Remote recovery of audio signals from videos of optical speckle patterns: a comparative study of signal recovery algorithms.

Optical remote sensors are nowadays ubiquitously used, thanks to unprecedented advances in the last decade in photonics, machine learning and signal processing tools. In this work we study experimentally the remote recovery of audio signals from the silent videos of the movement of optical speckle patterns. This technique can be used even when in between the source and the receiver there is a medium that does not allow for the propagation of sound waves. We use a diode laser to generate a speckle pattern on the membrane of a loudspeaker and a low-cost CCD camera to record the video of the movement of the speckle pattern when the loudspeaker plays an audio signal. We perform a comparative analysis of six signal recovery algorithms. In spite of having different complexity and computational requirements, we find that the algorithms have (except for the simplest one) good performance in terms of the quality of the recovered signal. The best trade-off, in terms of computational costs and performance, is obtained with a new method that we propose, which recovers the signal from the weighted sum of the intensities of all the pixels, where the signs of the weights are determined by selecting a reference pixel and calculating the signs of the cross-correlations of the intensity of the reference pixel and the intensities of the other pixels.

Machine learning algorithms for predicting the amplitude of chaotic laser pulses.

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.

Network-based features for retinal fundus vessel structure analysis.

Retinal fundus imaging is a non-invasive method that allows visualizing the structure of the blood vessels in the retina whose features may indicate the presence of diseases such as diabetic retinopathy (DR) and glaucoma. Here we present a novel method to analyze and quantify changes in the retinal blood vessel structure in patients diagnosed with glaucoma or with DR. First, we use an automatic unsupervised segmentation algorithm to extract a tree-like graph from the retina blood vessel structure. The nodes of the graph represent branching (bifurcation) points and endpoints, while the links represent vessel segments that connect the nodes. Then, we quantify structural differences between the graphs extracted from the groups of healthy and non-healthy patients. We also use fractal analysis to characterize the extracted graphs. Applying these techniques to three retina fundus image databases we find significant differences between the healthy and non-healthy groups (p-values lower than 0.005 or 0.001 depending on the method and on the database). The results are sensitive to the segmentation method (manual or automatic) and to the resolution of the images.

Unsupervised feature extraction of anterior chamber OCT images for ordering and classification.

We propose an image processing method for ordering anterior chamber optical coherence tomography (OCT) images in a fully unsupervised manner. The method consists of three steps: Firstly we preprocess the images (filtering the noise, aligning and normalizing the resolution); secondly, a distance measure between images is computed for every pair of images; thirdly we apply a machine learning algorithm that exploits the distance measure to order the images in a two-dimensional plane. The method is applied to a large (~1000) database of anterior chamber OCT images of healthy subjects and patients with angle-closure and the resulting unsupervised ordering and classification is validated by two ophthalmologists.

Organization and identification of solutions in the time-delayed Mackey-Glass model.

Multistability in the long term dynamics of the Mackey-Glass (MG) delayed model is analyzed by using an electronic circuit capable of controlling the initial conditions. The system's phase-space is explored by varying the parameter values of two families of initial functions. The evolution equation of the electronic circuit is derived and it is shown that, in the continuous limit, it exactly corresponds to the MG model. In practice, when using a finite set of capacitors, an excellent agreement between the experimental observations and the numerical simulations is manifested. As the delay is increased, different periodic or aperiodic solutions appear. We observe abundant periodic solutions that have the same period but a different alternation of peaks of dissimilar amplitudes and propose a novel symbolic method to classify these solutions.