Method and system for tracking position of one or more Wi-Fi devices
The invention provides a method and system for tracking a position of one or more Wi-Fi devices of a plurality of Wi-Fi devices. For tracking the position of the one or more Wi-Fi devices, a Triggering Router triggers the one or more Wi-Fi devices to transmit one of a broadcast probe and a directed probe through broadcasting hidden SSID networks and common SSIDs that increase a probing tendency of the one or more Wi-Fi devices. The plurality of Wi-Fi sniffers, then, collect measurement data associated with the one or more Wi-Fi devices in response to detecting the broadcast probe transmission and the directed probe transmission. Thereafter, the position of the one or more Wi-Fi devices is estimated using an adaptive machine learning model based on an indoor model whose parameters are tuned based on radio frequency (RF) measurements from the plurality of Wi-Fi devices and the measurement data.
1. A method for tracking a position of at least one Wi-Fi device of a plurality of Wi-Fi devices, the method comprising:
triggering, by a Wi-Fi access point of a plurality of Wi-Fi access points and a Wi-Fi sniffer of a plurality of Wi-Fi sniffers, one of a broadcast probe transmission or a directed probe transmission from the at least one Wi-Fi device, wherein the triggering comprises broadcasting, by the at least one Wi-Fi access point, one of hidden service set identifiers (SSIDs) or common SSIDs to increase a probing tendency of the at least one Wi-Fi device;
collecting, by the plurality of Wi-Fi sniffers, measurement data associated with the at least one Wi-Fi device in response to transmission of the broadcast probe or the directed probe from the at least one Wi-Fi device, wherein the plurality of Wi-Fi sniffers use a synchronization algorithm to switch to and sniff same channels simultaneously;
tuning, by one or more processors, at least one parameter corresponding to an indoor model based on radio frequency (RF) measurements from the plurality of Wi-Fi devices; and
estimating, by the one or more processors, a position of the at least one Wi-Fi device using an adaptive machine learning model based on the tuned indoor model and the measurement data.
2. The method according to claim 1 , wherein the triggering further comprises:
on receiving a beacon with a NULL SSID value, transmitting, by the at least one Wi-Fi device, a probe request message to at least one Wi-Fi access point of the plurality of Wi-Fi access points.
3. The method according to claim 1 , wherein the triggering further comprises:
counting, by the one or more processors, the common SSIDs to determine a router SSID corresponding to at least one Wi-Fi access point of the plurality of Wi-Fi access points;
enabling, by the one or more processors, the at least one Wi-Fi access point to broadcast the router SSID; and
on detecting the router SSID, transmitting, by the at least one Wi-Fi device, a probe request message to the at least one Wi-Fi access point.
4. The method according to claim 1 , wherein the collecting comprises, adjusting, by the one or more processors, a listening duration of the plurality of Wi-Fi sniffers based on a number of the Wi-Fi devices and a probing frequency corresponding to one of the Wi-Fi devices of the plurality of W-Fi devices.
5. The method according to claim 1 , wherein the measurement data comprise Received Signal Strength Indicator (RSSI) signals associated with the plurality of Wi-Fi devices.
6. The method according to claim 1 , further comprising training the adaptive machine learning model using data obtained through a solution of the indoor model based on the at least one parameter and the measurement data collected by the plurality of Wi-Fi sniffers.
7. The method according to claim 1 , further comprising updating the adaptive machine learning model based on checking a pre-training range associated with RSSI measurements from the plurality of Wi-Fi devices and a plurality of parameters associated with the indoor model.
8. A system for tracking a position of at least one Wi-Fi device of a plurality of Wi-Fi devices, the system comprising:
a memory;
a processor communicatively coupled to the memory, wherein the processor is configured to:
trigger, by a Wi-Fi access point of a plurality of Wi-Fi access points and a Wi-Fi sniffer of a plurality of Wi-Fi sniffers, one of a broadcast probe transmission or a directed probe transmission from the at least one Wi-Fi device, wherein the triggering comprises broadcasting, by the at least one Wi-Fi access point, one of hidden SSIDs and common SSIDs to increase a probing tendency of the at least one Wi-Fi device;
collect, by the plurality of Wi-Fi sniffers, measurement data associated with the at least one Wi-Fi device in response to transmission of the broadcast probe or the directed probe from the at least one Wi-Fi device, including adjusting a listening duration of the plurality of Wi-Fi sniffers based on a number of the Wi-Fi devices and a probing frequency corresponding to one of the Wi-Fi devices of the plurality of W-Fi devices;
tune at least one parameter associated with an indoor model based on radio frequency (RF) measurements from the plurality of Wi-Fi devices; and
estimate a position of the at least one Wi-Fi device using an adaptive machine learning model based on the tuned indoor model and the measurement data.
9. The system according to claim 8 , wherein the plurality of Wi-Fi sniffers use a synchronization algorithm to switch to and sniff same channels simultaneously.
10. The system according to claim 8 , wherein the processor is configured to:
transmit, by the at least one Wi-Fi device, a probe request message to at least one Wi-Fi access point of the plurality of Wi-Fi access points on receiving a beacon with a NULL SSID value.
11. The system according to claim 8 , wherein the processor is configured to:
count the common SSIDs to determine a router SSID corresponding to at least one Wi-Fi access point of the plurality of Wi-Fi access points;
enable the at least one Wi-Fi access point to broadcast the router SSID; and
on detecting the router SSID, transmit, by the at least one Wi-Fi device, a probe request message to the at least one Wi-Fi access point.
12. The system according to claim 8 , wherein the measurement data comprise Received Signal Strength Indicator (RSSI) signals associated with the plurality of Wi-Fi devices.
13. The system according to claim 8 , wherein the adaptive machine learning model is trained using data obtained through a solution of the indoor model based on the at least one parameter and the measurement data collected by the plurality of Wi-Fi sniffers.
14. The system according to claim 8 , wherein the adaptive machine learning model is updated based on checking a pre-training range associated with RSSI measurements from the plurality of Wi-Fi devices and a plurality of parameters associated with the indoor model.
15. A method for tracking a position of at least one Wi-Fi device of a plurality of Wi-Fi devices, the method comprising:
triggering, by a Wi-Fi access point of a plurality of Wi-Fi access points and a Wi-Fi sniffer of a plurality of Wi-Fi sniffers, one of a broadcast probe transmission or a directed probe transmission from the at least one Wi-Fi device, the triggering further including broadcasting, by the at least one Wi-Fi access point, one of hidden service set identifiers (SSIDs) or common SSIDs to increase a probing tendency of the at least one Wi-Fi device, counting, by the one or more processors, the common SSIDs to determine a router SSID corresponding to at least one Wi-Fi access point of the plurality of Wi-Fi access points, enabling, by the one or more processors, the at least one Wi-Fi access point to broadcast the router SSID and on detecting the router SSID, transmitting, by the at least one Wi-Fi device, a probe request message to the at least one Wi-Fi access point;
collecting, by the plurality of Wi-Fi sniffers, measurement data associated with the at least one Wi-Fi device in response to transmission of the broadcast probe or the directed probe from the at least one Wi-Fi device, wherein the plurality of Wi-Fi sniffers use a synchronization algorithm to switch to and sniff same channels simultaneously;
tuning, by one or more processors, at least one parameter corresponding to an indoor model based on radio frequency (RF) measurements from the plurality of Wi-Fi devices; and
estimating, by the one or more processors, a position of the at least one Wi-Fi device using an adaptive machine learning model based on the tuned indoor model and the measurement data.
16. The method of claim 15 , wherein the triggering further comprises:
on receiving a beacon with a NULL SSID value, transmitting, by the at least one Wi-Fi device, a probe request message to at least one Wi-Fi access point of the plurality of Wi-Fi access points.
17. The method according to claim 15 , wherein the collecting comprises, adjusting, by the one or more processors, a listening duration of the plurality of Wi-Fi sniffers based on a number of the Wi-Fi devices and a probing frequency corresponding to one of the Wi-Fi devices of the plurality of W-Fi devices.
18. The method according to claim 15 , wherein the measurement data comprise Received Signal Strength Indicator (RSSI) signals associated with the plurality of Wi-Fi devices.
19. The method according to claim 15 , further comprising training the adaptive machine learning model using data obtained through a solution of the indoor model based on the at least one parameter and the measurement data collected by the plurality of Wi-Fi sniffers.
20. The method according to claim 15 , further comprising updating the adaptive machine learning model based on checking a pre-training range associated with RSSI measurements from the plurality of Wi-Fi devices and a plurality of parameters associated with the indoor model.