Fiemke Both

An Agent Model for a Human's Functional State and Performance

This paper presents an agent model of the dynamics of a humanpsilas functional state in relation to task performance and environment. It can be used in agent systems that support humans in demanding circumstances. Simulation experiments under different parameter settings pointed out that the model is able to produce realistic behaviour of different types of personalities. Moreover, by a mathematical analysis the equilibria of the model have been determined, and by automated checking a number of expected properties of the model have been confirmed.

Model-Based Reasoning Methods within an Ambient Intelligent Agent Model

Ambient agents react on humans on the basis of their information obtained by sensoring and their knowledge about human functioning. Appropriate types of reactions depend on in how far an ambient agent understands the human. On the one hand, such an understanding requires that the agent has knowledge to a certain depth about the human’s physiological and mental processes in the form of an explicitly represented model of the causal and dynamic relations describing these processes. On the other hand, given such a model representation, the agent needs reasoning methods to derive conclusions from the model and the information available by sensoring. This paper presents a number of such model-based reasoning methods. They have been formally specified in an executable temporal format, which allows for simulation of reasoning traces and automated verification in a dedicated software environment. A number of such simulation experiments and their formal analysis are described.

BOA: A Cognitive Tactical Picture Compilation Agent

Simulation-based training in complex decision-making can be made more effective by using intelligent software agents to play key roles, such as teammates, opponents and instructors. This paper presents a cognitive software agent that is capable of compiling a tactical picture in the domain of Naval Anti-Surface Warfare. The agent is implemented in ACT-R and can perform this task in a simulated environment with a varying degree of quality, so it is usable for all the roles. The agents behavior was evaluated in a session with military experts and although much work remains to be done, the research was positively evaluated.The work described in this paper is embedded within a research project that has the principal goal of developing an instrument to support the complex interaction patterns of providers and consumers in an e-business setting. In particular, these providers and consumers, either humans or software agents, are members of a heterogeneous society cohabiting in a multi-agent based 3D virtual environment. Conceptually speaking, the environment is designed according to a three-layered architecture comprising i) the multi-agent system layer, ii) the middleware layer and iii) the visualization layer. This papers contribution lies in the description of the design and implementation of the middleware connecting the two other layers.

Methods for model-based reasoning within agent-based Ambient Intelligence applications

Within agent-based Ambient Intelligence applications agents react to humans based on information obtained by sensoring and their knowledge about human functioning. Appropriate types of reactions depend on the extent to which an agent understands the human and is able to interpret the available information (which is often incomplete, and hence multi-interpretable) in order to create a more complete internal image of the environment, including humans. Such an understanding requires that the agent has knowledge to a certain depth about the humans physiological and mental processes in the form of an explicitly represented model of the causal and dynamic relations describing these processes. In addition, given such a model representation, the agent needs reasoning methods to derive conclusions from the model and interpret the (partial) information available by sensoring. This paper presents the development of a toolbox that can be used by a modeller to design Ambient Intelligence applications. This toolbox contains a number of model-based reasoning methods and approaches to control such reasoning methods. Formal specifications in an executable temporal format are offered, which allows for simulation of reasoning processes and automated verification of the resulting reasoning traces in a dedicated software environment. A number of such simulation experiments and their formal analysis are described. The main contribution of this paper is that the reasoning methods in the toolbox have the possibility to reason using both quantitative and qualitative aspects in combination with a temporal dimension, and the possibility to perform focused reasoning based upon certain heuristic information.

Computational modeling and analysis of therapeutical interventions for depression

Depressions impose a huge burden on both the patient suffering from a depression as well as society in general. In order to make interventions for a depressed patient during a therapy more personalized and effective, a supporting personal software agent can be useful. Such an agent should then have a good idea of the current state of the person. A computational model for human mood regulation and depression has been developed in previous work, but in order for the agent to give optimal support during an intervention, it should also have knowledge on the precise functioning of the intervention in relation with the mood regulation and depression. This paper therefore presents computational models for these interventions for different types of therapy. Simulation results are presented showing that the mood regulation and depression indeed follow the expected patterns when applying these therapies. The intervention models have been evaluated for a variety of patient types by simulation experiments and formal verification.

Computational modeling and analysis of the role of physical activity in mood regulation and depression

Physical activity is often considered an important factor in handling mood regulation and depression. This paper presents a computational model of this role of physical activity in mood regulation. It is shown on the one hand how a developing depression can go hand in hand with a low level of physical activity, and on the other hand, how Exercise Therapy is able to reverse this pattern and make the depression disappear. Simulation results are presented, and properties are formally verified against these simulation runs.

Adaptation and Validation of an Agent Model of Functional State and Performance for Individuals

Human performance can seriously degrade under demanding tasks. To improve performance, agents can reason about the current state of the human, and give the most appropriate and effective support. To enable this, the agent needs a model of a specific persons functional state and performance, which should be valid, as the agent might otherwise give inappropriate advice and even worsen performance. This paper concerns the adaptation of the parameters of the existing functional state model to the individual and validation of the resulting model. First, human experiments have been conducted, whereby measurements related to the model have been performed. Next, this data has been used to obtain appropriate parameter settings for the model, describing the specific subject. Finally, the model, with the tailored parameter settings, has been used to predict human behavior to investigate predictive capabilities of the model. The results have been analyzed using formal verification.

Utilization of a Virtual Patient Model to Enable Tailored Therapy for Depressed Patients

Major depression is a prominent mental disorder that has significant impact upon the patient suffering from the depression as well as on the society as a whole. Currently, therapies are offered via the Internet in the form of self- help modules, and they have shown to be as effective as face-to-face counseling. In order to take automated therapies a step further, models which describe the development of the internal states associated with depression can be of great help to give dedicated advice and feedback to the patient e.g. by means of making predictions using the model. In this paper, an existing computational model for states related to depression (e.g. mood) is taken as a basis in combination with models that express the influence of various therapies upon these states. These models are utilized to give dedicated feedback to the patient, tailor the parameters towards the observed patient behavior, and give an appropriate advice regarding the therapy to be followed.

Validation of a Model for Coping and Mood for Virtual Agents

In order to make believable virtual agents, the incorporation of emotions within these agents is often said to be of crucial importance. A variety of computational models have been proposed for emotions, however the validation of these models is mostly limited to the validation of the overall behavior of the agent incorporating these emotions (e.g. evaluating whether the overall behavior is realistic or human like). Ideally, the validation would also investigate whether the strength of the generated emotions matches the emotions displayed by humans. Hereby, two approaches can be followed: (1) looking at average behavior of humans and seeing whether the emotions models exhibit similar patterns, and (2) trying to see whether the emotion models can replicate the emotions of individual humans with their own personality and characteristics. In this paper, the latter approach is taken. An experiment has been designed in the context of depression whereby humans were regularly asked to rate their emotions when undergoing therapy. Parameter estimation techniques have been used to tune an existing model for emotions towards the observed patterns. The results show that the model can describe the humans emotions accurately and is even able to make predictions of future emotional states in quite a precise manner.

Model-Based Default Refinement of Partial Information within an Ambient Agent

Ambient agents react on humans on the basis of partial information obtained by sensoring. Appropriate types of reactions depend on in how far an ambient agent is able to interpret the available information (which is often incomplete, and hence multi-interpretable) in order to create a more complete internal image of the environment, including humans. This interpretation process, which often has multiple possible outcomes, can make use of an explicitly represented model of causal and dynamic relations. Given such a model representation, the agent needs a reasoning method to interpret the partial information available by sensoring, by generating one or more possible interpretations. This paper presents a generic model-based default reasoning method that can be exploited to this end. The method allows the use of software tools to determine the different default extensions that form the possible interpretations.