Team:UCAS-China/Software

• Home
• Project
  1. Description
  2. Design
  3. Proof of Concept
  4. Safety
  5. Implementation
  6. Engineering Success
  7. Measurement
  8. Experiments
  9. Parts
  10. Notebook
• Hardware
  1. Hardware Overview
  2. Technical details
• Software
• Model
  1. Model Overview
  2. Model for the Tea Pack
  3. Model for the Loophole
  4. Modelling Methods
• Human Practice
  1. Integrated Human Practice
  2. Communication
  3. Education
  4. Collaboration
  5. Partnership
  6. Excellence In Another Area
• Team
  1. Meet the Team!
  2. Attributions
  3. Contribution
  4. Acknowledgement

• Software
• Module 1: Collect
• Module 2: Analyze
• Module 3: Bluetooth

This year, we have built an application Caffeine-monitor based on WeChat miniprogram platform, to help our users get a better handle on their caffeine intake amount (CIA). The app can not only collect the coffee data detected by the hardware, but also can analyze the data and user behavior to give coffee-lovers reasonable suggestions. Three major modules have been included in our app to provide all-through functions. See more in our Github repository.

Module 1: Collect

We collected health condition of registered users through the static form they submit and the real-time detected data of our hardware bracelets. And the coffee drinking history, including drinking time and drinking amount will be recorded in the app. A large database was created to store useful and convincing information, including smoking history, heart rate and sleep condition.

Module 2: Analyze

In the app, we analyze the user behavior to set and adjust upper limit of CIA according to users' own conditions. The recommended CIA is calculated by original algorithm, and currently we use the model built from common people. A new way of using machine learning and Backpropagation algorithm was also built to form an auto-adaptive upgrading process of the validity of recommending CIA value.

Module 3: Bluetooth

Bluetooth function was added to our app to transfer data to the hardware solution of our team, thus providing users a more convenient way to intake valid amount. We also decided to cooperative with major coffee sellers to provide our suggestions of coffee choice. After each time of experience, users’ feedback was collected to help our algorithm adjust arguments automatically.

To conclude, a brand-new app with full function of caffeine intake amount monitor and recommendation was created, and for further development, we hope to perfect and stablize our app to achieve industry standard.