• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.7
• /
• pp.1247-1253
• /
• 2008

A design method of a T-S fuzzy model based reduced order nonlinear unknown input observer(NUIO) is presented. The fuzzy NUIO is designed based on the parallel distributed compensation(PDC) concept. It consists of a number of the linear UIOs, each of which is designed for each local linear model in the T-S fuzzy model of a class of nonlinear systems. The fuzzy NUIO provides not only the state estimates insensitive to the unknown inputs, for example, disturbances and faults etc., but also the estimates of the unknown inputs. Therefore, It can be employed in the state feedback control and disturbance rejection control of a class of nonlinear systems with unknown disturbances. It also applied to the robust residual generation for the fault detection and isolation systems and to the design of fault tolerant control systems. As an example, the NUIO is applied to an inverted pendulum system to show the state and disturbance estimation performance and to illustrate the fuzzy reduced order NUIO design method.

• Journal of the Korean Statistical Society
• /
• v.36 no.1
• /
• pp.175-182
• /
• 2007

The support vector machine has been successful in many applications because of its flexibility and high accuracy. However, when a training data set is large or imbalanced, the support vector machine may suffer from significant computational problem or loss of accuracy in predicting minority classes. We propose a modified version of the support vector machine using the K-means clustering that exploits the information in class labels during the clustering process. For large data sets, our method can save the computation time by reducing the number of data points without significant loss of accuracy. Moreover, our method can deal with imbalanced data sets effectively by alleviating the influence of dominant class.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.6
• /
• pp.1501-1509
• /
• 1996

Mobile stations can be classified by the transmission power level in CDMA system. Different performance parameters will be given to each class of mobile stations so that the appropriate quality ofservices can be provided. In this paper, it is assumed that there are two clsses of mobile stations. with the classification of mobile stations, analytical models are presented for the estimates of the reverse link capacity and the blocking probability. From the model for the reverse link capacity, the maximum number of each class of mobile stations to be served is derived. It is shown that $E_{b/}$I reduction of 1 dB allows the capacity to be increased by 25% and the data transmission rate and the power control accuracy have a significant effect on the reverse link capacity and the blocking probability. Simulation results are provided for validating the anlaytical estimates of the blocking probability.ocking probability.y.

• Korean Journal of Computational Design and Engineering
• /
• v.13 no.2
• /
• pp.98-108
• /
• 2008

Plant, civil engineering and construction equipment data of overseas construction are obtained and then analyzed, classified and integrated by experts. With those refined data set, we built classification system and defined property information with reference to international standard (ISO 15926, IRDL). If class in ISO 15926 is predefined for equipment of interest, we used the class as is. If not, we created and defined new classes on the basis of ISO 15926 classes. If there is similar class for equipment of interest, extension or inheritance methods were used. As a result, classification system of five levels and 637 classes were built and construction equipment information were expressed in open structure of XML such as tree structure of classification system and detailed information with number equipments for each specific equipment. We also developed the electronic catalog system which is basically equipment information management system providing various product search functions.

• 한국데이터정보과학회:학술대회논문집
• /
• 2006.11a
• /
• pp.81-95
• /
• 2006

The usual arithmetic operations on real numbers can be extended to arithmetical operations on fuzzy intervals by means of Zadeh's extension principle based on a t-norm T. A t-norm is called consistent with respect to a class of fuzzy intervals for some arithmetic operation if this arithmetic operation is closed for this class. It is important to know which t-norms are consistent with a particular type of fuzzy intervals. Recently Dombi and Gyorbiro proved that addition is closed if the Dombi t-norm is used with two bell-shaped fuzzy intervals. A result proved by Mesiar on a strict t-norm based shape preserving additions of LR-fuzzy intervals with unbounded support is recalled. As applications, we define a broader class of bell-shaped fuzzy intervals. Then we study t-norms which are consistent with these particular types of fuzzy intervals. Dombi and Gyorbiro's results are special cases of the results described in this paper.

• The Transactions of the Korean Institute of Electrical Engineers C
• /
• v.53 no.4
• /
• pp.200-207
• /
• 2004

This paper presents a simple and fast delay metric RC-class interconnects under saturated ramp inputs. The RC delay metric under saturated ramp inputs, called FDM(Fast Delay Metric), can estimate delay times at an arbitrary node using a simple closed-form expression and is extended from delay metric under step input easily As compared with similar techniques proposed in previous researches, it is shown that the FDM technique complexity for a similar accuracy. As the number of circuit nodes increases, there will be a significant difference in estimation times of RC delay between the previous techniques based on two circuit moments and the FDM which do not depend on circuit moments.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.15 no.3
• /
• pp.145-152
• /
• 2015

We consider an online selective-sample learning problem for sequence classification, where the goal is to learn a predictive model using a stream of data samples whose class labels can be selectively queried by the algorithm. Given that there is a limit to the total number of queries permitted, the key issue is choosing the most informative and salient samples for their class labels to be queried. Recently, several aggressive selective-sample algorithms have been proposed under a linear model for static (non-sequential) binary classification. We extend the idea to hidden Markov models for multi-class sequence classification by introducing reasonable measures for the novelty and prediction confidence of the incoming sample with respect to the current model, on which the query decision is based. For several sequence classification datasets/tasks in online learning setups, we demonstrate the effectiveness of the proposed approach.

• Bulletin of the Korean Mathematical Society
• /
• v.59 no.4
• /
• pp.979-991
• /
• 2022

A special class of exponential dispersion models is the class of Tweedie distributions. This class is very significant in statistical modeling as it includes a number of familiar distributions such as Gaussian, Gamma and compound Poisson. A Tweedie distribution has a power parameter p, a mean m and a dispersion parameter 𝜙. The value of the power parameter lies in identifying the corresponding distribution of the Tweedie family. The basic objective of this research work resides in investigating the existence of the implicit estimator of the power parameter of the Tweedie distribution. A necessary and sufficient condition on the mean parameter m, suggesting that the implicit estimator of the power parameter p exists, was established and we provided some asymptotic properties of this estimator.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.585-587
• /
• 2023

Long-tailed datasets have an imbalanced distribution because they consist of a different number of data samples for each class. However, there are problems of the performance degradation in tail-classes and class-accuracy imbalance for all classes. To address these problems, this paper suggests a learning method for training of long-tailed dataset. The proposed method uses and combines two methods; one is a resampling method to generate a uniform mini-batch to prevent the performance degradation in tail-classes, and the other is a reweighting method to address the accuracy imbalance problem. The purpose of our proposed method is to train the learning models to have uniform accuracy for each class in a long-tailed dataset.

• The korean journal of orthodontics
• /
• v.13 no.1
• /
• pp.63-72
• /
• 1983

The author was to study the types and distribution of malocclusion in the 1217 patients with diagnostic charts, cephalograms and study models, who have been treated from March, 1973 to August, 1982 in the Department of orthodontics, Infirmary of Dental College, Yon Sei University. The results were as follows; 1. In the Angle's classification of malocclusion, it was presented that class I malocclusion was 671 persons $(55.1\%)$, class II division 1 malocclusion was 241 persons $(19.8\%)$, class II division 2 malocclusion was 30 persons $(2.5\%)$ and class III malocclusion was 275 persons $(22.6\%)$. 2. In the Angle's class I malocclusion, the crowding was most remarkable $(39\%)$ 3. In the Angle's class II malocclusion, 88 persons $(32.5\%)$ were due to the undergrowth of the mandible, and deep bite was most frequent. 4. In the Angle's class II malocclusion, 94 persons $(34.2\%)$ were .in the pseudo type, 84 persons $(29.8\%)$ were due to the overgrowth of the mandible, and openbite and edge to edge bite were most frequent. 5. In the sexual distribution of the patients, female patients were 791 persons $(65\%)$, male patients were 426 persons $(35\%)$, and the number of females was 1.8 times than that of males. 6. In the age distribution of the patients, 572 persons $(47\%)$ were in the 9-13 years old. 7. In the regional distribution of the patients, most of them lived near the hospital.