• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.4
• /
• pp.285-292
• /
• 2000

In general, exploratory data analysis consists of three processes: i) assessment of clustering tendency, ii) cluster analysis, and iii) cluster validation. This analysis method requiring a number of iterations of step ii) and iii) to converge is computationally inefficient. In this paper, we propose a density function-based approximate fuzzy clustering method with a hierachical structure which consosts of two phases: Phase I is a features(i.e., number of clusters and cluster centers) extraction process based on the tendency assessment of a given data and Phase II is a standard FCM with the cluster centers intialized by the results of the Phase I. Numerical examples are presented to show the validity of the proposed clustering method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.5
• /
• pp.853-862
• /
• 2003

With the data base subject of first grade paper test of information handling technician, We proposed special method of evaluating learning ability directivity to judge that student can understand the contents of each chapter exactly or not, using assigned function and fuzzy deduction in this thesis. Using fuzzy logic, the proposed method of evaluating learning ability is dividing the presenting frequency of setting questions for examination about the subject of database into three rank and we can define this as the important. We applied the fuzzy assigned rate about the number of times of studying through the important of studying and the fuzzy assigned rate about formative evaluation to each of nine fuzzy deduction theories and than evaluated comprehension rate of learning. With the fuzzy grade about learning comprehension of each chapter and assigned rate about the score of generalized evaluation; We applied these two thing to the deduction rule of fuzzy and made it as defuzzifier and finally evaluated learning. We made that the result of eventual evaluating learning is very useful for learners to diagnosis learned contents by themselves and also it can be great material to judge that learners can get the goal of learning or not synthetically.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.1
• /
• pp.81-88
• /
• 2008

In the game balancing. it is so difficult to choose suitable arms among various actions, or arms and to accurately calculate to which level we adjust the balance. The fuzzy method can be properly used in a particular environment which cannot be correctly processed in mathematics or in lessening the time-consuming problems during the accurate number crunching. Because a variety of actions, relations with opponents. previous battle experiences etc. are not easy to be reflected in every occasion, the fuzzy method could be useful in these cases. When the balancing is needed. the data which have been played to that Point are processed by the fuzzy function and calculated to adapt intensity to each action. The ability of characters is regulated in this process. To demonstrate the efficiency of this method. I would like to make clear the excellence of fuzzy method through the following five experiments; a case with invariable ability adjustment, a case adjusted by a randomly chosen action, a case with the strongest weapon selection. a case with the weakest weapon selection and a case with the fuzzy method application.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.2
• /
• pp.126-135
• /
• 2002

The study is concerned with an approach to the design of new architectures of fuzzy neural networks and the discussion of comprehensive design methodology supporting their development. We propose an Adaptive Fuzzy Polynomial Neural Networks(APFNN) based on Fuzzy Neural Networks(FNN) and Self-organizing Networks(SON) for model identification of complex and nonlinear systems. The proposed AFPNN is generated from the mutually combined structure of both FNN and SON. The one and the other are considered as the premise and the consequence part of AFPNN, respectively. As the premise structure of AFPNN, FNN uses both the simplified fuzzy inference and error back-propagation teaming rule. The parameters of FNN are refined(optimized) using genetic algorithms(GAs). As the consequence structure of AFPNN, SON is realized by a polynomial type of mapping(linear, quadratic and modified quadratic) between input and output variables. In this study, we introduce two kinds of AFPNN architectures, namely the basic and the modified one. The basic and the modified architectures depend on the number of input variables and the order of polynomial in each layer of consequence structure. Owing to the specific features of two combined architectures, it is possible to consider the nonlinear characteristics of process system and to obtain the better output performance with superb predictive ability. The availability and feasibility of the AFPNN are discussed and illustrated with the aid of two representative numerical examples. The results show that the proposed AFPNN can produce the model with higher accuracy and predictive ability than any other method presented previously.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.7
• /
• pp.51-60
• /
• 1997

Prototype based methods are commonly used in cluster analysis and the results may be highly dependent on the prototype used. In this paper, we propose a fuzzy clustering method that involves adaptively expanding convex polytopes. Thus, the dependency on the use of prototypes can be eliminated. The proposed method makes it possible to effectively represent an arbitrarily distributed data set without a priori knowledge of the number of clusters in the data set. Specifically, nonlinear membership functions are utilized to determine whether a new cluster is created or which vertex of the cluster should be expanded. For this, the membership function of a new vertex is assigned according to not only a distance measure between an incoming pattern vector and a current vertex, but also the amount how much the current vertex has been modified. Therefore, cluster expansion can be only allowed for one cluster per incoming pattern. Several experimental results are given to show the validity of our mehtod.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.25 no.2
• /
• pp.77-86
• /
• 2000

Consumers facing a large number of brands to choose from are known to use simplified heuristic to screen a set of relevant brands called the consideration set from the whole alternatives, Purchase decisions are then made from the brands in the consideration set, Two approaches have been suggested to model the two-stage choice process., One is to treat the con-sideration set as a crisp set (e.g Roberts and Lattin 1991) The other is to treat the set as a fuzzy set (e.g. Fortheringham 1988) The paper empirically compares the two types of models using data for soft drinks sneakers and departments. The results show that a model employing the crisp set approach fits the data better than that with the fuzzy set approach and better than a single-stage choice logit model.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.11
• /
• pp.997-1004
• /
• 2012

In enterprise software projects, performance issues have become more critical during recent decades. While developing software products, many performance tests are executed in the earlier development phase against the newly added code pieces to detect possible performance regressions. In our previous research, we introduced the framework to enable automated performance anomaly detection and reduce the analysis overhead for identifying the root causes, and showed Statistical Process Control (SPC) can be successfully applied to anomaly detection. In this paper, we explain the special performance trend in which the existing anomaly detection system can hardly detect the noticeable performance change especially when a performance regression is introduced and recovered again a while later. Within the fixed number of sampling period, the fluctuation gets aggravated and the lower and upper control limit get relaxed so that sometimes the existing system hardly detect the noticeable performance change. To resolve the issue, we apply dynamically tuned sampling window size based on the performance trend, and Fuzzy theory to find an appropriate size of the moving window.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2762-2764
• /
• 2001

In this study, we introduce and investigate a class of dynamic perceptron architectures, discuss a comprehensive design methodology and carry out a series of numeric experiments. The proposed dynamic perceptron architectures are called as Polynomial Neural Networks(PNN). PNN is a flexible neural architecture whose topology is developed through learning. In particular, the number of layers of the PNN is not fixed in advance but is generated on the fly. In this sense, PNN is a self-organizing network. PNN has two kinds of networks, Polynomial Neuron(FPN)-based and Fuzzy Polynomial Neuron(FPN)-based networks, according to a polynomial structure. The essence of the design procedure of PN-based Self-organizing Polynomial Neural Networks(SOPNN) dwells on the Group Method of Data Handling (GMDH) [1]. Each node of the SOPNN exhibits a high level of flexibility and realizes a polynomial type of mapping (linear, quadratic, and cubic) between input and output variables. FPN-based SOPNN dwells on the ideas of fuzzy rule-based computing and neural networks. Simulations involve a series of synthetic as well as experimental data used across various neurofuzzy systems. A detailed comparative analysis is included as well.

• Geomechanics and Engineering
• /
• v.30 no.3
• /
• pp.313-324
• /
• 2022

With the development of the economy, people's utilization of underground space are also improved, and a large number of cities have begun to build subways to relieve traffic pressure. The choice of subway station construction method is crucial. If an inappropriate construction method is selected, it will not only waste costs but also cause excessive deformation that may also threaten construction safety. In this paper, a subway station construction scheme selects model based on the AHP-fuzzy comprehensive evaluation. The rationality of the model is verified using numerical simulation and monitoring measurement data. Firstly, considering the economy and safety, a comprehensive evaluation system is established by selecting several indicators. Then, the analytic hierarchy process is used to determine the weight of the evaluation index, and the dimensionless membership in the fuzzy comprehensive evaluation method is used to evaluate the advantages and disadvantages of the construction method. Finally, the method is applied to Liaoyang east road station of Qingdao metro Line 2, and the results are verified by numerical simulation and monitoring measurement data. The results show that the model is scientific, practical and applicable.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• autumn
• /
• pp.473-476
• /
• 2003

This paper presents a systematic risk assessment procedure with uncertainty modeling for general construction projects. Since the approach is able to effectively deal with all the related construction risks in terms of the assumed probability with conditional probability concept that systematically incorporate expert's experiences and subjective judgement, the proposed methods with uncertainty modeling is able to apply to all the construction projects inherent in lots of uncertain risk events. The fuzzy set theory is adopted to enhance risk assessment to effectively handle the vague and dynamic phenomenon of an event Therefore, the fuzzy-based risk assessment is very useful, for those countries, such as Korea, where objective probabilistic data for risk assessment is extremely rare, and thus the utilization of subjective judgmental data based on expert's experiences is inevitable.