In this paper, we demonstrate that WiFi can be used for finger
gesture detection which is both effectively deployable and low in cost. Our
system uses a single WiFi device which is connected to a Access Point (AP) to recognize
gestures present in the Channel State Information (CSI). Recognizing correct
gestures can get challenging due to environmental changes. For example, a
person walking in the room or a moved chair or furniture can alter the finger
gesture in the CSI. Moreover, individual diversity can also cause distortions
in the finger gesture since different users have different speed of movement
and different finger dimensions. Also, same user can also produce variable
finger gesture due to lack of consistency.


To deal with environmental noise, we incorporate
environmental noise removal system which uses wavelet based denoising 1 to reduce
environmental noises and maintain the CSI gestures generated only from the
finger gestures. In particular, the environmental noise removal system
decomposes the CSI into details and approximations and removes any unwanted
noise above a predetermined threshold by thresholding. This helps to maintain
the necessary details while neglecting any unwanted noise. To deal with
individual diversity, our system identifies principal components in the CSI
pattern. By extracting the principal components, the system identifies those
parts of the CSI which are invariant across multiple instances and this makes
the system immune to individual diversity and gesture inconsistency.


I'm Dora!

Would you like to get a custom essay? How about receiving a customized one?

Click here