Abstract: A system and method for compressing sensor data at an edge node of a distributed computing network. The method includes training the edge node to with a plurality of known signal templates. Each known signal template corresponding to a corresponding one of a plurality of events observable by the sensor. A raw data signal is collected by a sensor of the edge node. The raw data signal is classified to one of the known signal templates based on a degree of similarity between the raw data signal and the known signal template. A compression scheme is selected based on the classification of the raw data signal. The raw data signal is compressed in accordance with the compression scheme.

Abstract: An object detection system (100) is disclosed herein. The system 100 includes a lighting system (50) to illuminate an object and at least one selectable light output quality, at least one image sensor (70) positioned to obtain an image of an object, and at least one processor (10) coupled to the image sensor (70) to receive the image of the object. The processor (10) includes a monitoring engine (30) configured to determine if the image has an image quality metric (IQM) value or an expected confidence value corresponding to the IQM value that meets a predetermined threshold and a light settings calculation module (40) configured to select the light output qualities of the lighting system (50) to improve the IQM value or the expected confidence value corresponding to the IQM value to meet the predetermined threshold.

Abstract: The described implementations provided herein relate to systems, methods, and apparatuses for using a network of luminaires to perform distributed computation of sensor data to identify hardware and network anomalies. In some implementations, a method is set forth as including operations such as receiving, from a first luminaire (114, 128, 216), first sensor data (122, 124) in response to a stimulus (204) affecting a network of luminaires (110), and receiving, from a second luminaire (208) in the network of luminaires, second sensor data. The method can also include determining a correlation between the first sensor data and the second sensor data, and modifying a luminaire spatial-temporal model (222) based at least partially on the correlation.

Abstract: The described embodiments relate to system, methods, and apparatuses for compensating sensor data from a luminaire based on an ambient temperature estimate that is generated from operating characteristics of the luminaire. The sensor data can be provided from a sensor, such as a passive infrared sensor, that is connected to the luminaire, and by compensating the sensor data, more accurate metrics can be generated from the sensor data. For instance, the compensated sensor data can be used to generate occupancy metrics that can be used as a basis for controlling a network of luminaires or other devices that can be influenced by occupants of an area. The compensated sensor data can also be used to calibrate the sensor.

Abstract: Disclosed are a system and method for improving the signal-to-noise ratio of sensors in a connected lighting system. At individual nodes of the system, sensor measurements are obtained during relatively quiescent time periods to model background noise. Collaboration between nodes is performed to yield a more accurate model of background noise. These noise models can then be used in de-noising subsequent sensor measurements.

Abstract: A system and method for determining a number of occupants at a location using multiple modalities. The method includes gathering a first data set with a motion sensor of the lighting system. A second data set is gathered with a transceiver of an RF subsystem. First and second estimates are calculated from the second data set using first and second algorithms. The first estimate and the second estimate are fused to create a fused occupant estimate. The first algorithm, the second algorithm, or both the first algorithm and the second algorithm are trained by inputting the second occupant estimate and/or the second set of data to recalibrate parameters of the first algorithm and/or inputting the first occupant estimate and/or the first set of data to recalibrate parameters during training of the second algorithm. A building control system can operated in response to the fused occupant estimate.

Abstract: A method and system for collecting luminaire information is disclosed. A first data collection apparatus collects first data related a plurality of luminaires and a second data collection apparatus collects second data related the plurality of luminaires. Further, a processing device is configured to analyze the first and second data to determine at least one characteristic for each of the plurality of luminaires.

Abstract: A system and methods are provided for using deep learning based on convolutional neural networks (CNN) as applied to Internet of Things (IoT) networks that includes a plurality of sensing nodes and aggregating nodes. Events of interest are detected based on collected data with higher reliability, and the IoT network improves bandwidth usage by dividing processing functionality between the IoT network and a cloud computing network.

Abstract: A method (100) and connected lighting system (10) for detecting an intruder to a wireless network (24) of a connected lighting system formed by a plurality of luminaires (14). Each luminaire receives (120), over a designated time interval, a physical layer characteristic of each client device (26) accessing the wireless network. An array (50) of reference distributions is retrieved (110) by a processor of the system. Each reference distribution corresponds to an expected distribution of the characteristics for one of the luminaires during a corresponding time interval. An observed distribution is generated (130) for each luminaire, representing an actual distribution of values of the characteristic received by one of the luminaires over the designated time interval. Each observed distribution is compared (140) to the appropriate reference distribution for the designated interval in order to detect an anomaly and initiate an alarm status.

Abstract: A system and method for providing object recognition using artificial neural networks. The method includes capturing a plurality of reference images with a camera associated with an edge node on a communication network. The reference images are received by a centralized server on the communication network. The reference images are analyzed with a parent neural network of the centralized server to determine a subset of objects identified by the parent neural network in the reference images. One or more filters that are responsive to the subset of objects are selected from the parent neural network. A pruned neural network is created from only the one or more filters. The pruned neural network is deployed to the edge node. Real-time images are captured with the camera of the edge node and objects in the real-time images are identified with the pruned neural network.

Abstract: The described embodiments relate to systems, methods, and apparatuses for controlling a network of lights (120) according to whether people (122) who are observing the lights are visitors from a different location (108). Visitors can be identified by using network connection data (116, 208) that includes entries corresponding to personal devices of visitors to a city. The network connection data can be filtered to identify how many personal devices are associated with people visiting from a different city. If the number of visitors exceeds some threshold relative to non-visitors, a lighting arrangement in the city can be controlled to display features that would appeal to the visitors. The features can correspond to aspects of the city where the visitors are from and can therefore make the city more attractive.

Abstract: Techniques are described herein for to improving optical wireless communications based on mobility patterns. In various embodiments, one or more mobility patterns observed in an area over time may be determined (302). The area may be illuminated by one or more lighting units (102) configured to transmit information using optical wireless communications (“OWC”). An applicable mobility pattern may be selected (308) from the one or more mobility patterns. Based on the selected mobility pattern, usage in the area of a plurality of OWC-based mobile apps (230) may be predicted (310). One or more OWC resources of at least one of the one or more lighting units may be allocated (312) for transmission of data to one or more of the plurality of OWC-based mobile apps operating on one or more mobile devices operated within the area. In various embodiments, the allocating may be based at least in part on the predicted usage.

Abstract: A lighting-system (100) for illuminating an environment, the lighting system comprising a plurality of lighting modules (111, 112, 113) and a lighting-system control device (130). The lighting modules comprise: —a light source (121) for emitting light, —a programmable controller (122) configured to control an operation of the light source, and —a network interface (123) configured to allow the lighting module to communicate via a network. The lighting-system control device (130) comprises: —a processor circuit (133) configured to determine lighting control data to change the light spectrum of the light source based on the mobility data of the at least one user, and to transmit the lighting control data to at least one lighting module of the plurality of lighting modules to program said lighting module according to the lighting control data.

Abstract: The described embodiments relate to systems, methods, and apparatuses for controlling energy resources available to micro-grids of a city based on mobility patterns of people moving within the micro-grids. The mobility patterns can be identified using a network of sensors within each micro-grid for collecting data related to the movement of people within the micro-grids. The mobility patterns can be used to estimate energy demand for each micro-grid and prioritize the energy demands to determine the energy resources that would be suitable for supplying power to each micro-grid. This allows for micro-grids to dynamically and efficiently change their power sources according to predictions about the movement of people within the micro-grids.

Abstract: The described embodiments relate to systems, methods, and apparatuses for controlling lights (130) in an area of a city (200) based on demographic data and/or mobility pattern data (120). Using the demographic data and/Gall or the mobility pattern data, the lights can be arranged to attract people (214) to the area (210) where the lights are located. The mobility pattern data can be used to identify when people are typically moving towards the area, in order that the lights can be prepared to attract people in advance of their arrival. Furthermore, an output of the lights can be measured to measure certain characteristics about the lights so that the lights can be adjusted to better appeal to the demographic of people in the area.