• Journal of the Korean Institute of Intelligent Systems
• /
• v.2 no.3
• /
• pp.40-49
• /
• 1992

In this paper, an approach to identify fuzzy rules is proposed. The decision of the optimal number of fuzzy rule is made by means of fuzzy c-means clustering. The identification of the parameters of fuzzy implications is carried out by use of genetic algorithms. For the efficinet and fast parameter identification, the reduction thechnique of search areas of genetica algorithms is proposed. The feasibility of the proposed approach is evaluated through the identification of the fuzzy model to describe an input-output relation of Gas Furnace. Despite the simplicity of the propsed apprach the accuracy of the identified fuzzy model of gas furnace is superior as compared with that of other fuzzy modles.

• The Bulletin of The Korean Astronomical Society
• /
• v.41 no.1
• /
• pp.39.1-39.1
• /
• 2016

The cosmic distance can be precisely determined using a 'standard ruler' imprinted by primordial baryon acoustic oscillation (hereafter BAO) in the early Universe. The BAO at the targeted epoch is observed by analyzing galaxy clustering in redshift space (hereafter RSD) of which theoretical formulation is not yet fully understood, and thus makes this methodology unsatisfactory. The BAO analysis through full RSD modeling is contaminated by the systematic uncertainty due to a non--linear smearing effect such as non-linear corrections and uncertainty caused by random viral velocity of galaxies. However, BAO can be probed independently of RSD contamination using the BAO peak positions located in the 2D anisotropic correlation function. A new methodology is presented to measure peak positions, to test whether it is also contaminated by the same systematics in RSD, and to provide the radial and transverse cosmic distances determined by the 2D BAO peak positions. We find that in our model independent anisotropic clustering analysis we can obtain about 2% and 5% constraints on $D_A$ and $H^{-1}$ respectively with current BOSS data which is competitive with other analysis.

• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.2929-2931
• /
• 1999

In this paper, an adaptive fuzzy inference and HCM(Hard C-Means) clustering method are used for on-line fuzzy modeling of nonlinear and complex system. Here HCM clustering method is utilized for determining the initial parameter of membership function of fuzzy premise rules and also avoiding overflow phenomenon during the identification of consequence parameters. To obtain the on-line model structure of fuzzy systems. we use the recursive least square method for the consequent parameter identification. And the proposed on-line identification algorithm is carried out and is evaluated for sewage treatment process system.

• East Asian mathematical journal
• /
• v.40 no.3
• /
• pp.307-318
• /
• 2024

This paper explores the application of matrix factorization, specifically CUR decomposition, in the clustering of Korean language documents by topic. It addresses the unique challenges of Natural Language Processing (NLP) in dealing with the Korean language's distinctive features, such as agglutinative words and morphological ambiguity. The study compares the effectiveness of Latent Semantic Analysis (LSA) using CUR decomposition with the classical Singular Value Decomposition (SVD) method in the context of Korean text. Experiments are conducted using Korean Wikipedia documents and newspaper data, providing insight into the accuracy and efficiency of these techniques. The findings demonstrate the potential of CUR decomposition to improve the accuracy of document clustering in Korean, offering a valuable approach to text mining and information retrieval in agglutinative languages.

• Journal of Information Processing Systems
• /
• v.20 no.3
• /
• pp.296-306
• /
• 2024

Traditional ecological driving (Eco-Driving) evaluations often rely on mathematical models that predominantly offer subjective insights, which limits their application in real-world scenarios. This study develops a robust, data-driven Eco-Driving evaluation model by integrating dynamic and distributed multi-source data, including vehicle performance, road conditions, and the driving environment. The model employs a combination weighting method alongside K-means clustering to facilitate a nuanced comparative analysis of Eco-Driving behaviors across vehicles with identical energy consumption profiles. Extensive data validation confirms that the proposed model is capable of assessing Eco-Driving practices across diverse vehicles, roads, and environmental conditions, thereby ensuring more objective, comprehensive, and equitable results.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.1 s.343
• /
• pp.57-70
• /
• 2006

This paper descWireless Sensor Network consisting of a number of small sensors with transceiver and data processor is an effective means for gathering data in a variety of environments. The data collected by each sensor is transmitted to a processing center that use all reported data to estimate characteristics of the environment or detect an event. This process must be designed to conserve the limited energy resources of the sensor since neighboring sensors generally have the data of similar information. Therefore, clustering scheme which sends aggregated information to the processing center may save energy. Existing multi-hop cluster energy consumption modeling scheme can not estimate exact energy consumption of an individual sensor. In this paper, we propose a new cluster energy consumption model which modified existing problem. We can estimate more accurate total energy consumption according to the number of clusterheads by using Voronoi tessellation. Thus, we can realize an energy efficient cluster formation. Our modeling has an accuracy over $90\%$ when compared with simulation and has considerably superior than existing modeling scheme about $60\%.$ We also confirmed that energy consumption of the proposed modeling scheme is more accurate when the sensor density is increased.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.11
• /
• pp.5379-5388
• /
• 2012

In fuzzy modeling for nonlinear process, the fuzzy rules are typically formed by selection of the input variables, the number of space division and membership functions. The Generation of fuzzy rules for nonlinear processes have the problem that the number of fuzzy rules exponentially increases. To solve this problem, complex nonlinear process can be modeled by generating the fuzzy rules by means of fuzzy division of input space. Therefore, in this paper, rules of non-fuzzy inference systems are generated by partitioning the input space in the scatter form using HCM clustering algorithm. The premise parameters of the rules are determined by membership matrix by means of HCM clustering algorithm. The consequence part of the rules is represented in the form of polynomial functions and the consequence parameters of each rule are identified by the standard least-squares method. And lastly, we evaluate the performance and the nonlinear characteristics using the data widely used in nonlinear process. Through this experiment, we showed that high-dimensional nonlinear systems can be modeled by a very small number of rules.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.4
• /
• pp.500-506
• /
• 2012

A method to model left ventricular assist device (LVAD) and detect suction occurrence for safe LVAD operation is presented. An axial flow blood pump as a LVAD has been used to assist patient with heart problems. While an axial flow blood pump, a kind of a non-pulsatile pump, has relative advantages of small size and efficiency compared to pulsatile devices, it has a difficulty in determining a safe pump operating condition. It can show different pump operating statuses such as a normal status and a suction status whether suction occurs in left ventricle or not. A fuzzy subtractive clustering method is used to determine a model of the axial flow blood pump with this pump operating characteristic and the developed pump model can provide blood flow estimates before and after suction occurrence in left ventricle. Also, a fuzzy subtractive clustering method is utilized to develop a suction detection model which can identify whether suction occurs in left ventricle or not.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.3
• /
• pp.14-22
• /
• 2007

Wireless sensor networks are composed of numerous sensor nodes and exchange or recharging of the battery is impossible after deployment. Thus, sonsor nodes must be very energy-efficient. As neighboring sensor nodes generally have the data of similar information, duplicate transmission of similar information is usual. To prevent energy wastes by duplicate transmissions, it is advantageous to organize sensors into clusters. The performance of clustering scheme is influenced by the cluster-head election method and the size or the number of clusters. Thus, we should optimize these factors to maximize the energy efficiency of the clustering scheme. In this paper, we propose a new energy consumption model for LEACH which is a well-known clustering protocol and determine the optimal number of clusters based on our model. Our model has accuracy over 80% compared with the simulation and is considerably superior to the existing model of LEACH.

• International Journal of Control, Automation, and Systems
• /
• v.1 no.2
• /
• pp.194-202
• /
• 2003

In this paper, we introduce a category of Multi-FNN (Fuzzy-Neural Networks) models, analyze the underlying architectures and propose a comprehensive identification framework. The proposed Multi-FNNs dwell on a concept of fuzzy rule-based FNNs based on HCM clustering and evolutionary fuzzy granulation, and exploit linear inference being treated as a generic inference mechanism. By this nature, this FNN model is geared toward capturing relationships between information granules known as fuzzy sets. The form of the information granules themselves (in particular their distribution and a type of membership function) becomes an important design feature of the FNN model contributing to its structural as well as parametric optimization. The identification environment uses clustering techniques (Hard C - Means, HCM) and exploits genetic optimization as a vehicle of global optimization. The global optimization is augmented by more refined gradient-based learning mechanisms such as standard back-propagation. The HCM algorithm, whose role is to carry out preprocessing of the process data for system modeling, is utilized to determine the structure of Multi-FNNs. The detailed parameters of the Multi-FNN (such as apexes of membership functions, learning rates and momentum coefficients) are adjusted using genetic algorithms. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between approximation and generalization (predictive) abilities of the model. To evaluate the performance of the proposed model, two numeric data sets are experimented with. One is the numerical data coming from a description of a certain nonlinear function and the other is NOx emission process data from a gas turbine power plant.