Entries Tagged as ''

Carnegie Mellon Develops Java Programming Tools Employing Human-Centered Design Techniques

PITTSBURGH—Researchers at Carnegie Mellon University’s School of Computer Science have developed two new tools to help computer programmers select from among thousands of options within the application programming interfaces (APIs) that are used to write applications in Java, today’s most popular programming language.

The tools — Jadeite (www.cs.cmu.edu/~jadeite) and Apatite (www.cs.cmu.edu/~apatite) — take advantage of human-centered design techniques to significantly reduce the time and guesswork associated with finding the right classes and methods of APIs.

APIs are standardized methods that a Java program uses to ask the computer’s operating system or another program to do something, such as opening a file or sending an email. Choosing APIs for accomplishing a given task is at the heart of Java programming, but is not intuitive, said Brad A. Myers, professor of human-computer interaction. With more than 35,000 methods listed in 4,100 classes in the current Javadoc library of APIs — and more being added in every new version — not even the savviest developer can hope to be familiar with them all.

“This is a fundamental problem for all programmers, whether they are novices, professionals or the growing number of end-users who just need to modify a Web page,” Myers said. “It’s possible to design APIs so that they are easier to use, but that still leaves thousands of existing APIs that are hard to use but essential for Java programming. Jadeite and Apatite help programmers find what they need among those existing APIs.”

Jadeite (Java Documentation with Extra Information Tacked-on for Emphasis) improves usability by enhancing the existing Javadoc documentation. For instance, Jadeite displays the names of API classes in font sizes that correspond with how heavily used they are based on Google searches, helping programmers navigate past little-used classes. The commonly used “PrintWriter” is in large, prominent letters, while the lesser used “PrintEvent” is in smaller type.

Jadeite also uses crowd-sourcing to compensate for the fact that an API sometimes doesn’t include methods that programmers expect. For instance, the Message and MimeMessage classes don’t include a method for sending an email message. So Jadeite allows users to put so-called placeholders for these expected classes and methods within the alphabetical listing of APIs. Users can edit the placeholder to guide programmers to the actual location of the desired method, explain why a desired method is not part of the API, or note that a desired functionality is impossible.

Finding the way to create certain types of objects, such as SSL sockets that enable secure Internet communications, may not be obvious to programmers the first time they encounter these objects. In these cases, Jadeite includes examples of the most popular code used by programmers to create these objects, allowing the user to learn from the examples.

User studies showed that programmers could perform common tasks about three times faster with Jadeite than with the standard Javadoc documentation.

Apatite (Associative Perusal of APIs That Identifies Targets Easily) takes a different approach, allowing programmers to browse APIs by association, seeing which packages, classes and methods tend to go with each other. It also uses statistics about the popularity of each item to provide weighted views of the most relevant items, listing them in larger fonts.

Both Jadeite and Apatite remain research tools, Myers said, but are available for public use. Broader use of the tools will enhance the crowd-sourcing aspects of the tools, while giving the researchers important feedback about how the tools can be improved.

Research by Jeffrey Stylos, who was awarded a Ph.D. in computer science this spring, underlies both Jadeite and Apatite. Besides Myers, research programmer Andrew Faulring and undergraduate computer science student Zizhuang Yang contributed to the development of Jadeite and computer science undergraduate Daniel S. Eisenberg led the implementation of Apatite. Eisenberg’s work on Apatite earned first place in the Yahoo! Undergraduate Research Awards competition at Carnegie Mellon this spring.

Jadeite and Apatite are part of the Natural Programming Project, www.cs.cmu.edu/~NatProg/, an initiative within Carnegie Mellon’s Human-Computer Interaction Institute that is investigating how to make programming easier. Both tools have been funded by grants from the National Science Foundation and software giant SAP AG Inc.

Contact:

Byron Spice
412-268-9068
bspice@cs.cmu.edu

Tags: Uncategorized by Fred
No Comments »

Teaching computers to recognise

From Cordis ICT Results

Recognising objects and groups of objects is something we humans take for granted. For computers, this is far from straightforward. A European project has come up with novel solutions to this conundrum.

Imagine your friends have blindfolded you and taken you to a “secret location”. When they take off your blindfold, you immediately see a group of people around you and realise that they have thrown you a surprise birthday party. How did you know? Because everyone shouted “surprise”, and there were balloons, a birthday cake and booze.

The question may seem like a silly one, but the processes involved are far from straightforward. In fact, you had to collate an awful lot of visual, as well as other sensory data, cross-reference it with your memories, and make mental deductions.

“Vision is our most important sense and about half of the human brain is involved with vision in one way or another,” explains Luc Van Gool of Belgium’s Leuven University (KUL) who also leads the Computer Vision Laboratory at the Swiss Federal Institute of Technology (ETH). “Enabling us to recognise the objects and places around us is a task it performs brilliantly.”

In fact, what we regard as the simple process of “recognition” would leave many computers stumped. Even something as apparently simple as recognising a birthday cake would normally require computers to be fed with information on what a cake generally looks like, the various shapes and sizes it comes in, the different forms and numbers of candles and other decorations you are likely to find adorning it, etc.

“The same object will look different depending on the viewpoint, the illumination, or the occlusions caused by other objects in front,” notes Van Gool.

Points of view

In brief, computers might be able to calculate pie to hundreds of decimal points and model complex weather patterns, but they may find it impossible, without complex and painstaking programming, to recognise a human whose grown their hair or realise that Chihuahuas and Dobermans belong to the same species.

Van Gool is involved in a project, Cognitive-Level Annotation Using Latent Statistical Structure (CLASS), which is developing technologies to recognise visually specific objects, such as your car, or classes of object, such as a random car on the street.

“The recognition of an object as belonging to a particular group is a harder problem for a computer than the recognition of a specific object. The reason is that object classes show large variability among their members,” Van Gool points out.

The 3.5-year, EU-funded project managed to achieve technological improvements compared with previous efforts. It developed a system in which the description of the objects is based on the appearance of many separate, small patches. Such localised features give the necessary robustness to deal with the massive variations mentioned earlier. In addition, CLASS created special mechanisms – known as efficient approximate neighbourhood searches – for the comparison of an image or an object with huge numbers of reference images.

A picture speaks a thousand words

The specific object recognition technology developed by CLASS has already found a commercial application. Through a company known as kooaba, CLASS technology enables mobile phone subscribers who install the relevant software to take a photo with their handset of, say, a monument, a film poster, or an album cover and get relevant online information about it.

“It’s like the object itself becomes the link to further information,” observes Van Gool. He expects the application of this technology to expand rapidly. For instance, cities and museums may offer interactive guided tours or guide books through kooaba.

CLASS project
CLASS fact sheet on CORDIS
kooaba

Tags: research by Fred
No Comments »

Computing in the quantum dimension

A huge consortium of European researchers is solving some of the fundamental obstacles blocking real quantum computing applications in the short term. At the same time, it is helping to pave the way to a quantum computer.

It is not easy being quantum. The rules are different, often they do not seem to make sense, and as soon as you look at one thing, everything else changes. Quantum science is difficult and challenging, but that is the main reason it is so darned interesting.

Quantum mechanics led to the systematic exploitation of materials at a subatomic scale, leading to the laser, transistor and all solid-state physics such as semiconductors and microprocessors. It illuminated biology and chemistry, because it showed that mystifying, almost incomprehensible subatomic principles governed the nature of matter.

Up to now, science has exploited quantum phenomena on a macro scale – how it impacts electrons in a conducting material, for example – and to explain why materials behave in seemingly strange ways under specific conditions.

Huge consortium

But now a huge consortium of 35 European scientific and industrial actors is working together to study how to directly exploit quantum phenomena like uncertainty, entanglement and others in real-world applications. The Qubit Applications integrated project, or QAP for short, is the start of the road to quantum computing.

“We are not looking to create a quantum computer directly,” explains Professor Ian Walmsley, co-coordinator of the QAP project. “Other people are working on that, and it will take a long time to solve that problem.”

“We are, however, looking at some of the problems facing real-world quantum applications that we could deploy now.

These are problems that must be solved anyway, if a quantum computer is to become possible. Problems like the storage of information encoded on a photon.

“But by focusing on these problems, we can perhaps create important new products that could be developed in the short and medium term, and we could solve some of the fundamental problems affecting the advent of quantum computing.”

Tied up over entanglement

It is a very effective approach and, luckily, the consortium has a wide choice of topics to consider. The work is divided into five sections, looking at issues such as the storage of quantum information and transmission of certain quantum states, like entanglement, over long distances using repeaters.

Unsurprisingly, the consortium will study networks, too, and will be looking at quantum applications for simulation of extremely complex problems. “Finally, all this will need a focused dose of theory that helps frame the right questions and to understand the experimental results,” notes Walmsley.

It is an ambitious programme but QAP has the resources to make it happen. Apart from the 35 scientific and industrial partners, most of them leading authorities in their field, QAP enjoys a four-year research period and a budget of almost €13m, €9.9 supplied by the European Union.

An even greater resource, however, is the multidisciplinary nature of the consortium, from computer scientists and applied mathematicians to experimental physicists, as well as some very impressive industrial scientists and engineers.

The project will need all that talent because quantum applications are a non-trivial problem.

The QAP project receives funding from the ICT strand of the EU’s Sixth Framework Programme for research.

The dawn of quantum applications

Representation of quantum measurement made by a detector. © QAP

Technologies that exploit the unique weirdness of quantum mechanics could debut in the very near future, thanks to the groundbreaking work of a huge European research consortium.

Unbreakable cryptography, unimaginable simulations of profoundly complex problems and super-fast networks are just some of the promise held out by quantum computing. And now European scientists are poised to deliver on that promise, thanks to the work of the Qubit Applications (QAP) project.

The integrated project has cherry-picked major obstacles in the path of quantum computing, problems that could have immediate applications and could command a ready market.

Chief among them is quantum cryptography. “Quantum computing, when it arrives, could make all current cryptographic technology obsolete,” notes QAP co-coordinator Professor Ian Walmsley.

Thankfully, researchers have developed quantum cryptography to deal with that issue.

“Quantum cryptography over short distances was demonstrated in a previous project,” explains Walmsley. “The problem is, it only works over a short distance.”

Weaving entangled webs

That is because quantum cryptography relies on entanglement. Entanglement is a concept that explains how two or more particles exhibit correlation – a relationship if you like – that would be impossible to explain unless you supposed that they belonged to the same entity, even though they might be separated by vast distance.

Imagine you were playing a game of quantum coin flipping with a colleague: you are heads and the colleague tails. You are two distinct individuals, but if the coin comes up heads your colleague loses, and you win. There is a correlation between the coin tossing. Now, with a quantum coin, it is heads the colleague wins and tails you win at the same time.

This is the extra bit that quantum mechanics gives us, and which we use in secure communications, suggests Walmsley.

That explains, with a little inaccuracy, the concept of entanglement, and it is at the core of quantum key distribution, or QKD. It is far too complex to break quantum encryption by brute force, and it is immune to eavesdropping because, at the quantum level, the act of observing an object changes the object observed. It means that encryption is guaranteed by the laws of physics.

The technique was demonstrated in Vienna 2008, but it works only over short distances. EU-funded QAP hopes to develop a quantum repeater that can maintain entanglement over large distances. It has already had considerable success up to the 200km range, and growing.

Ideal information carrier

Maintaining entanglement over long distances – so essential to QKD, but also communications and networks – is the most immediate and compelling application in the QAP programme, but it is far from the only one. Many other areas of work show signs of progress, too. Storage and memory are essential for quantum computing.

It is not too difficult to encode a piece of information on a photon, which is an ideal information carrier because of its high speed and weak interaction with the environment.

It is difficult to store that information for any length of time, so QAP is developing ways of transferring quantum information from photons to and from atoms and molecules for storage, and the project is making steady progress.

Similarly, QAP’s work to develop quantum networks is progressing well. One team within the overall research effort has managed to develop a reliable way to calibrate and test detectors, a prime element in the network system.

“This is important because it will be essential to develop reliable methods to test results if work on quantum networks is to progress,” notes Walmsley. The research group has submitted a patent application for this work.

Stimulating simulation

Quantum simulation, too, offers some tantalising opportunities. The primary goal of QAP’s Quantum Simulations and Control subproject is to develop and advance experimental systems capable of simulating quantum systems whose properties are not approachable on classical computers.

Imagine, for example, trying to model superconducting theory. It is hugely complex, and classic computers are quickly overwhelmed by the size of the problem.

But quantum methods are inherently capable of dealing with far greater complexity, because of the nature of the qubit, or quantum bit. Classical, digital bits operate on the basis of on or off, yes or no. But quantum bits can be yes, no, or both. It takes classical computing from 2D, into the 3D information world.

One could say that, while classical computers attack problems linearly, quantum computers attack problems exponentially. As a result, with just a few qubits, it is possible to do incredibly large computations, and that means that quantum simulation of complex problems could be a medium-term application.

“We are not saying we will solve all the problems in the area of simulation, but we will make a good start,” warns Walmsley.

That defines QAP nicely: a kick-start for quantum applications in Europe.

The QAP project received funding from the ICT strand of the EU’s Sixth Framework Programme for research.

From ICT
http://cordis.europa.eu/ictresults/index.cfm?section=news&tpl=article&ID=90645
http://cordis.europa.eu/ictresults/index.cfm?section=news&tpl=article&ID=90649

Tags: Quantum by Fred
No Comments »

The Internet is incomplete, says its co-designer, Vinton Cerf

By Patrick Thibodeau from Computerworld

WASHINGTON – The co-designer of the Internet’s basic architecture, Vinton Cerf, said the Internet “still lacks many of the features that it needs,” particularly in security, in a blunt talk to a tech industry crowd here.

Cerf, who is a vice president and chief Internet evangelist at Google Inc., co-designed with Robert Kahn the TCP/IP protocols that underpin the Internet. That was in 1973. And despite becoming operational in 1983, and commercially available in 1989, the Internet remains incomplete, he said.

Cerf is influential because of his accomplishments, but he may be even more so today because of his affiliation with Google. President Obama’s administration has appointed a number of Google employees, including CEO Eric Schmidt, to important positions.

One of the most critical needs is authentication, Cerf said, and he told the crowd at a TechAmerica gathering Wednesday that anyone who performs transactions over the Internet – which is everyone – should “should be deeply concerned about that technology.”

The lack of authentication is pervasive and is even a problem in simple cases, such as authenticating entries in the domain name system, he said.

“Authentication isn’t available on an end-to-end basis at all layers of the architecture,” Cerf said. While users are good “at building concrete tunnels” using simple SSL (Secure Sockets Layer) techniques, they don’t identify the end points and just secure the channel, he said. You can have an e-mail with an attached virus, thoroughly encrypted, and send it through an encrypted tunnel, and once it gets to the other end “it gets decrypted and then, of course, does its damage,” he said.

Mobile is another problem. “We do a terrible job serving up mobile,” Cerf said, referring to the ever broadening use of the Internet via mobile devices. He said protocol work is needed to address it.

Asked later what the White House should be doing in regard to this issue, Cerf cited the work that’s been assigned to the National Institute of Standards and Technology in coordinating standards on the smart grid and health IT. However, he said he would anticipate that Obama’s new CTO and CIO will “have some things to say about what the U.S. government hopes will emerge in the infrastructure of our digital communications system.”

The Obama administration recently released a report on cyberspace security and has promised to make this issue a priority. The actions have been met with cautious optimism by the security industry.

Tags: Internet, security by Fred
No Comments »

Computing Research that Changed the World: Reflections and Perspectives

From CCC

Slides by Session
Introductory Session: Changing the World

[ 992 KB | PDF] [Download Video (181 MB) | Watch at Youtube (12:35)]
Ed Lazowska (University of Washington)

Session 1: The Internet and the World Wide Web

Why We’re Able to Google
[1.1 MB | PDF] [Download Video (181 MB) | Watch at Youtube (19:41)]
Alfred Spector (Google)

The Magic of the “Cloud”: Supercomputers for Everybody, Everywhere
[2.9 MB | PDF] [Download Video (277 MB) | Watch at Youtube (17:36)]
Eric Brewer (University of California, Berkeley)

Human Computation
[1 MB | PDF] [Download Video (168 MB) | Watch at Youtube (11:50)]
Luis von Ahn (Carnegie Mellon University)

Session 2: Evolving Foundations

Security of Online Information
[208 KB | PDF] [Download Video (263 MB) | Watch at Youtube (19:26)]
Barbara Liskov (Massachusetts Institute of Technology)

Learning to Improve Our Lives
[Download Video (256 MB) | Watch at Youtube (17:34)]
[4.7 MB | PDF] [5.2 MB | helicopter.wmv (0:28)] [2.4 MB | quadruped.wmv (0:26)]
Daphne Koller (Stanford University)

Global Information Networks
[768 KB | PDF] [Download Video (340 MB) | Watch at Youtube (20:11)]
Jon Kleinberg (Cornell University)

Session 3: The Transformation of the Sciences via Computation

Supercomputers and Supernetworks are Transforming Research
[1.5 MB | PDF] [Download Video (258 MB) | Watch at Youtube (14:38)]
Larry Smarr (University of California, San Diego)

Computing and Visualizing the Future of Medicine
[Download Video (261 MB) | Watch at Youtube (16:03)]
[3.3 MB | PDF] [49.6 MB | Quicktime Movie (9:26)]
Chris Johnson (University of Utah)

Zooming In On Life
[Download Video (267 MB) | Watch at Youtube (18:09)]
[3.5 MB | PDF] [21.9 MB | Quicktime Movie (2:51)]
Gene Myers (Howard Hughes Medical Institute)

Session 4: Computing Everywhere!

Sensing Everywhere!
[2.5 MB | PDF] [Download Video (287 MB) | Watch at Youtube (18:23)]
Deborah Estrin (University of California, Los Angeles)

Pixels Everywhere!
[2 MB | PDF] [Download Video (391 MB) | Watch at Youtube (22:06)]
Pat Hanrahan (Stanford University)

Robots Everywhere!
[2.1 MB | PDF] [Download Video (280 MB) | Watch at Youtube (17:39)]
Rodney Brooks (Massachusetts Institute of Technology and Heartland Robotics)

Closing Session

[Download Video (211 MB) | Watch at Youtube (15:05)]
Ed Lazowska (University of Washington)

Demonstrations (available during the closing session)

Autonomous Flying Robots: A Bird’s Eye View

Brian J. Julian (Massachusetts Institute of Technology)
[Download Video (115 MB) | Watch at Youtube (5:20)]

Information Technologies to Support the Challenges of Autism and Related Developmental Disorders

Gregory D. Abowd (Georgia Institute of Technology/Emory University Health Systems Institute)
Gillian Hayes (University of California, Irvine)
Julie Kientz (University of Washington)
[Download Video (88 MB) | Watch at Youtube (3:56)]

Personal Environmental Impact Report (PEIR)

Jeff Burke (University of California, Los Angeles REMAP and CENS)
Deborah Estrin (University of California, Los Angeles CENS)
[Download Video (137 MB) | Watch at Youtube (5:46)]

Scientific Computing and Visualization for Medical Image Analysis

Ross Whitaker (University of Utah and the Scientific Imaging and Computing Institute)
[Download Video (127 MB) | Watch at Youtube (5:38)]

Tags: computer science by Fred
No Comments »

Visual system that detects movement, colors and textures created in Granada

Mimicking the way in which a retina works is a hard as it sounds. Scientists from Stanford University, in the United States, have spent the past two years working on imitating the way in which information is processed in biological systems, in other words through the transmission of events in specifically connected networks (where information is captured and transmitted at the same time).

Now a research team from the UGR has evaluated the degree of precision of different models in estimating movement, and have combined the responses of four movement detection cells, two of which are static (on and off), and two transitory (decrease and increase). “One of our developments is a multimodal attention operator, which can detect movement in objects of different colours and textures”, Fran Barranco, one of the researchers involved in this project, tells SINC.

The objective of this study, which has been published in the latest issue of the journal IEEE Transactions on Systems Man and Cybernetics, was to combine movement and attention based on information provided by the artificial retina, a visual system capable of selectively capturing moving objects in real time.

The use of an event-driven model, which makes it possible to focus only on areas of activity, has been fundamental, both in the movement processing model as well as in the multimodal selective attention model created in Granada.

One of the most interesting results of the study is the ability to estimate movement reasonably precisely using the responses from each of these cells alone (4% of the information provided by a camera). “By selecting only 10-20% of the information, which we selected on the basis of reliability of the measurements, we obtained precise results at a lower computational cost and with greater stability”, explains Barranco. This point is very important in enabling the model to be used in applications with broadband limitations.

The Spanish researchers have also developed ‘advanced integrated intelligent sensors’, which can pre-process a scene in a manner similar to that used by retinas.

A science fiction future

“We are carrying out reverse engineering. In other words we are trying to study how Nature behaves in order to imitate it, because thousands of years of evolution have created a highly-advanced model adapted to the task for which it evolved”, says Barranco.

The devices created have been designed for use in video surveillance and monitoring applications. However, their low energy consumption could make them of great interest in the future for implants in patients or in work to understand the functioning of the brain, and particularly the visual system.

References:

Francisco Barranco; Javier Díaz, Eduardo Ros, Begoña del Pino. ‘Visual System Based on Artificial Retina for Motion Detection’. IEEE Transaction on Systems Man and Cybernetics Part-B Cybertenics. Volumen 39 (3), páginas 752-762. Junio de 2009.

Tags: visual system by Fred
No Comments »

Extracting Meaning from Millions of Pages

University of Washington software pulls facts from 500 million Web pages.

By David Talbot from technologyreview.com

A software engine that pulls together facts by combing through more than 500 million Web pages has been developed by researchers at the University of Washington. The tool extracts information from billions of lines of text by analyzing basic relationships between words.
Some experts say that this kind of “automated information extraction” will likely form the basis for far more intelligent next-generation Web search, in which nuggets of information are first gleaned and then combined intelligently.

The University of Washington project represents a scaling up of an existing technology developed there called TextRunner in terms of both the number of pages and the scope of topics that it can analyze.

“The significance of TextRunner is that it is scalable because it is unsupervised,” says Peter Norvig, director of research at Google, which donated the database of Web pages that TextRunner analyzes. “It can discover and learn millions of relations, not just one at a time. With TextRunner, there is no human in the loop: it just finds relations on its own.”

Norvig explains that previous technologies have required more guidance from the programmer. For example, to find the names of people who are CEOs within millions of documents, you’d first need to train the software with other examples, such as “Steve Jobs is CEO of Apple, Sheryl Sandberg is CEO of Facebook.” Norvig adds that Google is doing similar work and is already using such technology in limited contexts.

TextRunner gets rid of that manual labor. A user can enter, for example, “kills bacteria,” and the engine will come up with of pages that offer the insights that “chlorine kills bacteria” or “ultraviolet light kills bacteria” or “heat kills bacteria”–results called “triples”–and provide ways to preview the text and then visit the Web page that it comes from.

The prototype still has a fairly simple interface and is not meant for public search so much as to demonstrate the automated extraction of information from 500 million Web pages, says Oren Etzioni, a University of Washington computer scientist leading the project. “What we are showing is the ability of software to achieve rudimentary understanding of text at an unprecedented scale and scope,” he says.

Etizioni says TextRunner’s ability to extract meaning quickly and at huge scale flowed from his group’s discovery of a general model for how relationships are expressed in English that holds true no matter the topic. “For example, the simple pattern ‘entity1, verb, entity2′ covers the relationship ‘Edison invented the light bulb’ as well as ‘Microsoft acquired Farecast’ and many more,” he says. “TextRunner relies on this model, which is automatically learned from text, to analyze sentences and extract triples with high accuracy.”

TextRunner also serves as a starting point for building inferences from natural-language queries, which is what the group is now working on. To give a simple example: if TextRunner finds a Web page that says “mammals are warm blooded” and another Web page that says “dogs are mammals,” an inference engine will produce the information that dogs are probably warm blooded.

This is analogous to technology developed by Powerset, which was acquired by Microsoft last year. Shortly before this acquisition, Powerset unveiled a tool that was limited to extracting facts from only about two million Wikipedia pages. The TextRunner technology handles Wikipedia pages plus arbitrary text on any page, including blog posts, product catalogues, newspaper articles, and more.

“This line of work has been making important advances in the scale at which these tasks can be approached,” says Jon Kleinberg, a computer scientist at Cornell University who has been following the University of Washington search research. He added that “this work reflects a growing trend toward the design of search tools that actively combine the pieces of information they find on the Web into a larger synthesis.”

Tags: search by Fred
No Comments »

Software ‘gives children a voice’ by BBC

Child with cerebral palsy with a classroom assistant

Pupils with communication problems have been testing the software

Scientists claim to have developed the first technology of its kind to allow children with communication problems to converse better.

‘How was school today?’ is software to help children with disabilities such as cerebral palsy communicate faster.

The system is the result of a project between computing scientists from the Universities of Aberdeen and Dundee, and Capability Scotland.

Pupils from Corseford School in Renfrewshire were first to trial it.

 

 I was happy to take part in How was school today? It made me feel good about myself 
Nicole Vallery
Corseford School pupil with cerebral palsy

Dr Ehud Reiter, from the University of Aberdeen’s school of natural and computing sciences, said: “How was school today? uses sensors, swipe cards, and a recording device to gather information on what the child using the system has experienced at school that day.

“This can then be turned into a story by the computer – using what is called natural language generation – which the pupils can then share when they get home.

“The system is designed to support a more interactive narration, allowing children to easily talk about their school day and to quickly answer questions.”

Rolf Black, from the University of Dundee’s school of computing, said: “For a child with severe motor disabilities and limited or no speech, holding a conversation is often very difficult and limited to short one to two word answers.

“To tell a longer story a communication device is often needed to form sentences but this can be very time consuming, putting a lot of strain on holding and controlling the conversation.”

‘Talk easily’

Sue Williams, head teacher at Capability Scotland’s Corseford School in Kilbarchan, said: “In the week we used the system we found it very useful to pupils, teachers, therapists and parents alike. It allows children to take control of the conversation without having to rely on help from us.”

 

Child with cerebral palsy

Children said they enjoyed using the new software

Nicole Vallery and Rebecca Clelland were two of the pupils at Corseford to test the new software.

Nicole, 11, who has cerebral palsy, said: “I was happy to take part in How was school today? It made me feel good about myself.”

Rebecca said: “It was something different, I enjoyed it.”

Nicole’s mother, Jan, said: “We really enjoyed using How was school today? and hearing Nicole’s story.

“The programme enabled her to talk easily and answer questions quickly, prompting more interaction and giving us a very detailed insight into her day.”

Plans are in place to examine how it could be used to support children with different levels and types of impairments.

The project was funded by the Engineering and Physical Sciences Research Council (EPSRC)

From BBC
 

 

Tags: Softwares, research, science by Fred
No Comments »

Next Page »