Page 8 - MSDN Magazine, November 2018

Editor’s NotE MICHAEL DESMOND
Sensors in Sports:
A Dive into Applied Machine Learning
Back in April, Microsoft Senior Architect Kevin Ashley led and co-authored a feature article in the magazine titled “Sensors in Sports: Analyzing Human Movement with AI” (msdn.com/magazine/ mt846466). The article explored the effort by the U.S. Olympic Ski Team to improve training techniques and race results through the application of remote sensor telemetry and machine learning (ML). It was a fascinating look at how ML can be used to improve outcomes in a physically dynamic environment.
This month, Ashley returns to our pages, exploring how sensor data and visual artificial intelligence (AI) are being used to improve the performance of athletes on the U.S. Olympic Diving Team. “Sensors in Sports: Analyzing Olympic Diving with Sensors and Vision AI,” details how Microsoft worked with coaches, athletes, and program leaders to deploy a sensor platform and smartphone app that lets coaches capture and analyze data related to athletes’ dives. At the time of this writing, the Microsoft team had just com- pleted a live exercise at Stanford University with U.S. Olympic Diving coaches. The session showed how the combination of detailed telemetry and high-resolution video allows coaches to identify flaws in technique, refine training regimes, and improve outcomes in competition.
TheeffortgotitsstartaspartofaprogramatMicrosofttoencour- age organizations to integrate Internet of Things (IoT) sensors, data ingestion, ML and AI, says Ashley.
“We started Sensors in Sports as a collaborative effort at Micro- soft to help our partners improve their integration of connected devices,technologyandsports,”Ashleyexplains.“Understanding human movement is key to many industries. The models we build to analyze sports are useful to individual athletes, as well as our partnersinmanyareasrelatedtosports.”
Tracking sports movement comes with its challenges. Fast action means that remote sensors must operate at high frequencies, often at 100 samples per second, to produce useful data. Likewise, IoT
algorithms must be autonomous and intelligent enough to keep pace. The physical sensors themselves must be hardened against environmental factors, such as water, ice and snow, as well as phys- ical impacts. They must also be small, light and able to operate at low power, so their presence in no way disrupts training sessions.
At the time of this writing, the Microsoft team had just completed a live exercise at Stanford University with U.S. Olympic Diving coaches.
“Over the last two years working with different sports, I’ve built about a hundred sensor prototypes, and now with the help of Microsoft Garage we can create even more custom designs for sports,” Ashley says, referring to the internal Microsoft program that supportswhatthecompanycallsthe“hackcultureatMicrosoft.”
Sports telemetry is a young and fast-moving discipline, and Ashley says that figuring out what data to capture, measure and analyze is a real challenge.
“This is precisely why we work with coaches and data scientists, training the best athletes in the world,” says Ashley. “Each sport is different, and at the same time, fundamentally, many activities are strikingly similar in how the human body reacts to the chal- lenges.Ourgoalassportsdatascientistsisfindingpatterns,using ML to classify and analyze
movements and find reusable
methods in each activity.”
Visit us at msdn.microsoft.com/magazine. Questions, comments or suggestions for MSDN Magazine? Send them to the editor: mmeditor@microsoft.com.
© 2018 Microsoft Corporation. All rights reserved.
Complying with all applicable copyright laws is the responsibility of the user. Without limiting the rights under copyright, you are not permitted to reproduce, store, or introduce into a retrieval system MSDN Magazine or any part of MSDN Magazine. If you have purchased or have otherwise properly acquired a copy of MSDN Magazine in paper format, you are permitted to physically transfer this paper copy in unmodified form. Otherwise, you are not permitted to transmit copies of MSDN Magazine (or any part of MSDN Magazine) in any form or by any means without the express written permission of Microsoft Corporation.
A listing of Microsoft Corporation trademarks can be found at microsoft.com/library/toolbar/3.0/trademarks/en-us.mspx. Other trademarks or trade names mentioned herein are the property of their respective owners.
MSDN Magazine is published by 1105 Media, Inc. 1105 Media, Inc. is an independent company not affiliated with Microsoft Corporation. Microsoft Corporation is solely responsible for the editorial contents of this magazine. The recommendations and technical guidelines in MSDN Magazine are based on specific environments and configurations. These recommendations or guidelines may not apply to dissimilar configurations. Microsoft Corporation does not make any representation or warranty, express or implied, with respect to any code or other information herein and disclaims any liability whatsoever for any use of such code or other information. MSDN Magazine, MSDN and Microsoft logos are used by 1105 Media, Inc. under license from owner.
4 msdn magazine