StaySharp

Inspiration

Fatigued driving is a serious risk, responsible for about 20% of fatal collisions in Canada alone. The impaired reaction time, decision-making, and awareness from drowsiness pose life-threatening risks, particularly for long-haul and night-shift drivers. StaySharp aims to address this issue by creating a solution that actively monitors drivers’ alertness, helping prevent fatigue-related accidents.

What it does

StaySharp is an anti-drowsiness monitoring program that uses real-time heart rate data from wearable devices to detect signs of drowsiness in drivers. It monitors heart rate and heart rate variability (HRV) to assess drowsiness levels and categorize them by severity. When signs of fatigue are detected, the system issues alerts through vibrations and notifications to keep drivers attentive. Additionally, StaySharp provides daily reports on drowsiness patterns, enabling users to identify trends and make lifestyle adjustments to enhance their alertness on the road.

How we built it

The system was developed using simulated heart rate data, given current limitations in real-time access to wearable data from APIs such as Google Fit and Fitbit. We implemented drowsiness detection algorithms that analyze heart rate and HRV patterns to determine the driver’s alertness level. The alerts and reporting features were tested using simulated drowsiness scenarios, focusing on providing timely feedback to the user.

Challenges we ran into

One of the main challenges was limited access to real user data due to privacy restrictions from wearable device APIs, which hindered real-time heart rate monitoring. We also faced difficulties in simulating realistic heart rate patterns that closely mirror actual driver drowsiness. These factors posed challenges in ensuring the accuracy of our drowsiness detection algorithms.

Accomplishments that we're proud of

We’re proud of developing a functional prototype that demonstrates the feasibility of real-time drowsiness detection using heart rate data. Despite data limitations, we created a reliable simulation that allowed us to test and refine our algorithms, providing valuable insights into real-time monitoring and alert mechanisms.

What we learned

Through this project, we learned about the complexities of accessing health data through wearables and the importance of accurate data simulation for testing health-related algorithms. We also gained experience in developing alert systems tailored for high-stakes environments like driving, where prompt feedback is crucial.

What's next for StaySharp

Our next steps involve enhancing data quality by integrating a proprietary device optimized for precise heart rate monitoring to improve drowsiness detection accuracy. We also plan to expand compatibility to popular wearables like the Apple Watch and other mainstream devices, making StaySharp widely accessible and easy to integrate with existing wearable technology.