Competence Models and the Maintenance Problem

Case-based reasoning (CBR) systems solve problems by retrieving and adapting the solutions to similar problems that have been stored previously as a case base of individual problem solving episodes or cases. The maintenance problem refers to the problem of how to optimize the performance of a CBR system during its operational lifetime. It can have a significant impact on all the knowledge sources associated with a system (the case base, the similarity knowledge, the adaptation knowledge, etc.), and over time, any one, or more, of these knowledge sources may need to be adapted to better fit the current problem-solving environment. For example, many maintenance solutions focus on the maintenance of case knowledge by adding, deleting, or editing cases. This has lead to a renewed interest in the issue of case competence, since many maintenance solutions must ensure that system competence is not adversely affected by the maintenance process. In fact, we argue that ultimately any generic maintenance solution must explicitly incorporate competence factors into its maintenance policies. For this reason, in our work we have focused on developing explanatory and predictive models of case competence that can provide a sound foundation for future maintenance solutions. In this article we provide a comprehensive survey of this research, and we show how these models have been used to develop a number of innovative and successful maintenance solutions to a variety of different maintenance problems.     

‘Adaptive’ and ‘Cooperative’ computer systems — A challenge for sociological research

The vision of the new generation of office systems is based on the hypothesis that an automatic support system is all the more useful and acceptable, the more systems behaviour and performance are in accordance with features ofhuman behaviour. Consequently recent development activities are influenced by the paradigm of the computer as man's “cooperative assistant”. The metaphors ofassistance andcooperation illustrate some major requirements to be met by new office systems. Cooperative office systems will raise a set of new questions about the future of human work, human-machine interaction, the forms of individual control of work, the scope of action and the development of competence in the frame of AI-supported cooperative work, the relative benefits of different types of organizations, etc. With increasing autonomy of the computer in task accomplishment, research should also be concerned with the question of the limits of such a development. In AI-research and development there is much discussion of the intended performance of that new technology. Perhaps this will provide insights into, how these new machines should support numerous aspects of individual or cooperative work. But we find fewer ideas about the future ofhuman work. What will the role of thehuman actor be in future AI-supported cooperative work? What kind of work do we want to support with AI-machines? In the following article I will try to identify some questions for further sociological research activities. I will base my considerations on some theoretical aspects ofunderstanding andmeaning. Regarding identical and non-identical aspects in communication behaviour of human and machines, I will focus on some questions to be investigated. Finally some methodological problems of sociological research in the field of Artificial Intelligence will be discussed, especially the so-called “Time-Dilemma” of sociological research in technology.     

A self-learning fuzzy discrete event system for HIV/AIDS treatment regimen selection.

The U.S. Department of Health and Human Services Human Immunodeficiency Virus (HIV)/Acquired Immune Deficiency Syndrome (AIDS) treatment guidelines are modified several times per year to reflect the rapid evolution of the field (e.g., emergence of new antiretroviral drugs). As such, a treatment-decision support system that is capable of self-learning is highly desirable. Based on the fuzzy discrete event system (FDES) theory that we recently created, we have developed a self-learning HIV/AIDS regimen selection system for the initial round of combination antiretroviral therapy, one of the most complex therapies in medicine. The system consisted of a treatment objectives classifier, fuzzy finite state machine models for treatment regimens, and a genetic-algorithm-based optimizer. Supervised learning was achieved through automatically adjusting the parameters of the models by the optimizer. We focused on the four historically popular regimens with 32 associated treatment objectives involving the four most important clinical variables (potency, adherence, adverse effects, and future drug options). The learning targets for the objectives were produced by two expert AIDS physicians on the project, and their averaged overall agreement rate was 70.6%. The system's learning ability and new regimen suitability prediction capability were tested under various conditions of clinical importance. The prediction accuracy was found between 84.4% and 100%. Finally, we retrospectively evaluated the system using 23 patients treated by 11 experienced nonexpert faculty physicians and 12 patients treated by the two experts at our AIDS Clinical Center in 2001. The overall exact agreement between the 13 physicians' selections and the system's choices was 82.9% with the agreement for the two experts being both 100%. For the seven mismatched cases, the system actually chose more appropriate regimens in four cases and equivalent regimens in another two cases. It made a mistake in one case. These (preliminary) results show that 1) the System outperformed the nonexpert physicians and 2) it performed as well as the expert physicians did. This learning and prediction approach, as well as our original FDESs theory, is general purpose and can be applied to other medical or nonmedical problems.     

A new breast tumor ultrasonography CAD system based on decision tree and BI-RADS features

In this paper, we present a novel computer-aided diagnostic (CAD) system based on the Breast Imaging Reporting and Data System (BI-RADS) terminology scores of screening ultrasonography (US). The decision tree algorithm is adopted to analyze the BI-RADS information to differentiate between the malignant and benign breast tumors. Although many ultrasonography CAD systems have been developed for decades, there are still some problems in clinical practice. Previous CAD systems are opaque for clinicians and cannot process the ultrasound image from different ultrasound machines. This study proposes a novel CAD system utilizing BI-RADS scoring standard and Classification and Regression Tree (CART) algorithm to overcome the two problems. The original dataset consists of 1300 ultrasound breast images. Three well-experienced clinicians evaluated all of the images according to the BI-RADS feature scoring standard. Subsequently, each image could be transformed into a 25?×?1 vector. The CART algorithm was finally used to classify these vectors. In the experiments, we used the oversampling method to balance the number of malignant samples and benign samples. The 5-fold cross validation was employed to evaluate the performance of the system. The accuracy reached 94.58%, the specificity was 98.84%, the sensitivity was 90.80%, the positive predictive value (PPV) was 98.91% and the negative predictive value (NVP) was 90.56%. The experiment results show that the proposed system can obtain a sufficient performance in the breast diagnosis and can effectively recognize the benign breast tumors in BI-RADS 3.     

A fuzzy-rough approach for the maintenance of distributed case-based reasoning systems

Case-based reasoning (CBR) means reasoning from prior examples and it has considerable potential for building intelligent assistant system for the World Wide Web. In order to develop successful Web-based CBR systems, we need to select a set of representative cases for the client side case-base such that this thin client is competence in problem solving. This paper proposes a fuzzy-rough method of selecting cases for such a distributed CBR system, i.e., a thin client system (a smaller case-base with rules) connected to a comparatively more powerful server system (the entire original case-base). The methodology is mainly based on the idea that an original case-base can be transformed into a smaller case-base together with a group of fuzzy adaptation rules, which could be generated using our fuzzy-rough approach. As a result, the smaller case-base with a group of fuzzy rules will almost have the same problem coverage as the entire original case-base. The method proposed in this paper, consists of four steps. First of all, an approach of learning feature weights automatically is used to evaluate the importance of different features in a given case-base. Secondly, clustering of cases is carried out to identify different concepts in the case-base using the acquired feature weights. Thirdly, fuzzy adaptation rules are mined for each concept using a fuzzy-rough method. Finally, a selection strategy which based on the concepts of case coverage and reachability is used to select representative cases. The effectiveness of our method is demonstrated experimentally using some testing data in the travel domain. This project is supported by the Hong Kong Polytechnic University Grant G-V957 and H-ZJ90.     

Measuring progress in multirobot research with rating methods--the RoboCup example.

Rating the intelligence of artificially made systems is important for measuring progress in scientific and engineering methods. Unfortunately, there is currently no universal agreement about what is considered an intelligent system, and how to measure its intelligence. This research focus on measuring the progress in the robotic technologies deployed for the RoboCup competitions, since one of the original premises of those competitions was to advance the development of intelligent robotic systems. A method used for rating the competence of human chess players is adapted for measuring the advancement in the competence of robotic teams. The results indicate significant yearly improvements in the capabilities of the robotic teams. The same method can be used to indirectly quantify the benefits in specific technology choices.     

Cognitive performance-altering effects of electronic medical records: an application of the human factors paradigm for patient safety

According to the human factors paradigm for patient safety, health care work systems and innovations such as electronic medical records do not have direct effects on patient safety. Instead, their effects are contingent on how the clinical work system, whether computerized or not, shapes health care providers’ performance of cognitive work processes. An application of the human factors paradigm to interview data from two hospitals in the Midwest United States yielded numerous examples of the performance-altering effects of electronic medical records, electronic clinical documentation, and computerized provider order entry. Findings describe both improvements and decrements in the ease and quality of cognitive performance, both for interviewed clinicians and for their colleagues and patients. Changes in cognitive performance appear to have desirable and undesirable implications for patient safety as well as for quality of care and other important outcomes. Cognitive performance can also be traced to interactions between work system elements, including new technology, allowing for the discovery of problems with “fit” to be addressed through design interventions.     

An investigation into the effects that digital media can have on the learning outcomes of individuals who have dyslexia

The effects that media can have on task performance have been greatly debated over the years. Whilst agreement has begun to emerge on the effects media have on cognitive performance, little is understood about the relationship between such media effects and individual differences such as individuals who have dyslexia. This paper presents findings from a study that investigated the effects computer-based media can have on the learning outcomes of individuals who have dyslexia. The purpose of the study was to obtain data that informed the development and design of e-learning and distance learning materials for universal use. The research process was based on Dual Coding Theory and refined by current theories on dyslexia. Findings from the research are intended to help academics and providers of e-learning materials to improve the design and delivery of their learning contents.     

Addressing Constraints Creatively: How New Design Software Helps Solve the Dilemma of Originality and Feasibility

Are designers doomed to sacrifice creativity when integrating new product development processes? Although many studies highlight the need to produce original and innovative designs, maintaining creativity in the design process continues to be difficult due to industrial constraints. Thus, creativity is restricted to phases in the ‘fuzzy front end’ to avoid those constraints that might effectively kill it. However, constraints are also acknowledged as a resource for creativity, as has previously been shown with artists and engineers. Thus, we pose the following research question: In which cases can a constraint be a resource for creativity? To answer this question, we investigate different types of computer‐aided design (CAD) software. Relying on an experimental method, we compare the performance of those types of software at the so‐called design gap where design sketches are transformed into digital models. We show that some CAD software enables designers to work under additional constraints, be more creative and avoid the trade‐off between robustness and creativity, and that understanding this performance means appreciating that such software enables designers to play with the embedded constraints to reveal associated fixations and to design models that follow the constraint but overcome the fixation. Constraints and creativity are linked by two competing processes: constraints decrease the degree of freedom and, as a result, creative possibilities, but embedding constraints increases the awareness of fixations and therefore the capacity to design original models. Today, new CAD tools more effectively support the second process, which leads to ‘acquired originality’ in design.     

WCOID-DG: An approach for case base maintenance based on Weighting, Clustering, Outliers, Internal Detection and Dbsan-Gmeans

The success of the Case Based Reasoning system depends on the quality of the case data and the speed of the retrieval process that can be costly in time, especially when the number of cases gets bulky. To guarantee the system?s quality, maintaining the contents of a case base (CB) becomes unavoidably. In this paper, we propose a novel case base maintenance policy named WCOID-DG: Weighting, Clustering, Outliers and Internal cases Detection based on Dbscan and Gaussian means. Our WCOID-DG policy uses in addition to feature weights and outliers detection methods, a new efficient clustering technique, named DBSCAN-GM (DG) which is a combination of DBSCAN and Gaussian-Means algorithms. The purpose of our WCOID-GM is to reduce both the storage requirements and search time and to focus on balancing case retrieval efficiency and competence for a CB. WCOID-GM is mainly based on the idea that a large CB with weighted features is transformed to a small CB with improving its quality. We support our approach with empirical evaluation using different benchmark data sets to show its competence in terms of shrinking the size of the CB and the research time, as well as, getting satisfying classification accuracy.     

A Human Activity Approach to User Interfaces

How can we understand why a bank teller has different needs for a user interface than those of casual users of a machine teller, or why a graphic designer needs a different user interface than a secretary? This article presents a framework for the design of user interfaces that originates from the work situations in which computer-based artifacts are used: The framework deals with the role of the user interface in purposeful human work. Human activity theory is used in this analysis. The purpose of this article is to make the reader curious and hopefully open his or her eyes to a somewhat different way of thinking about the user interface. The article applies examples of real-life interfaces to support this process, but it does not include a systematic presentation of empirical results. I focus on the role of the computer application in use. Thus, it is necessary to consider human-computer interaction and other related work conditions. I deal with human experience and competence as being rooted in the practice of the group that conducts the specific work activity. The main conclusions are: The user interface cannot be seen independently of the use activity (i.e., the professional, socially organized practice of the users and the material conditions for the activity, including the object of the activity). The standard view in these situations is to deduce an ultimate set of operations from an abstract use activity and apply these to design and analysis. This article argues that the user interface fully reveals itself to us only when in use. What is a good user interface for those with a certain degree of competence may not be efficient for those with different levels of competence. I give certain general recommendations for the user interface, but I have no guarantee that such recommendations are applicable to the specific case wherein these concerns may be overruled by specific social or material concerns.     

Towards Automated Case Knowledge Discovery in the M 2 Case-Based Reasoning System

In this paper we present the M ² Case-Based Reasoning (CBR) system. The M ² system addresses a number of issues that present methodologies for CBR systems have shied away from. We discuss techniques for removing the knowledge acquisition bottleneck when acquiring case knowledge. Here, case knowledge refers to the complementary knowledge structures, cases (more specific in nature) and adaptation rules (more general). We address the use of negative cases for updating the case knowledge as well as for refining the similarity measures. In particular we discuss in detail, showing experimental results, the use of Data Mining within the M ² system to build the case base from a database containing operational data, and discover adaptation rules. A methodology to monitor the competence of the CBR system and to utilize negative cases for updating the CBR system to enhance its competence is also discussed. The M ² CBR system also employs Rough Set and Fuzzy Set theories to further enhance its capabilities within real-world applications as well as providing a richer and truer model of human reasoning.     

From cognitive reliability to competence? An evolving approach to human factors and safety

When reviewing the research path of an author, we are inevitably influenced by our own background and approach. Tracing back the converging and diverging assumptions of the authors with respect to Erik Hollnagel’s research path, the paper focuses on the evolution of cognitive psychology as resulting from an original distinction between two models of human cognition: the first one more in line with the behaviourist tradition and the latter with the cybernetic and ecological approach. The former, which becomes dominant in the development of cognitive psychology, marginalizes some aspects that prove crucial in the latter. The concepts of anticipation and of intentional behaviour, together with the notion of variability of normal performance, are traditionally part of the cybernetic and ecological approach to cognitive psychology. These concepts have also been central in the development of the ergonomic analysis of work activities. Throughout the Resilience Engineering perspective, the two models of human cognition are brought closer, while the concept of competence is sketched as a possible mediator to a “positive” approach to Human Factors and Safety.     

Evaluating an intelligent diagnosis system of historical text comprehension

This work aims to present and evaluate a Fuzzy-Case Based Reasoning Diagnosis system of Historical Text Comprehension. The synergism of fuzzy logic and case based reasoning techniques handles the uncertainty in the acquisition of human expert's knowledge regarding learner's observable behaviour and integrates the right balance between expert's knowledge described in the form of fuzzy sets and previous experiences documented in the form of cases. The formative evaluation focused on the comparison of the system's performance to the performance of human experts concerning the diagnosis accuracy. The system was also evaluated for its behaviour when using two different historical texts. Empirical evaluation conducted with human experts and real students indicated the need for revision of the diagnosis model. The evaluation results are encouraging for the system's educational impact on learners and for future work concerning an intelligent educational system for individualized learning.     

Rethinking competence systems for knowledge-based organizations

Existing competence systems are based on a rationalistic view of competence. While these competence systems might work in job-based organizations, we argue that in more dynamic settings, such as in knowledge-based organizations, the interest-informed actions that capture the emergent competencies of tomorrow require different types of information technology support. The main objective of this paper is to elaborate on the possibilities and implications of using interest-activated technology as a design rationale for competence systems. This paper is based on an action case study of an implemented interest-activated Intranet recommender system prototype at Volvo Information Technology AB in Gothenburg, Sweden. On the basis of how organizational members used this prototype to find information they were interested in, our research team was able to inquire into how personal interest, embodied in information-seeking activities, could be a means for identifying competence. Building on the relation between personal interest and competence, we discuss competence systems design and spell out explicit implications for managerial practice in knowledge-based organizations.     

A method for reduction of examples in relational learning

Feature selection methods often improve the performance of attribute-value learning. We explore whether also in relational learning, examples in the form of clauses can be reduced in size to speed up learning without affecting the learned hypothesis. To this end, we introduce the notion of safe reduction: a safely reduced example cannot be distinguished from the original example under the given hypothesis language bias. Next, we consider the particular, rather permissive bias of bounded treewidth clauses. We show that under this hypothesis bias, examples of arbitrary treewidth can be reduced efficiently. We evaluate our approach on four data sets with the popular system Aleph and the state-of-the-art relational learner nFOIL. On all four data sets we make learning faster in the case of nFOIL, achieving an order-of-magnitude speed up on one of the data sets, and more accurate in the case of Aleph.     

An adaptive signal compression system with pre-specified reconstruction quality and compression rate

Two essential properties of a signal compression method are the compression rate and the distance between the original signal and the reconstruction from the compressed signal. These two properties are used to assess the performance and quality of the method. In a recent work [B. Tümer, B. Demir?z, Lecture Notes in Computer Science-Computer and Information Sciences, volume 2869, chapter Signal Compression Using Growing Cell Structures: A Transformational Approach, Springer Verlag, 2003, pp. 952-959], an adaptive signal compression system (ACS) is presented which defines the performance of the system as a function of the system complexity, system sensitivity and data size. For a compression method, it is desirable to formulate the performance of the system as a function of the system complexity and sensitivity to optimize the performance of the system. It would be further desirable to express the reconstruction quality in terms of the same system parameters so as to know up front what compression rate to end up with for a specific reconstruction quality. In this work, we modify ACS such that the modified ACS (MACS) estimates the reconstruction quality for a given system complexity and sensitivity. Once this relation is identified it is possible to optimize either compression rate or reconstruction quality with respect to system sensitivity and system complexity while limiting the other one.     

Crossing levels in systems ergonomics: A framework to support ‘mesoergonomic’ inquiry

In this paper we elaborate and articulate the need for what has been termed ‘mesoergonomics’. In particular, we argue that the concept has the potential to bridge the gap between, and integrate, established work within the domains of micro- and macroergonomics. Mesoergonomics is defined as an open systems approach to human factors and ergonomics (HFE) theory and research whereby the relationship between variables in at least two different system levels or echelons is studied, and where the dependent variables are human factors and ergonomic constructs. We present a framework which can be used to structure a set of questions for future work and prompt further empirical and conceptual inquiry. The framework consists of four steps: (1) establishing the purpose of the mesoergonomic investigation; (2) selecting human factors and ergonomics variables; (3) selecting a specific type of mesoergonomic investigation; and (4) establishing relationships between system levels. In addition, we describe two case studies which illustrate the workings of the framework and the value of adopting a mesoergonomic perspective within HFE. The paper concludes with a set of issues which could form part of a future agenda for research within systems ergonomics.