Showing papers in "IEEE Intelligent Systems in 2007"

Social Computing: From Social Informatics to Social Intelligence

Abstract: Social computing represents a new computing paradigm and an interdisciplinary research and application field. Undoubtedly, it strongly influences system and software developments in the years to come. We expect that social computing's scope continues to expand and its applications multiply. From both theoretical and technological perspectives, social computing technologies moves beyond social information processing towards emphasizing social intelligence. As we've discussed, the move from social informatics to social intelligence is achieved by modeling and analyzing social behavior, by capturing human social dynamics, and by creating artificial social agents and generating and managing actionable social knowledge

New Recommendation Techniques for Multicriteria Rating Systems

Abstract: Personalization technologies and recommender systems help online consumers avoid information overload by making suggestions regarding which information is most relevant to them. Most online shopping sites and many other applications now use recommender systems. Two new recommendation techniques leverage multicriteria ratings and improve recommendation accuracy as compared with single-rating recommendation approaches. Taking full advantage of multicriteria ratings in personalization applications requires new recommendation techniques. In this article, we propose several new techniques for extending recommendation technologies to incorporate and leverage multicriteria rating information.

Toward an Affect-Sensitive AutoTutor

Abstract: Here, we consider the possibility of enabling AutoTutor, an intelligent tutoring system, to process learners' affective and cognitive states. AutoTutor is a fully automated computer tutor that simulates human tutors and converses with students in natural language.

Controlling a Wheelchair Indoors Using Thought

Abstract: Amyotrophic lateral sclerosis, or ALS, is a degenerative disease of the motor neurons that eventually leads to complete paralysis. We are developing a wheelchair system that can help ALS patients, and others who can't use physical interfaces such as joysticks or gaze tracking, regain some autonomy. The system must be usable in hospitals and homes with minimal infrastructure modification. It must be safe and relatively low cost and must provide optimal interaction between the user and the wheelchair within the constraints of the brain-computer interface. To this end, we have built the first working prototype of a brain-controlled wheelchair that can navigate inside a typical office or hospital environment. This article describes the BCW, our control strategy, and the system's performance in a typical building environment. This brain-controlled wheelchair prototype uses a P300 EEG signal and a motion guidance strategy to navigate in a building safely and efficiently without complex sensors or sensor processing

The Semantic Web Vision: Where Are We?

Abstract: Semantic Web developers have adopted OWL to represent knowledge. OWL, or a language with similar theoretical foundations, will lead the way in the semantic exploration of the Web. Currently, Web-based standards are the preferred way to represent knowledge. Furthermore, respondents mainly use ontologies to allow both humans and computers to understand knowledge and domain models. Web 3.0 can bring a new breed of spectacular applications compared to Web 2.0. with the same magnitude that separates Web 2.0 from Web 1.0.

A Comparison of Collaborative-Filtering Recommendation Algorithms for E-commerce

Abstract: Collaborative filtering is one of the most widely adopted and successful recommendation approaches. Unlike approaches based on intrinsic consumer and product characteristics, CF characterizes consumers and products implicitly by their previous interactions. The simplest example is to recommend the most popular products to all consumers. Researchers are advancing CF technologies in such areas as algorithm design, human- computer interaction design, consumer incentive analysis, and privacy protection.

Acquiring and Revising Preferences in a Critique-Based Mobile Recommender System

Abstract: Many e-commerce Web sites offer numerous services, so a product search could return an overwhelming set of options. Without system support, filtering irrelevant products, comparing alternatives, and selecting the best option can be difficult or impossible - especially for users connecting to the Web through a mobile device. Few Web-based recommender systems have been designed for mobile users. A critique-based recommendation methodology aids the acquisition and revision of user preferences in a mobile recommender system. We designed a product recommendation methodology and implemented it in MobyRek, a mobile-phone recommender system that helps users search for travel products. MobyRek supports limited asking and answering of questions and is based mostly on critiques.

Toward a Paradigm Shift in Social Computing: The ACP Approach

Abstract: In a sense, social computing is a new research field with a long history. Its origins trace back to the beginning of modern computing and landmark work such as Vannevar Bush's Memex, Douglas Engelbart's vision for integrating psychology and organizational development with computer technology advances, and J.C.R. Licklider's emphasis on computers as communication devices, not computing machines. Over the past decades, social software from email to blogs, has fundamentally changed how to live, work and interact with each other.

Interactive Humanoid Robots for a Science Museum

Abstract: One objective of the Intelligent Robotics and Communication Laboratories is to develop an intelligent communication robot that supports people in an open everyday environment by interacting with them. A humanoid robot can help achieve this objective because its physical structure lets it interact through human-like body movements such as shaking hands, greeting, and pointing. Both adults and children are more likely to understand such interactions than interactions with an electronic interface such as a touch panel or buttons. To behave intelligently during an interaction, a robot requires many types of information about its environment and the people with whom it interacts. However, in open everyday environments, simple recognition functions such as identifying an individual are difficult because the presence and movement of a large number of people as well as unfavorable illumination and background conditions affect the robot's sensing ability. We integrated humanoid robots and ubiquitous sensors in an autonomous system to assist visitors at an Osaka Science Museum exhibit

Informed Recommender: Basing Recommendations on Consumer Product Reviews

Abstract: Recommender systems attempt to predict items in which a user might be interested, given some information about the user's and items' profiles. Most existing recommender systems use content-based or collaborative filtering methods or hybrid methods that combine both techniques (see the sidebar for more details). We created Informed Recommender to address the problem of using consumer opinion about products, expressed online in free-form text, to generate product recommendations. Informed recommender uses prioritized consumer product reviews to make recommendations. Using text-mining techniques, it maps each piece of each review comment automatically into an ontology.

Online Sequential Prediction via Incremental Parsing: The Active LeZi Algorithm

Abstract: Intelligent systems that can predict future events can make more reliable decisions. Active LeZi, a sequential prediction algorithm, can reason about the future in stochastic domains without domain-specific knowledge. In this article, potential of constructing a prediction algorithm based on data compression techniques are investigated. Active LeZi prediction algorithm approaches sequential prediction from an information-theoretic standpoint. For any sequence of events that can be modeled as a stochastic process, ALZ uses Markov models to optimally predict the next symbol

Autonomy and Common Ground in Human-Robot Interaction: A Field Study

Abstract: The use of robots, especially autonomous mobile robots, to support work is expected to increase over the next few decades. However, little empirical research examines how users form mental models of robots, how they collaborate with them, and what factors contribute to the success or failure of human-robot collaboration. A two-year observational study of a collaborative human-robot system suggests that the factors disrupting the creation of common ground for interactive communication change at different levels of robot autonomy. Our observations of users collaborating with the remote robot showed differences in how the users reached common ground with the robot in terms of an accurate, shared understanding of the robot's context, planning, and actions - a process called grounding. We focus on how the types and levels of robot autonomy affect grounding. We also examine the challenges a highly autonomous system presents to people's ability to maintain a shared mental model of the robot

Intelligent Tutors for All: The Constraint-Based Approach

Abstract: This paper presents a new type of intelligent tutoring systems, called constraint-based tutors. The system have been thoroughly evaluated and proven to achieve significant learning gains.

Integrating Human Inputs with Autonomous Behaviors on an Intelligent Wheelchair Platform

Abstract: Nearly five million individuals in the US have limited arm and hand movement, making it difficult or impossible for them to use computers and products with embedded computers, such as wheelchairs, household appliances, office electronic equipment, and robotic aids. Although some current wheelchair systems have embedded computers, they have very little computer control and require precise, low-level control inputs from the user; interfaces are similar to those found in passenger cars. The rider must continuously specify the chair's direction and, in some cases, velocity using a joystick-like device. Unfortunately, many users who could benefit from powered wheelchairs lack these fine motor skills. For instance, those with cerebral palsy might not be able to guide a chair through a narrow opening, such as a doorway, without repeatedly colliding into the sides. These types of physically challenging environments can be frustrating and require a lot of user effort. At the University of Pennsylvania's general robotics, automation, sensing, and perception lab, we developed the smart chair, a smart wheelchair with intelligent controllers that lets people with physical disabilities overcome these difficulties. By outfitting the wheelchair with cameras, a laser range finder, and onboard processing, we give the user an adaptable, intelligent control system. A computer-controlled wheelchair's shared control framework allows users complete control of the chair while ensuring their safety

Gender-Specific Approaches to Developing Emotionally Intelligent Learning Companions

Abstract: The nonverbal social behaviors of virtual learning companions and their affect and task support have gender-specific impacts on learners' frustration and self-awareness during a challenging problem-solving activity. Social bonding and affective support between teachers and learners have considerable impact on learners' performance and motivation. One way to develop a social bond with learners is to provide assistance. According to research in this area (see the sidebar "Related Work on Affective Tutoring Systems"), systems that provide affective support to frustrated users can reduce frustration. A study of expert human tutors' interactions with their students found that up to half of these interactions focus on supporting the learner's affective state. Currently, most intelligent tutoring systems provide predominantly task-based support.

Using Fuzzy Logic in Automated Vehicle Control

Abstract: Automated versions of a mass-produced vehicle use fuzzy logic techniques to both address common challenges and incorporate human procedural knowledge into the vehicle control algorithms. In-vehicle computing has been largely relegated to auxiliary tasks such as regulating cabin temperature, opening doors, and monitoring fuel, oil, and battery-charge levels. However, computers are increasingly assuming driving-related tasks in some commercial models. Among those tasks are: maintaining a reference velocity or keeping a safe distance from other vehicles; improving night vision with infrared cameras; and building maps and providing alternative routes

Attacks and Remedies in Collaborative Recommendation

Abstract: Collaborative-filtering recommender systems are an electronic extension of everyday social recommendation behavior: people share opinions and decide whether or not to act on the basis of what they hear. Collaborative filtering lets you scale such interactions to groups of thousands or even millions. Publicly accessible user-adaptive systems such as collaborative recommender systems introduce security issues that must be solved if users are to perceive these systems as objective, unbiased, and accurate.

Context-Aware Middleware for Anytime, Anywhere Social Networks

Abstract: Anytime, anywhere social computing requires several support mechanisms and tools, including location and proximity systems, expressive representation models of physical place and user characteristics, and effective social-matching algorithms. Anytime, anywhere social-network computing also requires shared and interoperable vocabularies for modeling location and entity characteristics. Current solutions tend to address only a subset of these issues. We believe that the success of anytime, anywhere social computing depends on middleware solutions that separate social-network management concerns from application requirements. Our middleware solution, the socially aware and mobile architecture (SAMOA), integrates a set of common management facilities for personalizing location-dependent social networks, and for propagating social networks' visibility up to the application level.

Evolutionary Computing on Consumer Graphics Hardware

Abstract: We propose implementing a parallel EA on consumer graphics cards, which we can find in many PCs. This lets more people use our parallel algorithm to solve large-scale, real-world problems such as data mining. Parallel evolutionary algorithms run on consumer-grade graphics hardware achieve better execution times than ordinary evolutionary algorithms and offer greater accessibility than those run on high-performance computers

Domain-Driven, Actionable Knowledge Discovery

Abstract: Data mining increasingly faces complex challenges in the real-life world of business problems and needs. The gap between business expectations and R&D results in this area involves key aspects of the field, such as methodologies, targeted problems, pattern interestingness, and infrastructure support. Both researchers and practitioners are realizing the importance of domain knowledge to close this gap and develop actionable knowledge for real user needs.

Argumentation-Based Inference and Decision Making--A Medical Perspective

Abstract: The argumentation services platform with integrated components (Aspic) project aims to provide advanced argumentation-based computational capabilities. Argumentation is a potentially important paradigm for developing commercial and public services that are flexible and easily understood by human users.

Guest Editors' Introduction: Recommender Systems

Abstract: This special issue presents eight articles, five long and three short, on techniques to improve recommender systems. They cover improving such aspects as user interaction with recommenders, the quality of results presented to users, and user trust in presented recommendations. This article is part of a special issue on Recommender Systems.

Modeling and Simulating Terrorist Networks in Social and Geospatial Dimensions

Abstract: A simple theoretical multiagent model reasons about the criticality of terrorists and regions as terrorist interactions coevolve in geographical and social spaces. Social and spatial relations evolve over time. Estimating their evolutions is important for management, command and control structures, and intelligence analysis research. By knowing future agent social and spatial distributions, an analyst can identify emergent leaders, hot spots, and organizational vulnerabilities. Historically, such estimations have depended heavily on qualitative data analyses by subject-matter experts. A few researchers approached the issue using multiagent models and simulation. The models addressed the complex nature of the organization and task assignments, resource distributions, or agent locations. The simulations addressed the near-term organizational changes. This research came from two perspectives: the effects of change in the social network and the effects of geospatial change. Both perspectives can project aspects of emerging organizational structure and future performance, but they can't examine the interaction between physical and social movements.

Driving into Intelligent Spaces with Pervasive Communications

Abstract: Recent advances in digital modulation and transmission, signal processing, wireless access protocols, and IC technology have spawned many intelligent devices and objects. A good example are intelligent transportation spaces (ITSP) which have shown many potential benefits including driving safety, transport efficiency, and comfort that accrue from increased traffic information, reduced driving loads, and improved route management. Although wireline communications might enable some ITSP requirements, the inherent mobility, flexibility and scalability of wireless communications clearly make them critical. Enabling technologies in this area include an array of wireless solutions such as ISM bands, DSRC bands, UWB radio, and MAC protocols

Collaborative Filtering Using Dual Information Sources

Abstract: Conventional collaborative-filtering methods use only one information source to provide recommendations. Using two sources - similar users and expert users - enables more effective, more adaptive recommendations. Conventional CF methods suffer from a few fundamental limitations such as the cold-start problem, data sparsity problem, and recommender reliability problem. Thus, they have trouble dealing with high-involvement, knowledge-intensive domains such as e-learning video on demand. To overcome these problems, researchers have proposed recommendation techniques such as a hybrid approach combining CF with content-based filtering. Because e-commerce Web sites for e-learning often have various product categories, extracting the many attributes of these categories for content-based filtering is extremely burdensome. So, it might be practical to overcome these limitations by improving the CF method itself.

An Argumentation Framework for Communities of Web Services

Abstract: As the number of Web services continues to increase, so does the opportunities to compose them to build more complex and complete business solutions. To facilitate and speed up Web-services discovery, Web services with similar (or equivalent) functionalities - such as flight booking and travel reservation - can be grouped into communities. Argumentation theory, implemented through a set of software agents that reason about Web services, can improve Web services performance through the notion of communities.

Portia: A User-Adapted Persuasion System in the Healthy-Eating Domain

Abstract: Our eating habits, an essential component of our well-being, are molded by cultural, psychological, and educational factors. These habits solidify over time and are difficult to modify. The information media are masters in employing tricky arguments to persuade people to consume products whose health benefits are doubtful. Attempting to persuade people to adopt more appropriate habits by employing only rational and scientific arguments is probably ineffective; this is one domain in which the mingling of rational and emotional strategies is justified. Of course, the persuader's arguments must be relevant and strong. This is a subjective judgment, dependent on the persuader's knowledge about the recipient and the conditions under which the message is expressed. Our prototype persuasion system is the argumentation module of a dialogue system we have developed. After the system acquires information about its users, it informs them about various eating habits' advantages and disadvantages, provides suggestions in this domain, and tries to persuade them to gradually modify problem behaviors.