TOOLBOXBROWSE TOPICS
RESOURCESABOUT THIS SITEpmwiki.org |
Telecommunications(a subtopic of Applications)
Smart Phone Suggests Things to Do - New software uses artificial intelligence to infer your behavior and serve up appropriate lists of restaurants, stores, and events. By Kate Greene. Technology Review (November 13, 2007). "[R]esearchers at Palo Alto Research Center (PARC) want to push the phone farther. They have developed software that turns a phone into a thoughtful personal assistant, one that helps people find fun things to do. The software, called Magitti, uses a combination of cues--including the time of day, a person's location, her past behaviors, and even her text messages--to infer her interests. It then shows a helpful list of suggestions, including concerts, movies, bookstores, and restaurants. ... The software employs artificial-intelligence algorithms that have traditionally been used in research to make tailored recommendations. If, for instance, a person prefers to eat inexpensive lunches and more-expensive dinners, Magitti will pick up on this (by comparing the GPS location of the restaurant with a database of establishments) and offer up corresponding recommendations. ... 'What's unique is that we've tried to build awareness of different kinds of activities,' says Victoria Bellotti, senior researcher at PARC. ... The idea of storing personal information as specific as location raises privacy concerns. But Bellotti says that this is something PARC considered when developing its system. " Talk to the Phone - Speech-recognition software from Vlingo could make the mobile Web easier to use. By David Talbot. Technology Review Magazine (September/October 2007). "Mobile phones can do lots of things: search the Web, download music, send e-mail. But the vast majority of the 233 million Americans who own them never use them for more than calls and short text messages. One reason is that other features often require users to enter sentences or long search terms, a tedious task. Speech-recognition interfaces could make such features easier to use. Vlingo, a startup in Cambridge, MA, is coming to market with a simple user interface that provides speech recognition across mobile-phone applications. ... 'Small platforms need speech, and search is a powerful way to find information,' says James Glass, head of the spoken-language systems group at MIT's Computer Science and Artificial Intelligence Laboratory. ... Mazin Gilbert, executive director of natural-language processing at AT&T Labs in Florham Park, NJ, says others, including AT&T, are also developing speech interfaces for mobile phones...."
New technology lets you read your voice mail - Several companies are betting on voice-recognition applications that transcribe those rambling messages into e-mail or text messages. By Marguerite Reardon. CNET News.com (April 6, 2007). "Why listen to your voice mail messages when you can read them? That's what a new crop of companies is asking--they're developing software that turns voice mail messages into transcribed e-mail or text messages. ... One indication that voice-recognition technology is getting hot is the recent Microsoft/Tellme deal. In March, Microsoft said it would buy privately held speech-recognition maker Tellme Networks in a deal believed to be in the range of $800 million. Tellme recently started testing a cell phone application that allows people to say out loud the information they are looking for and have data sent to their phone. 'Voice is still the killer application for any phone,' said Charles Golvin, an analyst with Forrester Research. 'And it is underappreciated as an opportunity and underutilized for development of new services. Carriers can use voice applications to drive data-oriented experiences.' ... [Jill Aldort,] agrees that voice recognition services are going to be hot, especially services like the one offered by Tellme, which can help people find information on the fly." Soon that cell will be all ears - Voice-recognition technology will cut out the wait time. By Ryan Kim. San francisco Chronicle & SFGate.com (April 24, 2006). "A handful of companies is creating solutions that allow users to find what they're looking for by utilizing an already familiar cell phone behavior: speaking into the phone. Companies are creating voice recognition applications that allow users to say a search term into the phone and be rewarded in seconds with results. ... The advances mean voice-search services can offer results in a couple of seconds with more than 90 percent accuracy. It saves people the time of scrolling through screen after screen of results. For many carriers, this technological advance could unlock revenue that is currently bottled up by the byzantine search format of cell phones. ... A study by ChangingWorlds, an Irish provider of artificial intelligence products, and Mobile Metrix, a Swedish research firm, found last year that almost two-thirds of mobile content was more than 12 clicks away. ... 'Voice isn't just for speaking. It's now an interface, and it's driving commands,' [Craig Hagopian said.]" Military research aims to develop self-configuring, secure wireless nets - Researchers develop military-grade intelligent wireless net. By Ryan DeBeasi. NetworkWorld.com (August 16, 2006). "Government, corporate and academic researchers are working on a network that would be able to configure itself, intelligently cache and route data, and allow for fast and reliable sharing of data, all while maintaining military-grade security. The project is called Knowledge Based Networking and is under development by the Department of Defense Research Projects Agency (DARPA). Researchers from schools including Northeastern, Virginia Tech, Lehigh University have been involved with the project, as have defense contractors including BBN Technologies and General Dynamics. Academic concepts such as artificial intelligence and Tim Berners-Lee’s 'Semantic Web,' combined with technologies such as the Mobile Ad-hoc Network (MANET), cognitive radio, and peer-to-peer networking, would provide the nuts and bolts of such a network. Although the project is intended for soldiers in the field, the resulting advances could trickle down to end users. ... The ideal MANET would not only choose the best paths for routing packets but would also pick the best radio frequency to use.... Such an intelligent network would not only understand how to move data; it would also be able to understand what the data meant to users." Fine-tuning “Smart” Radios. "In the News" article by Benjamin Alfonsi. IEEE Intelligent Systems (March/April 2006; 21(2): 6-7). "Outside the tech community, the big news in radio is, of course, satellite radio. Within the community and AI circles, cognitive or 'smart' radios are making a splash. ... Paving the way is Virginia Tech’s Center for Wireless Telecommunications Cognitive Wireless Technology (CWT<sup>2</sup>) group. ... The team’s approach to realizing the machine intelligence the CR requires for proper operation is strongly rooted in standard AI methods, including genetic algorithms, case-based reasoning, and neural networks." FCC investigates smart radios. By Joab Jackson. Government Computer News (December 19, 2003). "FCC chairman Michael Powell, in a statement accompanying the notice, said that smart radio technologies will become necessary. There is a shortage of spectrum for new wireless services, while much of the spectrum already allotted goes unused. ... The Defense Advanced Research Projects Agency has also funded a number of technologies that use dynamic frequencies. DARPA has funded cognitive radio work by Joseph Mitola, a consulting scientist for Mitre Corp. of McLean, Va. Mitola coined the terms software radio and cognitive radio. Cognitive radio draws on artificial intelligence to automatically negotiate the best transmission path based on factors it evaluates internally, such as what space other radios are using."
AI's Next Brain Wave. By Aaron Ricadela. InformationWeek (April 25, 2005). "[Eric] Horvitz's group [at Microsoft Research] also is building prototype software that can transmit artificial-intelligence rules to smart phones, which don't include much onboard computing power. The researchers have developed an application called SmartPhlow that turns a smart phone's small screen and telephone keypad into a way to interpret traffic data. ... A second mobile application, called BayesPhone, to be described in a paper to be released at the User Modeling conference in July in Edinburgh, Scotland, pre-computes rules on a Windows computer about whether to put a cellular call through or route it to voice mail based on background analysis of a user's calendar and the cost of interruption." CASCOM: Context-aware Business Application Co-ordination in Mobile Computing Environments. "The main objective of the project (CASCOM) is to implement, validate, and trial a value-added supportive infrastructure for Semantic Web based business application services across mobile and fixed networks."
Amid the Cacophony, a Quiet Conversation. By Anne Eisenberg. The New York Times (August 12, 2004; subscription req'd.). "Background noise gets in the way of many cellphone conversations. It can be hard to hear what the person on the other end is saying when there is competition from traffic or nearby people who are also talking. But several electrical engineers and other scientists are working to reduce or mask the distracting noises that can reach a cellphone and disrupt a conversation. At the University of Toronto, [Parham Aarabi] has devised a two-microphone system that can focus on the speaker's voice and filter out other noises, turning competing conversations into a mild hum. ... The device may also be useful in improving the accuracy of voice recognition interfaces used with computers and in cars, where voice commands are used to activate cellphones and navigation systems. Cars can be a difficult environment for speech recognition systems because of traffic and wind noise.Background sounds have long been a barrier to the widespread adoption of speech recognition systems, said Li Deng, an electrical engineer and senior researcher in the speech technology group at Microsoft in Redmond, Wash. Like Dr. Aarabi, Dr. Deng has developed software algorithms to improve speech recognition by reducing background noise." Municipal Mesh Network - Protocols developed at MIT are helping the city of Cambridge to go wireless. By Neil Savage. Technology Review (February 27, 2006). "The residents of Cambridge, MA, may soon be able to log onto the Internet from any bus stop or city park. The city is working with MIT to go wireless, with a special focus on giving low-income residents access to the Internet. The project is based on an experimental system called Roofnet, an unplanned, multiroute mesh network developed at MIT's Computer Science and Artificial Intelligence Laboratory. A mesh network is a series of radio transmitters and receivers randomly dispersed over an area. To get data from one part of the mesh to another, the network must figure out the best route between them, which can change depending on network traffic, data rates, and even the weather."
Promise of intelligent networks. By Mark Ward. BBC (February 24, 2003). "US researchers are working on ways to make wireless computer networks organise them. Computer scientists at Intel are developing mesh networking technologies that can automatically work out the best route for data as demand changes or devices join and leave the system. The researchers believe such automatic networking systems will be needed as the numbers of devices that can communicate wirelessly proliferate. ... Mr [Mike] Witteman and his colleagues are working on ways to instil wireless devices with the intelligence to work out all the different routes that data can take from one point to another in any network they form."  BT develops phone directory using AI. By John Tilak. Digital Media Europe News (January 13, 2005). "British telco BT’s researchers have developed an intelligent contacts directory for businesses using artificial intelligence software, called 'small world directories', or SWORD, which enables users to find the right person and makes use of company databases. It helps users find and contact the person they are looking for by learning about the user's own social networks and usage patterns. ... The directory’s underlying technology also has the potential to help in mobile telephone directory assistance." Smart cellphone antennas boost coverage. By Duncan Graham-Rowe. New Scientist (from the January 31, 2004 print edition; page 21). "Smart cellphone antennas that reduce the number of masts needed to get the new 3G broadband mobile networks up and running - and minimise 'dead' spots in phone coverage to boot - will be tested on a novel network during the Olympic Games in Athens this summer. ... It is no good expecting people in a control centre to decide where coverage needs expanding, as demand changes too often for them to keep up. So the researchers [at Queen Mary, University of London] have placed an autonomous software agent in charge of each antenna. Software agents are programs that cooperate with each other in unpredictable environments without human intervention. You might ask one to buy something on the web when the price is right, for instance, by negotiating with an agent on an e-commerce site. In Adamant, if a cell has too many users, the software agent in charge of that cell simply negotiates with those in charge of neighbouring antennas, asking which can help. If a neighbour is not too busy, that antenna can 'reach out' to those with no coverage." These content apps were kings. By L. C. Wong. The Star Online TechCentral (December 30, 2004). "What does a virtual girlfriend, a navigation system, a celebrity look-alike service and a barcode solution have in common? They were the mobile applications that beat 200 others from around the world to bag the top prizes at this year’s Ericsson Mobile Application Awards. ... Hong Kong’s Artificial Life Inc (www.artificial-life.com) bagged the top prize in the Best Mobile Gaming category for its Virtual Girlfriend or V-Girl application, which uses an interactive 3D role-playing engine to simulate a 'real-life' relationship. ... With [Eberhard] Schoneburg’s background in artificial intelligence (AI) technology, Artificial Life started creating 'virtual people' applications for the Internet in 1993, but only recently discovered a niche for AI applications on the mobile platform. ... Artificial Life plans to penetrate other markets, and is also working on using the same AI technology on applications for other market segments. It has already developed a 'virtual assistant' application that can take over some of the functions of the mobile phone. 'These virtual assistants can filter and read e-mail, manage the calendar function and send messages,' Schoneburg claimed."
Telecom fraud - Phreaking on the Rise. By Marina Bidoli. Financial Mail SA (January 17, 2003). "Phone pirates who operate illegal 'exchanges' by tapping into private and public telephone lines cost Telkom R174m in stolen call time in the past financial year. The figure is below the international norm. Worldwide phone 'phreaking' is on the increase. Telecom fraud has been identified as the single biggest cause of revenue loss for network providers, averaging between 3%-5% of an operator's annual revenue, says Dimension Data GM for service provider solutions Sean Taylor. At a global loss estimated at US$55bn/year, telecom fraud is bigger business than international drug trafficking. ... Telkom has been working hard to stop this practice. Its fraud-management system analyses calling patterns and abnormalities using a combination of rules and artificial intelligence to detect irregular behaviour. It also has a team of investigators countrywide who take immediate action." Designing Dependable Agent Systems for Mobile Wireless Networks. By Vincent A. Cicirello, Max Peysakhov, Gustave Anderson, Gaurav Naik, Kenneth Tsang, William C. Regli, and Moshe Kam. IEEE Intelligent Systems (September/October 2004; available for free for a limited time.). Abstract: "As mobile computing becomes ubiquitous, Mobile Ad Hoc Networks are becoming increasingly important. MANETs allow for a bring-your-own-network solution to rescue workers at natural-disaster locations, where traditional networking infrastructure is not likely to exist. As a design paradigm, multiagent systems (MASs) can help support management and coordination of such environments. The complex, ever-changing environments of MANETs pose difficult challenges to a MAS. Dependable agents must be environment-aware with the ability to reason about a constant flow of complex data, including network state and feedback of system performance. The MAS must be adaptive and self-stabilizing to ensure dependable operation." At the technology sharp end - In these days of constraint and focus, do carriers still have room for research laboratories? Hugh Bradlow thinks so, but then he runs one. Telstra’s CTO speaks to Robert Clark about how research groups today pay their way. Telecom Asia (March 1, 2004). "[Q] Is speech recognition the one that works for the Telstra's directory inquiries IVR? [A] Now, the expectation is that these natural language speech systems will become increasingly deployed because they offer some really significant advantages, both from the point of view of productivity and from the customer perspective. ... It's a hell of a lot easier than punching your way through an IVR system. But the grammar development is time-consuming, and at the moment it requires specialized expertise and that complicates the deployment. What we've developed is a very interesting tool, developed by one of our staff members who's actually doing a PhD on the topic. He’s come up with a way of actually doing grammar inference. Instead of having to have someone program the grammar in it, he's developed a tool where you can give it examples of the grammar and it will start to learn the grammar. ... [Q ] You've got a very broad range of research topics -- artificial intelligence, Internet systems and architecture. Are any of these bigger or given more resources or priority than others? ... [A] No, my joke is: you name it, we do it...." A Survey on Intelligent Agents in Telecommunications. From the Intelligent Agent Group at the Department of Computer Science, Trinity College Dublin. "The purpose of this survey is to explore current agent technology in telecommunications. After briefly introducing the concept of intelligent agents, we will review the impact that agents are having on telecommunications in the context of three application areas...." The ActComm Project on Transportable Agents and Wireless Networks.
Intelligent Agents for Telecommunication Applications, Proceedings of the Third International Workshop on Intelligent Agents for Telecommunication Applications. Edited by Sahin Albayrak. Lecture Notes in Artificial Intelligence, Vol. 1699; Springer. Intelligent Agents for Telecommunications Applications. Volume 36 in Frontiers in Artificial Intelligence and Applications (Springer; 1998). Edited by Sahin Albayrak. "Telecommunications applications pose strong requirements to agents such as: reliability, real-time performance, openness, security management and other integrated management, and mobility. In order to fulfil their promise, intelligent agents need to be fully dependable and typically require an integrated set of capabilities. This is the challenge that exists for intelligent agents technology in this application domain." Perspectives from the field. Gail Repsher Emery interviews Alex Pentland. Washington Technology (June 21, 2004; Vol. 19 No. 6). "The work of MIT's Alex 'Sandy' Pentland encompasses areas such as wearable computing, human-machine interfaces and artificial intelligence. ... WT: Your group pioneered the idea of wearable computers about 15 years ago. How has the field evolved? Pentland: About 15 years ago, the idea of putting computers and sensors on the body sounded quite crazy. But we won, it's here. All of you carry little computers, called cell phones, that are Internet connected and have some sort of sensors." Artificial Intelligence and Fraud Detection. A very informative site. Maintained by Jorn Dinkla. "Bell Labs Researchers Develop a 'Natural' Interface for Next Generation Phones. Pick up your telephone and ask it to dial someone for you, just by using their name if you choose. Then tell your computer you'd like to have the late breaking news read to you, or that you want to access your voice mail, e-mail and faxes. All you'll need to do this is an electronic personal assistant. Your wish will be its command. These are among the capabilities of an intelligent agent, one of the many components of the natural information interface (NII) that was developed at Bell Labs...." Also see our Interfaces page. "Nortel Networks Fraud Solutions is a business unit within the Nortel Networks Corporation, specialising in advanced software and artificial intelligence (AI) technologies. Established in 1997, NNFS is committed to helping operators minimise exposure to telecoms fraud, thereby helping to maximise profits." One of the many interesting pages offered at the site is: "What is Fraud" (An Introduction to Telecommunications Fraud). Useful Research Resources from the Network Management and Artificial Intelligence Laboratory at Carleton University. Bits & Pixels, a company that specializes in the area of Intelligent Agent applications, has a home page with links to many examples of their technology at work in the field of telecommunications. For example, see:
Enhancing Mobile Web Access Using Intelligent Recommendations. By Baoyao Zhou, Siu Cheung Hui, and Kuiyu Chang. IEEE Intelligent Systems (January/February 2006; Volume 21, Number 1). "As mobile phones continue to infiltrate the world, they could easily become the Internet client of choice—especially considering widespread adoption of third-generation mobile services. Although the mobile phone’s disproportionately small screen is ill-suited for Web surfing, it's here to stay because it's constrained by portability requirements. Using recommendations can aid mobile Web surfing." AUTOCELL: An Intelligent Cellular Mobile Network Management System. By Chee-Meng Low, You-Tong Tan, Soo-Yong Choo, Sie-Hung Lau, and Soo-Meng Tay. AI Magazine16(4): Winter 1995, 55-65. "AUTOCELL is a system developed to assist in the operation and management of cellular mobile networks operated by Singapore Telecom. Its deployment is in line with the company's strategic move to introduce intelligent software into its operations. With the help of AI concepts and techniques, the system has enhanced the operational efficiency and network capacity and increased customer satisfaction with the network." Autonomous Mobile RF Relays. From the Robotics Group at the Space and Naval Warfare Systems Center, San Diego. "Modern digital radios, while affording high bandwidth and Internet-protocol-based automatic routing capabilities, tend to operate on line-of-sight links. The communication link degrades quickly as a robot penetrates the interior of a building. This project, funded by DARPA/ITO, demonstrates intelligent use of autonomous mobile radio-frequency (RF) repeaters as a solution to this problem."  Phone Friend. Software agents can use your pattern of mobile phone use to foil thieves. By Duncan Graham-Rowe. New Scientist Magazine (January 31, 2001). "The way you use your mobile phone could help to foil potential thieves. So say software engineers who have developed a fraud detection system that uses artificial intelligence to monitor your phone usage, making sure you're the rightful owner. ... The system uses pattern recognition software built into intelligent agents - called sentinels - that assemble behaviour profiles of subscribers on a network." (A related article appears in New Scientist's special section about AI.)
Related AI Topics Pages |
