Knowledge Engineering Development Research Articles

Networked Knowledge and Complex Networks: An Engineering View

Along with the development of information technologies such as mobile Internet, information acquisition technology, cloud computing and big data technology, the traditional knowledge engineering and knowledge-based software engineering have undergone fundamental changes where the network plays an increasingly important role. Within this context, it is required to develop new methodologies as well as technical tools for network-based knowledge representation, knowledge services and knowledge engineering. Obviously, the term “network” has different meanings in different scenarios. Meanwhile, some breakthroughs in several bottleneck problems of complex networks promote the developments of the new methodologies and technical tools for network-based knowledge representation, knowledge services and knowledge engineering. This paper first reviews some recent advances on complex networks, and then, in conjunction with knowledge graph, proposes a framework of networked knowledge which models knowledge and its relationships with the perspective of complex networks. For the unique advantages of deep learning in acquiring and processing knowledge, this paper reviews its development and emphasizes the role that it played in the development of knowledge engineering. Finally, some challenges and further trends are discussed.

Fuzzy AHP-TOPSIS approaches to prioritize teaching solutions for Intellect Errors

Abstract: The teaching fraternity and intellects play an important role in students’ careers as they make students industry-ready. During their teaching, they make different types of errors. One of the neglected aspects during teaching is intellect errors and these directly or indirectly impact students learning capabilities. The scattered literature shows that there are twelve types of intellect errors like ‘error of coincidence’, ‘senses error’, ‘analogy error’, ‘subjectivity error’, etc. To minimize these errors, six solutions have been identified like ‘selection of right instruments’, ‘developmeand least rated intellect errors respectively. Thent of critical thinking in the students’, ‘aware about knowledge engineering development’ etc. This study aims to identify and prioritize the solutions to overcome the errors of the intellect that has been the ignored aspect of the teaching till now. A hybrid approach of fuzzy AHP (Analytical Hierarchy Process) and Fuzzy TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution) has been proposed to rank the solutions that minimize the intellect errors. Fuzzy AHP is used to compute the weights for intellect errors by doing the pairwise comparison and fuzzy TOPSIS is used to rank the identified solutions with the help of generated weights of fuzzy AHP. The results show that “error of proximity” and “senses error” are the highest topmost rated solution to handle errors of the intellect is “development of critical thinking in the students”. Keywords: Intellect errors, fuzzy AHP, fuzzy TOPSIS, industry-ready

Organization of a geophysical information space by using an event-bush-based collaborative tool

Development of knowledge engineering makes it possible to bring an information space relating to an entire domain of knowledge within the field of geoscience into a strict form, which is both computer-tractable and convenient for collaborative research work. Nevertheless, there are issues that seriously hamper this process – the problem of defining key terms, which is often not shared by the colleagueship, and interrelation of concepts developed by different schools within the colleagueship focused on different aspects of this domain. Another issue is the export of results to a wider community unfamiliar with the specificity of local studies. All these issues can be successfully addressed by a novel technique of knowledge engineering, the event bush, brought into the COLLA environment for geoscientific collaborative studies. This paper demonstrates how the said issues can be resolved by the example of one of the most important information domains in the field of seismology, the site effects. Text, graphics, tabular data and a physical model coming from different sources and different contexts are united in one context keeping all the specificity of original understanding and allowing the researchers keep on following their own context and terminology.

User interface issues raised by knowledge refinement

The concept of ease of use has evolved over the last 30 years, keeping pace with developments in user interface technology, in the manner of Carroll's task-artifact cycle. This paper argues that recent developments in knowledge engineering require yet further changes in the concept and discusses what implications they might have for user interface design. The development in question is that construction of knowledge bases is, in many cases, no longer a matter of assembling pieces of knowledge that have been made available by knowledge acquisition, but takes on the nature of creative design which results in the generation of new knowledge at the user interface. A key difference is that while knowledge base assembly can be seen as a series of discrete events, creative design is more of a continuous process in which the user's flow of thinking must not be interrupted. This means that traditional WIMP and GUI interfaces are no longer appropriate and a more “proximal” form must be found.

A HYBRID KNOWLEDGE ENGINEERING DEVELOPMENT ENVIRONMENT (KEDE)

This paper presents a brief overview of knowledge-based system building tools. Then a hybrid knowledge engineering development environment called KEDE is described as a powerful toolkit for large AI problems. It provides five kinds of knowledge representations: extended frames, semantic nets, procedural knowledge, object-oriented technique, and predicate logic. Correspondingly, it supports: procedure-oriented, data-oriented, object-oriented, and logic-oriented programming. KEDE gains a very powerful inheritance mechanism using frames. It further provides an automatic retrieval technique for processing implicit knowledge, a demon mechanism for firing functions, a message-sending mechanism for activating methods, and two inference engines for backward, forward, and even mixed reasoning. All these facilities are tightly integrated and formed an entirety. KEDE has been implemented in Common Lisp on Sun workstations.

Towards validation of expert systems as medical decision aids

Expert system evaluation is an important step in knowledge engineering development and is clearly not a simple process. The aim of this paper is to introduce methodological aspects of medical knowledge base validation. We distinguish two components of the evaluation: verification and validation. In the first part, the difficulties of evaluation are analysed, problems with some techniques used in the evaluation process are discussed. In the second part, our experiment gives guidelines to present these aspects and underline what and when to evaluate.

Computerizing protective services intake expertise: Preliminary research

Decision making at child welfare intake has been the subject of considerable investigation for the last thirty years. Previous reserach on the dynamics of abuse and neglect resulted in complexity and inconsistency to the extent that research moved away from determining the relevant information for creating a more structured decision making process. Recent developments in knowledge engineering and computerized expert systems provide new tools for examining protective services intake decision making. These tools are appropriate for organizing the vast amount of information workers use during decision making, extracting decisions from that information, and presenting the decisions and their supporting logic. This research examines existing expertise with a small sample of child welfare experts to determine the feasibility of developing an expert system for supporting intake decisions.