Component-Based Development Methods, AI and Design
Requirements Engineering, Verification and Validation
Temporal Semantics, Logical Foundations
Adaptive Ambient Empowerment of the Elderly (A²E²)
A²E² combines state-of-the-art psychological knowledge on elderly users' requirements for sustained behaviour change with modern ICT technology in suggesting an adaptive ambient solution for the prevention and management of two of the most prevalent chronic diseases in the elderly, and thus, resulting in a higher quality of life. Specifically, A²E² stimulates beneficial levels of exercising in elderly individuals who are at risk to come down with diabetes type II and cardio-vascular diseases. Furthermore, it supports exercise behaviour changes in patients who have already been diagnosed with these diseases in stabilizing or even reversing their condition. The focus on physical activity was chosen as exercise is recognized as a crucial element for the prevention, cure, and management of many chronic illnesses including diabetes type II and cardio-vascular diseases and directly related to physical and mental health and hereby substantially contributing to well-being and quality of life.
Funded by different national funding agencies: NWO-ZonMw (Netherlands), Research Council of Norway, Tekes (Finland).
Virtual Coach Reaches Out To Me (V2me)
Virtual Coach Reaches Out To Me, V2me, combines real life and virtual social network elements to prevent and overcome loneliness in Europe’s aging populations. Its overall goal is to enhance the joy of life of the network members. To fulfil this goal V2me supports active ageing by increased integration in the society through the provision of advanced social connectedness and social network services and activities.
V2me implements this goal by a flexible assistive living solution to prevent loneliness with particular emphasis on acceptance by senior end users. Rooted in scientific theory and research, it uses evidence-based prevention and intervention strategies to develop a social facilitator that enables both prevention of loneliness in young-old individuals (65-74 years) and successful
intervention in older generations (75+ years). V2me is encouraging older people to continue in participating in the society, to share their knowledge and experiences, to stay mobile and cognitively agile.
As an intelligent combination of off-the-shelf and innovative technology (hardware and software) hiding behind a simple, user friendly interface, V2me presents itself as a coach with two distinct functions:
1. Mediating relationships by supporting contact with other users from existing kin, friends, and professional networks, and potential new communication partners (enriching social networks).
2. Interacting with the user in an adaptive personalised way to establish a para-social relationship (as an additional contribution to preventing loneliness).
Funded by different national funding agencies: NWO-ZonMw (Netherlands), Research Council of Norway, Tekes (Finland), National Research Fund (Luxemburg), VDI/VDE-IT (Germany), Austrian Research Promotion Agency.
Within the ICT4Depression project, an intelligent system is developed and analysed for use in primary care. It consists of (1) devices for monitoring activities and biosignals in a non-intrusive and continuous way, (2) treatments for depression and automatic assessment of the patient using mobile phone and web-based communication, (3) computational methods for reasoning about the state of patients, progress of therapies, and the risk of relapse and (4) a flexible system architecture for monitoring and supporting people using continuous observations and feedback via mobile phone and the web.
Funded by the EU under the 7th Framework Programme.
SOCIONICAL focuses on Ambient Intelligence (AmI) based smart environments in a social context. In such environments the system reacts to human behaviour while at the same time affecting it. This leads to a tight entanglement between the human and the technical system. At the same time there is dynamic, heterogeneous human-human (e.g., social contagion), human-technology (e.g., monitoring), and technology-technology interaction. The project studies global properties and emergent phenomena that arise in AmI-based socio-technological systems in two types of scenarios: transportation and emergency/disaster.
Funded by the EU under the 7th Framework Programme.
Resilience is the capability of a complex system that actors may compensate for shortcomings of their colleague actors. Air Traffic Management (ATM) systems are complex socio-technological systems in which humans and automated components interact. The objectives of this project are to improve resilience engineering in ATM through a mathematical modelling and analysis approach and demonstrate its usability through application to SESAR 2020 scenarios. The project will enhance the set of psychological and organizational sub-models currently used in safety analysis and resilience engineering by a systematic inventory of new types of models in artificial intelligence and agent-based modelling and their capability to describe a wider variety of uncertainties and non-nominal behaviour in ATM. These models will be integrated in a formal mathematical framework, which will be applied to safety criticality modelling and analysis of 4D trajectory based SESAR 2020 scenarios, it will feed the resilience analysis outcomes back to the SESAR 2020 design. Expected Results are an improved understanding of safety and resilience of ATM operations, and more effective feedback in support of resilient operation design due to the ability to identify and analyse a large variety of emergent non-nominal conditions using mathematical power.
Funded by the EU and Eurocontrol as part of the SESAR WP E Long Term and Innovative Research Programme.
Interlevel Relations between Models within Air Traffic Management (ATM)
Air Traffic Management (ATM) systems are complex socio-technological systems that consist of a large number of interconnected human and automated components that as a whole exhibit global (emergent) properties that are not obvious from the local, individual parts. As a result, it is not trivial to oversee how the overall process depends on the behaviors of the individual agents involved, and the way in which interactions are organized. In fact, minor aspects of the behaviors of the individuals (e.g., skipping a procedure due to high workload, or misinterpreting incoming communication due to discrepancies in beliefs) may have serious consequences at the global level, potentially resulting in incidents or even larger accidents; however, this may strongly depend on whether some other actors compensate for shortcomings of their colleague actors: this is often referred to as resilience. When studying the design of such resilient organizations, an important problem is that this relation between local and global behaviors is usually not so trivial, and difficult to analyze and predict. To study the behavior of such complex resilient systems in a detailed manner, approaches are needed that are able to deal with this complexity. This project aims at establishing interlevel relations between different models describing ATM. The following research questions will be addressed in this project: Which properties are required for the agents at local levels to ensure certain behavior at the global level? How can descriptions at a global level of the system be related to descriptions at local levels and the organization of interactions? How does the global organizational behavior emerge? Can descriptions be found of the behavior at the global level that approximate the behavior of the local elements combined, but abstract from the local details? Which weaknesses in the organization can be identified?
Funded by the European Complex World Network and in collaboration with NLR.
An ageing society is also a society with fewer younger people. This means that pressure on the labour market for care services is and will be increasing rapidly in the years ahead. In 2025 more than twice the amount of care needs to be delivered per working care professional. This is obviously not acceptable nor possible. So, innovation in organization, technology and education is needed to reorganize the care for a sustainable future.
Health-Lab, a program in the metropolitan region Amsterdam, has the ambition to create and stimulate solutions for the care of tomorrow. This program focuses on increasing the efficiency in care as well as on allowing people to be independent longer. This should be done with the help of technology but not limited to technology. In Health-lab people from care institutions, research and companies work together with the end-users to co-create solutions.
Because care is as personal as you can get, involvement of the real users is fundamental. Health-lab has set up several ‘Living Labs’ locations where real users test applications in their daily life and help designers and developers to improve theirproducts. In this case the users are the elderly but also the professionals and informal care givers.
Health-Lab is a collaboration between the care institutions in the Amsterdam metropolitan region, the local universities, the government en several companies. The program is set up around three pillars:
a platform where all people meet, discuss and share development and implementation of new solutions in care;
several living lab locations were new solutions can be tested and improved, together with users;
the creation of new curricula's focused on the implementation of these new solutions in educational settings
Health-Lab is an initiative of: Amsterdamse Innovatie Motor (AIM), The University of Amsterdam (UvA), VU University Amsterdam (VU), University of Applied Sciences Amsterdam (HVA), INHolland, Sigra, AMSTA, Waag Society and the municipalities of Amsterdam and Almere. The province of Noord-Holland and the Ministry of Economic Affairs support Health-Lab.
Funded by the national funding agency AgentschapNL
Simulation-based Training of Resilience in Emergencies and Stressful Situations
In crisis situations, policemen and other emergency workers often face difficult decision making problems. Even though these people usually have clear instructions about how to act, they often have difficulties in making appropriate decisions, due to a combination of factors, including time pressure and heavy emotions. The main goal of the current project is to develop an intelligent system that is able to analyse human decision making processes in stressful circumstances, and analyse the causes of incorrect decisions. In addition, the system will be incorporated in an electronic training environment for emergency workers. In this environment, trainees will be placed in a virtual emergency scenario, in which they have to make difficult decisions, while negative emotions are induced. During the scenario, various existing techniques will be applied to measure their mental state (i.e., stress level and anxiety). This information will then be used as input for the intelligent system, to determine why they made certain incorrect decisions and teach them how to improve this.
Funded by the national NWO Brain and Cognition Programme and in collaboration with NSCR.
Intelligent Support for Chronic Patients
Treatment for chronic diseases often consists of a combination of lifestyle advices and medication. Adherence to these recommendations is often far from optimal, especially in patients with chronic diseases. In this project, we will develop an intelligent online self-monitoring and self-support system, with the aim of improving adherence to therapy, both with respect to lifestyle changes and medication intake. This system can be used within disease management programs as a new element or as long-term follow-up to support retaining the effects of personal counseling. The core of the system consists of a mobile phone and web application that gives a patient personalized advice, focused information, appropriate reminders and motivational messages.
Funded by the national NWO-ZonMw Diseasemanagement programme and in collaboration with VUmc and EMGO.
Today military missions become more and more tactical and complex. This makes integrated team training more necessary for pilots to gain the required level of tactical competencies. However, live training of such tactical complex missions is expensive and practically speaking infeasible because of the involvement of many parties and the unavailability of a real tactical environment. Therefore, the expectation is that in the future the use of simulated combat situations will gain importance for training tactical competencies. Still, the current use is not up to this expectation. In combat situations, the human contribution is a critical factor. Therefore in simulated combat situations the value of the contribution of computer generated forces (CGFs) is greatly affected by their ability to accurately represent human behaviour. However, the tactical behaviour of the current generation of CGFs leaves a lot to be desired according to the users. They are too easily distinguishable from human forces: their tactical/strategic behaviour is too predictable, they do not behave situation specific and they hardly improvise. The realism of the simulated combat situations decreases such that it hardly can be used to train tactical competencies. The objective of the Smart Bandits project is to improve the tactical behaviour of the CGFs such that they can be used succesfully in simulated combat situations to train tactical competencies.
Funded by Royal Dutch Airforce and in collaboration with NLR.
Involvement in sufficient physical activity declines rapidly during later adolescence and young adulthood. As social networks and interaction with friends is important for this age group (15-23 years), this should be included in future strategies aiming at motivating and empowering young people to engage in more PA. Since the majority of young people use the (mobile) internet for social networking activities, the current project aims to make use of web-based social networks, modern mobile technology and the social setting to provide cues to promote development of and engagement in PA and empower people to be more physically active. In this project three different technological solutions will be developed and combined. First, devices and reasoning mechanisms for capturing and understanding the context and physical activities will be developed. These form the basis for context-specific tailored feedback. Secondly, computational models of habit learning will be developed to make predictions of, and thus to guide, the effect of specific interventions (such giving a cue) to promote physical activity habits. Thirdly, a web-and mobile application based on social network sites of youngsters will be used to create and strengthen social support and descriptive norm groups of youngsters with similar motivations and contexts for further physical activity promotion. Thus, the current project aims to develop an innovative solution that is appealing to young people, makes use of existing social networks and mobile devices to automatically send coaching messages and feedback that empower people to become more physically active, based on an intelligent prediction of the effect of specific suggestions.
Funded by the national NWO-STW-Philips partnership and in collaboration with VUmc and EMGO.
Collective and Web Intelligence
Een studieprogramma gericht op het ontwikkelen van intelligente systemen, met name in de kontekst van Internet en Web.
Dit studieprogramma heeft als ingredienten diverse studieonderdelen over Internet en World Wide Web en ook een aantal psychologie- en taalkundevakken.
Robbert-Jan Merk, Making Enemies: Cognitive Modelling for Opponent Agents in Fighter Pilot Simulators. Ph.D. Thesis. Supervisor: J. Treur. Co-supervisors: T. Bosse, M. Hoogendoorn, J.J. Roessingh. VU University Amsterdam, Agent Systems Research Group, 2013, pp. 231.
Both, F., Helping People by Understanding Them: Ambient Agents Supporting Task Execution and Depression Treatment. Ph.D. Thesis. Supervisors: W.J.M.J. Cuijpers, J. Treur. Co-supervisor: M. Hoogendoorn. VU University Amsterdam, Agent Systems Research Group, 2012, pp. 284.
Wal, C.N. van der, Agent-Based Modelling of Integrated Internal and
Social Dynamics of Cognitive and Affective Processes. Ph.D. Thesis. Supervisors: W.J.M.J. Cuijpers, J. Treur. Co-supervisor: T. Bosse. VU University Amsterdam, Agent Systems Research Group, 2012, pp. 253.
Lambalgen, R.M. van, When the Going Gets Tough: Exploring Agent-based Models of Human Performance under Demanding Conditions. Ph.D. Thesis. Supervisor: J. Treur. Co-supervisor: M. Hoogendoorn. VU University Amsterdam, Agent Systems Research Group, 2012, pp. 330.
Pontier, M., Virtual Agents for Human Communication: Emotion Regulation and Involvement-Distance Trade-Offs in Embodied Conversational Agents and Robots. Ph.D. Thesis. Supervisors: E. Konijn, J. Treur. Co-supervisors: T. Bosse, J. Hoorn. VU University Amsterdam, Faculty of Social Sciences, 2011.
Maanen, P.P. van, Adaptive Support for Human-Computer Teams: Exploring the Use of Cognitive Models of Trust and Attention. Ph.D. Thesis. Supervisor: J. Treur. Co-supervisor: T. Bosse. VU University Amsterdam, Agent Systems Research Group, 2010, pp. 258.
Siddiqui, G.F., Integrative Modeling of Emotions in Virtual Agents. Ph.D. Thesis. Supervisor: J. Treur. Co-supervisors: T. Bosse, J. Hoorn. VU University Amsterdam, Agent Systems Research Group, 2010, pp. 257.
Gerritsen, C.S., Caught in the Act: Investigating Crime by Agent-Based Simulation. Ph.D. Thesis. Supervisor: J. Treur. Co-supervisor: M.C.A. Klein. VU University Amsterdam, Agent Systems Research Group, 2010, pp. 270.
Heuvelink, A., Cognitive Models for Training Simulations. Ph.D. Thesis. Supervisor: J. Treur. Co-supervisors: K. van den Bosch, M.C.A. Klein. VU University Amsterdam, Agent Systems Research Group, 2009, pp. 310.
Langen, P.H.G. van, The Anatomy of Design: Foundations, Models and Applications. Ph.D. Thesis. Supervisors: F.M.T. Brazier, J. Treur. VU University Amsterdam, Agent Systems Research Group, 2002, pp. 550.
Vries, W. de, Agent Interaction: Abstract Approaches to Modelling, Programming and Verifying Multi-Agent Systems. Ph.D. Thesis. Supervisors: J.-J. Chr. Meyer, J. Treur. Co-supervisors: F. de Boer, W. van der Hoek, C.M. Jonker. Utrecht University, Institute of Information and Computing Sciences, 2002, pp. 336.
Wijngaards, W.C.A., Agent-Based Modelling of Dynamics: Biological and Organisational Applications. Ph.D. Thesis. Supervisor: J. Treur. Co-supervisor: C.M. Jonker. VU University Amsterdam, Agent Systems Research Group, 2002, pp. 384.
Lucas, P.J.F., Structures in Diagnosis: from Theory to Medical Application. Ph.D. Thesis. Supervisor: J. Treur. Co-supervisors: F.M.T. Brazier, F. van Harmelen. VU University Amsterdam, Department of Mathematics and Computer Science, 1996, pp. 270.
Walker, R., An Expert System Architecture for Heterogeneous Domains: a Case-Study in the Legal Field. Ph.D. Thesis. Supervisor: J. Treur. Co-supervisor: A. Oskamp. VU University Amsterdam, Department of Mathematics and Computer Science, 1992, pp. 385.
Veerkamp, P.J., On the Development of an Artifact and Design Description Language. Ph.D. Thesis. Supervisor: J. Treur. Co-supervisor: F. Arbab. VU University Amsterdam, Department of Mathematics and Computer Science, 1992, pp. 227.
Tan, Y.H., Non-Monotonic Reasoning: Logical Architecture and Philosophical Applications. Ph.D. Thesis. Supervisors: J.F.A.K. van Benthem, J. Treur. VU University Amsterdam, Department of Mathematics and Computer Science, 1992, pp. 198.
Jonker, W., A Design and implementation of a knowledge representation and
processing language. Ph.D. Thesis. Supervisors: J.A. Bergstra, J. Treur. Utrecht University, Department of Philosophy, 1990, pp. 278.