Field Of Knowledge Acquisition Research Articles

Informative and Affective Determinants of Pro-Innovative Behaviours

Purpose: The aim of this article is to provide a comprehensive analysis of those conditions conducive to employee creativity, expressed in the development of ideas, as well as the initiation and continuation of such activities, leading to the implementation of an innovative solution. Design/Methodology/Approach: The research was of a qualitative character, and was based on interviewing the authors of those solutions which meet the assumed criteria. Findings: The research allowed us to identify the cognitive and affective determinants of the creative processes and of their transformation into the implementation of innovative solutions. The research has also shown the high importance of the process of organisational knowledge, and the catalysing influence that the fact of acquiring knowledge from external sources had on the creative processes themselves. The factors influencing the induction and maintenance of the useful emotional state of the authors of the ideas are also indicated. The emotions turned out to be important both for taking the initiative and for continuing the process of implementing the idea in practice. The research also showed the specific role that intrinsic and extrinsic motivation played in the initiation and implementation of the initiative. Practical implications: The article indicates those organisational conditions which are conducive to the development of ideas and to the taking of initiative to transform them into innovative organisational solutions. The research also shows the role of both intrinsic and extrinsic motivation in undertaking such creative and innovative activities. Attention is also paid to the influence that the practices of the authors of the projects themselves in the field of knowledge acquisition had on the dynamics of the innovation process. Originality/Value: The article focuses on the transformation of a result of the creative process, namely, the idea of an individual employee, into an innovative organisational process. As a result, such work combines the issues of individual creativity and organisational innovation, which are usually discussed separately. It also helps us understand the conditions necessary for the transformation of spontaneous ingenuity into worthwhile solutions.

An experimental investigation of knowledge acquisition techniques

PurposeKnowledge is a key driver for the competitive success of organizations, but about 90 percent of organizational knowledge is inside employees’ minds with personal essence; therefore, this paper provides valuable vision for managers by exploring knowledge acquisition (KA) techniques and personality type. The purpose of this paper is to examine KA techniques and explore the impact of personality type on the KA process in the aerospace industry.Design/methodology/approachThis paper examines KA techniques through an empirical study involving 83 participants to take part in KA sessions. For exploring techniques, a questionnaire was used, and also the Myers-Briggs Type Indicator was used to identify participants’ personality type. The impact of personality type on KA processes was determined by correlation analysis.FindingsAnalyses confirmed some association between the type of personality and KA process. In addition, the findings of exploring questionnaire items showed that participants gave the laddering technique the highest rating.Originality/valueThe paper may be of high value to researchers in the field of KA, especially in aerospace industries, because there is very little experimental investigation of KA, and it also provides valuable information and guidelines that hopefully will help researchers to select appropriate KA techniques.

Computer system to support medication reviews: a good but not new concept

In their recent article, de Wit and colleagues put forward a solid argument for the use of clinical decision support systems to support medication reviews for the elderly [1]. They point out that medication reviews are routinely performed, and they have positive effects in terms of reducing medication-related problems. They also rightly note that the quality of the findings and recommendations contained within these medication reviews are only going to be as good as the knowledge and skills of the professionals performing them. They then argue that a clinical decision support system using clinical rules that combine the available pharmacy, clinical and laboratory data may be able to improve the delivery of medication reviews. This we also accept. The authors then assert that doing this would be a ‘‘new approach’’, and outline a simple plan for how they intend to develop this innovative system. In their conclusions, they state ‘‘In our opinion the development of a system, which is able to reduce the time-consuming process of a traditional medication review and create high-quality suggestions for therapy optimisation, will be unique.’’ We wish to highlight that this approach is not unique. Over the past 8 years, we have developed and evaluated systems that can provide intelligent clinical decision support for medication reviewers, and have presented the results at a range of conferences and in international publications [2–4]. In these publications we described the rationale for and the implementation of an advanced system that allows expert medication reviewers to seamlessly and naturally build complex rules based on a patient’s biographical details, medications, medical history, and laboratory results, while performing their routine medication review duties. The approach we used for doing this is based on recent advances in the field of knowledge acquisition (a sub-field of artificial intelligence). This approach allows the expert to iteratively build up and refine a large and complex set of rules that are automatically used to identify medication-related problems. If the system ever identifies a problem that the expert disagrees with, or otherwise fails to identify a problem the expert has detected, the expert is asked to indicate what the problem should have been and why. In this way the system learns over time and the recommendations are highly individualised. Importantly, with this approach, very few false positives are identified, as the system’s knowledge is gradually refined such that problems are only identified when it is definitely appropriate to do so in the particular case. Even when best practice suddenly changes, the system is easily updated to reflect the newest information [3]. With relatively little training our system was capable of identifying approximately 90 % of all medication-related problems for a patient. Importantly, the system was capable of identifying problems that the expert had missed or incorrectly classified (errors). On average, we found that the system prevented the expert from making 2.02 errors per patient [2]. Furthermore, our approach was incorporated into a commercially available system to support medication reviewers. This product has since been used by pharmacists to perform more than 50,000 medication reviews. We have also compared the medication-related problems found by this product against original pharmacist’s findings, and even against the findings found by applying the STOPP/ START guidelines [4, 5]. A 12 member expert panel consisting of accredited medication review pharmacists, I. K. Bindoff (&) G. M. Peterson C. Curtain School of Pharmacy, University of Tasmania, Hobart, Tasmania, Australia e-mail: Ivan.Bindoff@utas.edu.au

INCREMENTAL DEVELOPMENT OF DIAGNOSTIC SET-COVERING MODELS WITH THERAPY EFFECTS

Although a lot of work in the field of knowledge acquisition has been done, the manual development of diagnostic knowledge systems by domain experts still is a very complex task. In this paper we will present an incremental approach for building diagnostic systems based on set-covering models. We start with a simple model describing the coarse structure between diagnoses and findings. Subsequently, this simple model can be euhanced by similarities, weights and probabilities to increase the accuracy of the knowledge and the resulting system. We will also show how these static set-covering models can be combined with dynamic set-covering models including higher level knowledge about causation effects. We will motivate how dynamic set-covering models can be used for implementing diagnostic systems including therapy effects. Finally, we report on two practical applications dealing with set-covering models from the geo-ecological and from the medical domain, respectively, that we have implemented.

Rationality and Use of Information in Policy Decisions

In the field of knowledge acquisition, dissemination, and utilization/impact, few studies have examined the appropriateness of rational actor theories as a theoretical framework. Rather, the rational actor perspective has been simply taken for granted as a relevant analytical tool for explaining the use of information in policymaking. This article singles out one major set of assumptions imbedded in rational actor theories, those dealing with information acquisition and processing in individual decisionmaking, and empirically examines to what extent the assumptions are realistic. It then puts forward an organizational interest and a communications perspective as alternative explanations for information processing in individual and organizational decisionmaking. The findings of this article show that decisionmakers' behavior does not conform to the assumptions put forward by the rational actor theorists. Instead, the organizational interest perspective is far more promising in accounting for the actual behavior of individuals in processing information in making policy decisions.

Providing understanding of the behavior of feedforward neural networks

The advent of artificial neural networks has stirred the imagination of many in the field of knowledge acquisition. There is an expectation that neural networks will play an important role in automating knowledge acquisition and encoding, however, the problem solving knowledge of a neural network is represented at a subsymbolic level and hence is very difficult for a human user to comprehend. One way to provide an understanding of the behavior of neural networks is to extract their problem solving knowledge in terms of rules that can be provided to users. Several papers which propose extracting rules from feedforward neural networks can be found in the literature, however, these approaches can only deal with networks with binary inputs. Furthermore, certain approaches lack theoretical support and their usefulness and effectiveness are debatable. Upon carefully analyzing these approaches, we propose a method to extract fuzzy rules from networks with continuous-valued inputs. The method was tested using a real-life problem (decision-making by pilots involving combat situations) and found to be effective.

An Analysis of Knowledge Acquisition Roles and Participants

Much recent research effort in the field of knowledge acquisition (KA) has focussed on extending knowledge acquisition techniques and processes to include a wider array of participants and knowledge sources in a variety of knowledge acquisition scenarios. As the domain of expert systems applications and research has expanded, techniques have been developed to acquire and incorporate knowledge from groups of experts and from various sources such as text, video, and audio tapes. However, the dominant participant‐role model remains that of the knowledge engineer eliciting knowledge from one or more human experts. This conceptual gap has contributed to the major divisions in the KA field between researchers interested in manual KA and those developing tools for automated KA. This article considers the wide variety of possible KA scenarios and presents a meta‐view of KA participants and the roles they may assume.We suggest that it is more appropriate to think of knowledge acquisition participants as playing one or more roles. These include knowledge sources, agents and targets for KA processes. We also present a participant model drawn from research in decision support systems that more accurately characterizes the diversity of the entities participating in the KA process. This view is more inclusive as it allows us to consider both human‐human and human‐computer KA interactions as well as the whole variety of knowledge sources and targets. A careful consideration of the meta‐view and its associated role‐participant mappings also yields the new ideas of the elemental and composite role and the multi‐role entity. These new constructs are then used to identify areas where research is currently needed and to generate specific research issues. Taken altogether, this view allows a more flexible consideration of the many possible combinations that can and frequently do occur in actual KA situations.

Enhance the automatic acquisition of knowledge

The first part of this paper gives a short review of the research work done in the field of knowledge acquisition. The second and third parts describe two sets of tools for knowledge, which are designed and implemented by a research group led by the author.