Detection and identification of auditory events in distributed lighting networks
Detection and identification of auditory events in distributed lighting networks is provided. Lighting fixtures or other devices in a distributed lighting network can incorporate an audio sensor (e.g., a microphone) through which auditory events (e.g., air leaks in compressed air systems, high noise events, shots fired, clapping, voice commands, etc.) are detected and measured. Through machine learning (e.g., a convolutional neural network), a type of auditory event can be identified, and action can be taken based on the type of the auditory event, such as to provide notification, alert nearby users, log events, provide sound cancelation, and so on. In some examples, the auditory event can be localized using multiple audio sensors. In some examples, a learning algorithm can fuse information from multiple sensor inputs, such as temperature sensors, cameras, occupancy sensors, light sensors, and so on.
1 . A method for detecting a health condition in a distributed lighting network, the method comprising:
measuring, with a sensor coupled to a lighting fixture in the distributed lighting network, one or more features indicative of a health status of a person;
applying a learning algorithm to identify the health status of the person from the one or more features, wherein applying the learning algorithm comprises comparing the measured one or more features of the person with one or more profiles of health statuses in a distributed fashion such that at least a portion of the learning algorithm is performed by processing circuitry within the lighting fixture to provide localized training in a space where the lighting fixture is installed; and
providing a notification when the health status is identified as a concerning health status.
2 . The method of claim 1 , wherein applying the learning algorithm comprises establishing a baseline health condition of the person based on a plurality of measurements from one or more sensors in the distributed lighting network.
3 . The method of claim 1 , wherein the measured one or more features comprise a temperature of the person.
4 . The method of claim 3 , further comprising:
tracking body temperature of a plurality of people; and
providing an additional notification when a threshold number among the plurality of people exhibits a body temperature above a given temperature.
5 . The method of claim 3 , wherein:
the measured one or more features further comprise an auditory event; and
applying the learning algorithm further comprises comparing the auditory event with an audio profile of a cough or a sneeze.
6 . The method of claim 1 , further comprising tracking movement of the person in a space where the distributed lighting network is deployed.
7 . The method of claim 1 , further comprising automatically performing an action based on a type of the health status of the person identified.
8 . The method of claim 7 , wherein the action comprises logging the concerning health status.
9 . The method of claim 7 , wherein when the health status comprises potential exposure to an infectious disease, and the action comprises tracing contact of the person with other people.
10 . The method of claim 7 , wherein the action comprises providing an audible or visual alert to the person.
11 . A distributed lighting network, comprising:
a plurality of lighting fixtures, each comprising:
a light source; and
a health sensor; and
processing circuitry in communication with at least one health sensor of the plurality of lighting fixtures, the processing circuitry comprising a convolutional neural network and configured to:
receive sensor input from the at least one health sensor;
measure a feature indicative of a health status of a person;
apply a learning algorithm to identify the health status of the person in a distributed fashion such that at least a portion of the learning algorithm is performed by the processing circuitry within each lighting fixture to provide localized training for each space where each lighting fixture is installed; and
perform an action based on the identified health status.
12 . The distributed lighting network of claim 11 , wherein the convolutional neural network is configured to apply the learning algorithm to temperature measurements from the at least one health sensor to identify the health status of the person.
13 . The distributed lighting network of claim 12 , wherein the learning algorithm is further applied to sensor inputs from at least one of an audio sensor, a camera, an occupancy sensor, or a light sensor.
14 . The distributed lighting network of claim 11 , wherein the convolutional neural network minimizes a cost function to reduce false positive and false negative identifications of the health status.
15 . A lighting fixture, comprising:
a light source;
a temperature sensor;
processing circuitry configured to:
receive temperature data associated with a person from the temperature sensor; and
apply a learning algorithm to identify a health status of the person in a distributed fashion such that at least a portion of the learning algorithm is performed by the processing circuitry within the lighting fixture to provide localized training in a space where the lighting fixture is installed; and
communications circuitry configured to send a message to a device, the message indicating the health status of the person, wherein the device is a communications device adjacent the lighting fixture, the communications device configured to provide an alert based on the identified health status.
16 . The lighting fixture of claim 15 , wherein:
the communications device is further configured to pair with a mobile device; and
the alert is provided to the mobile device when the mobile device is paired to the communications device.
17 . The lighting fixture of claim 15 , further comprising an atmospheric pressure sensor, wherein the processing circuitry is configured to:
receive atmospheric data from the atmospheric pressure sensor;
apply the learning algorithm to identify the health status of the person based on the temperature data and the atmospheric data; and
perform an action based on the identified health status of the person.