Self-learning based on Wi-Fi-based monitoring and augmentation
Technologies for attestation techniques, systems, and methods for determining an individual's movement are provided. The individual's movement is determined by passive indoor positioning technology using channel state information (CSI). A first set of data associated with an impulse or frequency response determined using channel state information (CSI) may be received from a Wireless access point located in proximity to a monitored space. A second set of data may also be received from an Internet of Things (IoT) device located in proximity to the monitored space. The first set of data may be compared to the second set of data. A profile database may be updated to replace the first set of data with the second set of data when the first and second sets of data are different.
1. A method for self-learning based on Wi-Fi-based localization and augmentation, the method comprising:
receiving a first set of data associated with a frequency response determined using channel state information (CSI), the first set of data retrieved from a wireless access point located in proximity to a monitored space;
receiving a second set of data from an Internet of Things (IoT) device located in proximity to the monitored space;
comparing the first set of data to the second set of data to identify when the first set of data differs from the second set of data; and
updating a profile database based on the comparison, wherein updating the profile database includes replacing the first set of data with the second set of data when the first set of data is determined to be different from the second set of data.
2. The method of claim 1 , further comprising taking a sample of the frequency response, wherein the sample is defined as linked to the IoT device.
3. The method of claim 1 , wherein the first and second sets of data includes location or activity data.
4. The method of claim 1 , further comprising receiving a third set of data retrieved from one or more context devices located in proximity to the monitored space.
5. The method of claim 1 , further comprising polling for known and unknown activities.
6. The method of claim 5 , further comprising:
detecting an unknown activity based on the polling;
identifying that a specific sequence of at least two data points coincide, the at least two data points from at least two different connected context devices and occur within a predefined time window;
assigning an activity definition to the detected unknown activity in a new profile; and
adding the new profile to the profile database.
7. The method of claim 5 , wherein detecting the unknown activity comprises:
retrieving all matching profiles without a known activity from the profile database; and
determining that a number of the matching profiles is greater than a sample size threshold.
8. A system for self-learning based on Wi-Fi-based localization and augmentation, the system comprising:
a wireless access point located in proximity to a monitored space, wherein the wireless access point provides a first set of data regarding the monitored space and associated with a frequency response determined using channel state information (CSI);
an Internet of Things (IoT) device located in proximity to the monitored space, the IoT device providing a second set of data regarding the monitored space; and
a cloud server that:
compares the first set of data to the second set of data to identify when the first set of data differs from the second set of data; and
updates a profile database based on the comparison, wherein updating the profile database includes replacing the first set of data with the second set of data when the first set of data is determined to be different from the second set of data.
9. The system of claim 8 , wherein the cloud server further takes a sample of the frequency response, wherein the sample is defined as linked to the IoT device.
10. The system of claim 8 , wherein the first and second sets of data includes location or activity data.
11. The system of claim 8 , wherein the cloud server further receives a third set of data retrieved from one or more context devices located in proximity to the monitored space.
12. The system of claim 8 , wherein the cloud server further polls for known and unknown activities.
13. The system of claim 12 , wherein the cloud server further:
detects an unknown activity based on the polling;
identifies that a specific sequence of at least two data points coincide, the at least two data points from at least two different connected context devices and occur within a predefined time window;
assigns an activity definition to the detected unknown activity in a new profile; and
adds the new profile to the profile database.
14. The system of claim 12 , wherein the cloud server detects the unknown activity by:
retrieving all matching profiles without a known activity from the profile database; and
determining that a number of the matching profiles is greater than a sample size threshold.
15. A non-transitory computer-readable storage medium having embodied thereon a program executable by a processor to perform a method for self-learning based on Wi-Fi-based localization and augmentation, the method comprising:
receiving a first set of data associated with a frequency response determined using channel state information (CSI), the first set of data retrieved from a wireless access point located in proximity to a monitored space;
receiving a second set of data from an Internet of Things (IoT) device located in proximity to the monitored space;
comparing the first set of data to the second set of data to identify when the first set of data differs from the second set of data; and
updating a profile database based on the comparison, wherein updating the profile database includes replacing the first set of data with the second set of data when the first set of data is determined to be different from the second set of data.