These days, many people use various devices to check on and track health data for themselves. A new IBM Code pattern, where you build the MyPulse web app, targets the most used device in the world: a smartphone. MyPulse uses accelerometer data from the mobile device. Unlike other health apps, though, MyPulse applies a design-based study that filters out the noise which eliminates errors.

MyPulse takes the accelerometer metrics (heart rate and time data) and makes a prediction using Watson Machine Learning on what the pulse rate is, translated as beats per minute. A generated number is associated with the mobile device, and the device is registered with Watson IoT Platform, where the gyroscope metrics are displayed in real-time on an ongoing graph. All the data is stored in a Cloudant database.

Do you want to try your hand at applying a machine learning model to your IoT sensor data? Then check out my new IBM Code pattern, Develop a web-based mobile health app that uses machine learning, and let me know what you think in the comments or star my repo if you like what you see!

Join The Discussion

Your email address will not be published. Required fields are marked *