The police are no strangers to big data, using analytical software to help them predict crime hotspots, and license plate scanners to identify stolen cars and disqualified drivers on the road. So it should come as no surprise to learn that other arms of law enforcement, specifically customs, are looking at data-driven solutions to help improve their efficiency too.
Our first report in this week’s big data special comes from Australia, where immigration authorities have been under increasing strain as they fight against a wave of illegal immigrants flooding into the country.
Up until now, customs officers at Sydney International Airport have had little to go on other than their instinct when it comes to screening new arrivals. Whilst one or two officers might have developed a keen eye for undesirables, the overreliance on their ability to read body language and make people crack during an interview has led to somewhat underwhelming results.
Previously, customs officers were stopping and interviewing an average 2,500 likely suspects a month at Sydney Airport, typically finding only 50 or so people who had arrived in the country on false documents or under false pretences.
Now though, thanks to a new data analytics system unveiled at this year’s CeBIT Big Data conference in Australia, officers are carrying out only 1,300 interviews a month, while the average number of illegal immigrants caught has risen to 60.
According to Klaus Felsche, Director, Intent Management & Analytics, Department of Immigration and Citizenship, who is overseeing the system:
“It can’t see whether someone in the arrivals hall is sweating but it sure as hell can predict that somebody should be. This means we’ve increased the refusal rate and reduced massively the inconvenience rate for people at the airports.”
The system scans analyzes tons of data accumulated by customs authorities over the years in order to try and find patterns that would suggest a passenger might not be who they claim to be. Although Felsche admits there’s still a long way to go to perfect it, it’s already thrown up some unusual theories:
“For example, it turned out if you had a Belgian passport, tried to get on board the plane to Perth or Brisbane on a variety of visas using Cathay Pacific flights, there was a 64 per cent chance match against imposters.”
“The beauty with this analytics process is we are on solid ground because it’s all in the data, and I know the system works when we ping the first Brit or the first American or the first Swede because that means it is agnostic.”
Back at home meanwhile, customs have a different kind of problem on their hands – illegal drugs, the vast majority of which are smuggled in from Mexico.
As we saw last week, when a couple of audacious Mexican smugglers attempted to drive a car over the US border fence using makeshift ramps, only to get stuck and have to abandon it, drugs gangs are devising ever more sophisticated means of getting their illicit cargo into the country.
One of the most popular methods is the use of microlights – small, inexpensive planes that weigh only a few hundred pounds and can be flown by almost anyone after a few hours of practice. The advantage of microlights, besides being cheap, is that they’re small enough and they fly low enough that most go undetected by US customs’ radar systems – a kind of poor man’s stealth, if you like.
To fight this new, low-flying menace, the US Customs and Border Protection agency has turned to a private research and development company called SRCTec, which, among other things, has designed a fiendishly clever radar system called VantagePoint.
SRCTec claims that its system, which can be set up anywhere and taken down in just a few hours, is able detect small, low flying aircraft within an altitude range of 33 feet to 15,000 feet, for up to 20 kilometers. In addition, the system can also track vehicles on the ground if it’s calibrated to do so.
VantagePoint is more effective if the sensors are placed at altitude, on hills and so forth, where they can deliver “complete 360 degree, short and long range ground and air surveillance, and communicate remotely with command and control systems via satellite.”
But the real beauty of VantagePoint is that it’s not limited to just radar tracking – the system can also identify those vehicles it detects, using a combination of its built-in camera and its IFF (Identification Friend or Foe) interrogation system.
Before joining SiliconANGLE, Mike was an editor at Argophilia Travel News, an occassional contributer to The Epoch Times, and has also dabbled in SEO and social media marketing. He usually bases himself in Bangkok, Thailand, though he can often be found roaming through the jungles or chilling on a beach.
Got a news story or tip? Email Mike@SiliconANGLE.com.
Latest posts by Mike Wheatley (see all)
- HPE & Microsoft to collaborate on Cloud, Mobility & Windows 10 - November 24, 2015
- AWS now offering dedicated servers for your eyes only - November 24, 2015
- IBM open-sources its SystemML machine learning tech - November 24, 2015