The problem The Goodmorning-er solves

One in four vehicle accidents are caused by drowsy driving and 1 in 25 adults have reported that they have fallen asleep at the wheel in the past 30 days. The scariest part is that a drowsy driving isn't just falling asleep while driving. Drowsy driving can be as small as a brief state of unconsciousness when the driver is not paying full attention to the road.

Our solution to this problem is to build a detection system that identifies key attributes of drowsiness and triggers an alert when someone is going sleepy before it's too late.

The Goodmorning-er will have the following features:

1. The music system of the vehicle will alert the driver by buzzing off an alarm
2. If the first feature fails to wake up the driver, the system will start vibrating the driver's seat with increasing intensity
3. Also, it'll attempt to slow down the vehicle using the braking mechanism
4. It'll also send a message to a preset number

All the above features will eventually will result in a safer driving experience.

Challenges we ran into

Any machine learning model is as good as the dataset it was trained on. Finding a perfect dataset for our purposes proved to be a daunting task. The final set that we actually trained our model on consisted of various different datasets, with over 85,000 data points.

For finding the correct hardware for our project, we had to select a microcontroller that is powerful enough to run a machine learning model on it while being well under the budget of a common man.

Accuracy!