Abstract:
Road safety depends on drivers’ physical and mental health as they spend more time driving. Drivers’ breathing patterns indicate their health. Existing breathing monitoring studies require user participation by wearing sensors or sleeping in quiet environments, which are unsuitable for noisy driving environments.
BreathListener, a smartphone-based fine-grained breathing monitoring system, estimates the driving breathing waveform using audio devices. We found that energy spectrum density (ESD) of acoustic signals can be used to capture breathing in real driving environments.
BreathListener removes driving noise from ESD signals using background subtraction and variational mode decomposition (VMD) to extract breathing patterns.
We then use a deep learning architecture based on generative adversarial network (GAN) to generate fine-grained breathing waveforms from the Hilbert spectrum of extracted breathing patterns in ESD signals. BreathListener accurately captured the breathing patterns of ten drivers in real driving environments.
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
