Optimize Motion/Activity Detection Using location data - BC-319

Preferred Disciplines: Masters or PhD in Mathematics, Data Science, Signal Processing or similar fields
Project length: 1 to 2 years
Desired start date: Sept 1 2016
Location: Vancouver, BC
No. of Positions: 1
Preferences: Universities in Lower Mainland
Company: Prizm Media Inc

About Company:

Prizm Media is Profit 500 listed company, w100 and 40 under 40 owned Healthcare Lead Generation Company.  Its focus is to connect patients (primarily diabetics) with products and services they need to improve their health outcomes

Project Description:

The availability and accuracy of GPS in some environments, such as indoors, is limited. Accuracy in motion/activity detection especially in concrete building where GPS data is scattered is of great importance. The proposed research aim to develop novel methods to get 100% accuracy on 3 activity types (walk, run, cycle) without the use of any wearable devices or input from user.

Optimization of existing algorithms and logic on neural network and client side dependencies will be part of the project.

 

Background and required skills

Research Objectives/Sub-Objectives:

  • To attain 100% accuracy on activity tracking in concrete buildings
  • To optimize current algorythms that speed up the parsing of big data being collected without moving to a quantum server
  • To achieve objectives above without the need for wearables

Methodology:

  • N/A

Expertise and Skills Needed:

  • Neural networks
  • Data scientist
  • Analytics and big data

For more info or to apply to this applied research position, please

  1. Check your eligibility and find more information about open projects.
  2. Complete this webform. You will be asked to upload your CV. Remember to indicate the title of the project(s) you are interested in and obtain your professor’s approval to proceed!
Program: