Abstract: A brain control interface system for determining a baseline for detecting brain activity of a user is disclosed. The brain control interface system comprising: a brain control interface configured to detect brain signals indicative of brain activity of a user in an environment, a memory configured to store activities of the user associated with different light scenes, a processor configured to: select, from the activities stored in the memory, a first activity of the user, control one or more lighting devices according to a first light scene associated with the first activity, detect brain signals of the user while the first light scene is active, determine, based on the detected brain signals, a first baseline for the brain signals, and store an association between the first baseline and the first light scene and/or the first activity.

Abstract: The brain control interface system comprises: a brain control interface configured to detect brain signals indicative of brain activity of a user in an environment, an input configured to obtain data indicative of a current light scene of one or more lighting devices in the environment, a memory configured to store processing methods associated with different light scenes, one or more processor configured to: select, from the processing methods stored in the memory, a processing method in accordance with the current light scene, apply the selected processing method to obtain and/or process the brain signals, derive a control command and/or a mental state of the user from the brain signals, and control the controllable device based on the derived control command and/or the derived mental state.

Abstract: A method for analyzing consumer behavior within a retail space can include receiving data associated with consumers in communications signals from local devices located in the retail space, where the local devices receive some of the data in visible light communication (VLC) signals broadcast by electrical devices, where each local device is associated with one of the consumers in the retail space at a point in time, and where the data lacks information that identifies the consumers. The method can also include attributing, by the controller using a multi-stage clustering process, the data to discrete consumers for a period of time that includes each point in time. The method can further include assigning the discrete consumers to at least one of a number of groups defined by one or more characteristics measured from the data, where the discrete consumers within a group share a common characteristic.

Abstract: The present disclosure is generally directed to systems and methods for controlling lighting based on the type of written content on smart coated surfaces. A smart coated surface generates pressure data based on the written content. A feature extractor then extracts features from the pressure data describing the written content. A content classifier then feeds the features into a recurrent neural network, such as a Long Short-Term Memory network to select a content label. A lighting controller then controls luminaires based on the content label and data from additional sensors. In this way, the system controls the luminaires based on the type of the written content without evaluating or decoding the content itself. For example, the system is able to label the content as text based on written patterns without interpreting what the text actually says. Accordingly, the content written on the smart coated surface remains private and secure.

Abstract: Monitoring systems and methods are disclosed. The systems include a sensor device having a single-pixel thermopile (SPT) sensor and a controller in communication with the sensor device. The controller is configured to determine or obtain training data for detecting first and second configurations of one or more occupants in the space; receive a temperature signal from the SPT sensor; detect a step change in the temperature signal; determine first and second probabilities for at least one feature of a shape or pattern of the temperature signal, the first and second probabilities corresponding to the first and second configurations of the one or more occupants in the space based on the training data, respectively; and identify a class label for the temperature signal based on the determined first and second probabilities. The class label corresponds with the first or second configurations of the one or more occupants in the space.

Abstract: The present invention is related to an application of a Single Pixel Thermopile (SPT). The invention provides a sensor device comprising a Single Pixel Thermopile and a controller, wherein the Single Pixel Thermopile is configured to monitor a detection region and to measure over time a temperature signal of said detection region; wherein the detection region is bounded by a surface and the Single Pixel Thermopile is oriented at an angle of at least 20 degrees normal to the surface; wherein a projection of the detection region onto the surface renders an elongated detection area with a length axis and a width axis; wherein the controller is configured to: obtain the temperature signal of the detection region; determine a movement characteristic of a person moving across said surface by detecting a pattern in the temperature signal of the detection region; output an output signal configured to control an electrical device upon determining the movement characteristic.

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 present disclosure is directed to inventive systems, methods, and devices for use in an outdoor lighting network for drone detection. The drone detection system includes one or more lighting fixtures, one or more radar sensors to detect a moving object, and one or more controllers. The controllers receive data from the sensors, determine the velocity and velocity change rate of the object over a period of time, and analyze flight data pertaining to the moving object to determine if the object is a drone. The system can determine the starting location of the moving object, and send a signal indicating its starting location. The system can also track the position of the moving object in the outside environment.

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 system for monitoring face mask wearing of a monitored person is provided. The system includes a controller communicatively coupled to one or more multipixel thermopile sensors (“MPTs”). The controller is configured to (1) detect a monitored person region within a heat map based on one or more data sets captured by the MPTs; (2) locate a head region within the monitored person region by identifying a high intensity pixel cluster within the monitored person region; (3) determine a facing-direction of the head region based on a major axis of the monitored person region or a minor axis of the monitored person region; (4) locate a mouth region within the head region based on the facing-direction; (5) determine an exhalation region of the heat map based on the mouth region; (6) determine a mask state of the monitored person based on the exhalation region and a temperature gradient classification model.

Abstract: A system for monitoring social distancing is provided. The system includes a controller communicatively coupled to sensors within an environment. The controller may be configured to (1) receive an expected sensor behavior model for each of the sensors; (2) generate an adjusted sensor behavior model for each of the sensors based on the expected sensor behavior model for each of the sensors and an environment adjustment model for each of the sensors; (3) receive a layout of the environment; (4) generate an expected layout behavior model based on the layout and the adjusted sensor behavior model; (5) capture, via the sensors, an observed behavior data set during a measurement period; and (6) determine a social distancing state of individuals in the environment as distanced or not-distanced based on the observed behavior data set and the expected layout behavior model.

Abstract: Systems and methods for controlling and interacting with plant lighting are provided. The methods include: determining or receiving location information indicative of relative locations of a plurality of sensors arranged around a portion of a plant, wherein the plurality of sensors are distributed among a plurality of lighting elements and the plurality of sensors are configured to capture sensor data for at least one parameter of the plant; measuring sensor data for the at least one parameter of the plant; annotating, by a processor, the sensor data with the location information of the plurality of sensors and timestamp information; analyzing, by the processor, the annotated sensor data; and determining a state of the plant based on the sensor data. Methods further include receiving, by a lighting controller, user input corresponding to the state of the plant and controlling the lighting elements based on the user input.

Abstract: A method for enforcing contact tracing is provided including: associating, via a processor associated with a plurality of connected sensors, a first person with a first mobile device based in part on a first distance between the first person and the first mobile device; determining, via the processor, that the first person and the first associated mobile device are separated from each other by a second distance; notifying, via at least one light effect provided by an illumination device in communication with the processor, the first person that the first person and the first associated mobile device are separated from each other by the second distance. The method can further include: determining, via the processor, that a second person is positioned within predetermined proximity to the first person, and receiving, via the illumination device, contact tracing data on behalf of the first mobile device from the second mobile device.

Abstract: A method for optimizing a neural network is provided, including: (1) capturing, via a first sensor group having a first field of view, a first sample set having a first sensor domain corresponding to the first field of view; (2) capturing, via a second sensor group having a second field of view, a second sample set having a second sensor domain corresponding to the second field of view; (3) generating regions of interest of the second sample set; (4) translating the regions of interest to the first sensor domain; (5) identifying nodes of the neural network which correspond to the translated regions; and (6) optimizing the neural network by at least one of (a) increasing the weight value of the nodes corresponding to the one or more translated regions and (b) decreasing the weight value of the nodes not corresponding to the one or more translated regions.

Abstract: The present invention is related to an application of a Single Pixel Thermopile (SPT). The invention provides a sensor device comprising a Single Pixel Thermopile and a controller, wherein the Single Pixel Thermopile is configured to monitor a detection region and to measure over time a temperature signal of said detection region; wherein the detection region is bounded by a surface and the Single Pixel Thermopile is oriented at an angle of at least 20 degrees normal to the surface; wherein a projection of the detection region onto the surface renders an elongated detection area with a length axis and a width axis; wherein the controller is configured to: obtain the temperature signal of the detection region; determine a movement characteristic of a person moving across said surface by detecting a pattern in the temperature signal of the detection region; output an output signal configured to control an electrical device upon determining the movement characteristic.

Abstract: A system for determining occupancy in an environment is provided. The system includes plurality of sensor bundles, with each bundle including a presence sensor and a motion sensor. The system further includes a controller in communication with each sensor bundle. The controller is configured to designate one of the sensor bundles as presence triggered if persons are present within a field of view of the presence sensor. The controller is further configured to designate one of the sensor bundles as motion triggered if persons are moving within a field of view of the motion sensor. The controller is further configured to determine a triggered bundle count of the sensor bundles which are both presence triggered and motion triggered. The controller is further configured to determine an occupancy count for the environment based upon the triggered bundle count.

Abstract: A system for determining an occupancy of an environment is provided. The system may include an image sensor, a motion sensor, and a controller in communication with the image sensor and the motion sensor. The controller may be configured to generate an encoded image representation by encoding the image signal based on an autoencoder. The controller may be further configured to generate an encoded motion representation by encoding the motion signal based on the autoencoder. The controller may be further configured to train the autoencoder with the image signal and/or motion signal. The controller may be further configured to generate a fused representation based on the encoded image representation and the encoded motion representation. The controller may be further configured to determine the occupancy of the environment based on the fused representation. The occupancy of the environment may be determined by applying the fused representation to a machine learning module.

Abstract: The present disclosure is directed to inventive systems and methods for automatically controlling illumination of a workplace. The lighting system includes one or more tunable luminaires and a calendar module executing on a computer-implemented device configured to receive a calendar entry. The calendar entry includes a starting time of a future event, the identity of one or more invitees to the future event, and a lighting scene selection for the workplace. A lighting controller receives the lighting scene selection from the calendar module and generates one or more control signals to automatically adjust at least one characteristic of light emitted by the tunable luminaires in the workplace for the future event based on the lighting scene selection in the calendar entry.

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: A system and method for compressive sensing using edge nodes of a distributed computing network. The method includes collecting a raw data signal continuously by a sensor of the edge node. A signal energy indicator is dynamically updated that quantifies an energy distortion in the raw data signal. One or more compression characteristics are determined as a function of the signal energy indicator as the signal energy indicator is updated. The raw data signal is subsampled in accordance with current values of the one or more compression characteristics to create a compressed data signal. An output is transmitted that includes the compressed data signal to a centralized node.