Method and device for performing wireless sensing based on wireless sensing

1 . A method in a wireless LAN system based on wireless sensing, the method comprising:

collecting, by a wireless device, Channel State Information (CSI) data and a lifelog;

obtaining, by the wireless device, a first user estimation result by learning and predicting based on the CSI data;

predicting, by the wireless device, a second user estimation result based on the lifelog when the first user estimation result is less than or equal to a threshold value;

obtaining, by the wireless device, a final result by putting weights on the first and second user estimation results;

obtaining, by the wireless device, a third user estimation result by learning and predicting based on the CSI data in which the final result is labeled; and

identifying, by the wireless device, a user based on the third user estimation result.

2 . The method of claim 1 , further comprising:

obtaining, by the wireless device, a feature set by combining the CSI data and the lifelog; and

obtaining, by the wireless device, a fourth user estimation result by learning and predicting based on the feature set.

3 . The method of claim 1 , wherein the CSI data is obtained based on a wireless signal received by the wireless device,

wherein the lifelog is obtained from a fixed device, a cloud, or a mobile device, wherein the lifelog obtained from the fixed device is room temperature, device operation, current time or date,

wherein the lifelog obtained from the cloud is current weather, outside temperature or calendar schedule information,

wherein the lifelog obtained from the mobile device is application usage information or alarm information.

4 . The method of claim 3 , wherein the lifelog is stored in the wireless device or in the cloud,

wherein the second user estimation result is predicted based on the stored lifelog.

5 . The method of claim 1 , further comprising:

identifying, by the wireless device, a user based on the first user estimation result when the first user estimation result exceeds the threshold value.

6 . A wireless device in a wireless LAN system based on wireless sensing, the wireless device comprising:

a memory;

a transceiver; and

a processor being operatively connected to the memory and the transceiver,

wherein the processor is configured to:

collect Channel State Information (CSI) data and a lifelog;

obtain a first user estimation result by learning and predicting based on the CSI data;

predict a second user estimation result based on the lifelog when the first user estimation result is less than or equal to a threshold value;

obtain a final result by putting weights on the first and second user estimation results; and

obtain a third user estimation result by learning and predicting based on the CSI data in which the final result is labeled.

7 . The wireless device of claim 6 , wherein the processor is further configured to:

obtain a feature set by combining the CSI data and the lifelog; and

obtain a fourth user estimation result by learning and predicting based on the feature set.

8 . The wireless device of claim 6 , wherein the CSI data is obtained based on a wireless signal received by the wireless device,

wherein the lifelog is obtained from a fixed device, a cloud, or a mobile device,

wherein the lifelog obtained from the fixed device is room temperature, device operation, current time or date,

wherein the lifelog obtained from the cloud is current weather, outside temperature or calendar schedule information,

wherein the lifelog obtained from the mobile device is application usage information or alarm information.

9 . The wireless device of claim 8 , wherein the lifelog is stored in the wireless device or in the cloud,

wherein the second user estimation result is predicted based on the stored lifelog.

10 . The wireless device of claim 6 , wherein the processor is further configured to:

identify a user based on the first user estimation result when the first user estimation result exceeds the threshold value.