• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1082-1085
• /
• 1993

In this paper, we notice the fact that a human learning process is characterized by a process under a natural language environment, and discuss an approach of learning based on indirect linguistic instructions. An instruction is interpreted through some meaning elements and each trend. Fuzzy evaluation rule are constructed for the searched meaning elements of the given instruction, and the performance of a system to be learned is improved by the evaluation rules. In this paper, we propose a framework of learning based on indirect linguistic instruction based learning using fuzzy theory: FULLINS(FUzzy-Learning based on Linguistic IN-Struction). The validity of FULLINS is shown by applying it to helicopter flight control.

• The Journal of Korean Association of Computer Education
• /
• v.6 no.4
• /
• pp.95-113
• /
• 2003

We introduce an AFES(Adaptive Fuzzy Evaluation System) that applies an evaluation system used to existing LCMS(Learning Contents Management System) to a fuzzy reasoning rule. The AFES confers a course level on the learner through a fuzzy diagnostic evaluation before the learner enters a learning course. After the learner completes a learning course through the tailored learning path that is suitable for the learner's level, the AFES confers a final grade on the learner by means of fuzzy final evaluation. The biggest characteristic of the AFES is a grade rule of the final grade. Although different learners get the same number of correct answers to the same number of Questions, AFES flexibly confers the different final grade on the learner by means of the number of 125's fuzzy reasoning rules.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.731-739
• /
• 1998

The probabilistic relaxation(PR) scheme based on the conditional probability and probability space partition has the important property that when its compatibility coefficient matrix (CCM) has uniform components it can classify m-dimensional probabilistic distribution vectors into different classes. When consistency or inconsistency measures have been defined, the properties of PRs are completely determined by the compatibility coefficients among labels of labeled objects and influence weight among labeled objects. In this paper we study the properties of PR in which both compatibility coefficients and influence weights are uniform, and then a learning rule for such PR system is derived. Experiments have been performed to verify the effectiveness of the learning rule.

• Journal of Advanced Marine Engineering and Technology
• /
• v.20 no.4
• /
• pp.11-19
• /
• 1996

Recently, fuzzy and neural network techniques have been successfully applied to control of complex and ill-defined system in a wide variety of areas, such as robot, water purification, automatic train operation system and automatic container crane operation system, etc. In this paper, we present a neuro-fuzzy controller which unifies both fuzzy logic and multi-layered feedforward neural networks. Fuzzy logic provides a means for converting linguistic control knowledge into control actions. On the other hand, feedforward neural networks provide salient features, such as learning and parallelism. In the proposed neuro-fuzzy controller, the parameters of membership functions in the antecedent part of fuzzy inference rules are identified by using the error backpropagation algorithm as a learning rule, while the coefficients of the linear combination of input variables in the consequent part are determined by using the least square estimation method. Finally, the effectiveness of the proposed controller is verified through computer simulation of an inverted pendulum system.

• Journal of Information Technology Applications and Management
• /
• v.17 no.2
• /
• pp.71-90
• /
• 2010

Electronic learning(or e-learning) has created hype for companies, universities, and other educational institutions. It has led to the phenomenal growth in the use of web-based learning and experimentation with multimedia, video conferencing, and internet-based technologies. Many researchers are interested in the factors that affect to the performance of e-learning or e-learning services. In this sense, this study is aimed at proposing e-learning system reuse prediction models in which e-learner intention to reuse influence factors(i.e., system accessibility, system stability, information clarity, information validity, self-regulated efficacy, computer self-efficacy, perceived usefulness, perceived ease of use, flow, and parental expectation) affect e-learner intention to reuse positively. A web survey was conducted for the full members of the e-learning education institute A in Seoul, Republic of Korea, an exclusive e-learning company that provides real time video lectures via the desktop conferencing system. The web survey was conducted for 20 days from November 5, 2009, through the e-learning web site of the company A. In this study, three data mining techniques were used : the multivariate discriminant analysis, CART, and C5.0 algorithm. This study was conducted to provide the e-learning service providers, e-learning operators, and contents developers with marketing and management strategies for improving the e-learning service companies, based on the data mining analysis results.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.2 no.3
• /
• pp.210-214
• /
• 2002

Association rule mining is an exploratory learning task to discover some hidden dependency relationships among items in transaction data. Quantitative association rules denote association rules with both categorical and quantitative attributes. There have been several works on quantitative association rule mining such as the application of fuzzy techniques to quantitative association rule mining, the generalized association rule mining for quantitative association rules, and importance weight incorporation into association rule mining fer taking into account the users interest. This paper introduces a new method for generalized fuzzy quantitative association rule mining with importance weights. The method uses fuzzy concept hierarchies fer categorical attributes and generalization hierarchies of fuzzy linguistic terms fur quantitative attributes. It enables the users to flexibly perform the association rule mining by controlling the generalization levels for attributes and the importance weights f3r attributes.

• Journal of the Korean Society of Industry Convergence
• /
• v.6 no.1
• /
• pp.37-42
• /
• 2003

In this paper a self-organizing fuzzy system with rule pruning is proposed. A conventional self-organizing fuzzy system having only rule generation has a drawback in generating many slightly different rules from the existing rules which results in increased computation time and slowly learning. The proposed self-organizing fuzzy system generates fuzzy rules based on input-output data and prunes redundant rules which are caused by parameter training. The proposed system has a simple structure but performs almost equivalent function to the conventional self-organizing fuzzy system. Also, this system has better learning speed than the conventional system. Simulation results on several numerical examples demonstrate the performance of the proposed system.

• Journal of Intelligence and Information Systems
• /
• v.1 no.2
• /
• pp.57-71
• /
• 1995

This paper presents a rule extraction algorithm RE to acquire explicit rules from trained neural networks. The validity of extracted rules has been confirmed using 6 different data sets. Based on experimental results, we conclude that extracted rules from RE predict more accurately and robustly than neural networks themselves and rules obtained from an inductive learning algorithm do. Rule extraction algorithm for neural networks are important for incorporating knowledge obtained from trained networks into knowledge based systems. In lieu of this, the proposed RE algorithm contributes to the trend toward developing hybrid and versatile knowledge-based system including expert systems and knowledge-based decision su, pp.rt systems.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.11
• /
• pp.1456-1462
• /
• 2016

In this paper, we apply a chord progression learning model to a rule-based generation of a four-part chorus. The proposed system is given a 32-note melody line and completes the four-part chorus based on the rule of harmonics, predicting the chord progression with the CRBM model. The data for the training model was collected from various harmony textbooks, and chord progressions were extracted with key-independent features so as to utilize the given data effectively. It was shown that the output piece obtained with the proposed learning model had a more natural progression than the piece that used only the rule-based approach.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.7
• /
• pp.170-178
• /
• 1994

The nearest neighbor classification rule is widely used because it is not only simple but the error rate is asymptotically less than twice Bayes theoretical minimum error. But the method basically use the whole training patterns as the reference vectors. so that both storage and classification time increase as the number of training patterns increases. LVQ(Learning Vector Quantization) resolved this problem by training the reference vectors instead of just storing the whole training patterns. But it is a heuristic algorithm which has no theoretic background there is no terminating condition and it requires a lot of iterations to get to meaningful result. This paper is to propose a new training method of the reference vectors. which minimize the given error function. The nearest neighbor network,the network version of the nearest neighbor classification rule is proposed. The network is funtionally identical to the nearest neighbor classification rule is proposed. The network is funtionally identical to the nearest neighbor classification rule and the reference vectors are represented by the weights between the nodes. The network is trained to minimize the error function with respect to the weights by the steepest descent method. The learning algorithm is derived and it is shown that the proposed method can adjust more reference vectors than LVQ in each iteration. Experiment showed that the proposed method requires less iterations and the error rate is smaller than that of LVQ2.