"uuid","repository link","title","author","contributor","publication year","abstract","subject topic","language","publication type","publisher","isbn","issn","patent","patent status","bibliographic note","access restriction","embargo date","faculty","department","research group","programme","project","coordinates"
"uuid:33283954-fd1d-40c9-a6bf-7bd020350bbe","http://resolver.tudelft.nl/uuid:33283954-fd1d-40c9-a6bf-7bd020350bbe","Context-specific value inference via hybrid intelligence","Liscio, E. (TU Delft Interactive Intelligence)","Jonker, C.M. (promotor); Murukannaiah, P.K. (copromotor); Delft University of Technology (degree granting institution)","2024","Human values are the abstract motivations that drive our opinions and actions. AI agents ought to align their behavior with our value preferences (the relative importance we ascribe to different values) to co-exist with us in our society. However, value preferences differ across individuals and are dependent on context. To reflect diversity in society and to align with contextual value preferences, AI agents must be able to discern the value preferences of the relevant individuals by interacting with them. We refer to this as the value inference challenge, which is the focus of this thesis. Value inference entails several challenges and the related work on value inference is scattered across different AI subfields. We present a comprehensive overview of the value inference challenge by breaking it down into three distinct steps and showing the interconnections among these steps.","Values; Natural Language Processing; Morality; Ethics; Explainable AI; Active Learning; Hybrid Intelligence","en","doctoral thesis","","978-94-6366-840-8","","","","","","","","","Interactive Intelligence","","",""
"uuid:46bc9dd8-c8a9-4de4-ab18-9b53b700e4bd","http://resolver.tudelft.nl/uuid:46bc9dd8-c8a9-4de4-ab18-9b53b700e4bd","Enabling Social Situation Awareness in Support Agents","Kola, I. (TU Delft Interactive Intelligence)","Jonker, C.M. (promotor); van Riemsdijk, M.B. (copromotor); Delft University of Technology (degree granting institution)","2022","The use of support agents that help people in their daily lives is steadily growing. While there have been continuous developments in integrating and modelling internal aspects of the user in these support agents, research shows that people's behavior is also shaped by their environment. While there have been attempts at integrating elements of the physical environment such as location, support agents generally lack the ability to take into account the effect of the user's social situation on their behavior. This is important since the majority of our daily life situations have a social nature.
This thesis proposes a social situation awareness framework for allowing support agents to take into account the user's social situation in order to offer more comprehensive support. The framework is inspired by existing work on situation awareness from research in human factors and computer science, instantiated with concepts from social sciences.
This thesis demonstrates how to integrate social situation awareness components in support agents. The studies presented in the thesis provide insight into the concepts and techniques that are needed for social situation awareness, and how they can be used in practice through a hypothetical case study involving a socially aware agenda management agent. This contribution serves as a blueprint for designers of support agents, and provides a basis towards more comprehensive support for users.","","en","doctoral thesis","","978-94-6469-099-6","","","","","","","","","Interactive Intelligence","","",""
"uuid:855bd55f-d297-4fff-9248-9cde0ad2b976","http://resolver.tudelft.nl/uuid:855bd55f-d297-4fff-9248-9cde0ad2b976","Explainable Artificial Intelligence for human-AI collaboration","van der Waa, J.S. (TU Delft Interactive Intelligence; TNO)","Neerincx, M.A. (promotor); Jonker, C.M. (promotor); van Diggelen, J. (promotor); Delft University of Technology (degree granting institution)","2022","As a society, we have come to notice the influence and impact Artificially Intelligent (AI) agents have on the way we live our lives. For these AI agents to support us both effectively and responsibly, we require an understanding on how they make decisions and what the consequences are of these decisions. The research _field of Explainable Artificial Intelligence (XAI) aims to develop AI agents that can explain its own functioning to provide this understanding. In this thesis we defined, developed, and evaluated a core set of explanations an AI agent can provide to support their collaboration with humans.","Artificial Intelligence; Explainable AI; Machine Learning; Human-AI collaboration; Explainable Artificial Intelligence","en","doctoral thesis","","978-94-6458-619-0","","","","","","","","","Interactive Intelligence","","",""
"uuid:8663c97e-945d-4a30-85c1-a30f269a10bc","http://resolver.tudelft.nl/uuid:8663c97e-945d-4a30-85c1-a30f269a10bc","Getting a grip on stress: Designing smart wearables as partners in stress management","Li, X. (TU Delft Human Information Communication Design)","Jansen, K.M.B. (promotor); Jonker, C.M. (promotor); Rozendaal, M.C. (copromotor); Delft University of Technology (degree granting institution)","2022","This thesis is motivated by the vision of designing smart wearables as partners for veterans with chronic posttraumatic stress disorder (PTSD). Everyday objects are becoming ‘smarter’ with the integration of computational and electronic technologies. It is now possible to start thinking of these objects as ‘intelligent agents’ that can form collaborative relationships to help us with issues that were hitherto impossible. Smart wearables show the potential to be designed as “partners” that are able to continuously monitor bodily and behavioural signals, to involve the human body as part of the interaction, and help the person whenever possible and in ways other products cannot. People with chronic PTSD, who face the challenge of constantly dealing with various everyday stressful situations, provide an interesting case to explore the concept of such partners.","","en","doctoral thesis","","978-94-6421-755-1","","","","","","","","","Human Information Communication Design","","",""
"uuid:4b70aa0a-8c13-421d-9043-6274311df2aa","http://resolver.tudelft.nl/uuid:4b70aa0a-8c13-421d-9043-6274311df2aa","Simulating Human Routines: Integrating Social Practice Theory in Agent-Based Models","Mercuur, R.A. (TU Delft Information and Communication Technology)","Dignum, M.V. (promotor); Jonker, C.M. (promotor); Delft University of Technology (degree granting institution)","2021","Our routines play an important role in a wide range of social challenges such as climate change, disease outbreaks and coordinating the staff and patients of a hospital. Studying these systems via agent-based simulations (ABS) enables researchers to gain insight into complex aspects of these challenges such as human interaction, learning, heterogeneity, feedback loops and emergence. Current agent frameworks do not integrate social and psychological evidence on human routines: humans make habitual decisions, interconnect these habits throughout the day and use these interconnected habits as a blueprint for social interaction. This thesis provides the domain-independent SoPrA (Social Practice Agent) framework that integrates theories on social practices to support the simulation of human routines. Social practice theory is a socio-cognitive theory applicable to model human routines as the theory aims to describe our ‘daily doings and sayings’. The first part of the thesis identifies the aspects of social practice theory that are relevant for agent-based simulation, distils requirements from the literature, reviews current agent models and provides the SoPrA framework that satisfies said requirements. The second part describes applications of SoPrA on the value-alignment problem in AI, identifying social bottlenecks in hospitals and comparing theories on how habits break. This results in an agent framework with a clear relation to current evidence and, due to its modularity and focus on domain-independence, is usable for a wide range of ABS studies that involve human routines. As such, SoPrA is relevant for scientific work in (1) ABS by enabling a new way to know, explore and improve the world, grounded in evidence on human routines; (2) in multi-agent systems by enabling agents that understand and interact with human routines; and (3) in the social sciences by crystallizing theories on human routines and enabling exploration of these theories via simulation. Furthermore, this thesis shows the societal relevance of SoPrA for understanding and improving the role of routines in AI safety, emergency rooms, commuting behaviour and consumption behaviour.","Social Practice Theory; Agent-based modelling; Agents; Agent Architecture; Simulation; Habits; Social agents; Human values","en","doctoral thesis","","978-94-6384-213-6","","","","","","","","","Information and Communication Technology","","",""
"uuid:5437884e-0078-4b36-b2c7-c6edfea3b418","http://resolver.tudelft.nl/uuid:5437884e-0078-4b36-b2c7-c6edfea3b418","The Intersection of Planning and Learning","Moerland, T.M. (TU Delft Interactive Intelligence)","Jonker, C.M. (promotor); Plaat, Aske (promotor); Broekens, D.J. (copromotor); Delft University of Technology (degree granting institution)","2021","Intelligent sequential decision making is a key challenge in artificial intelligence. The problem, commonly formalized as a Markov Decision Process, is studied in two different research communities: planning and reinforcement learning. Departing from a fundamentally different assumption about the type of access to the environment, both research fields have developed their own solution approaches and conventions. The combination of both fields, known as model-based reinforcement learning, has recently shown state-of-the-art results, for example defeating human experts in classic board games like Chess and Go. Nevertheless, literature lacks an integrated view on 1) the similarities between planning and learning, and 2) the possible combinations of both. This dissertation aims to fill this gap. The first half of the book presents a conceptual answer to both questions. We first present a framework that disentangles the common algorithmic space of both fields, showing that they essentially face the same algorithmic design decisions. Moreover, we also present an overview of the different ways in which planning and learning can be combined in one algorithm. The second half of the dissertation provides experimental illustration of these ideas. We present several new combinations of planning and learning, such as a flexible method to learn stochastic dynamics models with neural networks, an extension of a successful planning-learning algorithm (AlphaZero) to deal with continuous action spaces, and a study of the empirical trade-off between planning and learning. Finally, we also illustrate the commonalities between both fields, by designing a new algorithm in one field based on inspiration from the other field. We conclude the thesis with an outlook for the planning-learning field as a whole. Altogether, the dissertation provides a broad theoretical and empirical view on the combination of planning and learning, which promises to be an important frontier in artificial intelligence research in the coming years.
welfare. To this end, for each model (game), we find the Nash equilibria and their social welfare. A Nash equilibrium is division where no agent can increase her utility if the others do not change their behavior. The social welfare is defined as the sum of the utilities of all the agents. We concentrate on value-creating activities and on reciprocation (interactions where agents react on the previous actions). The value-creating activities model work projects, co-authoring articles, writing to Wikipedia, etc. We assume that all the agents who contribute to such an activity at least a predefined threshold share of the final value of the activity. Examples of reciprocation activities are politics and relationships with colleagues. We prove the actions stabilize around a limit value. Then, we assume that agents
strategically set their own interaction habits and model this as a game. We finally analyze dividing own effort between several reciprocal interactions. We lay the foundation of realistic mathematical modeling and analysis of effort
division between activities and provide advice about what the agents should do in order to maximize the personal and the social welfare.","Game theory; agent; Projects; Value creation; interaction; reciprocation; threshold; Nash-equilibrium; Efficiency; price of anarchy; price of stability; simulations; fictitious play; competition; interaction graph; Perron-Frobenius","en","doctoral thesis","","978-94-6186-766-7","","","","SIKS Dissertation Series No. 2016-49. The research reported in this thesis has been carried out under the auspices of SIKS, the Dutch Research School for Information and Knowledge Systems.","","","","","Algorithmics","","",""
"uuid:40736144-a35d-4b88-aa77-8d51f5e8d1fd","http://resolver.tudelft.nl/uuid:40736144-a35d-4b88-aa77-8d51f5e8d1fd","Accounting for Values in Design","Detweiler, C.A. (TU Delft Interactive Intelligence)","Jonker, C.M. (promotor); van den Hoven, M.J. (promotor); Hindriks, K.V. (copromotor); Delft University of Technology (degree granting institution)","2016","One of the more notable technologies to enter and affect everyday life is information and communication technology (ICT). Since the twentieth century, ICTs have had a considerable impact on many aspects of everyday life. This impact on individuals and society is rarely neutral; ICTs can have both desirable and undesirable consequences — ethical implications. One field of computing in particular envisions computing technology permeating everyday life. This field, known as Ubiquitous Computing or Pervasive Computing, aims to integrate computing technology seamlessly into the physical world and everyday life. This pervasiveness has the potential to amplify pervasive computing’s ethical implications. Human values such as social well-being, privacy, trust, accountability and responsibility lie at the heart of these ethical implications. With a technology already so deeply intertwined with so many aspects of everyday life, it is increasingly important to consider the human values at stake.","","en","doctoral thesis","","","","","","SIKS Dissertation Series No. 2016-40","","","","","Interactive Intelligence","","",""
"uuid:82438672-3e8b-477a-a39e-0ce189639e88","http://resolver.tudelft.nl/uuid:82438672-3e8b-477a-a39e-0ce189639e88","Governing Governance: A formal framework for analysing institutional design and enactment governance","King, T.C. (TU Delft Interactive Intelligence)","Jonker, C.M. (promotor); Dignum, M.V. (copromotor); van Riemsdijk, M.B. (copromotor); Delft University of Technology (degree granting institution)","2016","This dissertation is motivated by the need, in today’s globalist world, for a precise way to enable governments, organisations and other regulatory bodies to evaluate the constraints they place on themselves and others. An organisation’s modus operandi is enacting and fulfilling contracts between itself and its participants. Yet, organisational contracts should respect external laws, such as those setting out data privacy rights and liberties. Contracts can only be enacted by following contract law processes, which often require bilateral agreement and consideration. Governments need to legislate whilst understanding today’s context of national and international governance hierarchy where law makers shun isolationism and seek to influence one another. Governments should avoid punishment by respecting constraints from international treaties and human rights charters. Governments can only enact legislation by following their own, pre-existing, law making procedures. In other words, institutions, such as laws and contracts are designed and enacted under constraints.","","en","doctoral thesis","","978-94-6186-726-1","","","","SIKS Dissertation Series No. 2016-41","","","","","Interactive Intelligence","","",""
"uuid:24ff01b3-cb96-4a30-8ab0-1b88f65cc9c7","http://resolver.tudelft.nl/uuid:24ff01b3-cb96-4a30-8ab0-1b88f65cc9c7","Cognitive Coordination for Cooperative Multi-Robot Teamwork","Wei, C.","Jonker, C.M. (promotor)","2015","Multi-robot teams have potential advantages over a single robot. Robots in a team can serve different functionalities, so a team of robots can be more efficient, robust and reliable than a single robot. In this dissertation, we are in particular interested in human level intelligent multi-robot teams. Social deliberation should be taken into consideration in such a multi-robot system, which requires that the robots are capable of generating long term plans to achieve a global or team goal, rather than just dealing with the problems at hand. Robots in a team have to cope with dynamic environments due to the presence of the others. Thus, a robot cannot foresee what its environment will be because other robots may change the environment. Moreover, multiple robots may interfere with each other. We can say that the need for coordination in a robot team stems from interdependence relationships between the robots. More specifically, one robot performing an activity may influence another robot's activity. In order to achieve good team performance, the robots in a team all need to well coordinate their activities. This dissertation studies the multi-robot teamwork in the context of search and retrieval, which is known as foraging in robotics. In a foraging task, a team of robots is required to search targets of interest in the environment and also deliver them back to a home base. Many practical applications require search and retrieval such as urban search and rescue robots, deep-sea mining robots, and autonomous warehouse robots. Requiring both searching and delivering makes a foraging task more complicated than a pure searching, exploration or coverage task. Foraging robots have to consider not only where to explore but also when to explore. Coordination for a foraging task concerns how to direct the movements of the robots and how to distribute the workload more evenly in a team. In this dissertation, we first proposed an agent-based cognitive robot architecture that is used to bridge the gap between low-level robotic control with high-level cognitive reasoning. Cognitive agents realized by means of the agent programming language GOAL are used to control both real and simulated robots. We carried out an empirical study to investigate the role of communication and its impact on team performance. The results and findings were used to study the multi-robot pathfinding and multi-robot task allocation problems. A novel fully decentralized approach was proposed to deal with the multi-robot pathfinding problem, which also reduces the communication overhead, compared to usual decentralized approaches. An auction-based approach and a prediction approach were proposed to deal with the dynamic foraging task allocation problem. The difference is that the prediction approach performs better with respect to completion time, while the auction-based approach performs better with respect to travel costs. In order to facilitate the identification of interdependence relationships between the agents in the early design phase of a multi-agent system, we developed a formal domain-independent graphical language that reflects the need for coordination in multi-agent teamwork.","multi-agent/robot systems; coordination; cognitive robots; teamwork","en","doctoral thesis","","","","","","","","","Electrical Engineering, Mathematics and Computer Science","Intelligent Systems","","","",""
"uuid:6925c772-fb7f-4791-955d-27884f037da0","http://resolver.tudelft.nl/uuid:6925c772-fb7f-4791-955d-27884f037da0","Coactive Design: Designing Support for Interdependence in Human-Robot Teamwork","Johnson, M.J.","Jonker, C.M. (promotor)","2014","Coactive Design breaks with traditional approaches by focusing on effective management of the interdependencies among human-machine team members. Providing support for interdependence enables members of a human-machine team to recognize problems and adapt. Support for a variety of interdependence relations makes a team flexible. Flexibility, in turn, makes the team resilient by providing alternative ways to recognize and handle unexpected situations.","coactive; teamwork; human-robot; interaction","en","doctoral thesis","","","","","","","","","Electrical Engineering, Mathematics and Computer Science","Interactive Intelligence","","","",""
"uuid:3df6e234-a7c1-4dbe-9eb9-baadabc04bca","http://resolver.tudelft.nl/uuid:3df6e234-a7c1-4dbe-9eb9-baadabc04bca","What to Bid and When to Stop","Baarslag, T.","Jonker, C.M. (promotor)","2014","Negotiation is an important activity in human society, and is studied by various disciplines, ranging from economics and game theory, to electronic commerce, social psychology, and artificial intelligence. Traditionally, negotiation is a necessary, but also time-consuming and expensive activity. Therefore, in the last decades there has been a large interest in the automation of negotiation, for example in the setting of e-commerce. This interest is fueled by the promise of automated agents eventually being able to negotiate on behalf of human negotiators. Every year, automated negotiation agents are improving in various ways, and there is now a large body of negotiation strategies available, all with their unique strengths and weaknesses. For example, some agents are able to predict the opponent's preferences very well, while others focus more on having a sophisticated bidding strategy. The problem however, is that there is little incremental improvement in agent design, as the agents are tested in varying negotiation settings, using a diverse set of performance measures. This makes it very difficult to meaningfully compare the agents, let alone their underlying techniques. As a result, we lack a reliable way to pinpoint the most effective components in a negotiating agent. There are two major advantages of distinguishing between the different components of a negotiating agent's strategy: first, it allows the study of the behavior and performance of the components in isolation. For example, it becomes possible to compare the preference learning component of all agents, and to identify the best among them. Second, we can proceed to mix and match different components to create new negotiation strategies., e.g.: replacing the preference learning technique of an agent and then examining whether this makes a difference. Such a procedure enables us to combine the individual components to systematically explore the space of possible negotiation strategies. To develop a compositional approach to evaluate and combine the components, we identify structure in most agent designs by introducing the BOA architecture, in which we can develop and integrate the different components of a negotiating agent. We identify three main components of a general negotiation strategy; namely a bidding strategy (B), possibly an opponent model (O), and an acceptance strategy (A). The bidding strategy considers what concessions it deems appropriate given its own preferences, and takes the opponent into account by using an opponent model. The acceptance strategy decides whether offers proposed by the opponent should be accepted. The BOA architecture is integrated into a generic negotiation environment called Genius, which is a software environment for designing and evaluating negotiation strategies. To explore the negotiation strategy space of the negotiation research community, we amend the Genius repository with various existing agents and scenarios from literature. Additionally, we organize a yearly international negotiation competition (ANAC) to harvest even more strategies and scenarios. ANAC also acts as an evaluation tool for negotiation strategies, and encourages the design of negotiation strategies and scenarios. We re-implement agents from literature and ANAC and decouple them to fit into the BOA architecture without introducing any changes in their behavior. For each of the three components, we manage to find and analyze the best ones for specific cases, as described below. We show that the BOA framework leads to significant improvements in agent design by wining ANAC 2013, which had 19 participating teams from 8 international institutions, with an agent that is designed using the BOA framework and is informed by a preliminary analysis of the different components. In every negotiation, one of the negotiating parties must accept an offer to reach an agreement. Therefore, it is important that a negotiator employs a proficient mechanism to decide under which conditions to accept. When contemplating whether to accept an offer, the agent is faced with the acceptance dilemma: accepting the offer may be suboptimal, as better offers may still be presented before time runs out. On the other hand, accepting too late may prevent an agreement from being reached, resulting in a break off with no gain for either party. We classify and compare state-of-the-art generic acceptance conditions. We propose new acceptance strategies and we demonstrate that they outperform the other conditions. We also provide insight into why some conditions work better than others and investigate correlations between the properties of the negotiation scenario and the efficacy of acceptance conditions. Later, we adopt a more principled approach by applying optimal stopping theory to calculate the optimal decision on the acceptance of an offer. We approach the decision of whether to accept as a sequential decision problem, by modeling the bids received as a stochastic process. We determine the optimal acceptance policies for particular opponent classes and we present an approach to estimate the expected range of offers when the type of opponent is unknown. We show that the proposed approach is able to find the optimal time to accept, and improves upon all existing acceptance strategies. Another principal component of a negotiating agent's strategy is its ability to take the opponent's preferences into account. The quality of an opponent model can be measured in two different ways. One is to use the agent's performance as a benchmark for the model's quality. We evaluate and compare the performance of a selection of state-of-the-art opponent modeling techniques in negotiation. We provide an overview of the factors influencing the quality of a model and we analyze how the performance of opponent models depends on the negotiation setting. We identify a class of simple and surprisingly effective opponent modeling techniques that did not receive much previous attention in literature. The other way to measure the quality of an opponent model is to directly evaluate its accuracy by using similarity measures. We review all methods to measure the accuracy of an opponent model and we then analyze how changes in accuracy translate into performance differences. Moreover, we pinpoint the best predictors for good performance. This leads to new insights concerning how to construct an opponent model, and what we need to measure when optimizing performance. Finally, we take two different approaches to gain more insight into effective bidding strategies. We present a new classification method for negotiation strategies, based on their pattern of concession making against different kinds of opponents. We apply this technique to classify some well-known negotiating strategies, and we formulate guidelines on how agents should bid in order to be successful, which gives insight into the bidding strategy space of negotiating agents. Furthermore, we apply optimal stopping theory again, this time to find the concessions that maximize utility for the bidder against particular opponents. We show there is an interesting connection between optimal bidding and optimal acceptance strategies, in the sense that they are mirrored versions of each other. Lastly, after analyzing all components separately, we put the pieces back together again. We take all BOA components accumulated so far, including the best ones, and combine them all together to explore the space of negotiation strategies. We compute the contribution of each component to the overall negotiation result, and we study the interaction between components. We find that combining the best agent components indeed makes the strongest agents. This shows that the component-based view of the BOA architecture not only provides a useful basis for developing negotiating agents but also provides a useful analytical tool. By varying the BOA components we are able to demonstrate the contribution of each component to the negotiation result, and thus analyze the significance of each. The bidding strategy is by far the most important to consider, followed by the acceptance conditions and finally followed by the opponent model. Our results validate the analytical approach of the BOA framework to first optimize the individual components, and then to recombine them into a negotiating agent.","Negotiation; Bidding; Opponent modeling; Accepting; BOA; Artificial Intelligence; Automated negotiation; E-negotiation; E-commerce; Decision making; Agent; Bargaining; Decision support; Human-Computer Interaction; Negotiation Support System; Optimal stopping; Concession strategy; Negotiating strategy components; Performance measure; Accuracy measure; Learning; ANAC; Genius; Automated Negotiating Agents Competition","en","doctoral thesis","","","","","","","","","Electrical Engineering, Mathematics and Computer Science","Intelligent Systems","","","",""
"uuid:d6b8a31e-71f5-4509-adca-9cd672432c1e","http://resolver.tudelft.nl/uuid:d6b8a31e-71f5-4509-adca-9cd672432c1e","Multimodal Surveillance: Behavior analysis for recognizing stress and aggression","Lefter, I.","Jonker, C.M. (promotor)","2014","Nowadays, camera systems are installed in military areas as well as in public spaces like schools, shopping malls, airports, and football stadiums. Human operators are monitoring the screens, looking for any signs of unwanted behavior and negative incidents. The task requires working personnel 24/7. With the ever increasing number of cameras, surveillance operators become overloaded. The nature of the task to constantly watch screens and the sparsity of notable events are bound to decrease the operators' focus. Furthermore, some events are hard to distinguish by video only: severe events such as gunshots and screams are much easier to hear than see. For these reasons, negative events may go by unnoticed and typically the recorded footage is inspected after the fact. A solution to these problems is the development of automatic multimodal (audio-visual) surveillance systems, which was the aim of this research thesis. Such systems should not take over the decisions of the operators, but should assist them in identifying unwanted behaviour. Operators would be notified when and where to focus. This is likely to reduce the number of missed events caused by screen prioritising or external and internal distractions. It is important to note that such a system should not be limited to recognizing violence. It has been shown that negative emotions and stress might precede aggression. Recognizing them in an early stage is very relevant since adopting proper measures at an early time can prevent the situation from escalating. Therefore, in this research thesis, besides a variety of manifestations of aggression, we have focused on automatically recognizing stress. Our aim was to design and implement a surveillance system that is able to emulate human perception. For that reason, we asked people to annotate stress and aggression on audio-visual recordings. We investigated several approaches to compute their annotations automatically. Recordings from real surveillance cameras are in general not available due to privacy reasons. We had to construct our own datasets. In order to ensure a high degree of realism as well as sufficient samples of stress and aggression, we have designed scenarios and hired semi-professional actors to play them. The actors were free to improvise after they received roles and short scenario descriptions. We have recorded stressful scenes at service desk and aggression related scenarios in a train and train station. To automatically recognize the stress and aggression levels, we have extracted acoustic, linguistic and visual features, referred to as low-level features. Using classifiers, we trained models which can be used to make prediction of stress or aggression level on new data samples. One shortcoming of this approach is that there is a semantic gap between the low-level features and the high-level stress and aggression assessment. We have contributed by bridging the semantic gap with semantically-meaningful intermediate representations of the stress concept. The intermediate representation of stress consists of the degrees to which stress is conveyed by speech and gestures with respect to the semantic message and the way in which the semantic message is expressed (e.g. intonation for speech, speed, rhythm, tension for gestures). Adding such a representation as an intermediate level in the stress recognition architecture improves the stress assessment, especially when the level of stress is high. Having both audio and video offers the possibility to construct a more complete representation of the scene. The multimodal fusion approach is expected to be a solution to deal with the shortcomings of each modality (e.g. noise for audio, occlusion for video). Despite the expected benefits, fusing information coming from different modalities is challenging. Typical problems are that some pieces of information are only apparent in one modality (e.g. verbal fight), and that multiple people in the scene can have different behaviors which might lead to different assessments based on where the focus is. These problems can lead to incongruent, or even contradicting information from the different modalities, which makes coming to the correct interpretation hard. To deal with the problem of fusing incongruent information we have proposed and validated five meta-features: audio-focus, video-focus, context, semantics and history. The meta-features and the audio-only and video-only aggression assessments form the intermediate level of the aggression recognition model. This novel approach significantly improved automatic aggression recognition by multimodal fusion.","automatic surveillance; multimodal information fusion; audio processing; video processing; emotion; stress; aggression recognition","en","doctoral thesis","","","","","","","","","Electrical Engineering, Mathematics and Computer Science","Intelligent Systems","","","",""
"uuid:d9a0ae1d-3336-4e43-bc3d-7a3a06461f54","http://resolver.tudelft.nl/uuid:d9a0ae1d-3336-4e43-bc3d-7a3a06461f54","Language Models With Meta-information","Shi, Y.","Jonker, C.M. (promotor); Larson, M. (promotor)","2014","Language modeling plays a critical role in natural language processing and understanding. Starting from a general structure, language models are able to learn natural language patterns from rich input data. However, the state-of-the-art language models only take advantage of words themselves, which are not sufficient to characterize the language. In this thesis, we improve recurrent neural network language models (RNNLM) by training them with additional information. Different methods of integrating the different types of additional information into RNNLMs are proposed in this thesis. All the potential information beyond the word itself that can be used to characterize the language is called meta-information. In this thesis, we propose to use different types of meta-information to represent languages such as discourse level information, which is reflected from the whole discourse, sentence level information which characterize the patterns of sentences and morphological information which represents the word from different perspectives. For example, we consider the following Dutch paragraph. < s > represents sentence beginning. < /s > stands for the sentence ending. < s > kan allemaal nog natuurlijk < /s > < s > maar ze ontlopen dan de groepswinnaar in elk geval in de kwartfinale < /s > < s > en vooral Nederland wil graag in Rotterdam die kwartfinale spelen < /s > < s > en dan moet er groepswinst behaald worden < /s > < s > anders verhuizen ze naar Brugge en krijgt het Jan Breydelstadion Oranje dus op bezoek < /s > < s > we gaan er even uit < /s > < s > slotfase zit eraan te komen < /s > < s > twee minuten nog tot het einde plus de toegevoegde tijd < /s > < s > dat is uh toch nog ook wel een paar minuten denk ik < /s > < s > maar de wedstrijd is gespeeld < /s > On the discourse level, this paragraph is labeled as “Live commentaries (broadcast)” from the socio-situational setting (SSS) perspective and “sport” from the topic perspective. On the sentence level, each word except for the beginning word and ending word , is annotated with its preceding word information and succeeding word information. For example, we consider word “slotfase” in the following sentence. < s > slotfase zit eraan te komen < /s >. This word has preceding information “< s >” and succeeding information “zit eraan te komen ”. On the word level, the word “slotfase” is annotated by a vector containing some of the proposed meta-information. On the discourse level, we investigate classification methods for socio-situational settings and topics. On the sentence level, in this thesis, we focus on information such as succeeding words information and whole sentence information. In this thesis, each word is annotated by a vector containing the meta-information collected. Different methods are proposed in this thesis to integrate the meta-information into language models. On the discourse level, a curriculum learning method has been used to combine the socio-situational settings and topics. On the sentence level, forward-backward recurrent neural network language models have been proposed to integrate the succeeding word information and whole sentence information into language models. On the word level, each word has been conditioned on its preceding words as well as on preceding meta-information. The results reported in this thesis show that meta-information can be used to improve the effectiveness of language models at the cost of increasing training time. In this thesis, we address this problem by applying parallel processing techniques. A subsampling stochastic gradient descent algorithm has been proposed to accelerate the training of recurrent neural network language models.","Language Models; Recurrent Neural Networks; Meta-information","en","doctoral thesis","","","","","","","","","Electrical Engineering, Mathematics and Computer Science","Intelligent Systems","","","",""
"uuid:f32371b2-82cc-414e-9569-2d56b12a530a","http://resolver.tudelft.nl/uuid:f32371b2-82cc-414e-9569-2d56b12a530a","An Empathic Virtual Buddy for Social Support","Van der Zwaan, J.M.","Jonker, C.M. (promotor); Dignum, M.V. (promotor)","2014","Recent years have witnessed a growing interest in employing Embodied Conversational Agents (ECAs) as companions or coaches. These roles are typically performed by humans and require exhibiting certain social behaviors, such as providing social support. For interactions between users and coaching or companion ECAs to become truly social, providing social support is one of the tasks these agents should be able to perform. Social support can be defined as alleviating the emotional distress of another person. This thesis proposes a design for an 'empathic virtual buddy' that provides social support to victims of cyberbullying. It presents the underlying principles and an architecture for a prototype system, and provides both a quantitative and qualitative evaluation of the support conveyed by the empathic virtual buddy prototype.","Embodied Conversational Agents; pedagogical, companion and coaching agents; verbal and non-verbal expression; social support; cyberbullying","en","doctoral thesis","","","","","","","","","Technology, Policy and Management","Infrastructure Systems & Services","","","",""
"uuid:135a94e8-5900-428d-944a-73906e076ccf","http://resolver.tudelft.nl/uuid:135a94e8-5900-428d-944a-73906e076ccf","Qualitative multi-criteria preference representation and reasoning","Visser, W.M.","Jonker, C.M. (promotor)","2012","The research reported on in this thesis is part of a larger research project that aims to develop a negotiation support system called the Pocket Negotiator. This thesis focuses on the question how such a system can represent and reason about a user’s preferences between the possible outcomes of a negotiation. In real-world negotiations, there are many negotiation issues which can have many different values, resulting in a large space of complex outcomes. A negotiation support system needs to have a model of the user’s preferences over this outcome space. Although most current negotiation support systems use numerical measures such as utility to represent preferences, such quantitative preferences are hard to specify for human users, and so it would be more natural to model the user’s preferences in a qualitative way. Moreover, due to the exponential size of the outcome space, it is not feasible to specify a preference ordering directly. Therefore, we aim to represent the preferences in a more compact way by aggregating multiple evaluation criteria that influence preference. The main research objective of this thesis is to develop a framework for the representation of, and reasoning about such qualitative multi-criteria preferences. The thesis makes the following contributions. We propose strategies to derive preferences from incomplete or uncertain information about the objects to be compared. The decisive and safe strategy for incomplete information is based on the notion of least and most preferred completions of objects. The strategies for uncertain information are based on an ordinal representation of the certainty levels of facts. We argue that instead of negotiation issues, the negotiators’ underlying interests should be chosen as criteria, especially if the issues are not preferentially independent. We show that the use of interests as criteria is more flexible than modelling conditional preferences, and provides a better explanation of the derived preferences. We present a general framework for the representation of qualitative, multicriteria preferences, called Qualitative Preference Systems (QPS). The framework defines outcomes as value assignments to a set of variables which can have arbitrary domains, includes a knowledge base that can impose (hard) constraints and define new (abstract) concepts, and defines three types of criteria that can be combined in a tree structure. We show that the QPS framework is expressive, as it can model conditional preferences and underlying interests, goal-based preferences, bipolar preferences, and preferences represented in two other well-known approaches that are representative for a large number of purely qualitative preference modelling approaches. Moreover, we show that the goal-based variant of QPS is just as expressive. For all proposed preference representation frameworks we define corresponding argumentation frameworks that include a logical language, a set of inference rules, and a defeat relation. Some of the argumentation frameworks also provide the possibility to reason with background knowledge to derive information about the values of variables by default. We propose a mechanism to generate explanations for preferences represented in a QPS. We use the intuition that preferences can be explained by the criteria that are deciding in the overall preference. Moreover, we show how a system can use user-provided explanations to update its current preference model. Finally, we introduce a modal logic, called Multi-Attribute Preference Logic (MPL), that provides a language for expressing several strategies to qualitatively derive a preference between objects from property rankings. Three such strategies from the literature on prioritized goals are modelled. The additional value of the logic is that it is possible to reason not only about which objects are preferred according to a certain ordering, but also about the relation between different orderings.","","en","doctoral thesis","","","","","","","","","Electrical Engineering, Mathematics and Computer Science","Interactive Intelligence","","","",""
"uuid:6eaadf67-38cc-4e22-b23f-b74313bb596c","http://resolver.tudelft.nl/uuid:6eaadf67-38cc-4e22-b23f-b74313bb596c","Designing Human-Centered Systems for Reflective Decision Making","Pommeranz, A.","Jonker, C.M. (promotor)","2012","Taking major life decisions, e.g. what career to follow, is difficult and sometimes emotional. One has to find out what exactly one wants, consider the long-term consequences of the decisions and be empathetic for loved ones affected by the decisions. Decision making also deals with establishing and browsing a vast number of alternatives and weighing options according to one’s preferences. Decision support systems can offer help in this process. However, current systems are built on economic models and less suited for untrained decision makers. Therefore, this dissertation focuses on designing decision support systems from a human-centered perspective empowering people to take decisions. Investigations were two-fold, i.e. focusing on requirements and concrete design guidelines and on the methods for engaging of stakeholders in the design process. Requirements were derived from interdisciplinary literature research and exploratory studies with domain experts and users. These highlighted the crucial preparation phase of decision making and the social factors of the process. Design guidelines for the overall system, and in particular preference construction and value-reflection, were derived through design-based research involving experts and users. A dominant theme was the delicate balance between supporting human ways of thinking and reflecting and giving intelligent guidance created by system designers. This balance can only be achieved through close, iterative interactions with end-users, domain experts and designers throughout the design process supported by skilled facilitators. This thesis marks a shift in DSS research from engineering expert systems taking over decision making to designing human-centered support for people to make their own, informed decisions.","Human-Computer Interaction; Decision Making; Participatory Design","en","doctoral thesis","","","","","","","","","Electrical Engineering, Mathematics and Computer Science","Intelligent Systems","","","",""
"uuid:e6a0231f-6851-4f51-97f1-55072caa3efe","http://resolver.tudelft.nl/uuid:e6a0231f-6851-4f51-97f1-55072caa3efe","Agent-Based Modeling of Culture's Consequences for Trade","Verwaart, D.","Jonker, C.M. (promotor)","2011","In this thesis, culture is interpreted as a property of a group of people who share the meaning they attach to symbols, have a common way of expressing their opinions and feelings, and share value systems to judge what is good or bad. The unwritten rules of a culture govern the interpretation of observations and emotions and how to react appropriately. The rules are embedded in an individuals’ mind, form childhood on, by interactions with group members. People often are not aware of differences between their own unwritten rules and those of people having a different cultural background. This may result in unwarranted distrust or unwarranted trust, with serious consequences for the future of relationships. Cultural differences are known to have their effects on trade. Signals that indicate benevolence and trustworthiness of a trade partner in one’s own culture may be interpreted differently by people having a different cultural background. Hofstede (2001) has identified five dimensions of cultural differences: ? Given ingroup relation with relatives and community members may have a different impact on professional relationships in different cultures. ? The impact of hierarchical relationships on the freedom of action of trade partners may be different across cultures. ? Some cultures are oriented toward cooperation and care-taking; others are oriented toward performance and competition. ? Xenophobia is a wide-spread phenomenon in some cultures, while people in other cultures may be more open to the unknown. ? In some cultures people are anxious to keep up their status and display their societal success, while in other cultures thrift and perseverance are seen as virtues. Cultural differences may have their effects in trade on the acceptability of potential partners, on progress and success of negotiations, and on the extent to which partners live up to the negotiated contracts. In a research project Meijer (2009) developed a gaming simulation to study the role of trust in supply networks of food products. The game is called the TRUST & TRACING game. In this game, the producers are informed about product quality. The other players either have to trust the suppliers on their quality statements, or they can have the products traced by an independent authority, but the latter will cost them a fee. In addition to the financial considerations, they must take into account that showing distrust may bring damage to their relationships. Experiments with human subjects in different cultures have shown that the considerations lead to different actions in different countries. It was also found that the inclination to grab an opportunity to defect was different across countries. The subject of this thesis is a computer simulation of the TRUST & TRACING GAME. The purposes of the computer simulation are: ? Validation of theories about, implemented in models of, the players’ behaviors ? testing of hypotheses about relations of rules of the game and parameters of individual players with aggregated game statistics, ? the design of useful game configurations to be played with human players. In the computer simulation the players’ rolls are realized by software agents. The questions which are answered in this thesis concern the modeling of culture’s consequences for the decisions taken by the agents. Such an agent is a computer program which simulates the behavior of human players. In a multi-agent simulation a group of software agents is acting and interacting simultaneously. Autonomy is an important property of software agents. The agents decide what to do; there is no central computer program that imposes decisions on them. Important functions of agents in the present simulation are to approach new potential trade partners, to negotiate about a transaction and to exchange proposals, and, when the negotiation has ended successfully, to exchange products, and to decide and request a trace to be performed. The agents’ decision mechanisms are implemented according to models and data available from scientific literature. To model the influence of culture on the decision making, an expert systems approach is taken, using the Synthetic Cultures according to Hofstede en Pedersen (1999). To develop an expert system, knowledge engineers represent knowledge about some domain of application as a set of rules that can be interpreted by a computer system. Since culture is considered as a set of rules, such an approach is a natural way to model it. The development of expert systems always is an interdisciplinary project. In this case the work of Geert Hofstede has been used and an expert on this work and on Synthetic Cultures has been involved in the formulation of the rules. Synthetic Cultures are imaginary cultures in which the effects of a single dimension of culture are emphasized, isolated from the effects of the other dimensions. The purpose is to make the differences related to that dimension teachable. In reality the differences may be less pronounced and may be mixed with differences related with the other dimensions. In this thesis an approach has been elaborated to compute the simultaneous effect of several dimensions. The approach is based on the principle of weak disjunction, which implies that, if several dimensions have a similar effect, only the strongest effects counts. For instance, if dimension A would have an effect of 75% and dimension B would have an effect of 25%, then their simultaneous effect would be 75%. Expert systems must at least have face validity. An expert in the domain of application mustaccept the decisions that the system produces and the reasoning that leads to these decisions, as being believable. For this purpose computations for specific cases can be made, of which the results are judged by the expert. Further, the results of sensitivity analysis can be judged by an expert. Sensitivity analysis of a model is performed by studying how model outputs vary in relation with systematic variation of input parameter. In addition to face validity, the model must be tested empirically. To that end outputs from gaming simulations with human participants can be compared with outputs from multi-agent simulations. For example, Meijer et al. (2006) found different outcomes from the TRUST & TRACING game between games played in the United States and in the Netherlands. Compared with the Dutch, American players are found to be more eager to buy top quality products, have a stronger inclination to opportunism, anticipate to a greater extent on their partners to defect, and have a stronger preference for quality certification. These differences where reproduced by the multi-agent simulation. The main question of this research is, whether an expert systems approach is feasible to develop a valid model of cultural differentiation in multi-agent simulations, to be applied in research with gaming simulations. The conclusions are: 1. Effects of dimensions of culture can be modeled as an expert system based on Synthetic Cultures. Modeling the simultaneous effects of several dimensions as an expert system proved not feasible: the complexity exceeded the intellectual powers of both expert and modeler. 2. The simultaneous effect of several dimensions can be modeled by weak disjunction of effects. The results have face validity and have empirically been verified for a limited number of cases. 3. Sensitivity analysis of this model is a complex undertaking if both cultural parameters and other parameters are simultaneously varied, because of the strong interactions between these types of parameters. When only the culture parameters are varied (with a fixed setting of the other parameters), or only the other parameters are varied (in a fixed cultural setting), straightforward sensitivity analysis is feasible. Furthermore, it was found that the sensitivity of aggregate model outputs may greatly differ from sensitivity of individual level outputs: parameters that do not affect the aggregate system performance, may affect results of individual agents. 4. This thesis proves that multi-agent simulation is a potent instrument to be used in research with gaming simulations, in particular for the purpose of validation of behavioral models. A problematic issue is, that similarity of the outputs of gaming simulations and multi-agent simulations is no sound proof that the agent correctly implements the human decision making mechanism. This issue is known as under-determination. A validation method is proposed, which builds on the model’s composed structure. Under-determination can be avoided by separate validation of the components in micro-games. The results of this research contribute to the methodology of cultural adaptation of intelligent software agents. This is relevant for the development of research instruments (like the TRUST & TRACING game), educational and training applications to make people aware of cultural differences, and affective human-computer interfaces in a globalizing world.","culture; trade partner selection; negotiation; trust; deceit","en","doctoral thesis","","","","","","","","","Electrical Engineering, Mathematics and Computer Science","Mediamatics","","","",""
"uuid:092c8f55-997e-4ed2-884a-efe4992b1ace","http://resolver.tudelft.nl/uuid:092c8f55-997e-4ed2-884a-efe4992b1ace","Towards Robust Visual Speech Recognition: Automatic Systems for Lip Reading of Dutch","Chitu, A.G.","Jonker, C.M. (promotor); Rothkrantz, L.J.M. (promotor)","2010","In the last two decades we witnessed a rapid increase of the computational power governed by Moore's Law. As a side effect, the affordability of cheaper and faster CPUs increased as well. Therefore, many new “smart” devices flooded the market and made informational systems widely spread. The number of users of information systems has also increased many folds, and the user's characteristics have changed to include not only a small number of initiates but also a majority of non technical people. To make this transition possible systems' developers had to change the computer user interfaces in order to make it simpler and more intuitive. However, the interaction was still based on rather artificial devices such as mouse and keyboard. Since the Moore's Law continues to work over and over again we came to a critical moment when the current systems can easily cope with other input streams such as video and audio, to name the most important, and others. We can, therefore, envision systems with which we can communicate through speech and body movements and that can automatically and transparently adapt to the environment and user. This can be done for instance by recognizing the user affective state, by understanding the task of the user and recognizing the context of the interaction. Automatic speech recognition by capturing and processing the audio signal is one development in this direction. Even though in controlled settings automatic speech recognition has achieved spectacular results, its performance is still dependent on the context (for instance on the level of the background noise). Automatic lip reading has appeared in this context as a way to enhance automatic speech recognition in noisy environments. Even though it is still a relatively novel research domain, other applications were found which employ lip reading as stand alone: interfaces for hearing impaired persons, security applications, speech recovery from mute of deteriorated films, silence interfaces. With the advances in visual signal processing the research in lip reading was also revitalized. However, at the moment of writing of this thesis lip reading was still waiting for its great leap. This thesis investigates several techniques for directing lip reading towards more robust performances. The thesis starts by introducing the relevant methodologies that govern automatic lip reading. Next it introduces all the concepts needed to understand the technologies, experiments, results and discussions presented later on. It is, therefore, one of the most important parts of the thesis. The presentation of the state of the art in lip reading is setting the starting point of the research presented. Before, continuing to follow the lip reading process the thesis introduces the mathematical foundations that give the theoretical support for the analysis. All our systems are based on the Hidden Markov Models approach. This paradigm has proved to be very useful in similar problems and we successfully employed it for lip reading. The main idea behind it is the Bayesian rule which says that starting from some a-priori knowledge we can always improve our understanding of a system through observation. Observation translates into processing the video stream in a set of features that describe what is being said by the speaker. However, in order to appropriately train lip reading systems, a large amount of data is needed. The first important contribution of our research is a large data corpus for the Dutch language. This corpus, named “New Delft University of Technology Audio Visual Speech Corpus”, is at the date of writing this thesis one of the largest corpora for lip reading in Dutch. The corpus contains dual view high speed recordings (i.e. 100Hz) of continuous speech in Dutch. During the building of the corpus, we also produced an incipient set of guidelines for building a data corpus for lip reading which we hope to be useful for other researchers. However, the core of this thesis consists in the data parametrization. Data parametrization is the process that transforms the input video data in a set of features that are used later on for training and testing the resulting recognizer. The parametrization should reduce the size of the input data while preserving the most important information related with what the speaker says. We investigated three data parametrization techniques each coming from a different category of algorithms. We used Active Appearance Models which generate a combined geometric and appearance based set of features, we used optical flow analysis which is an appearance based approach that directly accounts for the apparent movement on the speaker's face and we used a statistical approach which generates the geometry of lips without starting from an a-priori fixed model. During the research presented in this thesis we investigated the performances of these data parametrization techniques and we pointed out their strengths and weaknesses. We also analysed the performance of lip reading starting from other points of view. We analysed the influence of the sampling rate of the video data, the performance of the lip readers as a function of the recognition task but also the performance as a function of the size of the corpus used. Answering to all these questions improved our understanding of the limitations and the possible improvements of lip reading.","lip reading; visual apeech recognition; automatic speech recognition; Active Appearance Models; Optical Flow","en","doctoral thesis","","","","","","","","","Electrical Engineering, Mathematics and Computer Science","Mediamatics","","","",""
"uuid:e2c8459b-1370-4950-84e6-600ff13a4766","http://resolver.tudelft.nl/uuid:e2c8459b-1370-4950-84e6-600ff13a4766","Designing Generic and Efficient Negotiation Strategies","Tykhonov, D.","Jonker, C.M. (promotor); Hindriks, K.V. (promotor)","2010","The central aim of this thesis is the design of generic and efficient automated strategies for two-party negotiations in which negotiating parties do not reveal their preferences explicitly. A strategy for negotiation is the decision mechanism for determining the actions of a negotiator. Generic refers to the idea that the strategy needs no forehand knowledge about the opponent or the domain of negotiation. A strategy thus should be generic in the sense that it can be successfully applied to any negotiation domain and fine-tuned to domainspecific features to produce even better results. Efficiency refers to the fact that the strategy should be able to negotiate effectively against another automated agent or human negotiator and obtain an outcome that cannot be improved for both parties. The design of the negotiating strategy that is proposed in this thesis is based on analyses of the state-of- the-art negotiation strategies using an analytical method that is also proposed in this work. The method significantly extends existing negotiation benchmarks by analysing dynamic properties of a negotiation strategy. One of the main findings of the analysis, in line with the management and social science literature on negotiation [20, 23], is that the strategy should learn the opponent’s preferences in order to increase the negotiation efficiency. We applied our results in learning the opponents’ profiles in a one-to-many negotiation setting. We additionally addressed the problem of issue-dependencies. Issue dependencies form an insurmountable barrier for the state of the art negotiation strategies [9]. Therefore, we developed an approximation method to eliminate dependencies. This part of the research seems a side track, however it was fundamental that we address this problem to prove the scalability and applicability of our research results.","","en","doctoral thesis","","","","","","","","","Electrical Engineering, Mathematics and Computer Science","Mediamatics","","","",""
"uuid:920fc493-664d-4fa9-8caa-ae957090df01","http://resolver.tudelft.nl/uuid:920fc493-664d-4fa9-8caa-ae957090df01","Sensing what matters","Van Norden, W.L.","Jonker, C.M. (promotor)","2010","Recently, the Royal Netherlands Navy (RNLN) is executing missions in coastal regions with a lot of civil traffic. Furthermore, the opponent of a typical modern mission is not as apparent as was the case during e.g., the Cold War. In the direct vicinity of naval vessels are many objects and it is increasingly complex to identify which of those objects pose a threat. This is the main reason for the need of decision support and automation aboard RNLN’s ships. This thesis introduces a new classification methodology that is suited for the military application domain. This methodology is based on fitting the incoming sensor information on predefined situation knowledge inserted by the operator. To verify the performance new evaluation criteria are introduced that are suited for the characteristics of the application domain. Multiple classifiers result from this new methodology and their results are combined using Dezert-Smarandache Theory. The performance gain of this new approach is shown in a simulation and using existing and new evaluation criteria compared to other known classifiers. The system introduced in this thesis additional has advantages in terms of user interaction. Furthermore, this new system enables the automation of describing the information requirements for classification. This in turn enables the automation of sensor management processes. Finally, this thesis argues that it is essential to integrate existing sensor performance programs in order to automate sensor management.","Classification; Sensor Management; Dezert-Smarandache Theory; Conflict Redistribution","en","doctoral thesis","","","","","","","","2010-02-16","Electrical Engineering, Mathematics and Computer Science","Man-Machine Interaction Group","","","",""