• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.76-78
• /
• 2020

본 논문에서는 합성곱 신경망을 이용한 이미지 분류에서 신뢰도와 실제 예측 정확도가 다른 문제점을 해결하기 위하여 변형된 두 가지 목적 함수를 제안하였다. 첫 번째는 기존 교차 엔트로피 함수에 새로이 신뢰도와 정확도의 차이를 더해준 것이고, 두번째는 예측값의 최댓값을 0.5로 제한한 것이다. 새로운 목적 함수를 통해 학습해본 결과 정확도의 차이는 거의 나지 않았고, 신뢰도와 실제 정확도는 매우 근접하게 되는 결과를 얻을 수 있었다.

• The KIPS Transactions:PartD
• /
• v.8D no.4
• /
• pp.409-420
• /
• 2001

Recently a new approach to evaluation of software reliability, one of important attributes of a software system, during testing has been devised. This approach utilizes test coverage information. The coverage-based software reliability growth models recently appeared in the literature are first reviewed and classified into two classes. Inherent problems of each of the two classes are then discussed and their validity is empirically investigated. In addition, a new mean value function in coverage and a heuristic procedure for selecting the best coverage are proposed.

• Journal of the Korean Geosynthetics Society
• /
• v.20 no.4
• /
• pp.141-149
• /
• 2021

In this study, an laboratory experiment was performed for prediction technology of water content in the ground using hyperspectral information. And the spectral reflectance with a specific wavelength band was obtained according to the fine and water content. Through it, the spectral information was normalized with the spectral index of the existing literature, and the relationship with the fine and water contents and the reliability of the prediction technology were analyzed. As a result of analysis, the spectral reflectance is decreased when the water and fine contents are increased under the high water contents. In addition, the reliability of prediction technology of water content was evaluated by examining 7 different spectral index calculation methods. Among them, DVI showed relatively high prediction reliability and was superior to other calculation methods in terms of sensitivity.

• The Korean Journal of Applied Statistics
• /
• v.20 no.2
• /
• pp.257-266
• /
• 2007

It is known that Agresti-Coull approach is an effective tool for the construction of confidence intervals for various problems related to binomial proportions. However, the Agrest-Coull approach often produces a conservative confidence interval. In this note, confidence intervals based on a Bayesian approach are proposed for a linear function of independent binomial proportions. It is shown that the Bayesian confidence interval slightly outperforms the confidence interval based on Agresti-Coull approach in average sense.

• Journal of the Korean Institute of Gas
• /
• v.7 no.4 s.21
• /
• pp.20-23
• /
• 2003

The analysis of reliabilities of process facilities often uses models based on the Weibull distribution. The parameters in these models are functions of operating conditions, and determined by experiments. Using these values, we calculate the reliability, mean time to failure, and standard deviation. The conventional method assumes that the operating condition is constant, and thus treats the model parameters as constants. In this paper, a reliability function is proposed which is applicable when the scale parameter is a function of time, and an analysis method based on this is also presented. A case study on a cooling fan resulted in a big difference from the conventional method to which the average operating conditions were applied. The proposed method is also applicable to other process facilities, and expected to effectively take into account the effects of changes in the operating conditions on the reliabilities of the facilities.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.25 no.4
• /
• pp.191-199
• /
• 2013

It is estimated and analyzed that the design wave height and the confidence interval (hereafter CI) according to the return period using the fourteen-year wave data obtained at Pusan New Port. The functions used in the extreme value analysis are the Gumbel function, the Weibull function, and the Kernel function. The CI of the estimated wave heights was predicted using one of the Monte-Carlo simulation methods, the Bootstrap method. The analysis results of the estimated CI of the design wave height indicate that over 150 years of data is necessary in order to satisfy an approximately ${\pm}$10% CI. Also, estimating the number of practically possible data to be around 25~50, the allowable error was found to be approximately ${\pm}$16~22% for Type I PDF and ${\pm}$18~24% for Type III PDF. Whereas, the Kernel distribution method, a typical non-parametric method, shows that the CI of the method is below 40% in comparison with the CI of the other methods and the estimated design wave height is 1.2~1.6 m lower than that of the other methods.

• Journal of the Korean Institute of Gas
• /
• v.6 no.1 s.17
• /
• pp.86-91
• /
• 2002

This study introduces a method that selects equipments, so as to reach the reliability level, carrying out an optimization analysis which considers the reliability data and cost of the equipments. A more practical optimization problem has been formed using the object function based on the discrete function and the constraints. The jacked reactor being the subject, an optimization analysis was performed on equipments that have different failure rates depending on costs in order to reach the target reliability level required by the system. The mixed-integer programming (MIP) was used for this optimization analysis. When the jacked reactors target level of reliability was $1.65{\times}10^{-4}$, the result of the analysis showed the equipments with high cost and low failure rate were selected. However when the target level of reliability was low, the result showed that by choosing the equipments with lower cost and reliability over the more expensive one, the desired target level could be reached.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2924-2926
• /
• 2005

몇몇 논문을 통하여 테스트 노력을 고려한 소프트웨어의 신뢰도 평가가 중요한 인자인 것으로 발표되었다. 여러 산업 현장의 경험 데이타에 의하면 그 형태가 지수함수형, 레일레이형, 웨이불형, 로지스틱형 테스트 노력 함수 중 하나인 것으로 보고되었다. 그러므로 연구자들은 각각의 소프트웨어 테스트 형태에 따라 이중하나의 적합한 형태를 사용해왔다. 테스트 노력이 어떤 형태의 그래프를 따르냐에 의해 신뢰도 예측 및 성장에 대한 평가가 달라지고 그에 따라 인도시기도 변한다. 따라서, 본 논문에서는 이 네 가지 형태의 테스트 노력을 가진 소프트웨어의 신뢰도 성장에 필요한 각종 파라미터를 구하는 방법에 대하여 고찰한다. 개발 현장에서 관찰된 테스트 노력 데이터와 결함검출을 비교하여 어느 형태의 테스트 노력 곡선이 그 경우에 적합한가를 연구하는 한편, 목표 신뢰도에 맞는 발행시기를 결정하는 문제를 연구한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.11a
• /
• pp.345-348
• /
• 2005

소프트웨어 개발 후 인도 전 테스트 단계중에 발생되는 테스트 노력 소요량을 고려한 소프트웨어 신뢰도 성장 모델을 제시하여 테스트 노력소요량 동태를 시간함수인 로지스틱 곡선으로 설명한다. 테스트 단계중에 소요되는 테스트노력의 양에 대한 결함 검출비를 현재의 결함 내용에 비례하는 것으로 가정하여 소프트웨어 신뢰도 성장 모델을 비동차 포아송 프로세스(NHPP)로 공식화하여, 이 모델을 이용하여 소프트웨어 신뢰도 척도에 대한 데이터 분석기법을 개발한다. 그간 여러 문헌에서 소프트웨어 신뢰도 향상 모델을 연구할 때 소프트웨어 테스트 중에 소요되는 테스트노력의 양으로서 지수함수 곡선, 레일레이 곡선, 웨이불 곡선을 사용해 왔다. 그러나, 모든 소프트웨어 개발 환경에서 지금까지 제시된 그러한 곡선중 하나에 의해서 테스트노력 소요 곡선을 표현하는 것은 적절하지 못하다는 것이 밝혀지고 있다. 본 논문에서는 로지스틱 테스트노력 곡선이 소프트웨어의 개발/테스트 노력곡선으로 적절하게 표현될 수 있다는 것과 실제 데이터를 근거로 하여 적용하여서 예측성이 매우 좋은 능력을 가지고 있다는 것을 보이고자 한다.

• Journal of Korean Society of Steel Construction
• /
• v.14 no.2
• /
• pp.365-373
• /
• 2002

In this paper, the system reliability concept was presented to predict the lifespan of bridges. Lifetime distribution functions (survivor functions) were used to model real bridges to predict their remaining life. Using the system reliability concept and lifetime distribution functions (survivor functions), a program called LIFETIME was developed. The survivor functions give the reliability of component at time t. The program was applied to an existing Colorado state highway bridge to predict the failure probability of the time-dependent system. The bridge was modeled as a system, with failure probability computed using time-dependent deteriorating models.