Abstract: A method for determining a substrate model for describing a first measurement dataset and a second measurement dataset relating to a performance parameter. The method include obtaining candidate basis functions for a plurality of substrate models. Steps 1 to 4 are performed iteratively for the first measurement dataset and the second measurement dataset until at least one stopping criterion is met so as to determine the substrate model, the steps including: 1. selecting a candidate basis function from the candidate basis functions; 2. updating a substrate model by adding the candidate basis function into this substrate model to obtain an updated substrate model; 3. evaluating the updated substrate model based on the first measurement dataset and/or second measurement dataset; and 4. determining whether to include the basis function within the substrate model based on the evaluation.

Abstract: The invention relates to a monitoring system (13) for monitoring electrical devices (A, B, C, D, K) like luminaires. An assignments providing unit (7) provides assignments between the electrical devices and behavior classes defining expected behaviors, wherein a deviation determination unit (9) determines a deviation a) between a monitored behavior of an electrical device assigned to a behavior class and an expected behavior defined by a behavior class and/or b) between a monitored behavior of an electrical device and a monitored behavior of another electrical device, wherein an output unit (10) provides an output depending on the determined deviation. The deviation can be indicative of a commissioning error, i.e., for instance, of an assignment of an electrical device to a wrong room within a building. The monitoring system can therefore allow for an automatic detection of commissioning errors in a building which may have thousands of electrical devices.

Abstract: The invention relates to detecting commissioning errors in a commissioned sensor system, wherein the sensor system comprises a plurality of sensor devices installed so as to cover an area. The sensor devices capture sensor data from the area whilst at least one entity moves through the area. A computer system of the sensor system processes the sensor data to generate a set of location data, which identifies locations traversed by the at least one moving entity. A discrepancy in the set of location data in detected, the discrepancy caused by at least one of the sensor devices having been incorrectly commissioned. Based on this detection, a modification can be made to the sensor system to compensate for or correct the incorrect commissioning of the at least one sensor device.

Abstract: A method for identifying sensor units (3) at fault in a lighting system (1) performed using three or more sensor units (3), each respective one of the sensor units (3) comprising a respective sensor (116) configured to generate sensor data, the method comprising at an external processing apparatus (20) external to the sensor units (3): receiving from each of the sensor units (3) the sensor data; generating correlation parameters from the sensor data for selected pairs of neighbouring sensor units (3); and monitoring the correlation parameters to determine a sensor unit (3) at fault.

Abstract: Some embodiments are directed to a sensor control device (200) for a connected lighting system (100), said connected lighting system comprising multiple luminaires (122) arranged in a region, the sensor control device obtaining from received sensor data the occupant locations in sub-regions associated with the sensor data and/or multiple illuminance levels for multiple points in the sub-region, and defines a virtual sensor at a virtual sensor location. The occupancy state and/or illuminance level from the virtual sensor are used to control a luminaire of the multiple luminaires, the luminaire covering the virtual sensor location in the region.

Abstract: Some embodiments are directed to a sensor control device (200) for a connected lighting system (100), said connected lighting system comprising multiple luminaires (122) arranged in a region, the sensor control device obtaining from received sensor data the occupant locations in sub-regions associated with the sensor data and/or multiple illuminance levels for multiple points in the sub-region, and defines a virtual sensor at a virtual sensor location. The occupancy state and/or illuminance level from the virtual sensor are used to control a luminaire of the multiple luminaires, the luminaire covering the virtual sensor location in the region.

Abstract: A verification device to detect malfunction in a connected lighting system, the connected lighting system comprising multiple luminaires and multiple occupancy sensors, the verification device comprising: —an input interface (301) arranged to connect to a database and obtain the sensor data obtained from the multiple occupancy sensors, —an aggregation unit (310) arranged to compute occupancy values which are indicative of occupancy over a specified time period at different hierarchical levels by applying a statistical measure, and —a processing unit (320) arranged to compare an occupancy value at a lower hierarchical level with an occupancy value at a higher hierarchical level, finding deviations that indicate a malfunction in the connected lighting system and producing a signal to communicate the malfunction.

Abstract: A method for identifying sensor units (3) at fault in a lighting system (1) performed using three or more sensor units (3), each respective one of the sensor units (3) comprising a respective sensor (116) configured to generate sensor data, the method comprising at an external processing apparatus (20) external to the sensor units (3): receiving from each of the sensor units (3) the sensor data; generating correlation parameters from the sensor data for selected pairs of neighbouring sensor units (3); and monitoring the correlation parameters to determine a sensor unit (3) at fault.

Abstract: A sensor such as a presence sensor for use in a lighting system or other system that adapts to information from a plurality of active presence sensors. If transmissions from the active sensors are uncoordinated, the overall detection performance may be adversely impacted (e.g. due to potential cross-interference), which may make sensing over the detection coverage area defined by a single presence sensor (or the like) become unreliable. The disclosure presents protocols for coordinating transmissions in active sensing systems. The invention may be applied to various active modalities (e.g. ultrasound, RF), for example that find applications in indoor and outdoor lighting controls.

Abstract: A method of testing a sensor unit which detects, locally at the sensor unit, whether a person appears in the images it captures. The method comprises causing a light-emitting device (e.g. screen of a user terminal) to emit a test pattern toward the sensor unit to be captured over a series of images, the test pattern comprising a spatio-temporal pattern of light simulating presence of a predetermined number of people. The method further comprises, at a processing apparatus external to the sensor unit, receiving one or more presence detection reports from the sensor unit indicating an apparent people count detected using the sensor unit when subject to the test pattern. The apparent people count is then compared with the predetermined number of people simulated by the test pattern. Based on this comparison, it is determining whether the sensor unit is functioning correctly.

Abstract: Devices (10) comprise target detectors (11) for detecting presences of targets in first areas (1) and transmitters (12) for in response to detected presences transmitting multicast messages to controllers (20) and lamps (21-24) in wireless networked lighting systems. Such multicast messages increase reliabilities of the systems. The multicast messages switch on the lamps (21-24). Preferably, the multicast messages are only transmitted in case relatively small amounts of light are detected in second areas (2). In case relatively large amounts of light are detected in the second areas (2), unicast messages are in response to detected presences transmitted from the devices (10) to the controllers (20) that in response control the lamps (21-24) to be switched on. The first and second areas (1, 2) may be at least partly overlapping areas.

Abstract: A verification device to detect malfunction in a connected lighting system, the connected lighting system comprising multiple luminaires and multiple occupancy sensors, the verification device comprising: an input interface (301) arranged to connect to a database and obtain the sensor data obtained from the multiple occupancy sensors, an aggregation unit (310) arranged to compute occupancy values which are indicative of occupancy over a specified time period at different hierarchical levels by applying a statistical measure, and a processing unit (320) arranged to compare an occupancy value at a lower hierarchical level with an occupancy value at a higher hierarchical level, finding deviations that indicate a malfunction in the connected lighting system and producing a signal to communicate the malfunction.

Abstract: A method of testing a sensor unit which detects, locally at the sensor unit, whether a person appears in the images it captures. The method comprises causing a light-emitting device (e.g. screen of a user terminal) to emit a test pattern toward the sensor unit to be captured over a series of images, the test pattern comprising a spatio-temporal pattern of light simulating presence of a predetermined number of people. The method further comprises, at a processing apparatus external to the sensor unit, receiving one or more presence detection reports from the sensor unit indicating an apparent people count detected using the sensor unit when subject to the test pattern. The apparent people count is then compared with the predetermined number of people simulated by the test pattern. Based on this comparison, it is determining whether the sensor unit is functioning correctly.

Abstract: A method to evaluate energy performance of a second lighting system in a building. Training-data of a first lighting system in the building is obtained (310) and used to train (330, 340) an energy-use prediction model for the first lighting system from the training-data. Use-data of the second lighting system is obtained (410) in the building. Energy-use prediction-data is computed (450) by evaluating the energy-use prediction model for use-data and compared to energy-use use-data.

Abstract: The invention relates to detecting commissioning errors in a commissioned sensor system, wherein the sensor system comprises a plurality of sensor devices installed so as to cover an area. The sensor devices capture sensor data from the area whilst at least one entity moves through the area. A computer system of the sensor system processes the sensor data to generate a set of location data, which identifies locations traversed by the at least one moving entity. A discrepancy in the set of location data in detected, the discrepancy caused by at least one of the sensor devices having been incorrectly commissioned. Based on this detection, a modification can be made to the sensor system to compensate for or correct the incorrect commissioning of the at least one sensor device.

Abstract: A calibration method comprising, for each of one or more light sensors: (a) under influence of one or more substantially non-zero illumination levels in the target environment, using the light sensor to measure the sensed light level corresponding to each of these one or more illumination levels; (b) receiving a template light level value corresponding to each of the one or more illumination levels, representing the light level at a target location in the target environment substantially removed in space from the location of the light sensor, each of the one or more template light level values being assumed for the environment rather than measured by a light meter; and (c) determining a relationship between the sensed light level and the light level experienced at the target location, based on an evaluation of the one or more sensed levels relative to the one or more template light level values.

Abstract: A computer-implemented method of optimizing non-uniform quantization boundaries for a quantization unit of a sensor is provided. The method comprises: obtaining a digital representation of a model (120) for predicting the target metric (124) from an unquantized sensor signal (122), the model being defined by at least the quantization boundaries, the model comprising: a first layer (130) of multiple continuous quantization functions (142, 144, 146; ƒ1, . . . , ƒQ), the quantization functions approximating block functions on quantization intervals defined by the quantization boundaries and receiving as input an unquantized sensor signal, and a second layer (132) comprising a function taking as input the output of the multiple continuous quantization functions and generating as output a prediction of the target metric, and training (530) the model using the training data by iteratively updating (126) the quantization boundaries.

Abstract: An energy measurement system for a lighting system is disclosed. The lighting system may comprise multiple lighting units arranged in multiple lighting zones, multiple sensors associated with the lighting zones, and an energy measurement device. The lighting system may be arranged to switch on a lighting zone depending on at least a sensor associated with the lighting zone. Power-on energy uses of the multiple lighting zones associated with the multiple sensors is obtained from sensor data from the multiple sensors, and energy use data from the energy measurement device, the energy use data indicating an aggregated energy use of the multiple lighting zones at different times, and a processor circuit.

Abstract: Devices (10) comprise target detectors (11) for detecting presences of targets in first areas (1) and transmitters (12) for in response to detected presences transmitting multicast messages to controllers (20) and lamps (21-24) in wireless networked lighting systems. Such multicast messages increase reliabilities of the systems. The multicast messages switch on the lamps (21-24). Preferably, the multicast messages are only transmitted in case relatively small amounts of light are detected in second areas (2). In case relatively large amounts of light are detected in the second areas (2), unicast messages are in response to detected presences transmitted from the devices (10) to the controllers (20) that in response control the lamps (21-24) to be switched on. The first and second areas (1, 2) may be at least partly overlapping areas.

Abstract: An energy measurement system for a lighting system is disclosed. The lighting system may comprise multiple lighting units arranged in multiple lighting zones, multiple sensors associated with the lighting zones, and an energy measurement device. The lighting system may be arranged to switch on a lighting zone depending on at least a sensor associated with the lighting zone. Power-on energy uses of the multiple lighting zones associated with the multiple sensors is obtained from sensor data from the multiple sensors, and energy use data from the energy measurement device, the energy use data indicating an aggregated energy use of the multiple lighting zones at different times, and a processor circuit.