World’s first software to automate production-line image recognition

Source – http://phys.org/news/2014-09-world-software-automate-production-line-image.html

Figure 1: The conventional process of developing and revising an image-recognition program used with a camera in automated assembly equipment

Fujitsu Laboratories has announced the development of a technology for automatically generating image-recognition programs that accurately detect the positions of components as captured by cameras in automated assembly processes by utilizing images of electronic components and IT equipment. Automatically generated image-processing programs that use machine learning have not been able to detect positions up until now, requiring that experts individually develop image-recognition programs. As a result, any changes to the manufacturing setup, such as a machine’s operating parameters, could involve more than a week’s time spent revising the program, during which time the production line would sit idle. What Fujitsu Laboratories has done is to develop a technique for automatically generating image-processing programs that detect positions by controlling the order in which the various image-processing functions that make up a program are combined, and using machine learning based on the similarity of shapes. Samples of the object to be detected are presented as teaching materials, and this makes it possible to automatically generate an image-recognition program in roughly eight hours, or one-tenth the time previously required. Fujitsu Laboratories plans to use this technology to help make production lines better able to respond to changes in their operating environment without long downtime.

Details of this technology are being presented at the Autumn Meeting of the Japan Society for Precision Engineering, opening September 16 in Tottori, Japan. Read more of this post

Advertisements

Genetic approach helps design broadband metamaterial

Tue, 05/06/2014 – 9:39am
Overall layers of the metamaterial absorber are shown. The black layer is the substrate, solid green layer is palladium, transparent blue layer is polyimide, broken green layer is the patterned layer and the transparent blue layer is again polyimide to seal and protect. (Credit: Bossard, Penn State)

Overall layers of the metamaterial absorber are shown. The black layer is the substrate, solid green layer is palladium, transparent blue layer is polyimide, broken green layer is the patterned layer and the transparent blue layer is again polyimide to seal and protect. (Credit: Bossard, Penn State)

A specially formed material that can provide custom broadband absorption in the infrared can be identified and manufactured using “genetic algorithms,” according to Penn State engineers, who say these metamaterials can shield objects from view by infrared sensors, protect instruments and be manufactured to cover a variety of wavelengths. “The metamaterial has a high absorption over broad bandwidth,” said Jeremy A. Bossard, postdoctoral fellow in electrical engineering.

“Other screens have been developed for a narrow bandwidth, but this is the first that can cover a super-octave bandwidth in the infrared spectrum.”

At left, a drawing of the metamaterial absorber pattern. At right, an actual metamaterial absorber pattern. (Credit: Bossard, Penn State)

At left, a drawing of the metamaterial absorber pattern. At right, an actual metamaterial absorber pattern. (Credit: Bossard, Penn State)

Having a broader bandwidth means that one material can protect against electromagnetic radiation over a wide range of wavelengths, making the material more useful. The researchers looked at silver, gold and palladium, but found that palladium provided better bandwidth coverage. This new metamaterial is actually made of layers on a silicon substrate or base. The first layer is palladium, followed by a polyimide layer. On top of this plastic layer is a palladium screen layer. The screen has elaborate, complicated cutouts — sub wavelength geometry — that serve to block the various wavelengths. A polyimide layer caps the whole absorber.

“As long as the properly designed pattern in the screen is much smaller than the wavelength, the material can work effectively as an absorber,” said Lan Lin, graduate student in electrical engineering.

“It can also absorb 90 percent of the infrared radiation that comes in at up to a 55 degree angle to the screen.”

This is an overall pattern of the metamaterial absorber. (Credit: Bossard, Penn State)

This is an overall pattern of the metamaterial absorber. (Credit: Bossard, Penn State)

To design the necessary screen for this metamaterial, the researchers used a genetic algorithm. They described the screen pattern by a series of zeros and ones — a chromosome — and let the algorithm randomly select patterns to create an initial population of candidate designs. The algorithm then tested the patterns and eliminated all but the best. The best patterns were then randomly tweaked for the second generation. Again the algorithm discarded the worst and kept the best. After a number of generations the good patterns met and even exceeded the design goals. Along the way the best pattern from each generation was retained. They report their results in a recent issue of ACS Nano.

“We wouldn’t be able to get an octave bandwidth coverage without the genetic algorithm,” said Bossard. “In the past, researchers have tried to cover the bandwidth using multiple layers, but multiple layers were difficult to manufacture and register properly.”

This evolved metamaterial can be easily manufactured because it is simply layers of metal or plastic that do not need complex alignment. The clear cap of polyimide serves to protect the screen, but also helps reduce any impedance mismatch that might occur when the wave moves from the air into the device.

“Genetic algorithms are used in electromagnetics, but we are at the forefront of using this method to design metamaterials,” said Bossard.

Copied from nature: Detecting software errors via genetic algorithms

According to a current study from the University of Cambridge, software developers are spending about the half of their time on detecting errors and resolving them. Projected onto the global software industry, according to the study, this would amount to a bill of about 312 billion US dollars every year. “Of course, automated testing is cheaper”, explains Andreas Zeller, professor of Software Engineering at Saarland University, as you could run a program a thousand times without incurring any charges. “But where do these necessary test cases come from?”, asks Zeller. “Generating them automatically is tough, but thinking of them yourself is even tougher”.

In cooperation with the computer scientists Nikolas Havrikov and Matthias Höschele, he has now developed the software system “XMLMATE”. It generates test cases automatically and uses them to test the given program code automatically. What is special about it is that the only requirement the program to be tested has to meet is that its input must be structured in a certain way, since the researchers use it to generate the initial set of test cases. They feed them to the so-called genetic algorithm on which the testing is based. It works similarly to biological evolution, where the chromosomes are operating as the input. Only the input that covers a significant amount of code which has not been executed yet survives. As Nikolas Havrikov explains their strategy: “It is not easy to detect a real error, and the more code we are covering, the more sure we can be that more errors will not occur.” Havrikov implemented XMLMATE. “As we use the real existing input interface, we make sure that there are no false alarms: Every error found can also happen during the execution of the program”, adds Zeller.

Read more of this post

A.I. SOLVER STUDIO

Source – Perceptio

A.I. Solver Studio

Download (520 KB) 

A.I. Solver Studio is a unique pattern recognition application that deals with finding optimal solutions to classification problems and uses several powerful and proven artificial intelligence techniques including neural networks, genetic programming and genetic algorithms. No special knowledge is required of users as A.I. Solver Studio manages all the complexities of the problem solving internally. This leaves users free to concentrate on formulating their problems of interest. 

Requirements:

  •  Windows XP or Windows Vista
  •  8MB of free disk space


How Big Data analysts reappropriate algorithms from evolution and warfare

By Olivia Solon 06 January 12

The amount of data we generate is exploding, and the ability to analyse large amounts of data is a key differentiator for businesses seeking to gain competitive advantage.

Opera Solutions is one Big Data company that is harnessing predictive analytics to inform the business decisions of its clients. Wired.co.uk spoke to Jacob Spoelstra, vice president of analytics at Opera, about how they are taking the algorithms from electrical engineering, physics and maths and applying them to business data. Read more of this post