Skill Level: Intermediate
N.B: All services used in this repo are Lite plans. Also, star this repo if you like what you see.
The idea behind this application is to have a way to check pulse rates with the most available devices and these are the mobile phones.
A brief description:
-
Create a classification Model using a dataset which contains the pulse data and its related derived values. Deploy the Model and expose it as WML endpoints
-
Register the Mobile device with Watson IoT Platform
-
Using the mobile app, generate the LIVE pulse data. This data is published to IoT platform and then stored in a NoSQL database
-
Streaming the pulse data from the app in real-time (or the database) and using WML validate it with the deployed model
- Steps 1 & 5 - Node.js application
- Step 2 - Watson Machine Learning
- Step 3 - Watson IoT Platform
- Step 4 - IBM Studios
-
After doing the above tutorial steps.
-
Try it on your mobile phone's browser:
http://<YOUR_APP_NAME>.mybluemix.netYou can try my running app http://mypulse.mybluemix.net/ to have a feel how it looks like, but mine exceeded the allowance plan for the machine learning service so the prediction parts will be displayed with "undefined"
-
Put your device id on there for real-time streaming view of your data.
- Bluemix aka IBM Cloud
- DSX aka Data Platform
- IBM Cloud
- IBM Cloud Documentation
- IBM Cloud Developers Community
- IBM Watson Internet of Things
- IBM Watson IoT Platform
- IBM Watson IoT Platform Developers Community
- Savitzky–Golay filter for smoothing the accelerometer data
- Thanks to Mark Watson for making the "watson-ml-model-utils" library
- Optional: additional use case lookup