Graphic design is the process of creating graphics to meet specific commercial needs based on knowledge of layout principles and esthetic concepts. This is usually an iterative trial and error process which requires a lot of time even for expert designers. This expert knowledge can be modelled, represented and used by a computer to perform design activities. This paper describes a novel approach named Gaudii (standing for "Intelligent Automated Graphic Design Generator") which utilizes principles and techniques known from the fields of Evolutionary Computation and Fuzzy Logic to automatically obtain design elements. Experimental results that demonstrate the potential of the proposed approach are presented in the area of poster design.

Human core body temperature (Tcore) is an important measure of thermal state, e.g., hypo-or hyperthermia, but is difficult to measure using noninvasive wearable sensors. We estimated parameters for a discrete KF model from data collected during several Military training events and from distance runners (n 38). Model performance was evaluated in 25 physically-active subjects who participated in various laboratory and field studies involving exercise of 2-to-8 h duration at ambient temperatures of 20 to 40 C. Overall, the KF model's estimate of Tcore had a root mean square error of 0.30 0.13 ºC from the observed Tcore, and was within 0.5 ºC over 85% of the time. The benefit of the KF approach is that it requires only one input while current state of the art models typically require multiple inputs including individual anthropometrics, metabolic rate, clothing characteristics, and environmental conditions. This state estimation problem in computational physiology illustrates the potential for collaboration between the artificial intelligence and ambulatory physiological monitoring communities. Figure 1: U.S. National Guard Civil Support Team (CST) member engaged in a chemical biological training event.

Network management is a complex task involving various challenges, such as the heterogeneity of the infrastructure or the information flood caused by billions of log messages from different systems and operated by different organiza- tional units. All of these messages and systems may contain information relevant to other operational units. For example, in order to ensure reliable DSL connections for IPTV cus- tomers, optimal customer traffic path assignments for the current network state and traffic demands need to be evalu- ated. Currently reassignments are only manually performed during routine maintenance or as a response to reported problems. In this paper we present a decision support sys- tem for this task. In addition, the system predicts future pos- sible demands and allows reconfigurations of a DSL access network before congestions may occur.

Software defect prediction aims to reduce software testing efforts by guiding testers through the defect-prone sections of software systems. Defect predictors are widely used in organizations to predict defects in order to save time and effort as an alternative to other techniques such as manual code reviews. The application of a defect prediction model in a real-life setting is difficult because it requires software metrics and defect data from past projects to predict the defect-proneness of new projects. It is, on the other hand, very practical because it is easy to apply, can detect defects using less time and reduces the testing effort. We have built a learning-based defect prediction model for a telecommunication company during a period of one year. In this study, we have briefly explained our model, presented its pay-off and described how we have implemented the model in the company. Furthermore, we have compared the performance of our model with that of another testing strategy applied in a pilot project that implemented a new process called Team Software Process (TSP). Our results show that defect predictors can be used as supportive tools during a new process implementation, predict 75% of code defects, and decrease the testing time compared with 25% of the code defects detected through more labor-intensive strategies such as code reviews and formal checklists.

NPCEditor is a system for building a natural language processing component for virtual humans capable of engaging a user in spoken dialog on a limited domain. It uses a statistical language classification technology for mapping from user's text input to system responses. NPCEditor provides a user-friendly editor for creating effective virtual humans quickly. It has been deployed as a part of various virtual human systems in several applications.

Parimutuel wagering is a significant source of revenue for many state governments. MonitorPlus is a surveillance system for parimutuel operators and regulators. Using industry expertise and best practices, MonitorPlus examines each and every wager and account transaction for evidence of fraud, crime, and money laundering. Alerts are generated in real-time. In forensic discovery mode, MonitorPlus is designed to collaborate with skilled analysts to discover more complex suspicious wagering patterns. MonitorPlus utilizes machine learning, so its risk profiles are current: its knowledge base improves with time. Each alert is accompanied by an automatically generated, rule-based explanation. This is critically important if an event rises to the level where legal action is required. Our development and deployment strategy is based on a new paradigm of a secure surveillance utility, where real-time alerts and dataintensive forensics support multiple regulatory jurisdictions. We believe this surveillance paradigm can be applied to other application domains such as lotteries, casinos, online gaming, and financial services.

A common problem faced by expanding companies is the lack of skilled and experienced domain experts, especially planners and controllers. This can seriously slow down or impede growth. This paper describes how we worked with one of the largest travel agencies in Hong Kong to alleviate this problem by using AI to support decision-making and problem-solving so that their planners/controllers can be more productive in sustaining business growth while providing quality service. This paper describes a Web-based mission critical Fleet Management System (FMS) that supports the scheduling and management of a fleet of luxury limousines. Clientele is mainly business travelers. The use of AI allowed our client to increase their business volume and expand fleet size with the same team of planners/controllers while maintaining service quality. This paper also describes our experience in building modern AI systems leveraging on Web 2.0 open-source tools and libraries. Although we used a proven AI model and search algorithm, we believe our innovation is in striking the right balance and combination of AI with modern Web 2.0 techniques to achieve low-risk implementation and deployment success as well as concrete and measurable business benefits.

In this abstract, we compare semantic search (in the RDF model) with keyword search (in the relational model), and illustrate how these two search paradigms are different. This comparison addresses the following questions: (1) What can semantic search achieve that keyword search can not (in terms of behavior)? (2) Why is it difficult to simulate semantic search, using keyword search on the relational data model? We use the term keyword search, when the search is performed on data stored in the relational data model, as in traditional relational databases, and an example of keyword search in databases is [Hri02]. We use the term semantic search, when the search is performed on data stored in the RDF data model. Note that when the data is modeled in RDF, it inherently contains explicit typed relations or semantics, and hence the use of the term “semantic search.” Let us begin with an example, to illustrate the differences between semantic search and keyword search.

Forming teams using heterogeneous agents that perform well together to accomplish a task in a game can be a challenging problem. There can often be an enormous amount of combinations to look through, and having an agent that is really good at a particular task is no guarantee that agent will perform well on a team with members with different abilities. Picking a good team is important, as changing teams is often not allowed midway through a task.

Building an intelligent agent, which simulates human-level learning appropriate for learning math, science, or a second language, could potentially benefit both education in understanding human learning, and artificial intelligence in creating human-level intelligence. Recently, we have proposed an efficient approach to acquiring procedural knowledge using transfer learning. However, it operated as a separate module. In this paper, we describe how to integrate this module into a machine-learning agent, SimStudent, that learns procedural knowledge from examples and through problem solving. We illustrate this method in the domain of algebra, after which we consider directions for future research in this area.