Team:CCU Taiwan/IOT system

No Sidebar - Helios by HTML5 UP

Introduction

We built an iOT system in order to transfer data from the device to the app or server. The system contains three parts, the device, the app and the server. The device contains an Arduino broad, biosensors and non-biosensors. The app is a visualize platform for the users to keep track of their own oral condition and also set the timer of the device. (for more introduction, please visit app:https://2017.igem.org/Team:CCU_Taiwan/APP) The server, the machine learning model will be trained and tested on it, as well as the risk of caries prediction too. As for the interaction of those three parts, it will be clearly introduced in the following content.

IOT structure



Device to APP

After the device successfully detect the three parameters, we use the Bluetooth module of Arduino to send the data to the app. The reason why we consider using Bluetooth instead of wifi is that although wifi is commonly used in daily life, but handing wifi module of Arduino is much more complicated than the Bluetooth module. Furthermore, the connection range of Bluetooth is enough for users to use around the device.

APP to Server

When receiving data from the device, app here plays as a register to store data temporarily. By using a socket server, making the server as a host and the app as a client in order to transfer data to the server for computing risk of caries then return the actual number back to the app.

APP to Device

The last piece of the iOT puzzle is the app to device. Users have to set a timer of the expected time they are going to use the device for the next time on the app, then the data will be send to the device for computing the best time for germinating the biosensor in the device.

Future Plan

For the future plan of our iOT system, we look forward to merging the machine learning model with the app in order to reduce the time lag of predicting the risk of caries, giving users a better using experience.

Please click here for more detail about the APP & machine learning

  1. APP
  1. Machine learning