In this paper, we study the problem of predicting optical chaos for semiconductor lasers, where data uncertainty can severely degrade the performance of chaos prediction. We hereby propose a multi-stage extreme learning machine (MSELM) based approach for the continuous prediction of optical chaos, which handles data uncertainty effectively. Rather than relying on pilot signals for conventional reservoir learning, the proposed approach enables the use of predicted optical intensity as virtual training samples for the MSELM model learning, which leads to enhanced prediction performance and low overhead. To address the data uncertainty in virtual training, total least square (TLS) is employed for the update of the proposed MSELM's parameters with simple updating rule and low complexity. Simulation results demonstrate that the proposed MSELM can execute the continuous optical chaos predictions effectively. The chaotic time series can be continuously predicted for a time period in excess of 4 ns with a normalized mean squared error (NMSE) lower than 0.012. It also demands much fewer training samples than state-of-the-art learning-based methods. In addition, the simulation results show that with the help of TLS, the length of prediction is improved significantly as the uncertainty is handled properly. Finally, we verify the prediction ability of the multi-stage ELM under various laser parameters, and make the median boxplot of the predicted results, which shows that the proposed MSELM continues to produce accurate and continuous predictions on time-varying optical chaos.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1364/OE.534975 | DOI Listing |
Phys Rev E
November 2024
Departamento de Química, Universidad Autónoma de Madrid, Cantoblanco, 28049 Madrid, Spain.
We study dynamical localization in an ultracold atom confined in an optical lattice that is simultaneously shaken by two competing pulsatile modulations with different amplitudes, periods, and waveforms. The effects of finite-width time pulses, modulation waveforms, and commensurable and incommensurable driving periods are investigated. We describe a particularly complex scenario and conclude that dynamical localization can survive, or even increase, when a periodic modulation is replaced by a quasiperiodic one of equal amplitude.
View Article and Find Full Text PDFParallel generation of multi-channel chaos is critical to applications, and the key challenge is the simultaneous generation of broadband chaos with multiple channels and low correlation. Here, we experimentally demonstrate a parallel broadband chaos generation scheme using a single long-active-cavity Fabry-Perot (LC-FP) semiconductor laser under optical feedback. The active-cavity length is designed to be 1500 μm, so the power spectrum of chaos is expanded and flattened by the mode-beating effect.
View Article and Find Full Text PDFChaos
December 2024
School of Electrical Engineering and Computer Science, College of Engineering & Mines, University of North Dakota, Grand Forks, North Dakota 58202-8367, USA.
This study examines the dynamical properties of the Ikeda map, with a focus on bifurcations and chaotic behavior. We investigate how variations in dissipation parameters influence the system, uncovering shrimp-shaped structures that represent intricate transitions between regular and chaotic dynamics. Key findings include the analysis of period-doubling bifurcations and the onset of chaos.
View Article and Find Full Text PDFNanophotonics
August 2024
Wuhan National Laboratory for Optoelectronics, School of Optical and Electronic Information, Huazhong University of Science and Technology, Wuhan 430074, China.
In this paper, we study the problem of predicting optical chaos for semiconductor lasers, where data uncertainty can severely degrade the performance of chaos prediction. We hereby propose a multi-stage extreme learning machine (MSELM) based approach for the continuous prediction of optical chaos, which handles data uncertainty effectively. Rather than relying on pilot signals for conventional reservoir learning, the proposed approach enables the use of predicted optical intensity as virtual training samples for the MSELM model learning, which leads to enhanced prediction performance and low overhead.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!