A Knowledge-based System for Intelligent Support in Pharmacogenomics Evidence Assessment: Ontology-driven Evidence Representation, Retrieval, Classification and Interpretation

Thesis (Ph.D.)--University of Washington, 2016-06

User-centred ontology learning for knowledge management

Automatic ontology building is a vital issue in many fields where they are currently built manually. This paper presents a user-centred methodology for ontology construction based on the use of Machine Learning and Natural Language Processing. In our approach, the user selects a corpus of texts and sketches a preliminary ontology (or selects an existing one) for a domain with a preliminary vocabulary associated to the elements in the ontology (lexicalisations). Examples of sentences involving such lexicalisation (e.g. ISA relation) in the corpus are automatically retrieved by the system. Retrieved examples are validated by the user and used by an adaptive Information Extraction system to generate patterns that discover other lexicalisations of the same objects in the ontology, possibly identifying new concepts or relations. New instances are added to the existing ontology or used to tune it. This process is repeated until a satisfactory ontology is obtained. The methodology largely automates the ontology construction process and the output is an ontology with an associated trained leaner to be used for further ontology modifications.

Enhancing performance through the introduction of customer orientation into the building components industry

Purpose: This paper aims to describe an investigation into how company performance can be improved by integrating internal and external customers and technology. The approach was developed, implemented and evaluated in the operations of the building components industry. The research was carried out in the precast concrete division of a Singapore company. Design/methodology/ approach: For the purpose of undertaking the investigation an exploratory case study approach was used. This was divided into conceptual and action research stages. The action research was also used to implement the changes in the company. Questionnaire surveys were carried out among company employees and external customers to assess the effect of these changes. Results of the investigation were derived using content and statistical analysis. Triangulation between three sources was used for validating the data. Findings: The exploratory case study strategy resulted in rich research data, which provided evidence of the changes taking place and integration happening, leading to improved performance. The action research approach proved a powerful tool where the uncertainty of outcomes makes it near impossible to make accurate forecasts. Another output of the research was the development of an "integrated customer orientation" (ICO) model. Research limitations/implications: The research in this paper used a single site action research investigation so should be interpreted within the specific company and industry context. There are implications for theory and practice in a number of areas of production and marketing as well as contributions to understanding about productivity improvement and organisational development. The investigation also fulfils the dual objectives of action research by contributing to both knowledge and practice. Originality/value: The paper describes a unique approach towards improving productivity, quality and service through the use of action research to implement changes, as well as providing the research evidence to evaluate both the process of implementation and results achieved. © Emerald Group Publishing Limited.

Improving the use of visual interactive simulation as a knowledge elicitation tool

Knowledge elicitation is a well-known bottleneck in the production of knowledge-based systems (KBS). Past research has shown that visual interactive simulation (VIS) could effectively be used to elicit episodic knowledge that is appropriate for machine learning purposes, with a view to building a KBS. Nonetheless, the VIS-based elicitation process still has much room for improvement. Based in the Ford Dagenham Engine Assembly Plant, a research project is being undertaken to investigate the individual/joint effects of visual display level and mode of problem case generation on the elicitation process. This paper looks at the methodology employed and some issues that have been encountered to date. Copyright © 2007 Inderscience Enterprises Ltd.

Responding to crisis through strategic knowledge management

Purpose - Many managers would like to take a strategic approach to preparing the organisation to avoid impending crisis but instead find themselves fire-fighting to mitigate its impact. This paper seeks to examine an organisation which made major strategic changes in order to respond to the full effect of a crisis which would be realised over a two to three year period. At the root of these changes was a strategic approach to managing knowledge. The paper's purpose is to reflect on managers' views of the impact this strategy had on preparing for the crisis and explore what happened in the organisation during and after the crisis. Design/methodology/approach - The paper examines a case-study of a financial services organisation which faced the crisis of its impending dissolution. The paper draws upon observations of change management workshops, as well as interviews with organisational members of a change management task force. Findings - The response to the crisis was to recognise the importance of the people and their knowledge to the organisation, and to build a strategy which improved business processes and communication flow across the divisions, as well as managing the departure of knowledge workers from an organisation in the process of being dissolved. Practical implications - The paper demonstrates the importance of building a knowledge management strategy during times of crisis, and draws out important lessons for organisations facing organisational change. Originality/value - The paper represents a unique opportunity to learn from an organisation adopting a strategic approach to managing its knowledge during a time of crisis. © Emerald Group Publishing Limited.

Building team-based working:a practical guide to organizational transformation

Building Team-based Working is designed for use by managers and consultants who are introducing team-based working into organizations. The book synthesizes knowledge about how to build team-based organizations, focusing particularly on the psychological and social processes that can facilitate or obstruct successful teamwork. Rather than advise managers on how to build effective teams, as most books in this area tend to do, this book instead focuses on how to build organizations structured around teams. The text is divided into six sections describing the six main stages of developing team-based working in an organization. The chapters follow a common structure. Each one opens with a summary of the aims and activities relevant to that stage and concludes with a selection of appropriate support materials and tools. These materials can also be downloaded from the CD accompanying the text. The advice given is based on evidence gathered by the authors over 20 years of practical management experience, research work in organizations, and consultancy across the public, manufacturing and service sectors.

Using secondary knowledge to support decision tree classification of retrospective clinical data

Retrospective clinical data presents many challenges for data mining and machine learning. The transcription of patient records from paper charts and subsequent manipulation of data often results in high volumes of noise as well as a loss of other important information. In addition, such datasets often fail to represent expert medical knowledge and reasoning in any explicit manner. In this research we describe applying data mining methods to retrospective clinical data to build a prediction model for asthma exacerbation severity for pediatric patients in the emergency department. Difficulties in building such a model forced us to investigate alternative strategies for analyzing and processing retrospective data. This paper describes this process together with an approach to mining retrospective clinical data by incorporating formalized external expert knowledge (secondary knowledge sources) into the classification task. This knowledge is used to partition the data into a number of coherent sets, where each set is explicitly described in terms of the secondary knowledge source. Instances from each set are then classified in a manner appropriate for the characteristics of the particular set. We present our methodology and outline a set of experiential results that demonstrate some advantages and some limitations of our approach. © 2008 Springer-Verlag Berlin Heidelberg.

Effective knowledge transfer: a terminological perspective - Dismantling the jargon barrier to knowledge about computer security

The research is concerned with the terminological problems that computer users experience when they try to formulate their knowledge needs and attempt to access information contained in computer manuals or online help systems while building up their knowledge. This is the recognised but unresolved problem of communication between the specialist and the layman. The initial hypothesis was that computer users, through their knowledge of language, have some prior knowledge of the subdomain of computing they are trying to come to terms with, and that language can be a facilitating mechanism, or an obstacle, in the development of that knowledge. Related to this is the supposition that users have a conceptual apparatus based on both theoretical knowledge and experience of the world, and of several domains of special reference related to the environment in which they operate. The theoretical argument was developed by exploring the relationship between knowledge and language, and considering the efficacy of terms as agents of special subject knowledge representation. Having charted in a systematic way the territory of knowledge sources and types, we were able to establish that there are many aspects of knowledge which cannot be represented by terms. This submission is important, as it leads to the realisation that significant elements of knowledge are being disregarded in retrieval systems because they are normally expressed by language elements which do not enjoy the status of terms. Furthermore, we introduced the notion of `linguistic ease of retrieval' as a challenge to more conventional thinking which focuses on retrieval results.

The application of knowledge based expert systems to mechanical engineering design

Investigation of the different approaches used by Expert Systems researchers to solve problems in the domain of Mechanical Design and Expert Systems was carried out. The techniques used for conventional formal logic programming were compared with those used when applying Expert Systems concepts. A literature survey of design processes was also conducted with a view to adopting a suitable model of the design process. A model, comprising a variation on two established ones, was developed and applied to a problem within what are described as class 3 design tasks. The research explored the application of these concepts to Mechanical Engineering Design problems and their implementation on a microcomputer using an Expert System building tool. It was necessary to explore the use of Expert Systems in this manner so as to bridge the gap between their use as a control structure and for detailed analytical design. The former application is well researched into and this thesis discusses the latter. Some Expert System building tools available to the author at the beginning of his work were evaluated specifically for their suitability for Mechanical Engineering design problems. Microsynics was found to be the most suitable on which to implement a design problem because of its simple but powerful Semantic Net Knowledge Representation structure and the ability to use other types of representation schemes. Two major implementations were carried out. The first involved a design program for a Helical compression spring and the second a gearpair system design. Two concepts were proposed in the thesis for the modelling and implementation of design systems involving many equations. The method proposed enables equation manipulation and analysis using a combination of frames, semantic nets and production rules. The use of semantic nets for purposes other than for psychology and natural language interpretation, is quite new and represents one of the major contributions to knowledge by the author. The development of a purpose built shell program for this type of design problems was recommended as an extension of the research. Microsynics may usefully be used as a platform for this development.

Building a strategy toolkit:lessons from business : executive briefings

In an increasingly competitive business environment, the ability to spot and seize new opportunities, to plot a path of successful growth for an organisation, and to use resources effectively and efficiently, becomes paramount. Managers have a number of management tools at their disposal to help meet the challenges that they face. By consulting with both business academics and alumni on their knowledge and use of strategy tools, this report contains a number of strategy tools that managers would benefit from being familiar and using in their work, particularly as their experience and seniority increases.

A simultaneous examination of the effects of salesperson relationship-building activities and marketing activities on retail buyers' purchase decisions

Firms’ contemporary selling practices often not only demand that salespeople meet sales quotas, but also that they build strong, profitable relationships with customers. Given the belief that relationship-building activities can develop closer customer ties and improve sales performance, scholars have increasingly studied salesperson behaviors aimed at nurturing buyer-salesperson relations. However, while previous sales research has investigated the effects of a number of relational activities on performance outcomes in isolation, knowledge about their effectiveness in comparison to other important performance drivers is virtually absent. The present study provides some first theoretical and empirical insights into this research gap by simultaneously examining the role of specific salesperson relationship-building activities, and product-focused variables, in retail buyers’ new product purchase decisions. Following an extensive literature review, a two-part qualitative field study was conducted to explore salesperson relationship-building activities that are regarded as important by retail buyers. Two key relational behaviors were suggested by the customer-centric and retail industry-specific data; salesperson consultation (communication-based) and salesperson helping behavior (action-based). Drawing on this as well as extant literature, a conceptual framework was developed concerning the influences of these relationship-building activities and other product-focused factors on retail buyers’ new product acceptance. The study’s quantitative component contained a mail and web survey of U.S. retail buyers, resulting in a total dataset of 192 responses. After a comprehensive measure validation process, the theoretical hypotheses were tested using logistic regression analysis. Contrary to existing assertions, the results suggest that salesperson relationship-building activities themselves do not directly and/or indirectly influence purchase decisions, but instead can moderate the effects of product-focused determinants on retail buyers’ new product selections. Data on actual purchase decisions provide a high level of external validity to the findings. The study closes with a concluding discussion, including theoretical and managerial implications of the findings, limitations of the research, and directions for future inquiry.

The importance of team-working in knowledge transfer partnerships

Research capacity can be built by collaboration between industry and universities, and Knowledge Transfer Partnerships (KTPs) are an ideal way to do this. While good collaboration and team-work has been recognised as crucial for success, projects tend to be evaluated on outcomes and not collaboration effectiveness. This paper discusses best practice for how a KTP project team might work together effectively.

Ontology-based knowledge capture and sharing in enterprise organisations

Despite years of effort in building organisational taxonomies, the potential of ontologies to support knowledge management in complex technical domains is under-exploited. The authors of this chapter present an approach to using rich domain ontologies to support sense-making tasks associated with resolving mechanical issues. Using Semantic Web technologies, the authors have built a framework and a suite of tools which support the whole semantic knowledge lifecycle. These are presented by describing the process of issue resolution for a simulated investigation concerning failure of bicycle brakes. Foci of the work have included ensuring that semantic tasks fit in with users’ everyday tasks, to achieve user acceptability and support the flexibility required by communities of practice with differing local sub-domains, tasks, and terminology.

Integrating skills profiling and purchasing portfolio management:an opportunity for building purchasing capability

Kralijc’s (1983) purchasing portfolio approach holds that different types of purchases need different sourcing strategies, underpinned by distinct sets of resources and practices. The approach is widely deployed in business and extensively researched, and yet little research has been conducted on how knowledge and skills vary across a portfolio of purchases. This study extends the body of knowledge on purchasing portfolio management, and its application in the strategic development of purchasing in an organization, and on human resource management in the purchasing function. A novel approach to profiling purchasing skills is proposed, which is well suited to dynamic environments which require flexibility. In a survey, experienced purchasing personnel described a specific purchase and profiled the skills required for effective performance in purchasing that item. Purchases were categorized according to their importance to the organization (internally-oriented evaluation of cost and production factors) and to the supply market (externally-oriented evaluation of commercial risk and uncertainty). Through cluster analysis three key types of purchase situations were identified. The skills required for effective purchasing vary significantly across the three clusters (for 22 skills, p<0.01). Prior research shows that global organizations use the purchasing portfolio approach to develop sourcing strategies, but also aggregate analyses to inform the design of purchasing arrangements (local vs global) and to develop their improvement plans. Such organizations would also benefit from profiling skills by purchase type. We demonstrate how the survey can be adapted to provide a management tool for global firms seeking to improve procurement capability, flexibility and performance.

A framework for automated construction of resource space based on background knowledge

Resource Space Model is a kind of data model which can effectively and flexibly manage the digital resources in cyber-physical system from multidimensional and hierarchical perspectives. This paper focuses on constructing resource space automatically. We propose a framework that organizes a set of digital resources according to different semantic dimensions combining human background knowledge in WordNet and Wikipedia. The construction process includes four steps: extracting candidate keywords, building semantic graphs, detecting semantic communities and generating resource space. An unsupervised statistical language topic model (i.e., Latent Dirichlet Allocation) is applied to extract candidate keywords of the facets. To better interpret meanings of the facets found by LDA, we map the keywords to Wikipedia concepts, calculate word relatedness using WordNet's noun synsets and construct corresponding semantic graphs. Moreover, semantic communities are identified by GN algorithm. After extracting candidate axes based on Wikipedia concept hierarchy, the final axes of resource space are sorted and picked out through three different ranking strategies. The experimental results demonstrate that the proposed framework can organize resources automatically and effectively.©2013 Published by Elsevier Ltd. All rights reserved.