full size

View in Article

Fig. 3. Calculation process of constellation diagram feature matrix.

Download full size

View in Article

Fig. 4. Comparison diagram of classifier performance under different learning algorithms.

Download full size

View in Article

Fig. 5. Classification accuracy in different modulation modes (SNR, in dB). (a) SVM; (b) bagging; (c) KNN; (d) classification tree; (e) AdaBoost.

Download full size

View in Article

Table 1. Simulation Parameters

View table

View in Article

Table 1. Simulation Parameters

Symbol rate	1200 bit/s
Sampling frequency	4800 Hz
Frequencies separation	5 Hz
Signal duration	1 s
Signal selectable signal-to-noise ratio range	$0 - 20 dB$
Modulation modes	BASK, BPSK, BFSK, QASK, QPSK, QFSK, 8ASK, 8PSK, 8FSK
Number of constellations	18,900
Constellations size	$512 \times 512 pixels$
Training and test ratio	7:3

Table 2. Accuracy of Classifier under Different SNR
View table
View in Article
Table 2. Accuracy of Classifier under Different SNR
SNR/dB 1 4 6 12 16 20
Accuracy 0.9519 0.9667 0.9741 0.9778 0.9926 1

Tools

Get Citation

Copy Citation Text

Shanshan Li, Qi Zhang, Xiangjun Xin, Ran Gao, Sitong Zhou, Ying Tao, Yufei Shen, Huan Chang, Qinghua Tian, Feng Tian, Yongjun Wang, Leijing Yang, "No prior recognition method of modulation mode by partition-fractal and SVM learning method," Chin. Opt. Lett. 18, 111404 (2020)

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites