Research on knowledge acquisition method about the IF/THEN rules based on rough set theory

The basic principles of IF/THEN rules in rough set theory are analyzed first, and then the automatic process of knowledge acquisition is given. The numerical data is qualitatively processed by the classification of membership functions and membership degrees to get the normative decision table. The regular method of relations and the reduction algorithm of attributes are studied. The reduced relations are presented by the multi-representvalue method and its algorithm is offered. The whole knowledge acquisition process has high degree of automation and the extracted knowledge is true and reliable.

Activity Theory Based Ontology Model for Efficient Knowledge Sharing in eHealth

Knowledge sharing has become an important issue that challenges the efficient healthcare delivery in eHealth system. It also rises as one of the most demanding applications with reference to dynamic interactivities among various healthcare actors (e.g. doctors, nurses, patients, relatives of patients). In this paper, we suggest an activity theory based ontology model to represent various healthcare actors. The goal of the suggested model is to enhance interactivities among these healthcare actors for conducting more efficient knowledge sharing, which helps to design eHealth system. To validate the feasibility of suggested ontology model, three typical use cases are further studied. A questionnaire based survey is carried out and the corresponding survey results are reported, together with the detailed discussions.

The Theory of Biomedical Knowledge Integration (Ⅶ)──The Non-Euclid Macro-Micro Transform Law

This article continued to do the scholastic pursuits on some profound mechanisms in the life systems, which are believed to be related to the further development of Medical Informatics. It discussed at first the structural nature of things, then probed a principle which is a basis for both of the fractal theory and the wavelet analysis, being called the shape-constancy law of the basic constructors at the different scale levels. And the paper also ventured the equivalency between the shape of wave and matrix, thus presented a new concept “shaped-number”, being expected to work in the operations of some bio-medical functions or shapes.

Granularity of Knowledge Computed by Genetic Algorithms Based on Rough Sets Theory

Rough set philosophy hinges on the granularity of data, which is used to build all its basic concepts, like approximations, dependencies, reduction etc. Genetic Algorithms provides a general frame to optimize problem solution of complex system without depending on the domain of problem.It is robust to many kinds of problems.The paper combines Genetic Algorithms and rough sets theory to compute granular of knowledge through an example of information table. The combination enable us to compute granular of knowledge effectively.It is also useful for computer auto-computing and information processing.

The Theory of Bio-Medical Knowledge Integration(Ⅵ)

This paper introduced the following new concepts:the cognitive goal, the cognitive goal for the declarative data of the patient records (PRs), The basic attributes of PR’s data at the sides of generation, construction and cognition, the generalized data creator (GDC), type Ⅰ to Ⅵ+ of GDC, the cognitive directions of data: forward direction and backward direction, the apparent cognitive orientation and inapparent cognitive orientation, the cognitive granularity difference principle between the natural intelligence and the artificial intelligence, the generalized variable(GVAR) and the generalized value(GVAL), the variable and value transitivity law(V-V transitivity law), the attribute-combination irreversibility between the concept abstracting and embodying, an open model of the launching engine of bio-medical cognition,

The Theory of Biomedical Knowledge Integration (Ⅶ)──The Non-Euclid Macro-Micro Transform Law

This article continued to do the scholastic pursuits on some profound mechanisms in the life systems, which are believed to be related to the further development of Medical Informatics. It discussed at first the structural nature of things, then probed a principle which is a basis for both of the fractal theory and the wavelet analysis, being called the shape-constancy law of the basic constructors at the different scale levels. And the paper also ventured the equivalency between the shape of wave and matrix, thus presented a new concept "shaped-number", being expected to work in the operations of some bio-medical functions or shapes.

The Theory of Bio-Medical Knowledge Integration(Ⅸ)──A venture in methodology for operations on the cognitive segment in HER

This paper pointed out, in the cognitive or semantic processes, the data of EHR reflect their physical nature, which makes mathematics and informatics of less computing capability. Based on this argument a new concept cognitive segment (CS), which is considered with having both physical and formalized quality, was introduced. Centered on CS, the paper presented a series of new basic concepts and their definitions, a set of symbols and expressions, and afterwards explored the types, quasi-formalized expressions, mapping nature, methodology for operations, two distinguished differences, commonsensible background analyses, cognitive dimension regression, supervising function of CSs.

Knowledge discovery method for feature-decision level fusion of multiple classifiers

To improve the performance of the multiple classifier system, a new method of feature-decision level fusion is proposed based on knowledge discovery. In the new method, the base classifiers operate on different feature spaces and their types depend on different measures of between-class separability. The uncertainty measures corresponding to each output of each base classifier are induced from the established decision tables （DTs） in the form of mass function in the Dempster-Shafer theory （DST）. Furthermore, an effective fusion framework is built at the feature-decision level on the basis of a generalized rough set model and the DST. The experiment for the classification of hyperspectral remote sensing images shows that the performance of the classification can be improved by the proposed method compared with that of plurality voting （PV）.

BACKGROUND KNOWLEDGE AND SECONDARY KNOWLEDGE BASES IN LEARNINGS YSTEMS

This paper presents the differences and relations between background knowledge and domain theories in learning systems. The roles they play during learning procedures are discussed. It is emphasized that background knowledge plays an important role in enhancing the ability of a learning system. An explanation based learning system with domain theory in primary knowledge base and background knowledge in secondary knowledge base is introduced as an example. It shows how background knowledge can be used to solve some of the problems caused by incomplete domain theory in an explanation based learning system. The system can accomplish knowledge level learning through purely deductive approach. At last the acquisition of background knowledge is briefly discussed.

Research into the Influencing Factors of Knowledge Transfer within Innovative Research Teams

Knowledge transfer within university-led innovative research teams helps to maximally gather knowledge sources and promote knowledge dissemination,exchange and digestion among different disciplines. T he effect of transfer directly affects the team's capacity of knowledge innovation and its outcomes. In this paper,a WSB-based research framework for the influencing factors of knowledge transfer within university-led innovative research teams is established by means of grounded theory with help of in-depth interviews,in which five fundamental categories that affect knowledge transfer within teams,namely,knowledge source,knowledge receiver,knowledge transfer context,knowledge characteristics and knowledge transfer medium,are proposed to elaborate on the relationship between the fundamental categories and the effect of knowledge transfer within teams.Finally,a theoretical saturation test is conducted to verify the rationality and scientific tenability of this theoretical framework.

Attribute reduction based on background knowledge and its application in classification of astronomical spectra data

To improve the efficiency of the attribute reduction, we present an attribute reduction algorithm based on background knowledge and information entropy by making use of background knowledge from research fields. Under the condition of known background knowledge, the algorithm can not only greatly improve the efficiency of attribute reduction, but also avoid the defection of information entropy partial to attribute with much value. The experimental result verifies that the algorithm is effective. In the end, the algorithm produces better results when applied in the classification of the star spectra data.

FAULT DIAGNOSIS OF ROTATING MACHINERY USING KNOWLEDGE-BASED FUZZY NEURAL NETWORK

A novel knowledge-based fuzzy neural network （KBFNN） for fault diagnosis is presented. Crude rules were extracted and the corresponding dependent factors and antecedent coverage factors were calculated firstly from the diagnostic sample based on rough sets theory. Then the number of rules was used to construct partially the structure of a fuzzy neural network and those factors were implemented as initial weights, with fuzzy output parameters being optimized by genetic algorithm. Such fuzzy neural network was called KBFNN. This KBFNN was utilized to identify typical faults of rotating machinery. Diagnostic results show that it has those merits of shorter training time and higher right diagnostic level compared to general fuzzy neural networks.

UNCERTAIN KNOWLEDGE MANAGEMENT IN EXPERT SYSTEMS USING FUZZY METAGRAPHS

This paper presented a new graph theoretic construct——fuzzy metagraphs and discussed their applications in constructing fuzzy knowledge base. Fuzzy metagraphs describe the relationships between sets of fuzzy elements but not single fuzzy element and offer some distinct advantages both for visualization of systems, as well as for formal analysis of system structure. In rule based system, a fuzzy metagraph is a unity of the knowledge base and the reasoning engine. Based on the closure of the adjacency matrix of fuzzy metagraphs, this paper presented an optimized inferential mechanism working mainly by an off line approach. It can greatly increase the efficiency of inference. Finally, it was applied in a daignostic expert system and satisfactory results were obtained.

A Formal Deductive Inference of the Law of Inertia in a Logically Formalized Axiomatic Epistemology System Sigma from the Assumption of Knowledge A-Priori-Ness

The general purpose of the research—systematical clarifying and explicating the too vague proper philosophical concepts of space, void, matter, motion, inertia, for making a logical harmony between them and the corresponding notions of proper physics. The special purpose of the research—invention (construction) of a formal inference of the well-known Newton’s first law of mechanics within a logically formalized axiomatic epistemology system from a set of precisely defined presumptions. For realizing this aim the following work has been done: a two-valued algebraic system of metaphysics as formal axiology has been applied to philosophical epistemology and philosophy of nature;a formal axiomatic theory called Sigma has been applied to physics for realizing the above-indicated special purpose of the research. Thus, constructing a discrete mathematical model of relationship between universal epistemology and philosophy of physics has been done. Research results: The main hitherto not published significantly new nontrivial scientific result of applied investigations presented in this article is a formal inference of the well-known Newton’s first law of mechanics within the formal axiomatic epistemology system Sigma from conjunction of the formal-axiological analog of the proper-law-of-mechanics (which analog is the formal-axiological law of two-valued algebra of metaphysics) and the assumption of a-priori-ness of knowledge. For obtaining this main research result, a set of accessory nontrivial novelties has been used, for instance;a precise algorithmic definition is given for the notion “law of metaphysics” in the algebraic system of metaphysics as formal axiology;a formal-axiological equivalence in the algebraic system is defined precisely. Precise tabular definitions are given for relevant evaluation-functions determined by evaluation-arguments, for example;“movement of (what, whom) x”;“speed of x”;“vector of x”;“velocity of x”;“magnitude of x”;“finiteness (definiteness) of x”;“dynamical closed-ness (isolated-ness) of x”;“constant-ness, immutability, conservation of x”.

Fuzzy Methodology for Taxonomy and Knowledge Base Design

This paper summarizes the research results dealing with washer and nut taxonomy and knowledge base design, making the use of fuzzy methodology. In particular, the theory of fuzzy membership functions, similarity matrices, and the operation of fuzzy inference play important roles.A realistic set of 25 washers and nuts are employed to conduct extensive experiments and simulations.The investigation includes a complete demonstration of engineering design. The results obtained from this feasibility study are very encouraging indeed because they represent the lower bound with respect to performance, namely correctrecognition rate, of what fuzzy methodology can do. This lower bound shows high recognition rate even with noisy input patterns, robustness in terms of noise tolerance, and simplicity in hardware implementation. Possible future works are suggested in the conclusion.

Community Based Flood Risk Management: Local Knowledge and Actor’s Involvement Approach from Lower Karnali River Basin of Nepal

Connecting to the disaster risk reduction (DRR) studies, community-based initiatives are found to be more effective in both developed and developing countries, with a specific focus on the empowerment of local communities to build resilience. Building on social capital theory, the paper investigates on local knowledge (LK) practices experienced by the actors in an emerging economy using the community-based flood risk management (CB-FRM) approach. The qualitative research method was used by collecting data from focused group discussions, and interviews with the key informants including actors from local governments and non-government organizations. Additionally, informal discussions, field visits, and desk studies were undertaken to support the findings. The findings reveal that the local communities carry out various local knowledge experiences to respond during disaster management phases. They own a creative set of approaches based on the LK and that empowers them to live in the flood-prone areas, accepting the paradigm shift from fighting with floods to living with that. The local actor’s involvement is recognized as an essential component for CB-FRM activities. Yet, their program’s implementation is more oriented towards humanitarian assistance in emergency responses. Even, they often overlook the role of LK. Additionally, the results show a high level of presence of local communities during the preparedness and recovery phases, while NGOs and local governments have a medium role in preparedness and low in recovery phase. The lack of local ownership has also emerged as the major challenge. The research provides valuable insights for integrated CB-FRM policies by adopting to LK practices.

Consumer Knowledge, Brand Image, Openness to Experience and Involvement: A Case in Cosmetic Consumption

The study adopted the theory of planned behavior (TPB) as research model to inspect what factors would influence consumers to purchase cosmetics by adding brand image, involvement, consumer knowledge and openness to experience to the model. A 7-point Likert scale questionnaire was designed to measure TPB items and totally 400 valid respondents were collected online. The results show that among the above, only “perceived behavioral control” has positive influence on intention of purchasing cosmetics. Neither attitude nor subjective norm has significant influence on purchasing intention. In addition, brand image and involvement have no significant influence on purchasing intention but consumer knowledge and openness to experience were found to have positive influence on purchasing intention.

The Effects of L1 Knowledge on L2(English) Reading Comprehension for Chinese Students in Middle School

Implications of second language reading learning are often aroused by the insights of reading experience in first language.Chi nese learners' performance concerning English reading comprehension may influenced by Chinese language or English language.This pa per attempts to explore the influence of first language(Chinese) knowledge on second language(English) reading comprehension for Chi nese students in middle school.This investigation concerns over three aspects of L1 knowledge:genre knowledge,reading skills,and cultur al knowledge.It firstly demonstrates the research question.Then,based on schema theory,it introduces the research method and partici pants in this study.Furthermore,this paper presents the data of the investigation along with the data analysis.It finally concludes that the positive effects of L1 knowledge on L2 reading comprehension overweigh its negative effects.

The Incentive Mechanism Research of Knowledge Workers

＂Knowledge workers＂ is the carrier of enterprise knowledge and technology and is undoubtedly the most important resource and core competence. How to effectively motivate such people create greater wealth for the enterprise has become the key problem of the era of knowledge economy. Based on the concept and characteristics of knowledge workers, this paper uses classical analysis framework of incentive theory; through quantitative and qualitative analysis, it points out the existing problems and puts forward solutions on the basis of full analysis of the present incentive situation.

Arrhythmia Detection by Using Chaos Theory with Machine Learning Algorithms

Heart monitoring improves life quality.Electrocardiograms(ECGs or EKGs)detect heart irregularities.Machine learning algorithms can create a few ECG diagnosis processing methods.The first method uses raw ECG and time-series data.The second method classifies the ECG by patient experience.The third technique translates ECG impulses into Q waves,R waves and S waves(QRS)features using richer information.Because ECG signals vary naturally between humans and activities,we will combine the three feature selection methods to improve classification accuracy and diagnosis.Classifications using all three approaches have not been examined till now.Several researchers found that Machine Learning(ML)techniques can improve ECG classification.This study will compare popular machine learning techniques to evaluate ECG features.Four algorithms—Support Vector Machine(SVM),Decision Tree,Naive Bayes,and Neural Network—compare categorization results.SVM plus prior knowledge has the highest accuracy(99%)of the four ML methods.QRS characteristics failed to identify signals without chaos theory.With 99.8%classification accuracy,the Decision Tree technique outperformed all previous experiments.