These days, we can weigh and pay for produce by ourselves at supermarkets, scan our own toiletries at drugstore chains, and even order food and pay the bill without having to flag down a Chili’s waiter. What’s next, self-service security checks at the airport? Exactly. Businessweek reports.
This week, California startup Qylur announced it would begin offering automated security checkpoints next year -- having tested the machines in airports, sporting arenas, and state parks over the last few months.
At the heart of Qylur’s idea is the basic Silicon Valley premise that machines can do an increasing number of jobs better than people, and do so without complaining, forming unions, or taking suspiciously long bathroom breaks.
The company takes its name from the star-nosed mole (Condylura cristata), a functionally blind animal that uses its fleshy snout, embedded with 25,000 sensory receptors, to hunt prey.
The security-screening kiosk is made of a series of honeycombed cells surrounding a sensor. It automatically checks for dangerous-looking items and sniffs for chemicals and nuclear material.
- You put a bag into one side of the machine, scan your ticket or a boarding pass, and close the door.
- The machine uses sensors to scan the bag, and using its knowledge of threat categories, it assesses whether those kinds of items are inside.
- It doesn’t just match a knife in a carry-on to known knives in some database. Its detection model can be regularly updated to improve its decision making and stay ahead of new threats.
According to the company, the system catches more things passing through while lowering the rate of false positives (like when an electric razor is mistaken for a bomb). A single machine with five cells could possibly replace five security lines at a TSA checkpoint, moving through the same number of people in a quarter of the space, and with only five employees, rather than 15.
The company charges clients between $0.20 and $1 per bag, while still owning and maintaining the hardware. The machine can come in "collaborative mode," where people can check the computer’s judgment:
The fact is, cutting out the middleman often comes with its own problems, which is why other companies running machine-learning projects have sometimes learned that it helps to keep people in the loop.
Editor's Note: This post reflects corrections made on Oct. 29 to the bulleted points on how the technology works.
This post was originally published on Smartplanet.com