• The KIPS Transactions:PartD
• /
• v.11D no.7 s.96
• /
• pp.1451-1458
• /
• 2004

Current software reliability growth models based on Gompertz growth curve are all logarithmic type. Software reliability growth models based on logarithmic type Gompertz growth curve has difficulties in parameter estimation. Therefore this paper proposes a software reliability growth model based on the logistic type Gompertz growth curie. Its usefulness is empirically verified by analyzing the failure data sets obtained from 13 different software projects. The parameters of model are estimated by linear regression through variable transformation or Virene's method. The proposed model is compared with respect to the average relative prediction error criterion. Experimental results show that the pro-posed model performs better the models based on the logarithmic type Gompertz growth curve.

• The KIPS Transactions:PartD
• /
• v.11D no.3
• /
• pp.597-604
• /
• 2004

Accurate software cost estimation is essential to both developers and customers. Most of the cost estimating models based on the size measure methods, such as LOC and FP, are obtained through size estimation. The accuracy of size estimation directly influences the accuracy of cost estimation. As a result, the overall structure of regression-based cost models applies the power function based on software size. Many growth phenomenon in nature such as the growth in living organism, performance of technology, and learning capability of human show an S-shaped curve. This paper proposes a model which estimates the developing effort by using the growth curve. The presented model assumes that the relation cost and size follows the growth curve. The appropriateness of the growth curve model based on Function Point, Full-Function Point and Use-Case Point, which are the general methods in estimating the software size have been confirmed. The proposed growth curve model shows similar performance with power function model. In conclusion, the growth curve model can be applied in the estimation of the software cost.

• Clinical and Experimental Pediatrics
• /
• v.51 no.1
• /
• pp.26-32
• /
• 2008

Purpose : This study was to provide the methods of developing the growth charts and the blood pressure nomogram among Korean children and adolescents. Methods : The growth charts were developed based on the data from the national growth surveys for children and adolescents in 1998 and 2005. The percentile charts were developed through two stages. At the first stage, the selected empirical charts were smoothed through several fitting procedures including parametric and non-parametric methods. At the second stage, a modified LMS (lambda, mu, sigma) statistical procedure was applied to the smoothed percentile charts. The LMS procedure allowed to estimate any percentile and to calculate standard deviation units and z-scores. The charts for weight-for-age, height-for-age, BMI-for-age, weight-for-height and head circumference-for-age were developed by sex. Age and normalized height controlled sex-specific nomograms of systolic and diastolic blood pressure were developed by a fixed effect model of general regression using the data from 2005 national growth survey. Results : The significant systemic differences between the percentiles of growth charts and the empirical data were not found. The final output of the study is available from Korean Center for Disease Control and Prevention homepage, http://www.cdc.go.kr/webcdc/. Blood Pressure nomogram was tabulated by height percentiles and age using the regression coefficients analyzed with regression model. Conclusion : 2007 growth charts and blood pressure nomogram were the first products based on the statistical modeling using the national survey data. The further study on the methodology including data collection, data cleaning and statistical modeling for representative growth charts would be needed.

• Korea journal of population studies
• /
• v.23 no.1
• /
• pp.197-215
• /
• 2000

이 논문에서는 선형·비선형 성장곡선모형의 종류와 특성을 살펴보고, 이들을 비교·검토하고, 모형선호기준 통계량에 입각하여 추정결과를 비교한다. 또한 최종사용자 환경을 위한 SAS/AF로 구현한 성장곡선모형에 의한 인구예측시스템을 소개한다.

• The Korean Journal of Applied Statistics
• /
• v.14 no.2
• /
• pp.439-448
• /
• 2001

본 연구는 시간자료(Longitudinal data)의 분석을 위하여 Fuzzy k-means 군집분석 방법을 확장한 알고리즘을 제안한다. 이 논문에서 제안하는 군집분석방법은 각각의 개체에 대응하는 성장곡선에 Fuzzy k-means 군집분석의 알고리즘을 결합하는 것을 핵심아이디어로한다. 분석결과는 생성된 군집을 성장곡선모형으로 표현할 수 있고 또한 추정된 모형의 식을 활용하여 새로운 개체를 분류도 할수 있음을 보인다. 그리고 이 군집분석방법은 아직 자라지 않은 나이 어린 개체가 미래에 어느 군집에 속할 것인가 하는 분류와 함께 이 개체의 향후 성장상태를 예측을 하는 데에도 적용이 가능하다. 제안된 알고리즘을 원숭이(macaque)의 상악동(maxillary sinus)의 자료에 적용한 실례로 보인다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.420-420
• /
• 2022

우리나라의 기후 변화(여름철 집중호우, 동절기 가뭄 등)로 인하여 과거에 비해 하천의 식생영향은 증가하는 추세이고, 하도 내 수중식생은 성장과 소멸을 반복하며 기존 수위-유량관계에 변동성을 유발하고 있다. 수중식생은 수위가 상승하는 경우(강우, 방류량 증가 등)에 일부 소멸하여 유량이 증가하고, 수위가 유지되거나 평균기온이 상승하는 경우에는 성장으로 인하여 유량이 감소하는 경향을 가지고 있다. 본 연구에서는 하도 내 수중식생의 성장과 소멸에 따른 수위-유량관계곡선식의 변화의 영향을 분석하기 위해 금호강 제1지류 자호천에 위치한 영천시(단포교)관측소를 대상으로 '18년~'21년까지의 수중식생의 성장과 소멸, 회귀하는 기간의 유량 측정 성과를 확보하고 수중식생 모니터링 자료를 수집하여, 식생영향에 따른 수위-유량관계 변화를 분석하였다. 영천시(단포교)관측소는 수중식생영향을 지속적으로 받고 있으며 단면 통제나 하도 통제가 아닌 식생통제를 고려하여 '18년~'20년까지는 식생 활착, 성장과 소멸이 진행되는 기간의 성과를 확보하였고, '21년은 저수위구간의 식생성장에서 소멸까지 점차 회귀하는 성과를 각 기간별로 확보하고 분석을 통해서 수위-유량관계 곡선식을 개발하였다. 수중식생의 성장에 따라 평균유속이 감소하며 곡선식은 (-)전이가 발생하였고, 수중식생의 소멸이 발생한 경우 평균유속이 증가하여 곡선식은 (+)전이가 발생하였다. 영천시(단포교)관측소는 이러한 모니터링 결과와 유량측정성과를 바탕으로 총 5개의 기간분리가 발생하였으며, 각 기간별 곡선식 불확도와 편차율 검토 결과 유량측정성과와 곡선식은 정밀도 높은 정확성을 갖고 있는 것으로 분석되었다. 결과적으로 본 연구에서는 하도 내 수중식생영향에 따른 유량측정성과를 확보하였으며 확보한 유량측정성과의 분석을 통한 신뢰도 높은 수위-유량관계곡선식을 개발하였고 이를 통해 생산된 유량자료는 정확도가 매우 높은 것으로 분석되었다.

• Korean Journal of Poultry Science
• /
• v.49 no.4
• /
• pp.229-237
• /
• 2022

This study investigated the growth characteristics of four strains of newly developed synthetic Korean native commercial chickens (KNCs). We investigated a suitable growth curve model in KNCs and estimated the number of days to reach a 2 kg market weight. Body weight was measured at 2-week intervals from birth to 12 weeks of age. The growth curves were estimated using von Berteralanffy, Gompertz, and logistic functions. The results showed that males were significantly heavier than females at all ages, but there were no significant differences in body weight between strains, except at birth and 2 and 6 weeks of age. The coefficients of determination and adjusted determination of growth function had high goodness-of-fit (97.4~99.7). Of the growth curve parameters, the mature weight and growth ratio were higher in males than in females, but the maturity rate was similar in males and females. The inflection point occurred at approximately 7 weeks of age for females and 8 to 9 weeks of age for males. The weights estimated from the growth curve functions almost agreed with the actual weights, except for male weights estimated using the von Bertalanffy function. The coefficients of determination of the regression equations for weight to age were 0.9583 to 0.9746. The 8- and 10-week-old body weights estimated using the regression equation, and the 12-week-old weight estimated using the logistic function were most similar to the actual weight. Using these models, the estimated age of KNCs to reach 2 kg was 62.0~64.6 days for males and 74.9~78.6 days for females.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.5
• /
• pp.903-910
• /
• 2011

The von Bertalanffy growth function (VBGF) is the result of the antagonistic effects of anabolism and cataboliem. However VGBF has limitations for describing the growth of continuous spawning fishes. In the present work, a new equation is proposed where the growth parameter Kis substituted by a function related to the sea surface temperature of spawning period. Examples for natural population of Pacific Anchovy are presented.

• Journal of Animal Science and Technology
• /
• v.49 no.2
• /
• pp.195-202
• /
• 2007

The growth traits in swine are economically important, which are measured by gain in weight during test period or by age of days to certain weight. However, the difference in growth rate due to individual performance and also other factors occurs. The more reasonable estimation of the measurements of these traits provides the less error in genetic evaluation of pigs. The data from 1,576 heads being weighed periodically of Gyungnam-heugdon(Berkshire) were analyzed to estimate the growth curve which is used to decide average daily gain and days to 90kg. It may not be possible to directly compare accuracy between the conventional methods and the alternative methods. However, the alternative methods by growth curve would be superior to the conventional methods not only in theoretical background, but also in acceptability for diverse factors such as breed, sex and age. The theoretical superiority of the alternative methods comes from estimation at same age in daily gain and calculation of additional days from measuring date to days to 90kg by growth curve of individual. Also this can be easily adopted in a computer system according to breed and sex.

• The korean journal of orthodontics
• /
• v.37 no.1 s.120
• /
• pp.16-28
• /
• 2007

Objective: Evaluation of individual growth is important in orthodontics. The aim of this study was to develop a convenient software that can evaluate current growth status and predict further growth. Methods: Stature data of 2 to 20 year-old Koreans (4893 boys and 4987 girls) were extracted from a nationwide data. Age-sex-specific continuous functions describing percentile growth curves were constructed using natural cubic spline function (NCSF). Then, final stature prediction algorithm was developed and its validity was tested using longitudinal series of stature measurements on randomly selected 200 samples. Various accuracy measurements and analyses of errors between observed and predicted stature using NCSF growth curves were performed. Results: NCSF growth curves were shown to be excellent models in describing reference percentile stature growth curie over age. The prediction accuracy compared favorably with previous prediction models, even more accurate. The current prediction models gave more accurate results in girls than boys. Although the prediction accuracy was high, the error pattern of the validation data showed that in most cases, there were a lot of residuals with the same sign, suggestive of autocorrelation among them. Conclusion: More sophisticated growth prediction algorithm is warranted to enhance a more appropriate goodness of model fit for individual growth.