Athletics Therapy    
Recent News |  Archives |  Tags |  Newsletter |  Message Board/Forum |  About |  Links |  Subscribe to AthleticsTherapy.com RSS Feed Subscribe


More Articles
Improvements in fuel cell designImprovements in fuel cell design

Rediscovering Venus to find faraway earths

Archaeologists discover bronze remains of Iron Age chariot

Researchers resolve the Karakoram glacier anomaly, a cold case of climate science

Fish tale: New study evaluates antibiotic content in farm-raised fishFish tale: New study evaluates antibiotic content in farm-raised fish

New 3-D display technology promises greater energy efficiencyNew 3-D display technology promises greater energy efficiency

Researchers break nano barrier to engineer the first protein microfiberResearchers break nano barrier to engineer the first protein microfiber

Magnetic mirrors enable new technologies by reflecting light in uncanny ways

Structure of an iron-transport protein revealedStructure of an iron-transport protein revealed

First step: From human cells to tissue-engineered esophagusFirst step: From human cells to tissue-engineered esophagus

Lift weights, improve your memory

Spiders: Survival of the fittest group

Autophagy helps fast track stem cell activationAutophagy helps fast track stem cell activation

Myelin vital for learning new practical skillsMyelin vital for learning new practical skills

More physical activity improved school performanceMore physical activity improved school performance

Around the world in 400,000 years: The journey of the red foxAround the world in 400,000 years: The journey of the red fox

Engineering new vehicle powertrainsEngineering new vehicle powertrains

Active aging is much more than exerciseActive aging is much more than exercise

Study: New device can slow, reverse heart failureStudy: New device can slow, reverse heart failure

Are the world's religions ready for ET?Are the world's religions ready for ET?

Gut bacteria, artificial sweeteners and glucose intoleranceGut bacteria, artificial sweeteners and glucose intolerance

Recreating the stripe patterns found in animals by engineering synthetic gene networksRecreating the stripe patterns found in animals by engineering synthetic gene networks

Laying the groundwork for data-driven scienceLaying the groundwork for data-driven science

Hold on, tiger momHold on, tiger mom

Nature's designs inspire research into new light-based technologiesNature's designs inspire research into new light-based technologies

Biologists delay the aging process by 'remote control'Biologists delay the aging process by 'remote control'

Geography matters: Model predicts how local 'shocks' influence U.S. economyGeography matters: Model predicts how local 'shocks' influence U.S. economy

Identified for the first time what kind of explosive has been used after the detonationIdentified for the first time what kind of explosive has been used after the detonation

Copied from nature: Detecting software errors via genetic algorithmsCopied from nature: Detecting software errors via genetic algorithms

Researchers build computer models to analyze play in pro basketball and soccer (12/18/2014)

<
Tags:
back, basketball, soccer, video

With the ball at the three-point line near the top of the key, what will Tim Duncan of the NBA's San Antonio Spurs do? Pass to a player posting up? Or does he take a shot? An analysis by Disney Research of player tracking data, however, suggests the highest probability is a pass to guard Tony Parker on his left.

It's just one play, by one player, in one sport - and perhaps not that hard for the average courtside observer to anticipate - but with the field of sports becoming more driven by sports analytics, predicting the next thing that a player will do has become a major challenge in computer modeling of player behavior.

In a new study, researchers at Disney Research Pittsburgh showed they could use player tracking data from more than 600 basketball games of the 2012-13 NBA season to build models that can make accurate in-game predictions of what each player is likely to do next in a game situation: pass or shoot.

In a separate study using a season's worth of ball and player tracking data from a professional soccer league - more than 400 million data points - Disney Research Pittsburgh researchers performed a different type of analysis that looked at team behavior rather than individual players. They showed their system could accurately detect and visualize team formations - well enough that they could identify teams based just on their style of play 70 percent of the time.

Both studies will be presented at the International Conference on Data Mining in Shenzhen, China, Dec. 14-17.

Patrick Lucey, an associate research scientist at Disney Research Pittsburgh, said such automated, data-driven methods might simply back up the intuition of a coach, but they can also serve as tools for educating players in the limited time available for practice, or as tools for scouting opposition teams and planning for specific game situations.

In the NBA study, the researchers were faced with the difficult, complex task of modeling the behavior not only of the ball handler, but of his teammates and defenders and their shifting positions on the court.

Instead, the researchers, directed by Yisong Yue, now an assistant professor of computing at California Institute of Technology, used a machine learning approach in which the models were trained based on the tendencies of each player to take shots or pass or receive passes in certain locations. It also incorporated such factors as how those tendencies varied in the presence of opposition and on the duration of their possession of the ball.

The approach utilized a "latent factor model." It not only made accurate predictions, but the model's learned factors were interpretable and corresponded with known intuitions of basketball gameplay.

In the soccer study, the researchers faced a different problem. "In basketball, you have a lot of events and outcomes - a score or a change in possession every 24 seconds," Lucey said. That provides a lot of data points for evaluating individual play. Soccer, on the other hand, is a famously low-scoring sport. "It means you have to understand behaviors in the absence of scoring," he added.

In fact, focusing on individual players can be misleading, he explained. A player may play left wing at one point in the game and later to switch to the right wing; the decisions the players make will be based on their relative position to their teammates and opposition. So simply evaluating the player without considering that context will yield meaningless statistics. The Disney researchers developed a "role-based" representation of teams that doesn't track individuals but instead automatically identifies the players in each position and how they play that position. This provides a view of the team's behavior as a whole and also provides more meaningful, contextual information about individuals.

In addition to Yue and Lucey, the Disney researchers included Alina Bialkowski, Peter Carr, and Iain Matthews. Sridha Sridharan of Queensland University of Technology participated in the soccer analysis.

For more information about the NBA study, please visit the project website at http://www.disneyresearch.com/publication/learning-fine-grain-spatial-models-for-dynamic-sports-play-prediction/.

For more information about the soccer study, please visit the project website at http://www.disneyresearch.com/publication/large-scale-analysis-of-soccer-matches-using-spatiotemporal-tracking-data/.

Note: This story has been adapted from a news release issued by the Disney Research

Post Comments:

Search
New Articles
Researchers build computer models to analyze play in pro basketball and soccer

A new way to diagnose brain damage from concussions, strokes and dementiaA new way to diagnose brain damage from concussions, strokes and dementia

Light-based technology tracks oxygen levels underwater for swim performance, muscle repair

Where hockey and engineering collide: NJIT Highlanders join a pioneering concussion studyWhere hockey and engineering collide: NJIT Highlanders join a pioneering concussion study

Do concussions have lingering cognitive, physical, and emotional effects?Do concussions have lingering cognitive, physical, and emotional effects?

WHACK! Study measures head blows in girls' lacrosseWHACK! Study measures head blows in girls' lacrosse

Athletes perform better when exposed to subliminal visual cues

High school football players show brain changes after one seasonHigh school football players show brain changes after one season

Researchers identify protein that predicts post-concussion severity in professional athletes

Athletes' testosterone surges not tied to winning, study finds

The American athletics track is still a man's world

Symmetrical knees linked to Jamaican sprinting prowess

Danger of repeat head injuries: Brain's inability to tap energy source

Do spinal cord injuries cause subsequent brain damage?

Enriched environments hold promise for brain injury patients



Archives
December 2014
November 2014
October 2014
September 2014
August 2014
July 2014
June 2014
May 2014
April 2014
March 2014
February 2014
January 2014
December 2013
November 2013
October 2013
September 2013
August 2013
July 2013
June 2013
May 2013
April 2013
March 2013
February 2013
January 2013
December 2012
November 2012
October 2012
September 2012
August 2012
July 2012
June 2012
May 2012
April 2012
March 2012
February 2012
January 2012
December 2011
November 2011
October 2011
September 2011
August 2011
July 2011
June 2011
May 2011
April 2011
March 2011
February 2011
January 2011
December 2010
November 2010
October 2010
September 2010
August 2010
July 2010
June 2010
May 2010
April 2010
March 2010


  Archives |  Submit News |  Advertise With Us |  Contact Us |  Links
Use of this site constitutes acceptance of our Terms of Service and Privacy Policy. All contents © 2000 - 2019 AthleticsTherapy.com. All rights reserved.