• Journal of the Korean Data and Information Science Society
• /
• 제25권6호
• /
• pp.1283-1291
• /
• 2014

본 논문에서는 대용량이거나 시간에 따라 순차적으로 들어오는 데이터의 분류를 위한 전진적 단계 알고리즘을 제안한다. Adaboost 알고리즘은 노이즈가 있는 데이터에 대하여 성능이 떨어지는 것으로 알려져 있다. 이를 해결하기 위한 한 가지 방법으로 전진적 단계 선형 회귀 방법을 사용한다. 대용량 데이터나 순차적 배치 데이터의 경우에도 이러한 상황을 극복하기 위해 전진적 단계 알고리즘 방법을 적용한 방법을 제안한다. 모의실험과 실제 자료 분석을 통해 제안된 알고리즘이 좋은 성능을 보임을 알 수 있었다.

• 응용통계연구
• /
• 제23권1호
• /
• pp.197-206
• /
• 2010

본 논문에서는 대용량 자료 혹은 시간에 따라 순차적으로 들어오는 자료의 분류를 위한 부스팅(boosting) 알고리즘을 제안한다. 대용량 자료나 순차적 자료의 경우 분석시 모든 훈련 자료(training data)들을 한번에 이용하기 어려우므로 보통의 부스팅 알고리즘은 적절하지 못하다. 이러한 상황을 극복하기 위해 AdaBoost와 Arc-x4와 같은 부스팅 알고리즘을 수정하여 제안한다. 모의 실험과 실제 자료 분석을 통해 대용량 자료나 순차적 자료에 제안된 알고리즘이 잘 적용됨을 보였다.

• 한국정보통신학회논문지
• /
• 제9권1호
• /
• pp.40-44
• /
• 2005

인공지능, 기계학습 및 데이터마이닝 기법들을 침입탐지 시스템에 적용하는 연구가 활발히 진행되고 있다. 그러나 많은 연구가 공격패턴의 분류를 위한 분류기(classifier)의 학습 알고리즘 성능 개선에 목적을 두고 있다. 그리고 이러한 학습 알고리즘은 대부분 일괄처리(batch) 방식으로 동작하여 실시간 침입탐지 시스템의 적용에는 적합하지 못하다. 본 논문에서는 실시간 침입탐지 시스템을 위한 점증적 특징 추출 기법과 분류가 가능한 실시간 침입탐지 시스템을 제안한다. 제안된 방법을 KDD CUP 99 자료에 적용한 결과 실시간 기법임에도 불구하고 일괄처리 방식과 비슷한 결과를 나타내었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1994년도 Proceedings of the Korea Automatic Control Conference, 9th (KACC) ; Taejeon, Korea; 17-20 Oct. 1994
• /
• pp.207-212
• /
• 1994

A mathematical model is developed for a batch reactor in which the free radical bulk copolymerization of styrene and acrylonitrile takes place. In this model, we introduce the free volume theory to quantify the diffusion controlled termination and propagation reactions, and develop a model for the chain length dependent termination reaction in the context of the pseudo kinetic rate constant method(PKRCM). The simulation results from this model are found to be in good agreement with experimental data under different copolymerization conditions. The present model can predict both the copolymer composition and the number and weight average molecular weights. These kinetic approaches provide greater insight into the performance of the batch reactor used for the free radical bulk copolymerization of styrene and acrylonitirle.

• 한국미생물·생명공학회지
• /
• 제22권3호
• /
• pp.304-308
• /
• 1994

A suitable culture method and bioreactor type for itaconic acid production were chosen by comparing the maximal concentration of itaconic acid produced in various systems. In batch culture, the maximal concentration of itaconic acid produced in a bubble column reactor was about 5% greater than that produced in stirred-tank or external-loop airlift reactor. These results were thought to be due to lower shear force and higher mass transfer efficiency in a bubble column reactor in comparison with other reactors. Moreover, the fed-batch mode in a bubble column was found to be a suitable one, producing about 25% higher concentration of itaconic acid compared to batch mode.

• 오토저널
• /
• 제12권1호
• /
• pp.40-48
• /
• 1990

Bake hardenability of batch annealed steel sheets is investigated in connection with the amount of tensile deformation and the bake hardening condition. This study associates with the method for producing bake hardening materials by means of batch annealing process and for measuring bake hardenability which is not yet fully established. The experimental result demonstrates the relationship between strain distribution and bake hardening behavior in various bake hardening conditions, which provides an essential information for automobile design and related sheet metal forming in a press shop. The result also shows the bake hardenability of the tested material increases as the baking temperature is increased from 150.deg. C. The result assures the bake hardening materials can guarantee reasonably high strength as well as good uniformity in yield strength for the automobile body by sheet metal forming process.

• Nuclear Engineering and Technology
• /
• 제28권3호
• /
• pp.331-338
• /
• 1996

In the thermal-hydraulic design, the effect of fuel rod bow is quantified tv the rod bow DNBR penalty which is a key design parameter to assure the coolability of fuel assembly in the pressurized water reactor. In this work, a computer program for the evaluation of the rod bow DNBR penalty based on Westinghouse methodology is developed and its application procedure is proposed. The computer simulation is based on the Monte-Carlo method. The qualification of developed computer program is performed by a comparison of calculational result with that given by Westinghouse's document. A new application procedure is built using batch mean and batch standard deviation. The normality of sample population generated by the batch calculation is confirmed by means of a chi-square test for goodness of fit. On the view point of statistics it is effected that the more reliable design value may be produced by the new application procedure.

• 한국환경과학회지
• /
• 제32권5호
• /
• pp.385-394
• /
• 2023

There is a need for a method that can effectively remove wastewater containing small-sized particles such as TiO₂. In this study, we attempted to remove TiO₂ wastewater using electrocoagulation-electroflotation two-step separation. The TiO₂ wastewater was effectively removed via batch electrocoagulation-electroflotation separation. However, in the batch process, the simultaneous operation of electrocoagulation and electoflotation was challenging due to the high residual turbidity. In the continuous operation, electrocoagulation and electoflotation reactors were kept separate. The turbidity removal in continuous operation was similar to that in the batch process, nevertheless, the residual Al concentration was high, leading to the conclusion that counterterm ensures against residual Al were necessary.

• 센서학회지
• /
• 제32권6호
• /
• pp.475-480
• /
• 2023

When modeling a sensor system mathematically, we assume that the sensor noise is Gaussian and white to simplify the model. If this assumption fails, the performance of the sensor model-based controller or estimator degrades due to incorrect modeling. In practice, non-Gaussian or non-white noise sources often arise in many digital sensor systems. Additionally, the noise parameters of the sensor model are not known in advance without additional noise statistical information. Moreover, disturbances or high nonlinearities often cause unknown sensor modeling errors. To estimate the uncertain noise and model parameters of a sensor system, this paper proposes an iterative batch calibration method using data-driven machine learning. Our simulation results validate the calibration performance of the proposed approach.

• Environmental Engineering Research
• /
• 제19권4호
• /
• pp.395-399
• /
• 2014

Operation characteristics of the sequencing batch reactor (SBR) process with electro-flotation (EF) as a solid liquid separation method (EF-SBR) were investigated. EF-SBR process showed excellent solid-liquid separation performance which enabled to separate biosolids from liquid phase within 30 min and to extend cyclic reaction time. Although influent organic loading rate was increased stepwise from 5 to 15 g COD/day, food to microorganisms (F/M) ratio could be maintained about 0.3 g COD/g VSS/day in EF-SBR because biomass concentration could be easily controlled at desired level by EF. However, it was impossible to increase biomass concentration at the same level in control SBR (C-SBR) process because solid-liquid separation by gravity settling showed a limitation at higher mixed liquor suspended solids (MLSS) concentration with 60 min of settling time. Total chemical oxygen demand (TCOD) removal efficiency of EF-SBR process was not decreased although influent organic loading rate became 3 times higher than initial value. However, it was seriously deteriorated in C-SBR process after increasing the rate over 10 g COD/day, which was accounted for insufficient organic removal by relatively higher food to microorganisms (F/M) ratio as well as biosolids wash-out by a limitation of gravity sedimentation.