H. J. van den Herik

Maastricht University, Maastricht, Provincie Limburg, Netherlands

Are you H. J. van den Herik?

Claim your profile

Publications (51)23.43 Total impact

  • A Latoszek-Berendsen, H Tange, H J van den Herik, A Hasman
    [Show abstract] [Hide abstract]
    ABSTRACT: Guidelines are among us for over 30 years. Initially they were used as algorithmic protocols by nurses and other ancillary personnel. Many physicians regarded the use of guidelines as cookbook medicine. However, quality and patient safety issues have changed the attitude towards guidelines. Implementing formalized guidelines in a decision support system with an interface to an electronic patient record (EPR) makes the application of guidelines more personal and therefore acceptable at the moment of care. To obtain, via a literature review, an insight into factors that influence the design and implementation of guidelines. An extensive search of the scientific literature in PubMed was carried out with a focus on guideline characteristics, guideline development and implementation, and guideline dissemination. We present studies that enable us to explain the characteristics of high-quality guidelines, and new advanced methods for guideline formalization, computerization, and implementation. We show how the guidelines affect processes of care and the patient outcome. We discuss the reasons of low guideline adherence as presented in the literature and comment upon them. Developing high-quality guidelines requires a skilled team of people and sufficient budget. The guidelines should give personalized advice. Computer-interpretable guidelines (CIGs) that have access to the patient's EPR are able to give personal advice. Because of the costs, sharing of CIGs is a critical requirement for guideline development, dissemination, and implementation. Until now this is hardly possible, because of the many models in use. However, some solutions have been proposed. For instance, a standardized terminology should be imposed so that the terms in guidelines can be matched with terms in an EPR. Also, a dissemination model for easy updating of guidelines should be established. The recommendations should be based on evidence instead of on consensus. To test the quality of the guideline, appraisal instruments should be used to assess the guideline as a whole, as well as checking the quality of the recommendations individually. Only in this way optimal guideline advice can be given on an individual basis at a reasonable cost.
    Methods of Information in Medicine 11/2010; 49(6):550-70. · 1.08 Impact Factor
  • H. J. van den Herik, E. O. Postma
    Journal of Intellectual Disability Research - J INTELLECT DISABIL RES. 01/2009;
  • E. N. Smirnov, H. J. van den Herik
    [Show abstract] [Hide abstract]
    ABSTRACT: The paper considers conjunctive and disjunctive version spa- ce learning as an incomplete search in complete hypotheses spaces. The incomplete search is guided by preference biases which are implemented by procedures based on the instance-based boundary sets representation of version spaces. The conditions for tractability of this representation are defined. As a result we propose to use instance-based boundary sets as a basis for the computationally feasible application of preference biases to version spaces.
    11/2008: pages 321-331;
  • S. C. J. Bakkes, P. H. M. Spronck, H. J. van den Herik
    Bijdragen. 01/2008;
  • Source
    01/2007;
  • Source
    L J P Van Der Maaten, E O Postma, H J Van Den Herik
    [Show abstract] [Hide abstract]
    ABSTRACT: In recent years, a variety of nonlinear dimensionality reduction techniques have been proposed that aim to address the limitations of traditional techniques such as PCA. The paper presents a review and systematic comparison of these techniques. The performances of the nonlinear techniques are investigated on artificial and natural tasks. The results of the experiments reveal that nonlinear techniques perform well on selected artificial tasks, but do not outperform the traditional PCA on real-world tasks. The paper explains these results by identifying weaknesses of current nonlinear techniques, and suggests how the performance of nonlinear dimensionality reduction techniques may be improved.
    Journal of Machine Learning Research - JMLR. 01/2007;
  • Source
    G De Croon, E O Postma, H J Van Den Herik
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper shows that sensory-motor coordination contributes to the performance of situated models on the high-level task of artificial gaze control for gender recog-nition in static natural images. To investigate the advantage of sensory-motor coor-dination, we compare a non-situated model of gaze control with a situated model. The non-situated model is incapable of sensory-motor coordination. It shifts the gaze according to a fixed set of locations, optimised by an evolutionary algorithm. The situated model determines gaze shifts on the basis of local inputs in a visual scene. An evolutionary algorithm optimises the model's gaze control policy. In the experiments performed, the situated model outperforms the non-situated model. By adopting a Bayesian framework, we show that the mechanism of sensory-motor coordination is the cause of this performance difference. The essence is that the mechanism maximises task-specific information in the observations over time, by establishing dependencies between multiple actions and observations.
    Pattern Recognition Letters 08/2006; 27. · 1.27 Impact Factor
  • Source
    01/2006;
  • Source
    H J Van Den Herik, H H L M Donkers, P H M Spronck
    [Show abstract] [Hide abstract]
    ABSTRACT: To play a game well a player needs to under-stand the game. To defeat an opponent, it may be suf-ficient to understand the opponent's weak spots and to be able to exploit them. In human practice, both ele-ments (knowing the game and knowing the opponent) play an important role. This article focuses on opponent modelling independent of any game. So, the domain of interest is a collection of two-person games, multi-person games, and commercial games. The emphasis is on types and roles of opponent models, such as specula-tion, tutoring, training, and mimicking characters. Vari-ous implementations are given. Suggestions for learning the opponent models are described and their realization is illustrated by opponent models in game-tree search. We then transfer these techniques to commercial games. Here it is crucial for a successful opponent model that the changes of the opponent's reactions over time are adequately dealt with. This is done by dynamic script-ing, an improvised online learning technique for games. Our conclusions are (1) that opponent modelling has a wealth of techniques that are waiting for implementa-tion in actual commercial games, but (2) that the games' publishers are reluctant to incorporate these techniques since they have no definitive opinion on the successes of a program that is outclassing human beings in strength and creativity, and (3) that game AI has an entertain-ment factor that is too multifaceted to grasp in reason-able time.
    01/2005;
  • Source
    G De, Croon E O Postma, H J Van Den Herik
    [Show abstract] [Hide abstract]
    ABSTRACT: There are two main approaches to active vision for classification. The probabilistic approach employs a belief state concerning the class of the in-stance and selects actions to reduce uncertainty in the belief state. The situated approach directly learns a mapping from observations to actions (including the classification), driven by the performance on the classification task. One of the advantages of the probabilistic approach is that its action selection takes uncertainty into account. In this paper, we show that the situated approach also takes uncertainty into account in its action selection. To this end, we investigate how a situated gaze-control model without any memory can improve its performance over time in a classification task. We show that it does so by reducing the entropy of the posterior distributions of the possible observations. In this manner, the situated gaze-control model reduces class uncertainty in its observations. In addition, we show that the fixation location of the model serves as a memory of previous observations, which allows the memory-less model to verify conjunctions and disjunctions of facial properties.
    01/2005;
  • F. Wiesman, H. J. van den Herik, A. Hasman
    [Show abstract] [Hide abstract]
    ABSTRACT: This article investigates a new, effective browsing approach called metabrowsing. It is an alternative for current information retrieval systems, which still face six prominent difficulties. We identify and classify the difficulties and show that the metabrowsing approach alleviates the difficulties associated with query formulation and missing domain knowledge. Metabrowsing is a high-level way of browsing through information: instead of browsing through document contents or document surrogates, the user browses through a graphical representation of the documents and their relations to the domain. The approach requires other cognitive skills from the user than what is currently required. Yet, a user evaluation in which the metabrowsing system was compared with an ordinary query-oriented system showed only some small indicatory differences in effectiveness, efficiency, and user satisfaction. We expect that more experience with metabrowsing will result in a significantly better performance difference. Hence, our conclusion is that the development of new cognitive skills requires some time before the technologies are ready to be used. © 2005 Wiley Periodicals, Inc.
    Journal of the American Society for Information Science and Technology 05/2004; 55(7):565-578. · 2.01 Impact Factor
  • M. H. M. Winands, H. J. van den Herik, J. W. H. M. Uiterwijk
    [Show abstract] [Hide abstract]
    ABSTRACT: Lines of Action (LOA) is a two-person zero-sum chess-like connection game. Building an evaluation function for LOA is a difficult task because not much knowledge about the game is available. In this paper the evaluation function of the tournament program MIA is explained. This evaluator consists of the following nine features: concentration, centralisation, centre-of-mass position, quads, mobility, walls, connectedness, uniformity, and player to move. These features have resulted in the evaluator MIA IV. The evaluator is tested in a tournament against other LOA evaluators, which have performed well at the previous Computer Olympiads. Experiments show that MIA IV defeats them with large margins. It turns out that the evaluator even performs better at deeper searches.
    10/2003;
  • [Show abstract] [Hide abstract]
    ABSTRACT: this paper I argue that the applicability of the technology is very limited, because it presupposes that such a question has some legal facts (a set of applicable rules, or cases) as its answer. It has not. Answering legal questions-also called legal information serving- involves making inferences about the world and about the structure of a regulation, as can be shown by analysing these questions. Legal information serving is more complex than typical problem solving, because no fixed, domain-independent methods appear to be used. However, in a legal reasoning architecture where reasoning about the world is not mixed with reasoning about applying the regulations, a non-combinatorial, tractable solution can be found. This is the more so, when reasoning about the world can be limited to its superficial, terminological structures
    01/2003;
  • Source
    H H L M Donkers, J W H M Uiterwijk, H J Van Den Herik
    [Show abstract] [Hide abstract]
    ABSTRACT: Opponent-model (OM) search comes with two types of risk. The first type is caused by a playerÕs imperfect knowledge of the opponent, the second type arises from low-quality evaluation functions. In this paper, we investigate the desirability of a precon-dition, called admissibility, that may prevent the second type of risk. We examine the results of two sets of experiments: the first set is taken from the game of LOA, and the second set from the KQKR chess endgame. The LOA experiments show that when admissibility happens to be absent, the OM results are not positive. The chess experi-ments demonstrate that when an admissible pair of evaluation functions is available, OM search performs better than minimax, provided that there is sufficient room to make errors. Furthermore, we conclude that the expectation Ôthe better the quality of the prediction of the opponentÕs move, the more successful OM search isÕ is only true if the quality of both evaluation functions is sufficiently high.
    Information Sciences 01/2003; 154. · 3.64 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper investigates to what extent learning methods are beneficial for the Lines of Action tournament program MIA. We focus on two components of the program: (1) the evaluation function and (2) the move ordering.
    11/2002;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Efficient instance retraction is a difficult problem for concept learning by version spaces. In this report, two new version-space representations are introduced: instance-based maximal boundary sets and instance-based minimal boundary sets. They are correct representations for the class of admissible concept languages and are efficiently computable.
    06/2002;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This report proposes adaptable boundary sets as a new version-space representation. It is shown that adaptable boundary sets can be adjusted to a version-space representation between boundary sets [5, 6, 7] and instance-based boundary sets [11, 12, 13]. This allows the choice of proper version-space representations to be realised dynamically during the learning phase. 1
    01/2002;
  • Source
    H.Jaap van den Herik, Jos W.H.M. Uiterwijk, Jack van Rijswijck
    [Show abstract] [Hide abstract]
    ABSTRACT: In this article we present an overview on the state of the art in games solved in the domain of two-person zero-sum games with perfect information. The results are summarized and some predictions for the near future are given. The aim of the article is to determine which game characteristics are predominant when the solution of a game is the main target. First, it is concluded that decision complexity is more important than state-space complexity as a determining factor. Second, we conclude that there is a trade-off between knowledge-based methods and brute-force methods. It is shown that knowledge-based methods are more appropriate for solving games with a low decision complexity, while brute-force methods are more appropriate for solving games with a low state-space complexity. Third, we found that there is a clear correlation between the first-player's initiative and the necessary effort to solve a game. In particular, threat-space-based search methods are sometimes able to exploit the initiative to prove a win. Finally, the most important results of the research involved, the development of new intelligent search methods, are described.
    Artificial Intelligence 01/2002; · 2.19 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Instance retraction is a difficult problem for concept learning by version spaces. In this paper, two new version-space representations are introduced: instance-based maximal boundary sets and instancebased minimal boundary sets. They are correct representations for the class of admissible concept languages and are efficiently computable. Compared to other representations, they are the most efficient practical version-space representations for instance retraction.
    12/2001: pages 275-296;
  • E. N. Smirnov, H. J. Herik
    [Show abstract] [Hide abstract]
    ABSTRACT: The choice of a representation is critical for version spaces when implemented.
    07/2001;

Publication Stats

517 Citations
23.43 Total Impact Points

Institutions

  • 1988–2010
    • Maastricht University
      • • CAPHRI School for Public Health and Primary Care
      • • Department of Knowledge Engineering
      • • Faculty of Humanities and Sciences
      Maastricht, Provincie Limburg, Netherlands
  • 1994–1998
    • Leiden University
      Leyden, South Holland, Netherlands