Integration Of Expert Knowledge Research Articles

An Evaluation of an Object-Oriented Paradigm for Land Use/Land Cover Classification*

Object-oriented image classification has tremendous potential to improve classification accuracies of land use and land cover (LULC), yet its benefits have only been minimally tested in peer-reviewed studies. We aim to quantify the benefits of an object-oriented method over a traditional pixel-based method for the mixed urban–suburban–agricultural landscape surrounding Gettysburg, Pennsylvania. To do so, we compared a traditional pixel-based classification using maximum likelihood to the object-oriented image classification paradigm embedded in eCognition Professional 4.0 software. This object-oriented paradigm has at least four components not typically used in pixel-based classification: (1) the segmentation procedure, (2) nearest neighbor classifier, (3) the integration of expert knowledge, and (4) feature space optimization. We evaluated each of these components individually to determine the source of any improvement in classification accuracy. We found that the combination of segmentation into image objects, the nearest neighbor classifier, and integration of expert knowledge yields substantially improved classification accuracy for the scene compared to a traditional pixel-based method. However, with the exception of feature space optimization, little or no improvement in classification accuracy is achieved by each of these strategies individually.

Operationalising the implementation puzzle: an argument for eclecticism in research and in practice

Efforts to implement organizational information systems (IS) have evolved through the years from purely technical processes to multi-faceted organizational change activities. Largely in reaction to implementation failures, numerous research models have been developed to prescribe appropriate implementation strategies and tactics. A multiple of such contributions has made the theory quite diverse and somewhat chaotic. This paper presents a survey of implementation models, research approaches, and investigation methods that have surfaced in the literature of the field. Using an implementation framework of Swanson (1988), an eclectic perspective of IS research, and an expert knowledge integration approach, a perspective is proposed that demonstrates the possibility of a unified view of IS implementation theory.

Likelihood-based image segmentation and classification: a framework for the integration of expert knowledge in image classification procedures

This paper describes a likelihood-based segmentation and classification method for remotely sensed images. It is based on optimization of a utility function that can be described as a cost-weighted likelihood for a collection of objects and their parameters. As the likelihood or posterior probabilities are calculated per object rather than per pixel, the variance in (spectral) likelihoods will be greatly reduced. From a user's point of view the result was either a maximum probability for truth (likelihood) or maximum utility (benefit). The method includes a new approach for segmentation, which is based on criteria derived from local average likelihoods, instead of local means or variances, making the segmentation method much less sensitive to radiometric outliers. As likelihoods are defined in the probability for spectral class domain, the method avoids problems with the segmentation of multi-spectral data encountered in methods based on edge detection. Due to these capabilities, the method represents a significant step towards operationalization of remote sensing. This approach can also be seen as a framework for integration of external knowledge with image classification procedures. To evaluate the concept, a software tool was designed and used for experimentation. The result showed that per-object maximum likelihood performs much better than the per-pixel method. It led to higher classification accuracy and explicit utilization of the geometrical and topological information about land use objects and land use processes. For generation and testing of the geometric models, the problem of deforestation in Thailand was used.

KNOWLEDGE UTILIZATION IN WATER MANAGEMENT IN THE NETHERLANDS RELATED TO DESICCATION1

ABSTRACT: The use of scientific knowledge in environmental policy making is an important topic. However, the relation between knowledge producers and policy makers is not a straightforward producer‐user relationship. The development of a national desiccation policy in the Netherlands and the implementation of desiccation plans in local situations are used as a case study to investigate the knowledge policy relationship. Three theoretical explanations were used to analyze this case: a difference between the cultures of producers and users; a different rationality of the policy making and research processes; and processes of social construction of problem definitions which imply that different knowledge stocks are used depending on the framing of the policy problem. Emergence of the policy issue at the national level is demonstrated to develop in close interaction between knowledge producers and policy makers, while the interactions at the local level were more based on integration of expert knowledge through personal expertise and closely tied to the development of management plans. This case study thus reveals a difference between general knowledge supporting measures at the national policy level and the way in which specific knowledge is applied in local cases. Therefore more attention should be paid to the translation of policy problems from rather high levels of political authority to the conceptualization at lower management levels. A final conclusion is that knowledge use in Dutch desiccation policy can be understood by pointing to multiple theoretical perspectives. The rational actor model and a construc‐tivist perspective turned out to be especially useful in explaining the different ways knowledge was used at the national and the local level.

The integration of expert knowledge in decision support systems for facility location planning

The integration of expert systems in DSS has led to a new generation of systems commonly referred to as knowledge-based or intelligent DSS. This paper investigates the use of expert system technology for the development of a knowledge-based DSS for the planning of retail and service facilities. The forms of knowledge involved in planning tasks are identified and organized in four layers. The layers describe the states and events in the facility system (the domain layer), their interrelationships (the inferential layer), procedures for solving well-defined subproblems (the task layer) and strategies for approaching the overall problem (the strategic layer). The potentials of decision tables for representing qualitative and complex knowledge is discussed and illustrated with applications in the field of retail planning. It is shown that expert knowledge from each of the four layers can be used to improve the modelling capabilities and intelligence of a DSS. The result is a powerful and flexible DSS that supports planning at the domain, inferential, task and strategic level dependent on the preference of the decision maker and characteristics of the problem.

Integration of expert knowledge and simulation tools for the thermal design of buildings and energy systems

SETIS is a computer support for thermal design of buildings. Starting at the initial stage of the design process, it deals with the envelope of the building and its HVAC system. This project is managed by OCGR, a French civil engineering firm, and the Laboratoire Equipement de l'Habitat de l'INSA. This collaboration is very important. SETIS is defined as a tool integrating both algorithmic programs and knowledge-based parts onto the same database, where a thermal description of the building to be designed is stored. The second aspect of SETIS is its decision-making ability: a supervisor can suggest modifications or actions to the designer in order to keep the description of his project consistent, or to achieve a specific design goal previously fixed by the user himself.

Avalanche modelling and integration of expert knowledge in the ELSA system

The choice of the best protection system against avalanches on a particular path requires an accurate description, or image, of these avalanches. In order to get this image, avalanche consultants can use several numerical models which are often difficult to handle. Moreover, these models deal only with a part of the phenomena involved in avalanches and ignore the others. As a result, the consultants must use their experience and knowledge to imagine the avalanches on any particular path. This paper presents ELSA (Etude et Limites de Sites Avalancheux), a computer system dedicated to the modelling of the knowledge of avalanche experts and to the integration of the new symbolic computer models with the classical numerical models. The basic aim of integration is to build a unique computer system incorporating all these models. After a description of the terrain representation, we present the different scenarios that ELSA takes into account. Then, the methods which deal with some phenomena occurring in avalanches are described. The problems involved in the integration of these methods close this paper.

Avalanche modelling and integration of expert knowledge in the ELSA system

The choice of the best protection system against avalanches on a particular path requires an accurate description, or image, of these avalanches. In order to get this image, avalanche consultants can use several numerical models which are often difficult to handle. Moreover, these models deal only with a part of the phenomena involved in avalanches and ignore the others. As a result, the consultants must use their experience and knowledge to imagine the avalanches on any particular path.This paper presents ELSA (Etude et Limites de Sites Avalancheux), a computer system dedicated to the modelling of the knowledge of avalanche experts and to the integration of the new symbolic computer models with the classical numerical models. The basic aim of integration is to build a unique computer system incorporating all these models.After a description of the terrain representation, we present the different scenarios that ELSA takes into account. Then, the methods which deal with some phenomena occurring in avalanches are described. The problems involved in the integration of these methods close this paper.

Expert systems for multivariate calibration, trendsetters for the wide-spread use of chemometrics

Abstract Gerritsen, M., Van Leeuwen, J.A., Vandeginste, B.G.M., Buydens, L. and Kateman, G., 1992. Expert systems for multivariate calibration, trendsetters for the wide-spread use of chemometrics, Chemometrics and Intelligent Laboratory Systems , 15:171–184. Chemometrics is less applied in practice than desirable. One of the reasons is the lack of software tools that allow an easy application of chemometrics by non-experts. A possible solution to this problem is the integration of expert systems with software for data analysis. This is illustrated with an example on high-performance liquid chromatography—ultraviolet data analysis. The integration of expert knowledge with chemometrical software will probably become an important future trend in chemometrical research as it is not restricted to multivariate data analysis.

Integration of expert knowledge into the machinery of government

Integration of expert knowledge into the machinery of government

Integration of expert knowledge into the machinery of government

Integration of expert knowledge into the machinery of government

Integration of expert knowledge into the machinery of government

Integration of expert knowledge into the machinery of government

On the integration of expert knowledge into the machinery of government.

To those who were members of Medical Planning Com mission of 1941-2 present state of National Health Service cannot but give rise to concern. That a plan, essentially similar to that then produced, should have sufficed in 1948 to get such a radically new undertaking off ground, and sustain it for more than a decade, is a good indication that, so far as it went, it was on right lines. Over more recent years, however, Service has experienced a diversity of difficulties. This state of affairs is usually attributed primarily to financial stringency. That is a comforting thought, for it implies that our difficulties will largely disappear when this ameliorates. But is not this too facile a diagnosis ? Shortage of funds may create problems for a service; but it does not create problems in it. It merely aggravates those that, actually or potentially, were already there. Is it not possible, therefore, that difficulties under which NHS is now labouring derive from something more fundamental ? Might it not be that those who originally planned service, in their preoccupation with what seemed to them most pressing questions, overlooked some basic requirement and that consequences of their having done so are now coming home to roost ? Looking back with this possibility in mind, I have been repeatedly reminded of a consideration which that wise old man, Dawson of Penn, persistently pressed on our attention. This was, so he contended, that the greatest problem facing modern civilisation is that of integrating expert knowledge into machinery of government. At time, however, we were so obsessed with overcoming obstacles to transforming what was then a parochially based service into a national one and ensuring that this provided a full career in clinical, as distinct from administrative, medicine that significance of what he was saying did not register with us. As a result we failed?or so I now think?to pay sufficient attention to central organisation required by service we were bent on creating. Accordingly, even at this late date, it may be worthwhile to look again at this aspect of matter.