• The Korean Journal of Applied Statistics
• /
• v.10 no.2
• /
• pp.261-274
• /
• 1997

Most of the data sets to which the conventional discriminant rules have been applied contain only those which belong to one and only one class among the classes of interest. However the extension of the bivalence to multivlaence like Fuzzy concepts strongly influence the traditional view that an object must belong to only class. Thus the goal of this paper is to develop new discriminant rules which can handle the data each object of which may belong to moer than two classes with certain degrees of belongings. A calibration model is used for the relationship between the feature vector of an object and the degree of belongings and a Bayesian inference is made with the Metropolis algorithm on the degree of belongings when a feature vector of an object whose membership is unknown is given. An evalution criterion is suggested for the rules developed in this paper and comparision study is carried using two training data sets.

• Proceedings of the KIEE Conference
• /
• 2009.07a
• /
• pp.1871_1872
• /
• 2009

본 논문 에서는 Type-2 퍼지 논리 시스템을 설계하고, 불확실한 정보를 갖는 입력 데이터에 대하여 Type-1 퍼지 논리 시스템과 성능을 비교한다. Type-1 퍼지 논리 시스템은 외부 잡음에 민감한 단점을 가지고 있는 반면, Type-2 퍼지 논리 시스템은 불확실한 정보를 잘 표현 할 수 있다. 따라서 Type-2 퍼지 논리 시스템을 이용하여 이러한 단점을 극복하고자 2가지의 모델을 설계한다. 첫 번째 모델은 규칙의 전 후반부가 Type-1 퍼지 집합으로 구성된 Type-1 퍼지 논리 시스템을 설계 한다. 두 번째는 규칙 전 후반부에 Type-2 퍼지 집합으로 구성된 Type-2 퍼지 논리 시스템을 설계한다. 여기서 규칙 전반부의 입력 공간 분할 및 FOU(Footprint Of Uncertainty)형성에는 FCM(Fuzzy C_Means) clustering 방법을 사용하고, 입자 군집 최적화(Particle Swarm Optimization) 알고리즘을 사용하여 최적의 파라미터를 설계한다. 본 논문 에서는 또한 입력 데이터에 인위적으로 가하는 노이즈에 따른 각각 모델의 성능을 비교한다. 마지막으로 비선형 모델 평가에 주로 사용되는 NOx 데이터를 제안된 모델에 적용하고, 실험을 통하여 노이즈가 첨가되고, 불확실한 정보를 다루기에 Type-1 퍼지 논리 시스템 보다 Type-2 퍼지 논리 시스템이 효율적이라는 것을 보인다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.1
• /
• pp.81-86
• /
• 2012

In this paper, we proposed a new design methodology of a pattern classification rule based on the local linear discriminant analysis expanded from the generic linear discriminant analysis which is used in the local area divided from the whole input space. There are two ways such as k-Means clustering method and the differential evolutionary algorithm to partition the whole input space into the several local areas. K-Means clustering method is the one of the unsupervised clustering methods and the differential evolutionary algorithm is the one of the optimization algorithms. In addition, the experimental application covers a comparative analysis including several previously commonly encountered methods.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.6
• /
• pp.1085-1091
• /
• 2012

Phase I clinical trials are designed to identify an appropriate dose; the maximum tolerated dose, which assures safety of a new drug by evaluating the toxicity at each dose-level. The adjusted maximum tolerated dose estimation is presented by stopping rule in phase I clinical trial on this research. The suggested maximum tolerated dose estimation is compared to the standard method3 and NM method using a Monte Carlo simulation study.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.13 no.4
• /
• pp.56-67
• /
• 1999

In this paper, the new composition Irethod of global and local fuzzy reasoning concepts is proposed to reduce, optimize and automatically acquire the number of rules, without any lose of the general performances in conventional fuzzy controllers. In order to control the interaction between global reasoning and local reasoning, the DNA coding algorithm is introduced to the local fuzzy reasoning of the proposed composition fuzzy reasoning rrethod. The method is awlied to the real liquid level control system for the purpose of evaluating the performance. The sinru1ation results show that the proposed technique can control the system with higher accuracy and automatical1y acquire the fuzzy rules with rmre feasibility, than the conventional methods.ethods.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.289-294
• /
• 2022

의존구문분석은 문장을 의존관계(의존소-지배소)로 분석하는 구문분석 방법론이다. 현재 사전학습모델을 사용한 전이 학습의 딥러닝이 좋은 성능을 보이며 많이 연구되지만, 데이터셋에 의존적이며 그로 인한 자료부족 문제와 과적합의 문제가 발생한다는 단점이 있다. 본 논문에서는 언어학적 지식에 기반한 강화된 지배소-의존소 제약규칙 에지 알고리즘을 심층학습과 결합한 모델을 제안한다. TTAS 표준 가이드라인 기반 모두의 말뭉치로 평가한 결과, 최대 UAS 96.28, LAS 93.19의 성능을 보였으며, 선행연구 대비 UAS 2.21%, LAS 1.84%의 향상된 결과를 보였다. 또한 적은 데이터셋으로 학습했음에도 8배 많은 데이터셋 학습모델 대비 UAS 0.95%의 향상과 11배 빠른 학습 시간을 보였다. 이를 통해 심층학습과 언어지식의 결합이 딥러닝의 문제점을 해결할 수 있음을 확인하였다.

• Fire Science and Engineering
• /
• v.26 no.1
• /
• pp.80-88
• /
• 2012

This study evaluates the fire resisting capacity of the beam of the legal fire resistance construction, which establishes the Article 3 of the Regulations on Escape and Fire Resistance of Buildings. There are a total of five structures that we consider as legal fire resistance constructions, however, this study has a primary target of the reinforced concrete beam, and tests the fire-resistant performance depend on the covering depth of reinforce concrete. The results showed that it meets the three hours, the maximum statutory fire resistance time, if it was a load ratio of 0.5 and covering depth of 40 cm. Steel framed mortar beam is legal fire resistance structure that it was possessed three hours fire resistance performance, if it was a load ratio of 0.4 and covering depth of 60 mm.

• The Journal of the Korea Contents Association
• /
• v.8 no.6
• /
• pp.26-33
• /
• 2008

The customer relation marketing in which companies can utilize to control and to get the filtered information efficiently has appeared in ubiquitous commerce. It is applying data mining technique to build the management that can even predict and recommend products to customers. In this paper, we proposed the case of customer relation management application using the associative mining. The proposed method uses the associative mining composes frequent customers with occurrence of candidate customer-set creates the association rules. We analyzed the efficient the feature of purchase customers using the hypergraph partition according to the lift of creative association rules. Therefore, we discovered strategies of the cross-selling and the up-selling. To estimate the performance, the suggested method is compared with the existing methods in the questionnaire dataset. The results have shown that the proposed method significantly outperforms the accuracy than the previous methods.

• The Journal of the Korea Contents Association
• /
• v.7 no.10
• /
• pp.19-26
• /
• 2007

Since collaborative filtering has used the nearest-neighborhood method based on item preference it cannot only reflect exact contents but also has the problem of sparsity and scalability. The item-based collaborative filtering has been practically used improve these problems. However it still does not reflect attributes of the item. In this paper, we propose the method of associative group using the FP-Tree to solve the problem of existing recommendation system. The proposed makes frequent item and creates association rule by using FP-Tree without occurrence of candidate set. We made the efficient item group using $\alpha-cut$ according to the confidence of the association rule. To estimate the performance, the suggested method is compared with Gibbs Sampling, Expectation Maximization, and K-means in the MovieLens dataset.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.10
• /
• pp.73-81
• /
• 2015

The paper proposes a prototype selection method and evaluates the generalization performance of standard algorithms and prototype based classification learning. The proposed prototype classifier defines multidimensional spheres with variable radii within class areas and generates a small set of training data. The nearest-neighbor classifier uses the new training set for predicting the class of test data. By decomposing bias and variance of the mean expected error value, we compare the generalization errors of k-nearest neighbor, Bayesian classifier, prototype selection using fixed radius and the proposed prototype selection method. In experiments, the bias-variance changing trends of the proposed prototype classifier are similar to those of nearest neighbor classifiers with all training data and the prototype selection rates are under 27.0% on average.