Koninklijke Philips Corporation N.v.

Philips Lighting Holding B.v.

Signify Holding B.v.

Beijing Xiaomi Mobile Software Co., Ltd.

Continental Automotive Gmbh

Ingrid Christina Maria Flinsenberg

Alexandre Georgievich Sinitsyn

Marc Aoun

Saeed Reza Bagheri

Evert Jan Van Loenen

Roel Peter Geert Cuppen

Leszek Holenderski

Johanna Maria De Bont

Parikshit Shah

Bartel Marinus Van De Sluis

Yi Qiang Yu

Ningjiang Chen

Erik Schuijers

Nicolle Hanneke Van Schijndel

Winfried Antonius Henricus Berkvens

Stephan Schlumbohm

Yuan Shu

Warner Ten Kate

Sheng Kim

Warner Rudoph Theophile Ten Kate

Elke Marieke Lambert Daemen

Rudie Bernardus Maria Schonenberg

Rosemarie Jolanda Elise Rajae-Joordens

Jacobus Hedrikus Verriet

A pollution estimation system () for estimating pollution level caused by exhaust gas of motor vehicles is provided. The system comprises an acoustic sensor interface () arranged to obtain use-data from an acoustic sensor comprising an audio sample of a motor vehicle sound and a trained exhaust gas model unit () arranged to receive as input the audio sample of the use-data and to apply a trained exhaust gas model to the received audio sample to produce an estimated pollution level associated with the received audio sample. The trained exhaust gas model has been obtained by training an exhaust gas model on multiple training items using a machine learning algorithm, the multiple training items comprising multiple audio samples of motor vehicle sounds obtained from one or more acoustic sensors and associated pollution levels.

Pollution estimation system

A device () for and a method of determining a length of a history of instances of a first type of data are provided. The device comprises a second data set unit (), a first data set unit (), a first conditional entropy unit (), a threshold unit (), and a length determining unit (). The first data set unit, the second data set unit and the threshold unit obtain input data. The first conditional entropy unit determines a first conditional entropy for a second data set given a first data set. The determining unit searches for a length of the relevant history by determining a smallest length for sequences of a reduced first set of data for which a second conditional entropy for the second set of data, given the reduced first set of data, is within a maximum entropy increase threshold from the first conditional entropy.

Device for and method of determining a length of a relevant history

A data reduction device () for and a method of reducing a data set based on a subset of variables from a set of variables are provided. Instances of the plurality of variables comprise information to predict an instance of a further type of data. The device comprises a first data set unit (), a second data set unit (), a searching unit () and a data reduction unit (). The first data set unit obtains a first set comprising tuples of instances of data. The second data set unit obtains a second set comprising instances of the further type of data. Each instance of the second set corresponds to one of the tuples of the first set. The searching unit obtains a reduced set of variables that represents an at least local optimum of an optimization function being a combination of a first mutual information value between the reduced first set and the second set and a penalty value being based on a number of variables in the reduced set of variables.

Data reduction for reducing a data set

A lighting system () comprises at least one lamp () and a processing unit () for estimating an end-of-life of the at least one lamp (). The processing unit () is configured to receive a lamp burning time during which the at least one lamp is turned on and a forecasted temperature over a selected period of time at a location of the at least one lamp. The processing unit () is configured to estimate the end of life of the at least one lamp based on the lamp burning time and the forecasted temperature. By using the forecasted temperature, use of dedicated lamp sensors measuring internal parameters of the lamp usable for the end-of-life estimate may be avoided and the estimate may be simplified.

Lighting system and a method of estimating an end of life of at least one lamp thereof

A device () for and method of determining clusters of sequences of instances of a first type of data for compacting a data set comprising sequences of instances of the first type of data is provided. Also a method of compacting a data set, a method of transmitting compacted data and a computer program product are provided. In a sequence clustering unit () of the device, sequences of a first set of data are clustered on basis of conditional probabilities. Each unique sequence of the first set of data is associated with one or more conditional probabilities that an instance of the second set of data has a specific value given the unique sequence. In the clustering a significant part of the mutual information between the first set of data and the second set of data is maintained.

Device for and method of determining clusters

A decision support unit for an outdoor lighting network () is disclosed. The outdoor lighting network includes a plurality of lighting units (LU-LU) grouped in a plurality of zones (). The decision support unit includes a controller () including safety monitor module () arranged to determine a safety factor for each of the plurality of zones (). The safety factor for each the plurality of zonesis determined using at least one factor that represents an aspect that contributes to an assessment of each of the plurality of zones' safety. The decision support unit may also include a decision module () that determines a repair priority of a faulty lighting unit (LU-LU) using the safety factors determined by the safety monitor module ().

Decision support system for a lighting network

A computing unit () and a method are provided. The method comprises obtaining data being indicative of operational statuses and geographic positions of a plurality of street devices (), and obtaining region description data for a region in which the street devices are located. Further, the geographic positions and operational statuses of the street devices are correlated with the region description data.

Monitoring of operational status of street devices

Alighting system may include: at least one controller which may be configured to: obtain lighting logging data including feature information related to features of the lighting system and obtained from a plurality of feature spaces; determine lighting prediction data which predicts at least one component failure in the lighting system at a future time in accordance with the lighting logging data and include at least one complex feature; model predicted component failures which are predicted to occur at a future time in accordance with the lighting prediction data and maintenance cost; and/or store the predicted component failures model in a memory.

Intelligent lighting system with predictive maintenance scheduling and method of operation thereof

The invention relates to a method and to an apparatus that enables the ambience of e.g. hospital rooms to adapt according the scheduled or non-scheduled activities throughout the day. The ambience generated by lights, sound devices, image, movie displays and other devices is controlled by an ambience controller () in dependence of day phases defined by a patient's day schedule or in dependence of other non-scheduled phases which may have been initiated in dependence of a trigger signal () generated in response to activities such as the entering of a caterer.

Adaptive control of ambience settings

A lighting system which includes at least one controller which is configured to: obtain lighting logging information related to operation of a lighting system including a plurality of lamps from a lighting logging data portion; model lamp failures in the lighting system in accordance with the lighting logging information in the lighting system and maintenance cost, the model having a time range; predict failures in the lighting system at future times at least in part in accordance with the prediction model; form a graphical user interface (GUI) which includes a graphical depiction of the model; and render the GUI on a rendering device.

A method for routing a medical alert to a selected staff member-, the method comprising receiving an alert signal generated by an alert generation device-, obtaining the current location and identity of multiple staff members from a location tracking system-configured to track the locations of the multiple staff members, upon receiving the alert signal, selecting from the multiple staff members a selected staff member by at least determining that the distance between a location of the alert generation device and the location of the selected staff member is shorter than the distance between the location of the alert generation device and the location of at least one of the multiple staff members other than the selected staff member, and sending an alert signal to an individually addressable mobile device associated with the selected staff member.

Device and method for routing a medical alert to a selected staff member

There is provided a fall detection system, comprising one or more sensors for monitoring the movement of a user of the fall detection system and for generating corresponding signals; means for determining a threshold from one or more measurements of the physical condition of the user; a processor for analyzing the signals to identify a fall by the user; analyzing the signals to identify a period of inactivity of the user following the fall; and comparing the length of the period of inactivity of the user with the threshold to determine the severity of the fall.

Fall detection system

The invention relates to a fall detection system, for detecting human fall incidents. The detection system comprises a sensor module to be worn by a user, for collecting motion data of his body, for instance acceleration data; first evaluation logic for identifying a potential fall incident on the basis of an impact observed in the acceleration data; and second evaluation logic for verifying that the sensor module is actually worn by the user, at least around the time of said impact, to prevent the system from raising an alarm if only the sensor module has fallen. The second evaluation logic may comprise free fall detection means for evaluating the acceleration data on characteristics which are typical for a free falling object, such as one or more full rotation and/or a free falling phase, during which the magnitude of the acceleration data is relatively stable and small. Additionally or alternatively the second evaluation logic may comprise body proximity detection means for detecting whether the sensor module is in close proximity to the human body.

Growing community of inventors

Eindhoven, Netherlands

Ingrid Christina Maria Flinsenberg