Git Product home page Git Product logo

unsupervised-pd-assessment's Introduction

Unsupervised Parkinson's Disease Assessment

Our goal is to create a device that will utilize patient’s daily actions instead of choreographed actions to monitor and quantify Parkinson’s disease based on part of the motor control section of the UPDRS scale.

Library Resources

Project Notes

December 13th, 2017

  • ShareLatex information has been commented, add correction of comments to next sprint
  • change design document from sensor tag to teensy, and explain to group

January 2nd, 2018

  • Latency to read from a MPU9250 is worst case 1ms

January 21st, 2018

  • wearable device (V1: Iron Fist) built

January 22nd, 2018

  • wireless communication between XBee and Artik 710 over Zigbee
  • Xbee is configured using XCTU
  • end-to-end system prototype by the end of January (~February 2nd, 2018)

March 18th, 2018

  • started phase 2 of code which consists of:

    • a FSM that will set the device in an online mode or offline mode depending on network availablility
    • a kill state that will put the device into a stasis
    • adding the position data to the information
    • either in online mode or offline mode
    • sd card commnication for backup
  • currently have done most hw and network checks EXCEPT SD card initialization

  • currently cannot change out of ONLINE or OFFLINE

  • ONLINE just sends data out as best it can

  • OFFLINE just stores all the data on the SD card

  • maybe if communication is bad (given a counter) have ONLINE transition to OFFLINE and never go back

April 11th, 2018

  • mahoney filter (courtesy of sparkfun), is now functional with the UPDA system
  • radio energy saving
  • offline code completed
    • gathers data at the correct rate
    • stores data on the SD card
    • can send information to the serial console
  • error handling complete
  • switching over to digi xbee python library for Zigbee communication

unsupervised-pd-assessment's People

Contributors

samlux avatar silversmithe avatar yousef-zoumot avatar

Stargazers

 avatar

Watchers

 avatar  avatar

unsupervised-pd-assessment's Issues

wearable communication infrastructure

  • creating functions to connect xbee
  • packetization of data samples
  • send packets to server
  • TCP communication protocol
  • test wearable -> python server
  • BASIC error handling

Battery Tests

  • re-wire circuit to be powered with battery
  • test runtime with (1|2) batteries running without power consumption

Neural Net Prototyping

  • Organize Full Set of data samples that we must gather in order to begin training our Neural Network
  • Train Network
  • Test Hypothesis and generate confidence function (Otherwise known as a minimized cost function)

EMG Sensor Evaluation

  • re-evaluate the accuracy of the current EMG sensor
  • look for a potentially better EMG sensor
  • gather wires for longer-range electrodes

Error Handling

  • implement an error handling system that will allow for the wearable device to emit and react to different error messages both on the server side and on the wearable side

PCB Testing

create the PCBs for the device and make sure that they are electronically equivalent

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.