Systems and methods for probabilistic semantic sensing in a sensory network

1. A method comprising:

receiving, by a device, raw sensor data from a plurality of sensors in a light sensory network,

the light sensory network including a plurality of nodes, and

the plurality of sensors including a first sensor located on a first node, of the plurality of nodes;

generating, by the device, semantic data based on the raw sensor data,

the semantic data including a plurality of sensed event records that each indicate a corresponding event sensed by a corresponding sensor of the plurality of sensors,

the corresponding sensor being associated with a corresponding node, of the plurality of nodes, and

each sensed event record including a set of classifiers that classify the semantic data and signify meaning of the raw sensor data,

a first classifier, of the set of classifiers, indicating an event detected by the corresponding sensor, and

a second classifier, of the set of classifiers, indicating a probability that the first classifier is true,

the probability being based on at least one of a sensor location of the corresponding sensor, an event location at which the event occurred, or an obstruction of the corresponding sensor in relation to the event;

grouping, by the device, the sensed event records into groups of sensed event records based on the set of classifiers;

generating, by the device, a derived event record based on a group of sensed event records, of the groups of sensed event records,

the derived event record including:

a third classifier that indicates an event detected by multiple sensors, of the plurality of sensors, and

a fourth classifier that indicates a probability that the third classifier is true; and

enabling, by the device, at least one application to perform a service based on the derived event record.

2. The method of claim 1 , wherein the raw sensor data includes one or more of:

visual data,

audio data, and

environmental data, and

wherein the event includes at least one of:

detecting a person,

detecting a vehicle,

detecting an object, and

detecting an empty parking space.

3. The method of claim 1 , wherein the event represented by the semantic data is associated with a binary state.

4. The method of claim 1 , wherein each sensed event record includes an application identifier that is utilized to identify the at least one application from a plurality of applications,

wherein each application of the plurality of applications is utilized to perform a different service.

5. The method of claim 1 , wherein the set of classifiers further includes a fifth classifier that indicates the sensor location of the corresponding sensor.

6. The method of claim 1 , wherein set of classifiers further includes a fifth classifier that indicates the event location at which the event occurred.

7. A system comprising:

one or more memories; and

one or more processors, communicatively coupled to the one or more memories, to:

receive raw sensor data from a plurality of sensors in a light sensory network, the light sensory network including a plurality of nodes, and

the plurality of sensors including a first sensor located on a first node, of the plurality of nodes;

generate semantic data based on the raw sensor data,

the semantic data including a plurality of sensed event records, each sensed event record including:

a first classifier that indicates an event detected by a corresponding sensor, of the plurality of sensors, the corresponding sensor being associated with a corresponding node, of the plurality of nodes, and

a second classifier that indicates a probability that the first classifier is true, the probability being based on at least one of a sensor location of the corresponding sensor, an event location at which the event occurred, or an obstruction of the corresponding sensor in relation to the event;

generate a derived event record based on a group of sensed event records, of groups of sensed event records,

the generated derived event record including:

a third classifier that indicates an event detected by multiple sensors, of the plurality of sensors, and

a fourth classifier that indicates a probability that the third classifier is true; and

enable at least one application to perform a service based on the generated derived event record.

8. The system of claim 7 , wherein the raw sensor data includes one or more of:

visual data,

audio data, or

environmental data, and

wherein the event includes at least one of:

a detection of a person,

a detection of a vehicle,

a detection of an object, or

a detection of an empty parking space.

9. The system of claim 7 , wherein the event is associated with a binary state,

the binary state including at least one of:

a parking space being occupied; or

the parking space not being occupied.

10. The system of claim 7 , wherein the one or more processors are further to:

analyze the semantic data based on user input, and

wherein the user input includes at least one of:

a desired accuracy, or

a user preference.

11. The system of claim 7 , wherein the one or more processors are further to:

analyze the semantic data based on a weight that is assigned to the second classifier, and

wherein the one or more processors are further to:

alter the weight over time.

12. The system of claim 7 , wherein the one or more processors are further to:

analyze the semantic data based on a first threshold, and

wherein the first threshold defines a minimum level of raw sensor data that is utilized to produce a first derived event.

13. The system of claim 7 , wherein the at least one application includes at least one of:

a parking location application,

a surveillance application,

a traffic application,

retail customer application,

a business intelligence application,

an asset monitoring application,

an environmental application, or

an earthquake sensing application.

14. The system of claim 7 , wherein each sensed event record further includes:

a fifth classifier that indicates the sensor location of the corresponding sensor, and

a sixth classifier that indicates the event location at which the event occurred.

15. A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions, when executed by one or more processors, cause the one or more processors to:

generate semantic data based on raw sensor data,

the semantic data including a plurality of sensed event records that each indicate a corresponding event sensed by a corresponding sensor, of a plurality of sensors, the corresponding sensor being located on a corresponding node, of a plurality of nodes in a light sensory network, and each sensed event record including:

a first classifier that indicates an event detected by the corresponding sensor, and

a second classifier that indicates a probability that the first classifier is true, the probability being based on at least one of a sensor location of the corresponding sensor, an event location at which the event occurred, or an obstruction of the corresponding sensor in relation to the event;

generate a derived event record based on a group of sensed event records, of groups of sensed event records,

the generated derived event record including:

a third classifier that indicates an event detected by multiple sensors, of the plurality of sensors, and

a fourth classifier that indicates a probability that the third classifier is true; and

enable at least one application to perform a service based on the generated derived event record.

16. The non-transitory computer-readable medium of claim 15 , wherein the at least one application includes at least one of:

a parking location application,

a surveillance application,

a traffic application,

retail customer application,

a business intelligence application,

an asset monitoring application,

an environmental application, or

an earthquake sensing application.

17. The non-transitory computer-readable medium of claim 15 , wherein the derived event record includes derived event information,

the derived event information being associated with business intelligence monitoring.