• Title/Summary/Keyword: yield behavior

Search Result 1,194, Processing Time 0.029 seconds

Implicit Numerical Integration of Two-surface Plasticity Model for Coarse-grained Soils (Implicit 수치적분 방법을 이용한 조립토에 관한 구성방정식의 수행)

  • Choi, Chang-Ho
    • Journal of the Korean Geotechnical Society
    • /
    • v.22 no.9
    • /
    • pp.45-59
    • /
    • 2006
  • The successful performance of any numerical geotechnical simulation depends on the accuracy and efficiency of the numerical implementation of constitutive model used to simulate the stress-strain (constitutive) response of the soil. The corner stone of the numerical implementation of constitutive models is the numerical integration of the incremental form of soil-plasticity constitutive equations over a discrete sequence of time steps. In this paper a well known two-surface soil plasticity model is implemented using a generalized implicit return mapping algorithm to arbitrary convex yield surfaces referred to as the Closest-Point-Projection method (CPPM). The two-surface model describes the nonlinear behavior of coarse-grained materials by incorporating a bounding surface concept together with isotropic and kinematic hardening as well as fabric formulation to account for the effect of fabric formation on the unloading response. In the course of investigating the performance of the CPPM integration method, it is proven that the algorithm is an accurate, robust, and efficient integration technique useful in finite element contexts. It is also shown that the algorithm produces a consistent tangent operator $\frac{d\sigma}{d\varepsilon}$ during the iterative process with quadratic convergence rate of the global iteration process.

The Effect of Online Multiple Channel Marketing by Device Type (디바이스 유형을 고려한 온라인 멀티 채널 마케팅 효과)

  • Hajung Shin;Kihwan Nam
    • Information Systems Review
    • /
    • v.20 no.4
    • /
    • pp.59-78
    • /
    • 2018
  • With the advent of the various device types and marketing communication, customer's search and purchase behavior have become more complex and segmented. However, extant research on multichannel marketing effects of the purchase funnel has not reflected the specific features of device User Interface (UI) and User Experience (UX). In this study, we analyzed the marketing channel effects of multi-device shoppers using a unique click stream dataset from global online retailers. We examined device types that activate online shopping and compared the differences between marketing channels that promote visits. In addition, we estimated the direct and indirect effects on visits and purchase revenue through customer's accumulated experience and channel conversions. The findings indicate that the same customer selects a different marketing channel according to the device selection. These results can help retailers gain a better understanding of customers' decision-making process in multi-marketing channel environment and devise the optimal strategy taking into account various device types. Our empirical analyses yield business implications based on the significant results from global big data analytics and contribute academically meaningful theoretical framework using an economic model. We also provide strategic insights attributed to the practical value of an online marketing manager.

A Comparative Study on Attitude of the Collegiate an4 Non-Collegiate Nursing Students toward Their Clinical Affiliation in a Mental Hospital (정신과 간호 실습에 대한 간호 대학생과 간호학교 학생들의 태도 비교 연구)

  • 김소야자
    • Journal of Korean Academy of Nursing
    • /
    • v.4 no.2
    • /
    • pp.17-31
    • /
    • 1974
  • Today, over seventy five percent of nursing in Korea provide a psychiatric experience in the basic curriculum. The psychiatric affiliation presents numerous major problems of adjustment to the student. The Importance of positive attitude toward the nursing care of psychiatric patients is recognized by the nursing profession. I have fined out the unfavorable attitude of non collegiate nursing students toward psychiatric nursing affiliation by previous research. This study was undertaken in response to a felt need to explore the use of several devices which might yield information about attitudes toward psychiatric nursing as a basis for future planning of the program offered at a selected hospital. This study is designed to meet the following objectives; (1) In order to find out the expressed attitudes of fifty·three collegiate nursing students toward their psychiatric affiliation. (2) To compare responses given by selected group of collegiate and non collegiate nursing students to same questionnaire (3) To determine the relationship between the attitudes of nursing students toward psychiatric nursing and the type of instructions where experience was obtained. A questionnaire, a Korean translation of the "Psychiatric Nursing Attitude Questionnaire" by Moldered Elizabeth fletcher, was administered to fifty-three collegiate nursing students who had completed a four-week psychiatric affiliation in a S hospital psychiatric ward during May 7, 1973 to Dec. 16, 1973. - The questionnaire of 100 statements was administered in the following way; (1) Part Ⅰ, Preconceptions, was, given in individual conferences with each subject, during the first few days of their affiliation, and again during the final week of affiliation. The responses to Part I were oral. (2) Part Ⅱ, Expectations, Part Ⅲ, Personal Relations, Part Ⅳ, Personal Feelings, and Part V, Attitudes and Activities of Patients were given to all of the subjects in a group meeting during the second week of the affiliation, and again, during the fourth week at the termination of the affiliation. Responses to Parts Ⅱ, Ⅲ, Ⅳ·, and V, were written. Each of the 100 statements of the questionnaire was considered to be either Positive or Negative. A favorable response was assigned the positive value of 1 and an unfavorable response was assigned the Negative value of O. The coefficient of correlation was computed between the two sets of scores for the fifty-three nursing students, The mean score, the standard deviation, and the differences in the means on each of the five parts of the questionnaire were computed and the relationships calculated by at-test. The results of the study were as follows; 1. There was no significant correlation between the two sets of the scores for the fifty-three nursing students during the four-week psychiatric affiliation. (r= 0.36) 2. There was no significant difference in the mean scores between the first and final tests for any of the questionnaire. 3. The Part Ⅰ, Preconceptions, data indicated collegiate nursing students have positive attitudes in preconceptions than non collegiate nursing students and preconceptions toward the psychiatric affiliation which affect their psychiatric nursing experience. 4. The Part Ⅱ, Expectations, data indicated more appropriate expectations of collegiate nursing students related to pre psychiatric affiliation orientation and sufficient theory learning than non-collegiate nursing students. 5. The Part Ⅲ, Personal relations, data indicated some students have negative attitudes in personal relations with normal people in respect to psychological security and social responsibilities. 6. The Part Ⅳ, Personal feelings, data indicated nursing students have psychological insecurity & inappropriateness. 7. The Part V, Attitudes and activities of patients, data indicated collegiate nursing students have more positive attitudes to the psychotic behavior of certain situations due to sufficient theory learning. 8. The data indicated collegiate·nursing students have more positive attitude than non-collegiate nursing students. 5. The Part Ⅲ, Personal relations, data indicated some students have negative attitudes in personal relations with normal people in respect to psychological security and social responsibilities. 6. The Part Ⅳ, Personal feelings, data indicated nursing students have psychological insecurity & inappropriateness. 7. The Part V, Attitudes and activities of patients, data indicated collegiate nursing students have more positive attitudes to the psychotic behavior of certain situations due to sufficient theory learning. 8. The data indicated collegiate·nursing students have more positive attitude than non-collegiate nursing students through psychiatric affiliation.

  • PDF

STUDIES ON THE DIMORPHISM AND FERTILITY OF PERSICARIA JAPONICA (MEISSNER) GROSS ET NAKAI (Persicaria Japonica (MISSNER) Gross et Nakai의 이형화와 수정력에 관한 연구)

  • HARN, Chang Yawl
    • Journal of Plant Biology
    • /
    • v.3 no.1
    • /
    • pp.1-15
    • /
    • 1960
  • HARN, Chang Yawl : Studies on the dimorphism and Fertility of Persicaria japonica (MEISSNER) Gross et Nakai. Kor Jour. Bot. 3(I) 1-15 1960 Numerous investigations, since the works of DARWIN, have been made regarding the heterostylous plants by JOST (1907), CORRENS (1924), LAIBACK (1924), LEWIS (1943), and many others. Studies on the heterostylous Polygomum, however, were not reported except for the buckwhent, Fagopyrum esculentum, which was investigated by SCHOCH-BODMER (1930), EAST (1934), FROLOVA & Co-Workers (1946), MORRIS (1947, 1951) TATEBE (1949, 1951, 1953), present author (1957), and others. It is because no heterostylous species, besides buckwheat, have been known to exist in the Polygonum family. The author, during his studies on both heterostylism and fertility of Polygonaceae, has found that the species, persicaria japonica (Meissner) Gross et Nakai, is not diecious as has been known in taxonomy, but in reality beterostylous both morphologically and physiologically. It was found that this plant, regarded by taxonomist, as a male plant setting no seed, actually set seed (botanical fruit) when legitimate combination was made. Since his brief report on the dimorphic phenomens of this plant in 1956, the author's further research on the manner of fertilization has revealed that this species is a peculiar type whose dimorphism has undergone extreme specialization structurally and physiologically, the short-styled individual behaving in nature as a male plant and the long-styled individual, as female, whereas in controllled pollination the plant shows highly differentiated typical dimorphism. When compared with the other dimorphous species of this family, F. esculentum and P. sentiosa. it has been clarified that these three species differ in the degree of differentiation of their dimorphism morphologically and physiologically. That is, P. japonica has developed such a high specialization as to mislead the taxonomists, while P. senticosa shows almost no noticeable difference between long- and shortstyled individuals retaining most of the inherent physiological character cmmon to the genus except for the fact that it has two forms of flowers. F. esculentum appears to have taken the intermediate position in every respect. The result obtained in the present experiment are summarized as follows: 1) P. japonica has two kinds of individuals, one long style-short stamened; the other, short style-long stamened. The floral structure of this plants shows typical characteristics of dimorphic heterostylism. The differentiation between the two forms of flower has proceeded so highly both in primary and secondary difference of flower structure that this may be regarded as the most specialized form of dimorphism. 2) The differences of floral structure between the long and short styled individuals are remarkable compared with the other dimorphic species of the family. 3) The stamens of long styled plants show the sign of deteriolation whereas those of the short styled flower are well-developed. 4) When legitimate combinations are made, both L- and S-styled individuals are fertilized well and set seed (fruit), while in the illegitimate combination no fertilization and seed setting occur. Physiologically this species exhibits the typical behavior of dimorphic plants. 5) The self-fertile character, so common in other species of the other non-heterostyle Polygonum family, has disappeared completely. 6) Under natural conditions, no or few seed setting is observed in short styled individuals that behave as if they were male plants. 7) In hand pollination, the combination of both $L{\times}S$ and $S{\times}L$ alike yield relatively good fertility and seed-formation, the behavior of short styled individuals in artificial pollination differing remarkably from that in nature. 8) Under controlled pollination, $L{\times}S$ combination sets far more seed than in the combination of $S{\times}L$. In the S-styled individuals, the fertilized flower has the tendency of its seed more readily falling off in every stage of seed development than in the L-styled individuals. 9) The behaviors of pollen tubes just parallels the results of fertility test. That is, in the illegitimate combination, L-selfed, $L{\times}L$, S-selfed, and $S{\times}S$, the growth of pollen tubes is checked in the style, while in legitimately combined $L{\times}S$ and $S{\times}L$, the pollen tubes grow well reaching the ovaries within 40-50 minutes after pollination. The response of short styled individuals, known as male plant among taxonomists, is identical, as far as behavior fo pollen tube growth and fertilization are concerned, to that of long styled individuals, the so-called female plant. 10) The pollen grains from the short-styled plants are complete and fertile, whereas 70% of those of L-styled are found to be abortive, i.e., empty contents. 11) The remaining 30% of pollen of L-plant shows varied degree of stainability when stained with iron-aceto-carmine......mostly light red, while the pollen grains of S-style individuals are dark brown indicating complete fertility and viability. 12) The abundance of sterile pollen in L-styled and the nature of seed-dropping which occurs in S-styled individuals appear to be the main causes why the short styled individuals bear no seed in nature. Under controlled legitimate union, $S{\times}L$, the careful and elaborate pollination would give the S-styoled flowers the opportunities to receive the fertile pollens, though few in number, from L-styled plant, thus enabling S-plant to bear seed. 13) This species is not dioecious as is regarded by taxonomists, but typical dimorphic plant which has so highly specialized in floral structures and funcitons that the long-styled plant behaves just like a female individual; and the short-styled, like a male.

  • PDF

The Characteristics of Korean Smoker, Enrolled in '5 day Smoking Cessation School' and The Effect of Inpatient Smoking Cessation Program (서울 위생 병원 5일 금연 학교를 방문한 우리나라 흡연자의 특성 및 입원 금연 교육 프로그램의 효과)

  • Lee, Byung Soo;Kang, Ki Hoon;Chae, Eun Ha;Kim, Myung Chan;Jung, Jae Il;Chang, Hee Jong;Lee, Sang Hoon;Cho, Dong Sik;Shin, Jai Gyu;Kim, Hui Jung
    • Tuberculosis and Respiratory Diseases
    • /
    • v.57 no.5
    • /
    • pp.411-418
    • /
    • 2004
  • Background : Cigarette smoking is the single biggest avoidable cause of death and disability in most countries. Effective prevention of cigarette Smoking and help for those wishing to quit can therefore yield enormous health benefits for populations and individuals. Although most of smokers try to stop smoking for themselves, the success rate of quitting smoking is very low. Promoting and supporting smoking cessation should be an important health policy priority for healthcare professionals in all clinical settings. In this study, we tried to evaluate the effect of the educational program for smoking cessation of our hospital, the smoking pattern, and characteristics of adult smokers enrolled in the program. Methods : We enrolled 640 smokers, who has visited the '5 day stop smoking school' for smoking cessation from Jan 1998 to 2001. we evaluated the characteristics of the smokers based on the self report questionnaire at the beginning of the program and we also checked 100 smokers, enrolled in Inpatient Smoking Cessation Educational program, their smoking behavior and the cessation rate with postal questionnaire after finishing this program from Nov 2002 to Jan 2003. Results : The health was most common motivation for smoking cessation. The stress was the most important motivation of smoking. The overall smoking cessation rate of the smokers enrolled in inpatient smoking cessation school was 60%. The age of starting smoking and the kind of occupation have a significant difference between the success group and failure group of smoking cessation. Conclusion : The inpatient smoking cessation program was effective smoking cessation intervention in the adult smokers who enrolled in '5 day stop smoking school'.

A Review on Ultimate Lateral Capacity Prediction of Rigid Drilled Shafts Installed in Sand (사질토에 설치된 강성현장타설말뚝의 극한수평지지력 예측에 관한 재고)

  • Cho Nam Jun;Kulhawy F.H
    • Journal of the Korean Geotechnical Society
    • /
    • v.21 no.2
    • /
    • pp.113-120
    • /
    • 2005
  • An understanding of soil-structure interaction is the key to rational and economical design for laterally loaded drilled shafts. It is very difficult to formulate the ultimate lateral capacity into a general equation because of the inherent soil nonlincarity, nonhomogeneity, and complexity enhanced by the three dimensional and asymmetric nature of the problem though extensive research works on the behavior of deep foundations subjected to lateral loads have been conducted for several decades. This study reviews the four most well known methods (i.e., Reese, Broms, Hansen, and Davidson) among many design methods according to the specific site conditions, the drilled shaft geometric characteristics (D/B ratios), and the loading conditions. And the hyperbolic lateral capacities (H$_h$) interpreted by the hyperbolic transformation of the load-displacement curves obtained from model tests carried out as a part of this research have been compared with the ultimate lateral capacities (Hu) predicted by the four methods. The H$_u$ / H$_h$ ratios from Reese's and Hansen's methods are 0.966 and 1.015, respectively, which shows both the two methods yield results very close to the test results. Whereas the H$_u$ predicted by Davidson's method is larger than H$_h$ by about $30\%$, the C.0.V. of the predicted lateral capacities by Davidson is the smallest among the four. Broms' method, the simplest among the few methods, gives H$_u$ / H$_h$ : 0.896, which estimates the ultimate lateral capacity smaller than the others because some other resisting sources against lateral loading are neglected in this method. But it results in one of the most reliable methods with the smallest S.D. in predicting the ultimate lateral capacity. Conclusively, none of the four can be superior to the others in a sense of the accuracy of predicting the ultimate lateral capacity. Also, regardless of how sophisticated or complicated the calculating procedures are, the reliability in the lateral capacity predictions seems to be a different issue.

Analysis on the Users′ Behaviors and Satisfaction on the Actual Conditions of Management in Chiri Mountain National Park (지리산국립공원의 이용자 행태분석과 관리실태에 대한 만족도 조사에 관한 연구)

  • 김광래;진희성;김세천
    • Journal of the Korean Institute of Landscape Architecture
    • /
    • v.16 no.2
    • /
    • pp.43-57
    • /
    • 1988
  • The purpose of this thesis is to suggest objective basic data for park management proposal through the quantitative analysis of users' behaviors and satisfaction for the actual conditions of management in the Chiri Mountain National Park. For this users' behaviors and socio-economic characteristics have been cross-analyzed. Specifically, it attempts to investigate users' anticipate and degree of satisfaction applied Expectancy Theory by Likert attitude scale. Users'behaviors patterns of each site have been analyzed by the factor analysis algorithm, and each factor scores of sites have been clustered by the cluster method. And also user' satisfaction for the actual conditions of management have been analyzed by using the multiple regression. The major user groups were students and youth groups accompanied by their friends ranging from 3 to 10. The values of user'post occupancy-evaluation for such as rockwall climbing and praying on the mountain of each site showed higher than those of anticipated, but evaluation values of other activities were lower. The user'behaviors of each site have been analyzed five factors by factor analysis algorithm. By using the control method for the number of factors, T.V. has been obtained as 50.58%. The factor score of factor covering the behavior patterns of student and youth yield high EV. and C.V.. On the analysis of cluster using factor score, factor IV in Hwaomsa temple site and Ssanggyesa temple site, factor II, v in Jungsanri Valley site, factor, I, III in Bangmudong valley site and factor I. IV in Baemsagol vallry site showed very high values, respectively. According to the multiple regression analysis, the major variables related to the satisfaction for the actual conditions of vegetation and landscape managements were reservation of groundcover, recovery of artificial injury, the surroundings of camping and temple site. In the park facilities and operation, the major variables related to the satisfaction were conditions of management such amenity facilities as privy, sign board, junk yard, camping site, and guidance of excursion, campaign and preservation of nature.

  • PDF

Optimal Configuration of the Truss Structures by Using Decomposition Method of Three-Phases (3단계(段階) 분할기법(分割技法)에 의한 평면(平面)트러스 구조물(構造物)의 형상(形狀) 최적화(最適化)에 관한 연구(硏究))

  • Lee, Gyu Won;Song, Gi Beom
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • v.12 no.3
    • /
    • pp.39-55
    • /
    • 1992
  • In this research, a Three Level Decomposition technique has been developed for configuration design optimization of truss structures. In the first level, as design variables, behavior variables are used and the strain energy has been treated as the cost function to be maximized so that the truss structure can absorb maximum energy. For design constraint of the optimal design problem, allowable stress, buckling stress, and displacement under multi-loading conditions are considered. In the second level, design problem is formulated using the cross-sectional area as the design variable and the weight of the truss structure as the cost function. As for the design constraint, the equilibrium equation with the optimal displacement obtained in the first level is used. In the third level, the nodal point coordinates of the truss structure are used as coordinating variable and the weight has been taken as the cost function. An advantage of the Three Level Decomposition technique is that the first and second level design problems are simple because they are linear programming problems. Moreover, the method is efficient because it is not necessary to carry out time consuming structural analysis and techniques for sensitivity analysis during the design optimization process. By treating the nodal point coordinates as design variables, the third level becomes unconstrained optimal design problems which is easier to solve. Moreover, by using different convergence criteria at each level of design problem, improved convergence can be obtained. The proposed technique has been tested using four different truss structures to yield almost identical optimum designs in the literature with efficient convergence rate regardless of constraint types and configuration of truss structures.

  • PDF

Rheological Properties of Chitosan Manufactured from the Pens of Domestic (Todarodes pacificus) and Foreign (Ommastrephes bartrami) Squid (연안산 및 남미산 오징어 연골로부터 제조한 Chitosan의 레올로지 특성)

  • KIM Sang-Moo;PARK Seong-Min;CHOI Hyeon-Mee;LEE Keun-Tai
    • Korean Journal of Fisheries and Aquatic Sciences
    • /
    • v.30 no.5
    • /
    • pp.859-867
    • /
    • 1997
  • In order to utilize the processing wastes of squid, chitosans were manufactured from the pens of domestic squid, Todarbdes pacificus and foreign squid, Ommastrephes bartrami and then, its rheological properties were studied. The amounts of nitrogen and minerals of the domestic squid pens were $11.4\%\;and\;0.1\%$ respectively, whereas those of its chitosan were $7.5\%\;and\;0.2\%$. In case of foreign squid pen and chitosan, the amounts of nitrogen and minerals were $12.1\%,\;0.8\%\;and\;7.8\%,\;0.2\%$ respectively. Intrinsic viscosity $([\eta]) $ of domestic and foreign squid pen chitosans were decreased with increasing pH from 3.4 to 5.4 which might be due to the reduced repulsion in inter- of intra- chitosan molecules. Intrinsic viscosity of the domestic and foreign squid pen chitosans were decreased with increasing NaCl concentration thus indicated that the domestic and foreign squid pen chitosans were polyelectrolyte molecules and stiffness of squid pen thitosans were 0.11 similar to that of k-carrageenan. Flow type of squid pen chitosan solutions were pseudoplastic fluids without yield stress by the viscosity measurement. But the squid pen chitosan solutions showed newtonian fluid up to $0.15\~0.24\%$ concentration for domestic and $0.21\~0.24\%$ concentration for foreign at $10\~50\%$. Concentration dependence of consistency index in infinitive dilute domain (Kc) were higher in the dilute domain than entangled domain. Activation energies (Ea) of the squid pen chitosans were 3.7, 6.3, 3.6, 4.0 and 4.1 Kcal/g moi for domestic and 3.2, 3.1, 3.4, 3.8 and 3.6 Kcal/g mol for foreign at 0.1, 0.15, 0.25, 0.35 and $0.5\%$, respectively.

  • PDF

Optimal Selection of Classifier Ensemble Using Genetic Algorithms (유전자 알고리즘을 이용한 분류자 앙상블의 최적 선택)

  • Kim, Myung-Jong
    • Journal of Intelligence and Information Systems
    • /
    • v.16 no.4
    • /
    • pp.99-112
    • /
    • 2010
  • Ensemble learning is a method for improving the performance of classification and prediction algorithms. It is a method for finding a highly accurateclassifier on the training set by constructing and combining an ensemble of weak classifiers, each of which needs only to be moderately accurate on the training set. Ensemble learning has received considerable attention from machine learning and artificial intelligence fields because of its remarkable performance improvement and flexible integration with the traditional learning algorithms such as decision tree (DT), neural networks (NN), and SVM, etc. In those researches, all of DT ensemble studies have demonstrated impressive improvements in the generalization behavior of DT, while NN and SVM ensemble studies have not shown remarkable performance as shown in DT ensembles. Recently, several works have reported that the performance of ensemble can be degraded where multiple classifiers of an ensemble are highly correlated with, and thereby result in multicollinearity problem, which leads to performance degradation of the ensemble. They have also proposed the differentiated learning strategies to cope with performance degradation problem. Hansen and Salamon (1990) insisted that it is necessary and sufficient for the performance enhancement of an ensemble that the ensemble should contain diverse classifiers. Breiman (1996) explored that ensemble learning can increase the performance of unstable learning algorithms, but does not show remarkable performance improvement on stable learning algorithms. Unstable learning algorithms such as decision tree learners are sensitive to the change of the training data, and thus small changes in the training data can yield large changes in the generated classifiers. Therefore, ensemble with unstable learning algorithms can guarantee some diversity among the classifiers. To the contrary, stable learning algorithms such as NN and SVM generate similar classifiers in spite of small changes of the training data, and thus the correlation among the resulting classifiers is very high. This high correlation results in multicollinearity problem, which leads to performance degradation of the ensemble. Kim,s work (2009) showedthe performance comparison in bankruptcy prediction on Korea firms using tradition prediction algorithms such as NN, DT, and SVM. It reports that stable learning algorithms such as NN and SVM have higher predictability than the unstable DT. Meanwhile, with respect to their ensemble learning, DT ensemble shows the more improved performance than NN and SVM ensemble. Further analysis with variance inflation factor (VIF) analysis empirically proves that performance degradation of ensemble is due to multicollinearity problem. It also proposes that optimization of ensemble is needed to cope with such a problem. This paper proposes a hybrid system for coverage optimization of NN ensemble (CO-NN) in order to improve the performance of NN ensemble. Coverage optimization is a technique of choosing a sub-ensemble from an original ensemble to guarantee the diversity of classifiers in coverage optimization process. CO-NN uses GA which has been widely used for various optimization problems to deal with the coverage optimization problem. The GA chromosomes for the coverage optimization are encoded into binary strings, each bit of which indicates individual classifier. The fitness function is defined as maximization of error reduction and a constraint of variance inflation factor (VIF), which is one of the generally used methods to measure multicollinearity, is added to insure the diversity of classifiers by removing high correlation among the classifiers. We use Microsoft Excel and the GAs software package called Evolver. Experiments on company failure prediction have shown that CO-NN is effectively applied in the stable performance enhancement of NNensembles through the choice of classifiers by considering the correlations of the ensemble. The classifiers which have the potential multicollinearity problem are removed by the coverage optimization process of CO-NN and thereby CO-NN has shown higher performance than a single NN classifier and NN ensemble at 1% significance level, and DT ensemble at 5% significance level. However, there remain further research issues. First, decision optimization process to find optimal combination function should be considered in further research. Secondly, various learning strategies to deal with data noise should be introduced in more advanced further researches in the future.