The measurement of meaning

Multiagent Systems is the title of a collection of papers dedicated to surveying specific themes of Multiagent Systems (MAS) and Distributed Artificial Intelligence (DAI). All of them authored by leading researchers of this dynamic multidisciplinary field.

/pdf/multiagent-systems-a-modern-approach-to-distributed-5fon0donq1.pdf

Multiagent systems: a modern approach to distributed artificial intelligence

Healthy ageing can be defined as "the process of developing and maintaining the functional ability that enables wellbeing in older age". Functional ability (i.e., the health-related attributes that enable people to be and to do what they have reason to value) is determined by intrinsic capacity (i.e., the composite of all the physical and mental capacities of an individual), the environment (i.e., all the factors in the extrinsic world that form the context of an individual's life), and the interactions between the two. This innovative model recently proposed by the World Health Organization has the potential to substantially modify the way in which clinical practice is currently conducted, shifting from disease-centered toward function-centered paradigms. By overcoming the multiple limitations affecting the construct of disease, this novel framework may allow the worldwide dissemination of a more proactive and function-based approach toward achieving optimal health status. In order to facilitate the translation of the current theoretical model into practice, it is important to identify the inner nature of its constituting constructs. In this article, we consider intrinsic capacity. Using the International Classification of Functioning, Disability and Health (ICF) framework as background and taking into account available evidence, five domains (i.e., locomotion, vitality, cognition, psychological, sensory) are identified as pivotal for capturing the individual's intrinsic capacity (and therefore also reserves) and, through this, pave the way for its objective measurement.

Evidence for the Domains Supporting the Construct of Intrinsic Capacity.

Automated fire detection is an active research topic in computer vision. In this paper, we propose and analyze a new method for identifying fire in videos. Computer vision-based fire detection algorithms are usually applied in closed-circuit television surveillance scenarios with controlled background. In contrast, the proposed method can be applied not only to surveillance but also to automatic video classification for retrieval of fire catastrophes in databases of newscast content. In the latter case, there are large variations in fire and background characteristics depending on the video instance. The proposed method analyzes the frame-to-frame changes of specific low-level features describing potential fire regions. These features are color, area size, surface coarseness, boundary roughness, and skewness within estimated fire regions. Because of flickering and random characteristics of fire, these features are powerful discriminants. The behavioral change of each one of these features is evaluated, and the results are then combined according to the Bayes classifier for robust fire recognition. In addition, a priori knowledge of fire events captured in videos is used to significantly improve the classification results. For edited newscast videos, the fire region is usually located in the center of the frames. This fact is used to model the probability of occurrence of fire as a function of the position. Experiments illustrated the applicability of the method.

A Probabilistic Approach for Vision-Based Fire Detection in Videos

Review: The contribution of learner characteristics in the development of computer-based adaptive learning environments

Personalized Coaching Systems to support healthy behavior in people with chronic conditions

This report describes the development of a teaching environment that uses agents to support learning. An Intelligent Tutoring System will be described, that guides students during learning. This system is meant for nurse education in the first place, but it is generic in the sense that the core is separated from the exercise modules and user interfaces. This means that the system can also be used for other (non-nursing) exercises. Exercises can be provided to the system in the form of XML data-files. A user interface can be text-based or 2D, but it can also be a 3D virtual reality environment. An application of the teaching environment for nurse training is described.

/pdf/an-agent-based-intelligent-tutoring-system-for-nurse-1762u7vgzq.pdf

An agent-based intelligent tutoring system for nurse education

A modular hybrid neural network architecture, called SHAME, for emotion learning is introduced. The system learns from annotated data how the emotional state is generated and changes due to internal and external stimuli. Part of the modular architecture is domain independent and part must be
adapted to the domain under consideration.
The generation and learning of emotions is based on the event appraisal model.
The architecture is implemented in a prototype consisting of agents trying to survive in a virtual world. An evaluation of this prototype shows that the architecture is capable of
generating natural emotions and furthermore that training of the neural network modules in the architecture is computationally feasible.
Keywords: hybrid neural systems, emotions, learning, agents.

/pdf/learning-emotions-in-virtual-environments-3a93cc76ji.pdf

Learning emotions in virtual environments

We present the Dutch IMIX research programme on multimodal interaction, speech and language technology. We discuss our contributions to this programme in the form of two research projects, IMOGEN and VIDIAM, and the technical integration of the various modules developed by IMIX subprojects to build a demonstrator that shows the project’s aims and achievements. In this paper we pay special attention to the role that images could play in iterative question answering.

/pdf/questions-pictures-answers-introducing-pictures-in-question-5533e37ilh.pdf

Questions, pictures, answers : Introducing pictures in question-answering systems

This paper presents a generic architecture and a dialogue model for multimodal interaction Architecture and model are transparent and have been used for different task domains In this paper the emphasis is on their use for the navigation task in a virtual environment The dialogue model is based on the information state approach and the recognition of dialogue acts We explain how pairs of backward and forward looking tags and the preference rules of the dialogue act determiner together determine the structure of the dialogues that can be handled by the system The system action selection mechanism and the problem of reference resolution are discussed in detail

/pdf/a-generic-architecture-and-dialogue-model-for-multimodal-2tak5cb97v.pdf

H.J.A. op den Akker

Papers

Personalized Coaching Systems to support healthy behavior in people with chronic conditions

An agent-based intelligent tutoring system for nurse education

Learning emotions in virtual environments

Questions, pictures, answers : Introducing pictures in question-answering systems

A generic architecture and dialogue model for multimodal interaction