Datamining The Government

February 3, 2010

The article is a bit old now (June 2009), but Wired had an interesting interview with Vivek Kundra about Data.gov. This is the usual Web 2.0 pitch about making data transparent and available and hoping that crowdsourcing will magically create useful things.

I will however admit to having been intrigued by the concept of one of the apps mentioned in the article:

In DC, someone combined several of the data sets released by local government—maps, liquor license info, crime statistics—into an app called Stumble Safely, which shows users the safest way to walk home when drunk.

Now someone just needs to mash it up with some augmented reality software or turn-by-turn GPS directions (“Turn left at the next corner. Stagger 2 blocks east. Try not to walk into that telephone pole.”).

Also of interest is DataMasher, which I spotted on LifeHacker. It appears to be a site for mashing up various government data sources. You can also save your own mashup and make it available to others. Looks interesting. So far, the Highest Rated and Most Discussed mashups seem to focus on health, mortality, guns, alcohol, obesity, and reproduction.

Finally, if you’ve read Freakonomics, check out this article on “bad boy” baby names as a predictor of behavior.


Datamining Games

February 3, 2010

The rise of the online always-on videogame opens a new world of stat tracking. The recent changes is this area are well beyond simple high score boards or achievements/trophies. For example, consider the article “You Are Being Watched” from a recent issue of the Official Xbox Magazine. The article details the datamining that Bungie is doing for Halo 3 and Halo 3: ODST, that Criterion is doing for Burnout Paradise, and Valve is doing for Team Fortress 2 and Left 4 Dead.

All of these companies are gathering data that shows them how their games are really being played. One usage for this data is to potentially make improvements and bug fixes. In the case of Bungie, players can actually log onto bungie.net and see their own stats and own personal heat maps for the matches they have played. Valve shares some of the overall data, and has recently started adding personalized data (for Steam players only).

For the personalized data, it would be interesting to see some numbers for how many players actually review their stats and whether it has an impact on their playing.

See also:

While I’m clearing out the videogame datamining links…


StarCraft AI Competition At AIIDE 2010

February 3, 2010

Spotted on Kotaku, the AIIDE (Artificial Intelligence and Interactive Digital Entertainment) 2010 conference will be hosting a StarCraft AI competition. Looking forward to the results.


The Gaming Brain

January 31, 2010

Scientific American’s online edition has an article touching on the study I previously blogged in which videogames were observed to improve vision. The article is a nice contrast to much of the game journalism coverage of the research, and gives me an opportunity to briefly revisit this topic.

Obviously, we know that games can teach information or hone motor skills – but there isn’t a lot of research around games and brain plasticity.

This article has a nice point calling out the lack of good research in this area (I’m looking at you, Brain Age.):

To date, much of the claims around this rapidly growing area of technology-supported medical interventions are insufficiently supported by scientific data.

(I have since found a study examining the effect of videogames upon memory and thinking skills in the elderly – using Boom Blox.)

Out of a number of online mentions of this research that I have seen, this article comes closest to referencing Steven Johnson‘s book “Everything Bad Is Good For You”. Perhaps I have just missed the articles that make the logical connection.

It also amuses me to see a study showing that playing Call Of Duty 2 or Unreal Tournament 2004 is in any measurable sense “better” than playing The Sims 2.

In other news, it seems that Dr. Richard Haier is still researching with Tetris. Dr. Haier did some of the original brain research with Tetris back in 1992 (two publications: one in Intelligence, another in Brain Research). In 2009, Dr. Haier did some new research involving Tetris while acting as a consultant to Blue Planet Software. MSNBC has a brief interview with Dr. Haier. Wired has another writeup on the research. (I would be remiss if I didn’t include a link to a certain someone declaring themselves as a Gameboy Tetris purist: “Tetris on the Gameboy…only.”)

I’ll close with another link I had lying around: scientists studying mice brains by using Quake 2.

Update, March 2010: Another bit of research on Tetris and PTSD.


Game Changers

January 30, 2010

The latest Wired has an interesting article Game Changers: How Videogames Trained a Generation of Athletes. It is a summary of the rise of sports videogames and how the Madden franchise in particular is now having an effective on the actual sport. It appears at this point that most new players entering the NFL have grown up playing the videogame and are bringing certain habits and play styles with them. The article briefly touches on the brain science aspects of videogames by touching on the FPS study that I have mentioned before. The article also does point out that we are not likely see trends such as this except in a few areas such as football and poker.


Mario Bros. AI Competition Results

November 19, 2009

The results of the Mario Bros. AI competition have been made available. (Not really surprising that the top three entries used A*.)

Robin Baumgarten has won, and has made his source code available. AIGameDev.com also has an interview with Robin.


Knowledge Transfer Through Video Games

October 12, 2009

Certainly, if you’ve been around the rule space long enough, you will be familiar with such terms as “knowledge engineering” and “knowledge capture”.

Robert X. Cringely’s latest column is (somewhat) about a knowledge capture platform. Nestled in among the usual rant about IBM and outsourcing (and I say that as a fan), is a link to an IBM patent for a “Platform for Capturing Knowledge”.

I haven’t read the patent myself, only Cringely’s commentary. But it seems the end result is not an expert system, but a video game for training experts. That’s an interesting aspect, although I’m not sure what the patent has that is unique. I seem to recall seeing plenty of prior art in this area years ago, especially in terms of expert systems for training medical personnel.

I don’t have time to spend digging up prior art right now, but I bet a number of readers have seen some as well.


Using The XBox 360 For Heart Disease Research

October 8, 2009

Just a quick post to highlight some recent media coverage about the XBox 360 being used to research heart disease. The article suggest that Simon Scarle used – you guessed it – some of the graphics hardware in the console.


Learning To Play Mario Bros.

August 6, 2009

Julian Togelius and Sergey Karakovskiy have organized a competition to create an agent (or AI) that plays the video game Super Mario Bros. – or, more accurately, Infinite Mario Bros. a tribute game featuring random level generation.

The advantage of using Infinite Mario Bros. is the random level generation – which can let the agent learn more generalized playing tactics rather than tactics that are tailored to a static set of levels as in Ms. Pac-Man or Pitfall.

I look forward to seeing the results of the competition, and hope to see source code published as well.


A Computer That Plays Pitfall

June 29, 2009

From Rutgers university comes a learning algorithm that they have applied to playing the Atari 2600 game “Pitfall!”.

An example video is on YouTube.

One of the research papers is apparently here (although the site isn’t being very responsive at the moment).

I’ll get around to posting on machine learning for Pac-Man/Ms. Pac-Man at some point as well.

(Spotted on Kotaku and GameSetWatch.)