Showing papers in "IEEE Intelligent Systems in 2008"

Ambient Intelligence—the Next Step for Artificial Intelligence

Abstract: Ambient intelligence (AmI) deals with a new world of ubiquitous computing devices, where physical environments interact intelligently and unobtrusively with people. These environments should be aware of people's needs, customizing requirements and forecasting behaviors. AmI environments can be diverse, such as homes, offices, meeting rooms, schools, hospitals, control centers, vehicles, tourist attractions, stores, sports facilities, and music devices. Artificial intelligence research aims to include more intelligence in AmI environments, allowing better support for humans and access to the essential knowledge for making better decisions when interacting with these environments. This article, which introduces a special issue on AmI, views the area from an artificial intelligence perspective.

Brain-Computer Interfacing for Intelligent Systems

Abstract: Advances in cognitive neurosci- ence and brain-imaging technologies give us the unprecedented ability to interface directly with brain activity. These technologies let us monitor the physical processes in the brain that correspond with certain forms of thought. Driven by society's growing recognition of the needs of people with physical disabilities, researchers have begun using these technologies to build brain-computer interfaces (BCIs)communication systems that don't depend on the brain's normal output pathways of peripheral nerves and muscles. In BCIs, users explicitly manipulate their brain activity instead of motor movements to produce signals that control computers or communication devices. This research has extremely high impact, especially for disabled individuals who can't otherwise physically communicate.

Games with a Purpose for the Semantic Web

Abstract: Weaving the semantic Web requires that humans contribute their labor and judgment for creating, extending, and updating formal knowledge structures. Hiding such tasks behind online multiplayer games presents the tasks as fun and intellectually challenging entertainment. The games we've presented are the first prototypes of the OntoGame series. We're extending and improving the scenarios in several directions.

Activity Recognition for the Smart Hospital

Abstract: Although researchers have developed robust approaches for estimating, location, and user identity, estimating user activities has proven much more challenging. Human activities are so complex and dynamic that it's often unclear what information is even relevant for modeling activities. Robust approaches to recognize user activities requires identifying the relevant information to be sensed and the appropriate sensing technologies. In our effort to develop an approach for automatically estimating hospital-staff activities, we trained a discrete hidden Markov model (HMM) to map contextual information to a user activity. We trained the model and evaluated it using data captured from almost 200 hours of detailed observation and documentation of hospital workers. In this article, we discuss our approach, the results, and how activity recognition could empower our vision of the hospital as a smart environment.

GerAmi: Improving Healthcare Delivery in Geriatric Residences

Abstract: Many countries face an ever-growing need to supply constant care and support for their disabled and elderly populations. In this paper, we've developed geriatric ambient intelligence, an intelligent environment that integrates multiagent systems, mobile devices, RFID, and Wi-Fi technologies to facilitate management and control of geriatric residences. At GerAmi's core is the geriatric agent (GerAg), a deliberative agent that incorporates a case-based planning (CBP) mechanism to optimize work schedules and provide up-to-date patient and facility data. We've successfully implemented a system prototype at a care facility for Alzheimer patients.

Toward a New Generation of Semantic Web Applications

Abstract: Although research on integrating semantics with the Web started almost as soon as the Web was in place, a concrete Semantic Web that is, a large-scale collection of distributed semantic metadata emerged only over the past four to five years. The Semantic Web's embryonic nature is reflected in its existing applications. Most of these applications tend to produce and consume their own data, much like traditional knowledge- based applications, rather than actually exploiting the Semantic Web as a large-scale information source. These first-generation semantic Web applications typically use a single ontology that supports integration of resources selected at design time.

AVA: Adjective-Verb-Adverb Combinations for Sentiment Analysis

Abstract: Most research on determining the strength of subjective expressions in a sentence or document uses single, specific parts of speech such as adjectives, adverbs, or verbs. To date, almost no research covers the development of a single comprehensive framework in which we can analyze sentiment that takes all three into account. The authors propose the AVA (adjective verb adverb) framework for identifying opinions on any given topic. In AVA, a user can select any topic t of interest and any document d. AVA will return a score that d expresses topic t. The score is expressed on a –1 (maximally negative) to +1 (maximally positive) scale.

Self-Driving Cars and the Urban Challenge

Abstract: Self-driving cars have been a dream as long automobiles have existed. The automobile is ubiquitous in the developed world and is becoming so in the developing world. In 2007, the world's two largest automakers sold over 18 million vehicles worldwide. As we consider domains to which we can apply intelligent systems, the automotive industry stands out as having the most potential for impact.

Toward a Revolution in Transportation Operations: AI for Complex Systems

Abstract: This article presents an parallel traffic management system for integrated control and management of urban transportation systems. This system's construction and operation are based on the ACP (artificial, computational, parallel) approach, which consists of modeling with artificial systems, analysis with computational experiments, and operation through parallel execution for control and management of complex systems with social and behavioral dimensions.

Web Semantics in the Clouds

Abstract: Cloud computing refers to the use of large-scale computer clusters often built from low-cost hardware and network equipment, where resources are allocated dynamically among users of the cluster. While the paradigm is not entirely novel, recent developments in software frameworks for cloud computing are making it increasingly easy for programmers to parallelize and thereby scale-up complex data-processing tasks. This article investigates how this trend is impacting the semantic Web field and shows how cloud computing can be used to analyze, query, and reason with the massive amounts of metadata handled by semantic search engines.

Linking Documents to Encyclopedic Knowledge

Abstract: Wikipedia has become one of the largest online repositories of encyclopedic knowledge. Wikipedia editions are available for more than 200 languages, with entries varying from a few pages to more than 1 million articles per language. Embedded in each Wikipedia article is an abundance of links connecting the most important words or phrases in the text to other pages, thereby letting users quickly access additional information. An automatic text-annotation system combines keyword extraction and word-sense disambiguation to identify relevant links to Wikipedia pages.

Interlinking the Social Web with Semantics

Abstract: This paper deals with applying semantic Web technologies to the social Web can lead to a social semantic Web, creating a network of interlinked and semantically rich knowledge. One of the most visible trends on the Web is the emergence of social Web sites, which help people create and gather knowledge by simplifying user contributions via blogs, tagging and folksonomies, wikis, podcasts, and online social networks. The social Web has enabled community-based knowledge acquisition.

Estimating Location Using Wi-Fi

Abstract: This department presents the results of the first Data Mining Contest held at the 2007 International Conference on Data Mining.

DynaCAS: Computational Experiments and Decision Support for ITS

Abstract: Accurate, reliable, and timely traffic information is critical for deployment and operation of intelligent transportation systems (ITSs). Traffic forecasting for travelers and traffic operators should become at least as useful and convenient as weather reports. In the US, the Federal Highway Administration (FHWA) has envisioned a real-time traffic estimation and prediction system (TrEPS) as an ITS support platform that resides at traffic management centers (TMCs) for dynamic route assignment (DRA) and other transportation operations.

Avoiding Another AI Winter

Abstract: Is artificial intelligence headed for another AI Winter? Not if we take action now.

Greedy Neighborhood Search for Disaster Relief and Evacuation Logistics

Abstract: Two major activities in disaster response are evacuation and logistics support. Evacuation from affected areas to medical centers occurs during the initial response phase. Logistics support from supply centers to distribution centers in affected areas tends to continue for a longer time to sustain the basic needs of survivors remaining there. Minimizing delay in providing priority commodities and healthcare to the survivors can greatly improve the survival rate. As a first step toward solving the emergency-logistics problem, we developed Path-Builder, a simple, fast constructive heuristic for identifying a feasible, acceptable solution. Path-Builder is based on a greedy l-neighborhood search technique that extends the definition of neighborhood to suit the problem's special needs. The heuristic selects partial paths to append to vehicle itineraries on the basis of the vehicles' utilities. It constructs all vehicle itineraries in parallel and iteratively, trying to exploit foreseeable opportunities within the vehicles' limited neighborhood.

Weighing Stars: Aggregating Online Product Reviews for Intelligent E-commerce Applications

Abstract: A new task in text-sentiment analysis adds usefulness scoring to polarity/ opinion extraction to improve product- review ranking services, helping shoppers and vendors leverage information from multiple sources. Human language is a medium not only for exchanging information but also for conveying subjective opinions and emotion. Recently, interest in text-subjectivity and sentiment analysis has increased as part of the larger research effort in affective computing, which aims to make computers understand and generate human-like emotions through language and other expressive activities such as gesture.

Proactive Fuzzy Control and Adaptation Methods for Smart Homes

Abstract: Proactive, context-aware computing isn't new. In 2000, David Tennenhouse called for a change in the boundary between the physical and virtual worlds. He identified proactive computing as an alternative to interactive computing and defined how future systems should become more involved with the real world. He also considered context-aware control systems with online adaptation especially promising. Today, ambient-intelligence researchers show increasing interest in both proactive applications and context-aware applications. Using different context-recognition methods, researchers can easily gather application-specific information from the environment and enable context-triggered actions. According to Hee Eon Byun and Keith Cheverst, a context-aware home can serve its inhabitants more flexibly and adaptively than an ordinary home. They also claim that proactive systems can be built using machine-learning algorithms with context recognition. In addition to context recognition, adaptivity is essential in intelligent environments. In terms of computing systems, the environment can adjust itself using adaptation mechanisms to comply with user preferences; it can become unobtrusive and better support user activities. A home adapting to its inhabitants' living style is much more convenient than a user adapting to the home's behavior. In this article, we show how to develop a proactive, adaptive, fuzzy home-control system, present the algorithm we used for adaptation, and evaluate the test results we obtained.

Case-Based Plan Adaptation: An Analysis and Review

Abstract: Case-based planning (CBP) is a problem-solving method that uses a library of cases, where a case associates a past problem and goal description with a plan that solves the problem by achieving the goal. Given a new problem, CBP systems retrieve one or more cases that solve similar problems and adapt the retrieved cases' plans to achieve the new goal. Case retrieval involves intelligent search of the case library. Plan adaptation can include steps copied from the retrieved case plans and steps derived by other means, such as first-principles planning. Important relationships exist between the technology that measures similarity during case retrieval and the technology that performs effective adaptation during case reuse. However, we concentrate here on the adaptation process itself.

Cassandra or False Prophet of Doom: AI Robots and War

Abstract: The US military currently deploys more than 4,000 ground robots in Iraq Most are for bomb disposal but some are armed In addition to the robots, semi-autonomous unmanned air vehicles come equipped with hellfire missiles For now, all these systems employ a human-in-the-loop for the application of lethal force But this is set to change In the near- to mid-term future, the military might allow autonomous unmanned systems to make their own lethality decisions This article probes the published US military plans and raises questions about the application of AI to discriminate between innocents and combatants in modern warfare It points to the main ethical issues in terms of the laws of war and discusses the responsibilities of AI researchers embarking on military projects

Cheek to Chip: Dancing Robots and AI's Future

Abstract: Recent generations of humanoid robots increasingly resemble humans in shape and articulatory capacities. This progress has motivated researchers to design dancing robots that can mimic the complexity and style of human choreographic dancing. Such complicated actions are usually programmed manually and ad hoc. However, this approach is both tedious and inflexible. Researchers at the University of Tokyo have developed the learning-from-observation (LFO) training method to overcome this difficulty.1-2 LFO enables a robot to acquire knowledge of what to do and how to do it from observing human demonstrations. Direct mapping from human joint angles to robot joint angles doesn't work well because of the dynamic and kinematic differences between the observed person and the robot (for example, weight, balance, and arm and leg lengths). LFO therefore relies on predesigned task models, which represent only the actions (and features thereof) that are essential to mimicry. Then it adapts these actions to the robot's morphology and dynamics so that it can mimic the movement. This indirect, two-step mapping is crucial for robust imitation and performance.

Near-Term Prospects for Semantic Technologies

Abstract: Tor the past few years, the Semantic Web has been enjoying significant investment, mostly through research but to a lesser extent through start-ups and commercial projects. A major topic of discussion is where we can see those investments' results, so I asked several experts to consider what semantic technology will accomplish in the near future. The experts are from academia, venture capitalist firms, and companies focused on semantic technology, telecommunication, and Web 2.0.

Web Services from an Agent Perspective

Abstract: Multiagent systems evolved from a need for knowledge-aware, distributed, problem-solving mechanisms. These systems are formally grounded using theoretical approaches, including those that assume mentalistic notions. As a result, much of this research into multiagent systems has provided formal proofs or proof-of-concept demonstrators (such as example systems or prototypes). It has provided only limited, pragmatic support (systems, software, and tools) for the user community. Research into Web services, in contrast, has focused on the user community, resulting in a pragmatic, bottom-up enabling technology that readily facilitates the robust construction of service-oriented systems. Much of the focus of Web services research has been on developing declarative descriptions that application developers can share and that their tools can use to construct and develop large-scale distributed software. Despite these differing approaches, the inherent component-based structure underlying both agents and Web services raises questions about how exactly they differ and whether they can coexist.

Building a Pragmatic Semantic Web

Abstract: Many real-world tasks require the acquisition and integration of information from a distributed set of heterogeneous sources. Hence, there's no shortage of opportunities for applications using Semantic Web (SW) technologies. The power of publishing and linking data in a way that machines can automatically interpret through ontologies is beginning to materialize. However, market penetration level is relatively low, and it's still no routine matter for an enterprise, organization, governmental agency, or business with large distributed databases to add them to the Web of linked and semantically enriched data. In part, they may suspect that they're expected to pioneer an approach in which quick wins are few. Moreover, cost and privacy issues arise when ever-increasing amounts of information are linked into the Web. A practical approach to adopting semantic Web technologies enables large organizations to share data while achieving clear private as well as public reuse benefits.

The CKC Challenge: Exploring Tools for Collaborative Knowledge Construction

Abstract: A new generation of tools supports the integration of Web 2.0 and semantic Web approaches. Some of these tools-such as Semantic MediaWiki (http://meta.wikimedia. org/wiki/SemanticMediaWiki), BOWiki, (http://onto.eva. mpg.de/bowiki), and Platypus Wiki (http://platypuswiki. sourceforge.net)-provide wiki extensions for creating semantic links between pages. Other tools let users organize tags in some semantic structure, and fully fledged ontology editors such as pOWL support the distributed and collaborative development of ontologies. Commercial tools such as Freebase (http://freebase.com) are also entering the field. Most of these tools are in early development-the collaborative-knowledge-construction field is in its infancy. Few, if any, user studies outline what users expect from such tools and what does or doesn't work. So, we organized the collaborative knowledge construction challenge. The CKC challenge let users try different tools and provide feedback to help us assess the state of the art.

DALICA: Agent-Based Ambient Intelligence for Cultural-Heritage Scenarios

Abstract: Villa Adriana is an enormous archaeological area where ancient artifacts and modern technology have found an unexpected equilibrium. The old artifacts are huge stone monuments; the modern technology includes PDAs and signals from the Galileo satellite combined with intelligent software agents. As part of the European CUSPIS project (Cultural Heritage Space Identification System, www. cuspis-project.info), we exploited intelligent agents for two ambient-intelligence scenarios applicable to Villa Adriana. One scenario involves cultural assets fruition-the possibility of accessing and enjoying cultural assets. This scenario concerns the dissemination of information about cultural assets; for example, users can visit a museum or archaeological site and receive on their mobile devices appropriate, personalized information about that place. The other scenario involves cultural assets monitoring, which concerns securely transporting cultural assets from the owner organization to a renter organization and back.

The Semantic Web: Apotheosis of Annotation, but What Are Its Semantics?

Abstract: This article discusses what kind of entity the proposed semantic Web is, principally by reference to the relationship of natural language structure to knowledge representation. The concept of the SW has two distinct origins, and this, bifurcation persists in two differing lines of SW research: one closely allied to notions of documents and natural language processing (NLP) and one not. These differences of emphasis or content carry with them different commitments about what it is to interpret a KR and what the interpretation method has to do with meaning in natural language.

Behavioral Inference across Cultures: Using Telephones as a Cultural Lens

Abstract: Most people carry mobile telephones, which automatically capture behavioral data and store it in service provider databases around the world. The different types of captured data can provide insight into human cultures. Examples from various cultures and hundreds of millions of individuals illustrate how phones can serve as a cultural lens, improving our understanding of social networks, outlier events, and a culture's pace of life.

Mining the Web to Create Specialized Glossaries

Abstract: TermExtractor and GlossExtractor, two Web-mining-based applications, support glossary building by exploiting the Web's evolving nature to allow continuous updating of an emerging community's vocabulary.

Enhancing Residential Gateways: A Semantic OSGi Platform

Abstract: The OSGi (open service gateway initiative) service platform specification is the most widely adopted technology for building a control system for the networked home. Three main features contribute to its success. First, it supports various well-known protocols, simplifying communication among home devices. In addition, it defines a cooperative model for applications to dynamically discover and use services provided by others. Finally, it allows flexible remote management of these applications and the services they provide. So, an OSGi solution supports decentralization, diversification, and ubiquity not only in smart homes but in pervasive environments generally.