Unveil the time delay signature of optical chaos systems with a convolutional neural network

被引：21

作者：

Chen, Yetao ^{[1
]}

Xin, Ronghuan ^{[2
]}

Cheng, Mengfan ^{[1
]}

Gao, Xiaojing ^{[3
]}

Li, Shanshan ^{[1
]}

Shao, Weidong ^{[4
]}

Deng, Lei ^{[1
]}

Zhang, Minming ^{[1
]}

Fu, Songnian ^{[1
]}

Liu, Deming ^{[1
]}

机构：

[1] Huazhong Univ Sci & Technol HUST, Sch Opt & Elect Informat, Natl Engn Lab Next Generat Internet Access Syst N, Wuhan 430074, Peoples R China

[2] China Informat Technol Design & Consulting Inst C, Beijing, Peoples R China

[3] China Univ Geosci, Sch Comp Sci, Bldg 1,North Campus,CUG Lumo Rd 388, Wuhan 430074, Peoples R China

[4] Huazhong Univ Sci & Technol HUST, Sch Cyber Sci & Engn, Wuhan 430074, Peoples R China

来源：

OPTICS EXPRESS | 2020年 / 28卷 / 10期

关键词：

SEMICONDUCTOR-LASERS; FEEDBACK; COMMUNICATION; SYNCHRONIZATION; GENERATION; INJECTION;

D O I：

10.1364/OE.388182

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

We propose a time delay signature extraction method for optical chaos systems based on a convolutional neural network. Through transforming the time delay signature of a one-dimensional time series into two-dimensional image features, the excellent ability of convolutional neural networks for image feature recognition is fully utilized. The effectiveness of the method is verified on chaos systems with opto-electronic feedback and all optical feedback. The recognition accuracy of the method is 100% under normal conditions. For the system with extremely strong nonlinearity, the accuracy can be 93.25%, and the amount of data required is less than traditional methods. Moreover, it is verified that the proposed method possesses a strong ability to withstand the effects of noise. (C) 2020 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

引用

页码：15221 / 15231

页数：11

共 37 条

[21] Routes to chaos and multiple time scale dynamics in broadband bandpass nonlinear delay electro-optic oscillators[J]. Peil, Michael;Jacquot, Maxime;Chembo, Yanne Kouomou;Larger, Laurent;Erneux, Thomas. PHYSICAL REVIEW E, 2009(02)
[22] Petitcolas F.A., 2011, Encyclopedia of cryptography and security, P675, DOI [10.1007/978-1-4419-5906-5_487, DOI 10.1007/978-1-4419-5906-5_487]
[23] Generation of flat wideband chaos based on mutual injection of semiconductor lasers[J]. Qiao, Lijun;Lv, Tianshuang;Xu, Yong;Zhang, Mingjiang;Zhang, Jianzhong;Wang, Tao;Zhou, Rikai;Wang, Qin;Xu, Hongchun. OPTICS LETTERS, 2019(22)
[24] Numerical study of optical feedback coherence in semiconductor laser dynamics[J]. Radziunas, Mindaugas;Little, Douglas J.;Kane, Deborah M. OPTICS LETTERS, 2019(17)
[25] Shao W., 2019, IEEE ACCESS, V7
[26] Time Scales of a Chaotic Semiconductor Laser with Optical Feedback Under the Lens of a Permutation Information Analysis[J]. Soriano, Miguel C.;Zunino, Luciano;Rosso, Osvaldo A.;Fischer, Ingo;Mirasso, Claudio R. IEEE JOURNAL OF QUANTUM ELECTRONICS, 2011(02)
[27] Hybrid electronic/optical synchronized chaos communication system[J]. Toomey, J. P.;Kane, D. M.;Davidovic, A.;Huntington, E. H. OPTICS EXPRESS, 2009(09)
[28] Time delay identification in chaotic cryptosystems ruled by delay-differential equations[J]. Udaltsov, VS;Larger, L;Goedgebuer, JP;Locquet, A;Citrin, DS. JOURNAL OF OPTICAL TECHNOLOGY, 2005(05)
[29] Cracking chaos-based encryption systems ruled by nonlinear time delay differential equations[J]. Udaltsov, VS;Goedgebuer, JP;Larger, L;Cuenot, JB;Levy, P;Rhodes, WT. PHYSICS LETTERS A, 2003(01)
[30] Long Short-Term Memory Neural Network (LSTM-NN) Enabled Accurate Optical Signal-to-Noise Ratio (OSNR) Monitoring[J]. Wang, Chunxiao;Fu, Songnian;Xiao, Zhuopeng;Tang, Ming;Liu, Deming. JOURNAL OF LIGHTWAVE TECHNOLOGY, 2019(16)

← 1 2 3 4 →