Wireless device detection systems and methods incorporating streaming survival modeling for discrete rotating identifier data
A wireless device detection system includes sensors to receive temporary identifiers transmitted between a base station and a mobile wireless device. A cumulative distribution function for survival probability is generated based on delta times between multiple access events for each temporary identifier. In response to a new access event, a corresponding temporary identifier is added to a streaming list and assigned a survival probability value, based on the cumulative distribution function, to a latest access event for each temporary identifier contained in the streaming list. Temporary identifiers that have a survival probability value less than a threshold value are removed from the streaming list. The number of temporary identifiers contained in the streaming list are compared to a number of devices known to be present. The probability that a device corresponding to each of the temporary identifiers contained in the streaming list is present is determined.
1 . A computer-implemented method performed by a security monitoring device for tracking people at a location, the method comprising:
receiving, by at least one hardware processor of the security monitoring device, streaming data from a streaming data source at the location,
wherein the streaming data is associated with observed events;
discarding at least one event of the observed events based on evaluating event metadata;
identifying a presence of a device at the location based on the streaming data;
building a probability distribution function based on access events for temporary identifiers received from devices at the location;
determining that the device is an unknown device based on network data associated with known devices;
determining, based on the streaming data and the network data, that the unknown device corresponds to a presence of an unwelcome entity at the location; and
in response to determining that the unknown device corresponds to the presence of the unwelcome entity:
providing, to a user, visual feedback indicating the presence of the unwelcome entity.
2 . The computer-implemented method of claim 1 , comprising:
determining an intruder probability corresponding to the presence of the unwelcome entity.
3 . The computer-implemented method of claim 1 , comprising:
determining a probability that a streaming list is associated with more than a number of confirmed devices known to be present at the location.
4 . The computer-implemented method of claim 1 , wherein the device associated with the streaming data is a wireless device, and wherein the security monitoring device is a base station.
5 . The computer-implemented method of claim 1 , wherein the streaming data source is a camera or an image-based input device.
6 . The computer-implemented method of claim 1 , wherein the visual feedback comprises text and/or graphics.
7 . The computer-implemented method of claim 1 , wherein the visual feedback is provided using an electronic display.
8 . A security monitoring device, comprising:
one or more processors; and
one or more non-transitory memory devices having stored thereon instructions that when executed by the one or more processors cause the one or more processors to:
receive streaming data from a streaming data source at a location,
wherein the streaming data is associated with observed events;
discard at least one event of the observed events based on evaluating event metadata;
identify a presence of a device at the location based on the streaming data;
build a probability distribution function based on access events for temporary identifiers received from devices at the location;
determine that the device is an unknown device based on network data associated with known devices;
determine, based on the streaming data and the network data, that the unknown device corresponds to a presence of an unwelcome entity at the location; and
in response to determining that the unknown device corresponds to the presence of the unwelcome entity:
provide visual feedback indicating the presence of the unwelcome entity.
9 . The security monitoring device of claim 8 , wherein the instructions cause the one or more processors to:
determine an intruder probability corresponding to the presence of the unwelcome entity.
10 . The security monitoring device of claim 8 , wherein the instructions cause the one or more processors to:
determine a probability that a streaming list is associated with more than a number of confirmed devices known to be present at the location.
11 . The security monitoring device of claim 8 , wherein the device associated with the streaming data is a wireless device, and wherein the security monitoring device is a base station.
12 . The security monitoring device of claim 8 , wherein the streaming data source is a camera or an image-based input device.
13 . The security monitoring device of claim 8 , wherein the visual feedback comprises text and/or graphics.
14 . The security monitoring device of claim 8 , wherein the visual feedback is provided using an electronic display.
15 . A non-transitory memory device having stored thereon instructions that when executed by one or more processors cause the one or more processors to:
receive streaming data from a streaming data source at a location,
wherein the streaming data is associated with observed events;
discard at least one event of the observed events based on evaluating event metadata;
identify a presence of a device at the location based on the streaming data;
build a probability distribution function based on access events for temporary identifiers received from devices at the location;
determine that the device is an unknown device based on network data associated with known devices;
determine, based on the streaming data and the network data, that the unknown device corresponds to a presence of an unwelcome entity at the location; and
in response to determining that the unknown device corresponds to the presence of the unwelcome entity:
provide visual feedback indicating the presence of the unwelcome entity.
16 . The non-transitory memory device of claim 15 , wherein the instructions cause the one or more processors to:
determine an intruder probability corresponding to the presence of the unwelcome entity.
17 . The non-transitory memory device of claim 15 , wherein the instructions cause the one or more processors to:
determine a probability that a streaming list is associated with more than a number of confirmed devices known to be present at the location.
18 . The non-transitory memory device of claim 15 , wherein the device associated with the streaming data is a wireless device.
19 . The non-transitory memory device of claim 15 , wherein the streaming data source is a camera or an image-based input device.
20 . The non-transitory memory device of claim 15 , wherein the visual feedback comprises text and/or graphics.