• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.120-123
• /
• 1997

This paper presents models of fuzzy inference systems that can be built from a set of input-output training data pairs through hybrid structure-parameter learning. Fuzzy inference systems has the difficulty of parameter learning. Here we develop a coding format to determine a fuzzy neural network(FNN) model by chromosome in a genetic algorithm(GA) and present systematic approach to identify the parameters and structure of FNN. The proposed FNN can automatically identify the fuzzy rules and tune the membership functions by modifying the connection weights of the networks using the GA and the back-propagation learning algorithm. In order to show effectiveness of it we simulate and compare with conventional methods.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.2
• /
• pp.21-27
• /
• 2017

In this paper, we propose a pupil detection method using PCA(principal component analysis) and Hough transform. To reduce error to detect eyebrows as pupil, eyebrows are detected using projection function in eye region and eye region is set to not include the eyebrows. In the eye region, pupil candidates are detected using rank order filter. False candidates are removed by using symmetry. The pupil candidates are grouped into pairs based on geometric constraints. A similarity measure is obtained for two eye of each pair using PCA and hough transform, we select a pair with the smallest similarity measure as final two pupils. The experiments have been performed for 1000 images of the BioID face database. The results show that it achieves the higher detection rate than existing method.

• Journal of applied mathematics & informatics
• /
• v.31 no.3_4
• /
• pp.533-544
• /
• 2013

The multiplicative version of Wiener index (${\pi}$-index), proposed by Gutman et al. in 2000, is equal to the product of the distances between all pairs of vertices of a (molecular) graph G. In this paper, we first present some sharp bounds in terms of the order and other graph parameters including the diameter, degree sequence, Zagreb indices, Zagreb coindices, eccentric connectivity index and Merrifield-Simmons index for ${\pi}$-index of general connected graphs and trees, as well as a Nordhaus-Gaddum-type bound for ${\pi}$-index of connected triangle-free graphs. Then we study the behavior of ${\pi}$-index upon the case when removing a vertex or an edge from the underlying graph. Finally, we investigate the extremal properties of ${\pi}$-index within the set of trees and unicyclic graphs.

• Animal Systematics, Evolution and Diversity
• /
• v.30 no.2
• /
• pp.81-86
• /
• 2014

Three new species of Amynthas (Clitellata: Megascolecidae) were discovered in the Nam Ha National Protected Area (NPA) of Laos. These are Amynthas namhaensis sp. nov., Amynthas vanhi sp. nov., and Amynthas angtanensis sp. nov. Amynthas namhaensis sp. nov. and Amynthas vanhi sp. nov. are athecal, with male pores 0.14-0.17 and 0.17-0.19 circumference apart ventrally, respectively. Amynthas angtanensis sp. nov. has four pairs of spermathecal pores on 4/5-7/8, with male pores very closely set at 0.07-0.1 circumference apart. Descriptions of the new species are provided, including illustrations of the ventral view, intestinal caeca, and spermathecae.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.2
• /
• pp.328-333
• /
• 2003

This paper did to do with 18 muscle pairs that do fetters in anatomy that influence in facial expression change and mix motion of muscle for face facial animation. After set and change mash and make standard model in individual's image, did mapping to mash using individual facial front side and side image to raise truth stuff. Muscle model who become motive power that can do animation used facial expression creation correcting Waters' muscle model. Created deformed face that texture is dressed using these method. Also, 6 facial expression that Ekman proposes did animation.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.6
• /
• pp.1867-1873
• /
• 2000

Function approximation from a set of input-output pairs has numerous applications in scientific and engineering areas. Support vector machine (SVM) is a new and very promising classification, regression and function approximation technique developed by Vapnik and his group at AT&TG Bell Laboratories. However, it has failed to establish itself as common machine learning tool. This is partly due to the fact that this is not easy to implement, and its standard implementation requires the use of optimization package for quadratic programming (QP). In this appear we present simple iterative Kernel Adatron (KA) algorithm for function approximation and compare it with standard SVM algorithm using QP.

• Communications for Statistical Applications and Methods
• /
• v.13 no.3
• /
• pp.635-649
• /
• 2006

In this paper, we perform a simulation study of genetic model-free age-of-onset methods in linkage tests which has been proposed by Zhu et al. (1997). They performe. Haseman-Elston regression on a set of bipolar pedigree data using each of three dependent variables: a binary trait indicating disease concordance or discordance, a binary trait adjusted for age-of-onset, and the residuals from a survival analysis. We compare the powers of the proposed test statistics for various situations. Simulations that we have carried out show that the gains in power are observed when the residuals from a survival analysis are used in linkage tests.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.19 no.1
• /
• pp.271-276
• /
• 1995

This paper presents a systematic method for the dynamic analysis of flexible mechanical systems containing closed kinematic loops. Kinematics between pairs of contiguous flexible bodies is described with the joint coordinates and the deformation modal coordinates. The cut-joint constraint equations associated with the closed kinematic loops are derived, simply using the geometric conditions. The equations of motions are initially written in terms of the joint and modal coordinates using the velocity transformation technique. Lagrange multipliers associated with the cut-joint constraints for closed-loop systems are then eliminated systematically using the generalized coordinate partitioning method, resulting to a minimal set of equations of motion.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.807-810
• /
• 1995

The effects of weae particles on the friiction and wear behavior of metals in dry sliding conditions are presented. The tribological test were performed using pure metal specimens which were selected based on their degrees of compatibility and hardness ratio. Friction and wear experiments were conducted using both pin-on-disk and reciprocating pin-on-plate type tribotesters to investigate the effect of motion history. Experimental results show that in the case of dry sliding the frictional behavior observed during pin-on-disk test differed form that of pin-on-reciprocator test for the given set of material pairs. The friction coefficient and wear rate were found to be higher for the pin-on-disk tests. It is suspected that the sliding motion of the pin affects the wear particle dynamics, which in turn influences the frictional behavior. The effect of material pair properties seemed to be relatively smaller than that of wear particles. The results of this paper is expected to aid in the design of mechanical systems for best tribological performance.

• Korean Management Science Review
• /
• v.21 no.3
• /
• pp.129-147
• /
• 2004

Scenario analysis for strategic planning, unlike most forecasting methods, provides a qualitative, contextual description of how the present will evolve into the future. It normally tries to identify a set of possible futures, each of whose occurrence is plausible but not assured. In this paper, we propose the use of Cross Impact Analysis(CIA) approach for scenario generation about the future of Korean IT environments. In this analysis, we classified IT environments into technical, social, legislative, and economic factor. And various variables and events were defined in each factor. From the survey collected from IT related experts, we acquire probability of occurrence and compatibility estimates of every possible pairs of events as input. Then 2 phase analysis is used in order to choice events with high probability of occurrence and generate scenario. Finally, after CIA using Monte Carlo simulation, a detail scenario for 2010 was developed. These scenario drawn from the CIA approach is a result considered by cross impacts of various events.