Slashdot Mirror
Australia's Technological World Cup Advantage
hotsauce writes "The BBC has a piece about how Australia is using software to gain an advantage in the World Cup. The Socceroos are running software that looks for patterns in attacks of the opposing team. It also shows the effectiveness of different response strategies by recording where attacks fail when countered. This is the first time Australia has reached the World Cup in 30 years, but a real test of the technology will come today when Australia must take on five-time and current world champions Brasil. The Socceroos talk about specific strategies for that game, also."
Technology Quarterly
Sounds good?
Jun 8th 2006
From The Economist print edition
Software: “Music intelligence” systems that can distinguish hits from misses could change the way pop music is made and marketed
IMAGE
THE versificator, a machine described in George Orwell’s novel “1984”, automatically generated music for the hapless masses. The idea of removing humans from the creative process of making music, an art form so able to stir the soul, made for a good joke when the book was published in 1949. But today, computer programmers working in a new field called “music intelligence” are developing software capable of predicting which songs will become hits. This surprisingly accurate technology could profoundly change the way pop music is created.
The software uses a process called “spectral deconvolution” to isolate and analyse around 30 parameters that define a piece of music, including such things as sonic brilliance, octave, cadence, frequency range, fullness of sound, chord progression, timbre and “bend” (variations in pitch at the beginning and end of the same note). “Songs conform to a limited number of mathematical equations,” says Mike McCready of Platinum Blue, a music-intelligence company based in New York, that he founded last December. Platinum Blue has compiled a database of more than 3m successful musical arrangements, including data on their popularity in different markets.
To the human ear, music has changed a lot over the years. Music-intelligence software, however, can reveal striking similarities in the underlying parameters of two songs from different eras that, even to a trained ear, seem unrelated. According to Platinum Blue’s software, called Music Science, for example, a number of hit songs by U2 have a close kinship to some of Beethoven’ s compositions. If a song written today has parameters similar to those of a number of past hits, it could well be a hit too.
Carlos Quintero, a producer and remixer at Orixa Producciones in Madrid, recently tried out another music-intelligence system, called Hit Song Science (HSS). “It practically left me in shock, it’s stunning,” he says. Mr Quintero’s production company now has the most promising demo songs it receives from aspiring musicians evaluated by Polyphonic HMI, the Barcelona-based developer of HSS and Platinum Blue’s only serious competitor. (Both companies perform analyses in-house, rather than selling software.) The results—consisting of a graph, numerical scores, computer-generated comments and suggested changes—help Orixa’s managers decide which songs to produce. Then, during the recording and post-production phases, Orixa uses HSS to reanalyse successive versions of each track for fine-tuning.
Belief in music intelligence is spreading, as Polyphonic HMI and Platinum Blue rack up bull’s-eye predictions of success, including “Candy Shop” by 50 Cent, “Be the Girl” by Aslyn, “Unwritten” by Natasha Bedingfield, “She Says” by Howie Day, and “You’re Beautiful” by James Blunt. Still, labels that use music intelligence generally prefer to keep quiet about it, so non-disclosure agreements are common. “No one wants people to think their decisions are coming from a box,” says Ric Wake, an American producer of two Grammy-winning acts who routinely employs Music Science. Even so, the names of many customers have leaked out. They include Capitol Records, Universal Music Group, Sony Music, EMI and Casablanca Records. Labels sometimes don’t tell even their established artists when they use music intelligence to help decide which singles to promote.
Revenues at Polyphonic HMI will exce
The extreme centre is the paper's historical position. --Geoffrey Crowther
I *DOES* help strategy, NFL teams have been using similar techniques for years to analyze what their opponents might do in a given situation. This is especially critical in American Football, where the defenses don't have time to react to what is actually happening in that instant the ball is hiked. Its the difference between stopping a play in the backfield or giving up a 6 yard play. In soccer, being able to anticipate where a play is going could reduce the amount of running a team has to do, keeping players fresher and getting them into position sooner. This would yield a pretty good advantage, but probably not enough to overcome the gap between a great team and a mediocre one. More to the point, its more likely the great team is already doing similar analysis, and just not chatting about it.
You are in a maze of twisted little posts, all alike.
Australia, ranked 88th in the world of football, played Brazil, ranked 1st in the world of football, almost to a standstill in the first half.
They had two clear chances to equalize Brazil's first goal, but couldn't quite get there.
Then, late in the game, Brazil helped themselves to a freakish goal off a goalpost rebound, which made the score 2:0.
Australia losing to Brazil ONLY 2:0 is a testament to the Aussie's coach, Gus Hiddink, fearless play, and, very probably, the software that you're saying "didn't do it".
Look, I know you don't really understand "soccer" but this is as if, off the back of a crushing Superbowl victory, the best team in the NFL played the wooden-spooners, and ONLY won by one touchdown...
First goal was scored by a player who can only hit the ball with his left foot, the defender didn't force him onto his right, didn't close down and Brazil scored. Everyone in the world knows Adriano is only left footed, you would have thought the technology would have stressed this a little more.
And yesterday the US (by any reasonable ranking system about the same level as Australia) played Italy to a standstill and a draw with one less player on the park.
Technology helps in coaching, but what really helped the Australians and the US was guts and effort from the players.
As one commentator said today
"Imagine the talent of Brazil with Australia's work ethic"
An Eye for an Eye will make the whole world blind - Gandhi
It would seem to me that evaluating the effectiveness of this software vs Brazil would be a rather pointless exercise. Brazil is known for having a extraordinarily creative approach to the game, and marvelous individual talent, almost beyond what could be expected from human performance. The result of their approach is extreme unpredictability. When it works it is astonishing in its results, and it generates acutally beauty and grace, when it doesn't work it results in surprisingly uninspired play. It is almost chaotic.
Nobody would normally expect the "Socceroos", a team of mediocre skills to be able to compete with Brazil. They are totally outmanned respect in every respect, talent, culture, skill and tradition. The evaluation of this softwware needs to be done at a different level, looking at its predictions and result. And more likely the predictions should be made examining a different data set than what a match against Brazil would provide.
I'm not sure whether you think the AIS is good or bad from your post. Yes, we have a goverment sponsored research institution into sport. But I don't see this as very different to say the US model with universities having a big emphasis on sports, or having corporate sponsorship of good athletes in certain games. The Australian model is clearly better bang for buck, and so if I'm going to pay for sports research I'd rather do it as efficiently as possible.
The Americans have a state subsidized dept. of defense which has no other goal but to "make our guys win".
I do think Australians are a little parochial about sport, and I do wish that more australians would play than watch on TV. Australians are on average, quite unhealthy. I also wish more money would be spent on other research, but perhaps not at the expense of sports research. (Less money on defence instead?) I think the drive for being good at sport is perhaps a little bit of arrogance, we like to think we're better than average, but in fact we're pretty much on target for an economy of our size.
Disclosure: I trained at the AIS, and my nephew is currently training for the australian swim team.