Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 11
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Machine learning algorithms for predicting the amplitude of chaotic laser pulses

  • Amil, Pablo
  • Soriano, Miguel C.
  • Masoller, Cristina
Forecasting the dynamics of chaotic systems from the analysis of their output signals is a challenging problem with applications in most fields of modern science. In this work, we use a laser model to compare the performance of several machine learning algorithms for forecasting the amplitude of upcoming emitted chaotic pulses. We simulate the dynamics of an optically injected semiconductor laser that presents a rich variety of dynamical regimes when changing the parameters. We focus on a particular dynamical regime that can show ultrahigh intensity pulses, reminiscent of rogue waves. We compare the goodness of the forecast for several popular methods in machine learning, namely, deep learning, support vector machine, nearest neighbors, and reservoir computing. Finally, we analyze how their performance for predicting the height of the next optical pulse depends on the amount of noise and the length of the time series used for training., P. A. and C. M. acknowledge support by the BE-OPTICAL project (No. H2020-675512). C. M. also acknowledges support from the Spanish Ministerio de Ciencia, Innovación y Universidades (No. PGC2018-099443-B-I00) and ICREA ACADEMIA. M. C. S. was supported through a “Ramon y Cajal” Fellowship (No. RYC-2015-18140). This work is the result of a collaboration established within the Ibersinc network of excellence (No. FIS2017-90782-REDT).
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Speckle reduction in double-pass retinal images

UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Incoherent Light Sources for Speckle Reduction in Double Pass Ocular Imaging

UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Whole anterior segment and retinal swept source OCT for comprehensive ocular screening

  • Rodríguez Aramendía, Ana|||0000-0002-5855-9435
  • Díaz Douton, Fernando|||0000-0003-3699-015X
  • Fernández Trullàs, José
  • Falgueras Navarro, Pol
  • González Alvarez, Laura
  • Pujol Ramo, Jaume|||0000-0003-0811-9244
  • Grulkowski, Ireneusz
  • Güell, José Luis
Whole eye visualization and morphometry are of high relevance in clinical practice. However, most standard ophthalmic OCT instruments are dedicated either to retinal or to anterior segment imaging. We demonstrate a swept source optical coherence tomography system (SS-OCT) that images both the whole anterior segment and the retina alternately using a single source and detector. A pilot population was imaged with the proof of concept prototype. We demonstrate the clinical potential of whole eye OCT screening for the description and early detection of relevant clinical features in the anterior segment and retina of several patients., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Machine learning algorithms for predicting the amplitude of chaotic laser pulses

  • Amil Marletti, Pablo|||0000-0002-6253-9242
  • Cornelles Soriano, Miguel
  • Masoller Alonso, Cristina|||0000-0003-0768-2019
Forecasting the dynamics of chaotic systems from the analysis of their output signals is a challenging problem with applications in most fields of modern science. In this work, we use a laser model to compare the performance of several machine learning algorithms for forecasting the amplitude of upcoming emitted chaotic pulses. We simulate the dynamics of an optically injected semiconductor laser that presents a rich variety of dynamical regimes when changing the parameters. We focus on a particular dynamical regime that can show ultrahigh intensity pulses, reminiscent of rogue waves. We compare the goodness of the forecast for several popular methods in machine learning, namely, deep learning, support vector machine, nearest neighbors, and reservoir computing. Finally, we analyze how their performance for predicting the height of the next optical pulse depends on the amount of noise and the length of the time series used for training. Predicting the dynamical evolution of chaotic systems is an extremely challenging problem with important practical applications. With unprecedented advances in computer science and artificial intelligence, many algorithms are nowadays available for time series forecasting. Here, we use a well-known chaotic system of an optically injected semiconductor laser that exhibits fast and irregular pulsing dynamics to compare the performance of several algorithms [deep learning, support vector machine (SVM), nearest neighbors, and reservoir computing (RC)] for predicting the amplitude of the next pulse. We compare the predictive power of such machine learning methods in terms of data requirements and the robustness toward the presence of noise in the evolution of the system. Our results indicate that an accurate prediction of the amplitude of upcoming chaotic pulses is possible using machine learning techniques, although the presence of extreme events in the time series and the consideration of stochastic contributions in the laser model bound the accuracy that can be achieved., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Experimental characterization of the speckle pattern at the output of a multimode optical fiber

  • Halpaap, Donatus
  • Tiana Alsina, Jordi|||0000-0001-8359-9378
  • Vilaseca Ricart, Meritxell|||0000-0001-8166-1617
  • Masoller Alonso, Cristina|||0000-0003-0768-2019
Speckle patterns produced by coherent waves interfering with each other are undesirable in many imaging applications (for example, in laser projection systems) but on the other hand, they contain useful information that can be exploited (for example, for blood flow analysis or reconstruction of the object that generates the speckle). It is therefore important to understand how speckle can be enhanced or reduced by tailoring the coherence of laser light. Using a conventional semiconductor laser and a multimode optical fiber we study experimentally how the speckle pattern depends on the laser pump current and on the image acquisition settings. By varying the pump current from below to above the lasing threshold, and simultaneously tuning the image exposure time to compensate for the change in brightness, we find conditions that allow for recorded images with similar average intensity, but with speckle contrast (the standard deviation of the intensity over the average intensity) as low as 0.16, or as high as 0.99., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Experimental characterization of the speckle pattern at the output of a multimode optical fiber

  • Halpaap, Donatus
  • Tiana Alsina, Jordi
  • Vilaseca Ricart, Meritxell
  • Masoller Alonso, Cristina
Speckle patterns produced by coherent waves interfering with each other are undesirable in many imaging applications (for example, in laser projection systems) but on the other hand, they contain useful information that can be exploited (for example, for blood flow analysis or reconstruction of the object that generates the speckle). It is therefore important to understand how speckle can be enhanced or reduced by tailoring the coherence of laser light. Using a conventional semiconductor laser and a multimode optical fiber we study experimentally how the speckle pattern depends on the laser pump current and on the image acquisition settings. By varying the pump current from below to above the lasing threshold, and simultaneously tuning the image exposure time to compensate for the change in brightness, we find conditions that allow for recorded images with similar average intensity, but with speckle contrast (the standard deviation of the intensity over the average intensity) as low as 0.16, or as high as 0.99., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Incoherent Light Sources for Speckle Reduction in Double Pass Ocular Imaging

Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Whole anterior segment and retinal swept source OCT for comprehensive ocular screening

  • Rodríguez Aramendía, Ana
  • Díaz Douton, Fernando
  • Fernández Trullàs, José
  • Falgueras Navarro, Pol
  • González Alvarez, Laura
  • Pujol Ramo, Jaume
  • Grulkowski, Ireneusz
  • Güell, José Luis
Whole eye visualization and morphometry are of high relevance in clinical practice. However, most standard ophthalmic OCT instruments are dedicated either to retinal or to anterior segment imaging. We demonstrate a swept source optical coherence tomography system (SS-OCT) that images both the whole anterior segment and the retina alternately using a single source and detector. A pilot population was imaged with the proof of concept prototype. We demonstrate the clinical potential of whole eye OCT screening for the description and early detection of relevant clinical features in the anterior segment and retina of several patients., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Machine learning algorithms for predicting the amplitude of chaotic laser pulses

  • Amil Marletti, Pablo
  • Cornelles Soriano, Miguel
  • Masoller Alonso, Cristina
Forecasting the dynamics of chaotic systems from the analysis of their output signals is a challenging problem with applications in most fields of modern science. In this work, we use a laser model to compare the performance of several machine learning algorithms for forecasting the amplitude of upcoming emitted chaotic pulses. We simulate the dynamics of an optically injected semiconductor laser that presents a rich variety of dynamical regimes when changing the parameters. We focus on a particular dynamical regime that can show ultrahigh intensity pulses, reminiscent of rogue waves. We compare the goodness of the forecast for several popular methods in machine learning, namely, deep learning, support vector machine, nearest neighbors, and reservoir computing. Finally, we analyze how their performance for predicting the height of the next optical pulse depends on the amount of noise and the length of the time series used for training. Predicting the dynamical evolution of chaotic systems is an extremely challenging problem with important practical applications. With unprecedented advances in computer science and artificial intelligence, many algorithms are nowadays available for time series forecasting. Here, we use a well-known chaotic system of an optically injected semiconductor laser that exhibits fast and irregular pulsing dynamics to compare the performance of several algorithms [deep learning, support vector machine (SVM), nearest neighbors, and reservoir computing (RC)] for predicting the amplitude of the next pulse. We compare the predictive power of such machine learning methods in terms of data requirements and the robustness toward the presence of noise in the evolution of the system. Our results indicate that an accurate prediction of the amplitude of upcoming chaotic pulses is possible using machine learning techniques, although the presence of extreme events in the time series and the consideration of stochastic contributions in the laser model bound the accuracy that can be achieved., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Speckle reduction in double-pass retinal images