Abstract:
Gesture control for ubiquitous sensing and interaction has grown with smart devices and their applications. Acoustic signals track hand movement and recognize gestures in recent work. Frequency selective fading, interference, and insufficient training data reduce their robustness.
RobuCIR, a robust contact-free gesture recognition system, works under various practical impact factors with high accuracy and robustness. RobuCIR avoids signal interference by frequency-hopping.
We investigate data augmentation techniques based on a small volume of collected data to emulate different practical impact factors to increase system robustness. The augmented data trains neural network models to handle various factors like gesture speed and transceiver distance. RobuCIR recognized 15 gestures and outperformed state-of-the-art works in accuracy and robustness.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
