Koninklijke Philips Corporation N.v.

Pedro Miguel Fonseca

Reinder Haakma

Ronaldus Maria Aarts

Xi Long

Koen Theo Johan De Groot

Igor Berezhnyy

Nicolaas Gregorius Petrus Den Teuling

Jenny Margarito

Erik Gosuinus Petrus Schuijers

Gary Nelson Garcia Molina

Adrienne Heinrich

Milan Pastrnak

A method and system for detecting sleep apnea involves determining the sleep stage, and detecting an apnea event based on a physiological sensor signal using selection of a detection algorithm which is dependent on the determined sleep stage. By taking account of the sleep stage when performing an automated apnea detection process, the accuracy of the apnea detection is improved.

Sleep apnea detection system and method

A method for generating sleep apnea information for a portion of body sensor data. The method of generating sleep apnea information is made dependent upon a determined presence or absence of arrhythmia within the portion of body sensor data. A first sleep apnea detection methodology is used in response to an absence of arrhythmia being detected within the portion of body sensor data.

Arrhythmic heartbeat resilient sleep apnea detection

The present disclosure pertains to a system configured to detect slow wave sleep and/or non-slow wave sleep in a subject during a sleep session based on a predicted onset time of slow wave sleep and/or a predicted end time of slow wave sleep that is determined based on changes in cardiorespiratory parameters of the subject. Cardiorespiratory parameters in a subject typically begin to change before transitions between non-slow wave sleep and slow wave sleep. Predicting this time delay between the changes in the cardiorespiratory parameters and the onset and/or end of slow wave sleep facilitates better (e.g., more sensitive and/or more accurate) determination of slow wave sleep and/or non-slow wave sleep.

System and method for slow wave sleep detection

The present disclosure pertains to a system configured to determine one or more parameters based on cardiorespiratory information from a subject and determine sleep stage classifications based on a discriminative undirected probabilistic graphical model such as Conditional Random Fields using the determined parameters. The system is advantageous because sleep is a structured process in which parameters determined for individual epochs are not independent over time and the system determines the sleep stage classifications based on parameters determined for a current epoch, determined relationships between parameters, sleep stage classifications determined for previous epochs, and/or other information. The system does not assume that determined parameters are discriminative during an entire sleep stage, but maybe indicative of a sleep stage transition alone. In some embodiments, the system comprises one or more sensors, one or more physical computer processors, electronic storage, and a user interface.

System and method for cardiorespiratory sleep stage classification

Systems and methods for providing sensory stimuli induce and/or enhance sleep and/or slow wave neural activity of a subject during sleep. Operation of the systems and methods is based on measured information related to cardiac attributes and/or respiratory attributes of the subject, and corresponding cardiac parameters and/or respiratory parameters based thereon. Attributes may be measured and/or monitored via one or more sensors, e.g. worn on an extremity of the subject and/or placed at a distance from the subject. Sensory stimulation delivered to the subject during specific targeted periods of sleep may enhance slow wave neural activity.

System and method for enhancing sleep slow wave activity based on cardiac characteristics or respiratory characteristics

A sleep monitoring device () is disclosed for measuring a biophysical variable () of a living-being (), comprising at least two pressure sensors (-) spatially arranged in a predefined planar geometry. The living-being rests on the supporting layer () contacted by the sensors that generate sensor signals in response to pressure caused by the living being via the supporting layer. A processing unit () determines the position of the living-being on the supporting layer based on differences between the sensor signals; a magnitude attenuation factor is determined based on the position of the living-being and a position of a sensor; the biophysical variable is determined from a sensor signal generated by that sensor, including a magnitude correction based on the magnitude attenuation factor. The effect of the invention is that only few sensors are needed to measure a biophysical variable accurately, irrespective of the living-being's position on the supporting layer.

Device and method for sleep monitoring

An actigraphy method includes receiving a physiological parameter signal as a function of time for a physiological parameter other than body motion (such as electrocardiography or a respiration monitor), computing a body motion artifact (BMA) signal as a function of time from the physiological parameter signal (for example, using a local signal power signal, a local variance signal, a short-time Fourier transform, or a wavelet transform over epochs of duration on order a few minutes or less), and computing an actigraphy signal as a function of time from the BMA signal, for example by applying a linear transform to the BMA signal and optionally applying filtering such as median removal and/or high-pass filtering.

Actigraphy methods and apparatuses

An electronic switch for controlling a deviceby switching a function of the device at least in dependence on a sleep stage of a human. The switch includes an EEG data interface configured to receive brain activity data from an EEG sensorconfigured to monitor electrical activity of the brain of the human during a training phase, an EEG sleep classifierconfigured to classify sleep stages of the human from the received brain activity data, and a body data interface configured to receive body activity data from an alternative sensorconfigured to monitor a bodily function of the human both during the training phase and during a subsequent usage phase. The alternative sensor is different from the EEG sensor, and the electronic switch further includes an alternative sleep classifierand a machine learning system, the machine learning system being configured to train the alternative sleep classifierto classify a sleep stage of the human from the received body activity data, the learning system using sleep stages classified by the EEG sleep classifierand concurrent body activity data received from the alternative sensor as training data, wherein in the usage phase, the deviceis controlled in dependency on sleep stages of the human classified by the alternative sleep classifier. A control logicis configured to at least determine that the classified sleep stage is one of a set of particular sleep stages and to switch a function of the device at least in dependency on said determination.

Electronic switch for controlling a device in dependency on a sleep stage

A method of generating a summary of an audio/visual data stream is provided, the data stream comprising a plurality of consecutive frames having audio and visual properties. A plurality of shots of an audio/visual data stream are detected (step). A plurality of segments of the audio/visual data stream are determined (step), each segment comprising a plurality of the shots of the data stream having similar visual properties. A segment of the determined plurality of segments is selected (step). For each shot of said selected segment of said data stream, the audio in a plurality of consecutive frames which occur after the end of said shot is extracted (step). At least one of the shots is selected based on the extracted audio (step). A summary is generated to include the selected at least one of the shots (step).

Growing community of inventors

Borgerhout, Belgium

Pedro Miguel Fonseca