Abstract: An anomaly detector uses two neural networks, the first, a general purpose classifying convolutional neural network operates as a teacher neural network, while a second neural network in an auto-encoder type configuration. Each of the two neural networks receives the same input stream, and generates respective feature outputs at different levels, corresponding to different resolutions for image data. The respective outputs of the two neural networks are compared at each level, and the resulting difference values consolidated across the difference levels to obtain a final difference value. In a training phase this difference value is used to drive the determination of the weights and biases of the auto-encoder, so as to obtain a auto-encoder trained for a particular input type, under the influence of the teacher neural network. In an operational mode, the difference value is compared to a threshold to determine whether a particular sample is anomalous or not.

Abstract: A device comprising at least one processing logic configured for: obtaining an input vector representing an input data sample; until a stop criterion is met, performing successive iterations of: using an autoencoder trained using a set of reference vectors to encode the input vector into a compressed vector, and decode the compressed vector into a reconstructed vector; calculating a reconstruction loss between the reconstructed and the input vectors, and a gradient of the reconstruction loss; updating said input vector for the subsequent iteration using said gradient.

Abstract: A wearable electronics system for helping a user fall asleep comprising: a wearable portion; an electronic portion comprising: an acquisition module for making a physiological measurement of the user; a playing module for playing an acoustic stimulation to the user; a memory storing a plurality of elemental acoustic stimulation sequences; a processing module comprising a selection module which selects elemental acoustic stimulation sequences depending on a history of previously played acoustic stimulations and depending on the physiological measurement, until the end of the period of falling asleep The acquisition module and the playing module are assembled in the wearable portion.

Abstract: According to the method to measure in real-time the phase of a pseudo-periodic physiological signal of a user: one provides a physiological signal of the user;—a trigonometric function determination module of a processor determines parameters of a trigonometric function, which minimize a distance between the physiological signal and the trigonometric function on the time interval ]ta; tb[; and—a phase determination module of a processor determines the phase of the physiological signal at time tb based on the phase of the trigonometric function at time tb.

Abstract: The method for commanding the production of an acoustic waveform based on a physiological control signal, includes: one provides sampled sound data including S sound samples stored on a data carrier; repeatedly, for n successive respective time intervals [tn; tn+1[ between an initial time ta and a final time tb: one provides a physiological control signal phi(t) as a function of time, during the current time interval [tn; tn+1[; a rate determination module of a processor determines a rate rn of samples to be played during that time interval based on a value phi (tn) of the physiological control signal at time tn; a command module of the processor commands the play of a part of the acoustic waveform from the sampled sound data as a function of the determined rate rn of samples.

Abstract: An image sensor including: a first control circuit; a plurality of pixels, each including a photodetector, a comparator of the level of an output signal of the photodetector with a reference value, and a second control circuit connected to the first control circuit, the second circuit being capable of sending a signal of address reading request to the first circuit when the pixel turns on, of receiving an address reading acknowledgement signal transmitted by the first circuit, and of deactivating the pixel on reception of the reading acknowledgement signal; and at least one third control circuit capable, when a pixel receives a reading acknowledgement signal, of blocking the transmission of address reading request signals in at least one adjacent pixel.

Abstract: An image sensor including: a first control circuit; a plurality of pixels, each including a photodetector, a comparator of the level of an output signal of the photodetector with a reference value, and a second control circuit connected to the first control circuit, the second circuit being capable of sending a signal of address reading request to the first circuit when the pixel turns on, of receiving an address reading acknowledgement signal transmitted by the first circuit, and of deactivating the pixel on reception of the reading acknowledgement signal; and at least one third control circuit capable, when a pixel receives a reading acknowledgement signal, of blocking the transmission of address reading request signals in at least one adjacent pixel.

Abstract: A method of compression preprocessing of raw data ui(tN) of measurements of electrocorticographic signals (ECoG) evolving over time with the aid of electrodes disposed in direct contact with a cortex comprises an actual step of compression preprocessing in which each raw signal ui(tN) acquired by the observed electrode i is transformed into a preprocessed signal ?i (tN) equal to the difference between a first term and a second term and appropriate for a second entropy encoding step. The first term is equal to the raw signal acquired at the electrode i at the current instant tN, and the second term is a prediction function fi which depends on past raw signals observed in a near past at at least neighbour electrodes ?i(j) of the observed electrode or at most at neighbour electrodes ?i(j) of the observed electrode i and at the observed electrode.