Flow Charts
System Architecture |
Wired Device
The accelerometer connected to Intel Edison collects acceleration. Intel Edison do data cleaning and then the data are pushed to Kinesis by Intel Edison, Kinesis triggers lambda function, and AWS Lambda executes a code to call AWS Machine Learning to get real time prediction as soon as it discovers the presence of data from a Kinesis stream.
|
Wireless Device
The MetawearC collects acceleration and angular velocity. The Android App can communicate with MetawearC by Bluetooth and send collected data to Web server deployed on AWS EC2 using Flask. After the server receives the original data, it first do data cleaning then feed the cleaned data into neural network designed using Keras. The output of the neural network will be sent back to our Android App for display.
|