Promoting Fitness with Automated Movement Recognition Using Machine Learning
This is a paid opportunity. In order to be eligible to apply for this project, you need to be part of the Omdena community and have finished at least one AI Innovation Challenge.
You can find our upcoming AI Innovation Challenges at https://omdena.com/projects.
The problem
The problem that this Omdena-Playfitt project is trying to address is the lack of motivation and ability to track physical movements for users who want to exercise more. The goal is to encourage people to move more by making it easy and fun to track their movements using sensors on an iPhone. Specifically, PlayFitt aims to automatically measure whether a user is performing a given movement and how many repetitions they have completed. This involves two tasks: a classification task (identifying the movement being performed) and a counting task (counting the number of repetitions completed). By solving these tasks, users can be provided with feedback on their progress, get motivated to move more, and also help them achieve their fitness goals.
The project goals
This project will be based on building a python framework that is capable of handling multiple parallel requests and a robust counter for which accuracy will be dependent on various factors.
Project Scope:
- Have live counting in the app to know the count as the user is doing the movements.
- It should be as robust as possible wrt cheat detection. For example, shaking one’s phone shouldn’t count as any real movement.
- It is important to minimize false negatives (e.g. users really doing movements getting called Non-movements by the classifier) as those are horrible for user experience.
- It is better to be more generous rather than more strict. The optimization should not be only concerned about the accuracy of the confusion matrix.
- Build a Python infrastructure that can handle many incoming requests from users and have the built-in capabilities to process the classifier – counter for many different sessions happening in parallel.
**More details will be shared once the project is joined.
Why join? The uniqueness of Omdena Top Talent Projects
Top Talent opportunities come as a natural next step after participating in Omdena’s AI Innovation Challenges.
Everyone in the community is eligible to participate once they have shown the relevant skills based on the merit of involvement in past Omdena challenges and the community.
If you are looking for the next challenge after participating in one or more Omdena AI Innovation Challenges, then we believe you have made the right choice! With a healthy, pressured environment, you will be pushed to contribute, learn and grow even more.
Find more information on how an Omdena Top Talent Program works
First Omdena Project?
Join the Omdena community to make a real-world impact and develop your career
Build a global network and get mentoring support
Earn money through paid gigs and access many more opportunities
Eligibility to join an Omdena Top Talent project
Finished at least one AI Innovation Challenge
Received a recommendation from the Omdena Core Team Member/ Project Owner (PO) is a plus
Skill requirements
Good English
Machine Learning Engineer
Experience working with Smartphone Sensor Data is a plus.
This project is hosted with our friends at
Application Form
Become an Omdena Collaborator