Machine Learning for Readiness and Performance Improvement

You are here

Inside Signal Processing Newsletter Home Page

Top Reasons to Join SPS Today!

1. IEEE Signal Processing Magazine
2. Signal Processing Digital Library*
3. Inside Signal Processing Newsletter
4. SPS Resource Center
5. Career advancement & recognition
6. Discounts on conferences and publications
7. Professional networking
8. Communities for students, young professionals, and women
9. Volunteer opportunities
10. Coming soon! PDH/CEU credits
Click here to learn more.

News and Resources for Members of the IEEE Signal Processing Society

Machine Learning for Readiness and Performance Improvement

Dr. Alessio Medda

Military operations and training present a broad variety of demanding physical tasks which may impact the Warfighter physical performance and health. As it is for anyone who exercises intensely, the possibility of injury is always lurking around the corner.

Imagine if you had a “virtual coach” that would inform you about your physiological status, cautioning you when you are pushing yourself too hard and can incur an injury, warning you when you are in an unsafe condition and offering you guidance for interventions to optimize your exercise. Such a tool would be of great value for the military in training and other military operations.

In April 2020, the Georgia Tech Research Institute (GTRI) in collaboration with the School of Electrtic and Computer Engineering at the Georgia Instute of Thecnology  (Georgia Tech) was awarded a $1.6M grant by the Office of Naval Research for a project titled Supporting Human Adaptation for Readiness and Performance Improvements (SHARPI ).

The goal of the project is to advance the state of the art of Machine Learning and Artificial Intelligence (ML/AI) in the field of human performance and adaptation. Researchers at the GTRI will be analyzing data collected from various sources to create a model that leverages wearable sensor data to provide actionable information for the benefit of soldiers engaged in physical training. Professor Omer Inan, director of the Inan Research Lab at Georgia Tech will be providing expertise on physiological sensing, directing research into extracting key features from wearable physiological measurements, and providing access to datasets collected for past studies.

GTRI researchers will leverage data acquired directly from wearable sensors on military trainees performing standard training activities.This data will be analyze for relevant features that correlate to performance and injury and used to develop a “virtual coach” model.

“Most of the time, the way that [the military trains] people is purely based on previous knowledge and personal experience of the drill sergeant maybe, what we call doctrinal guidance, so imagine if could have something like a personal coach as you go through — say, a run — that will tell you if your pace is OK, or if you need to slow down, or if you are about to get an injury because your gait is not appropriate for the type of exercise you’re doing,” Dr. Medda explained. He also pointed out that injuries could delay a soldier’s progression through the training and sometime directly impact their careers.

This model will also consider the trainee’s personal history as well as the average performance of everyone who is going through the same training to build a framework that does not yet exist.

Injury and performance go hand in hand. So if you want to achieve high performance you will have to minimize injury first.



Table of Contents:


IEEE SPS Educational Resources

IEEE SPS Resource Center

IEEE SPS YouTube Channel