• The Korean Journal of Applied Statistics
• /
• v.35 no.5
• /
• pp.645-655
• /
• 2022

In this paper, we investigate automatic functions for time series forecasting in R system and compare their performances. For the exponential smoothing models and ARIMA (autoregressive integrated moving average) models, we focus on the representative time series forecasting functions in R: forecast::ets(), forecast::auto.arima(), smooth::es() and smooth::auto.ssarima(). In order to compare their forecast performances, we use M3-Competiti on data consisting of 3,003 time series and adopt 3 accuracy measures. It is confirmed that each of the four automatic forecasting functions has strengths and weaknesses in the flexibility and convenience for time series modeling, forecasting accuracy, and execution time.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2003.10a
• /
• pp.155-163
• /
• 2003

마이크로어레이를 이용한 발현실험이 기하급수적으로 늘어남에 따라 마이크로어레이이미지를 자동으로 처리하는 기술에 대한 요구가 커지고 있고, 이에 대한 연구도 많아지고 있다. 마이크로어레이 이미지를 자동으로 처리하기 위해서는 각 이미지가 가지고 있는 스팟 패턴를 알아보고, 자동화 정도를 측정할 수 있는 품질평가함수가 필요하다. 우리는 본 논문에서 마이크로어레이 이미지 분석의 자동화에 대한 평가를 도와주는 스팟 패턴의 품질평가함수(quality measure)를 정의하고, 각 실험이 얼마나 잘 이루어졌는지를 예측할 수 있는 품질제어평가함수(quality control measure)를 정의한다. 또한 마이크로어레이 실험과 이미지에 대한 품질을 평가하기 위해서 이미지내의 블럭들과 스팟들에 대한 통계량을 이용하고, 스팟들의 발현값에 대한 정확도를 측정하기 위한 품질평가함수들을 정의한다. 이러한 품질평가함수의 측정을 위해서 최대정규정점의 집합(maximal regular point set)과 메타그리드를 이용한다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.05a
• /
• pp.153-156
• /
• 2001

최근 들어 두드러지고 있는 승조원의 승선 기피현상에 따른 항해인력 부족현상을 근원적으로 해결하기 위하여 선박 항해 전반에 걸친 자동화 및 지능화에 대한 연구가 활발히 진행되고 있다. 특히 선박의 자동화된 항해를 위해서는 영역전문자 수준의 안전성과 정확성이 보장된 충돌회피 시스템이 요구된다. 충돌회피는 자선에서 이루어지는 해상 장애물들에 대한 피항 행위로 그 판단 기준은 각 장애물에 대한 충돌 위험도에 기반한다. 본 연구에서는 DCPA와 TCPA를 이용한 기존의 기법에 변침도(VDH: Variation Degree of Heading)의 개념을 추가하여 새로운 충돌 위험도 산출 기법을 제안한다. 입력변수가 되는 DCPA, TCPA, VDH의 퍼지 소속함수를 산출하고, 이를 기반으로 퍼지 규칙을 이용하여 세부적인 충돌 위험도를 산출한다. 본 연구에서 제안하는 기법은 충돌 위험도 산출시 장애물의 직선운항뿐만 아니라 곡선운항에 대한 경로예측이 가능하다는 장점을 지닌다. 과거의 변침도가 다음시점의 변침에 영향을 끼침으로써 장애물의 이동 경로에 대한 예측이 이루어지고, 이를 기반으로 보다 세분화된 충돌위험도 산출이 이루어진다. 제안된 기법은 DCPA와 TCPA만으로 충돌위험도를 산출해 낸 연구와 비교.평가하여 성능을 검증한다.

• Journal of the Korean Wood Science and Technology
• /
• v.48 no.6
• /
• pp.917-935
• /
• 2020

In this study, an automated sensor to measure forest fire surface fuel moistures was developed to predict changes in the moisture content and risk of forest fire surface fuel, which was indicators of forest fire occurrence and spread risk. This measurement sensor was a method of automatically calculating the moisture content of forest fire surface fuel by electric resistance. The proxy of forest fire surface fuel used in this sensor is pine (50 cm long, 1.5 cm in diameter), and the relationship between moisture content and electrical resistance, R(R:Electrical resistance)=2E(E:Exponent of 10)+13X(X:Moisture content)-9.705(R²=0.947) was developed. In addition, using this, the software and case of the automated measurement sensor for forest fire surface fuel moisture were designed to produce a prototype, and the suitability (R²=0.824) was confirmed by performing field monitoring verification in the forest. The results of this study would contribute to develop technologies that can predict the occurrence, spread and intensity of forest fires, and are expected to be used as basic data for advanced forest fire risk forecasting technologies.

• Proceedings of the KAIS Fall Conference
• /
• 2001.05a
• /
• pp.119-123
• /
• 2001

본 논문에서는 자동화 사격장 Pop-Up시스템의 안정성 및 성능 향상을 위해 예측제어기를 설계하여 시간지연에 따른 문제를 보상하였다. 확률 모델에 기반한 예측제어기는 지연된 이전의 값들로부터 선형예측 기법과 확률함수를 이용하여 실제의 값을 추정하며, 이를 제어기에 적용하여 시간지연에 따른 문제점을 최소화하였다. 제안된 알고리즘의 타당성을 검정하기 위해 사격용 Pop-Up시스템에 본 알고리즘을 실현하였으며, 상이한 시간지연과 이득 변화에 따른 제어기의 성능을 관측하였다. 실험결과 제안된 예측제어기는 시간지연에 대해 PID 제어기보다 빠른 수렴 특성을 보이며, 제어기의 안정범위 내에서 허용할 수 있는 최대 시간지연 값도 증가시킬 수 있었다. 따라서 사격용 타겟의 Pop & Up동작이 제어시간 이내에 원활하게 작동되어 연속 사격의 실시간 제어를 효율적으로 수행하였다.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1995.04a
• /
• pp.504-509
• /
• 1995

컴퓨터에 의한 생산시스템의 통합체계화와 온-라인화에 따라 자동화된 설비진단 방법이 요구되어지고 있다. 이에 따라 기계설비에 각종 센서를 부착하여 실시간으로 수집된 출력신호를 이용하여 기계설비를 온-라인으로 감시하는 여러가지 기법들이 제시되고 있다. 본 연구에서는 진동센서로부터의 신호를 radial 함수에 근거한 다단계 뉴럴 네트워크(Neural Network)로 모형화하여 기계설비 상태를 감시하는 방법을 제시한다. 또한 다단계 모델링 분석을 통하여 신호를 예측하고 설비고장 원인을 분류하며, 다른 모형과의 비교를 통하여 효율성 평가와 최적 단계수를 결정하였다. 온라인 학습 알고리즘은 recursive least squares와 clustering 방법을 이용한다.

• Journal of the Society of Naval Architects of Korea
• /
• v.31 no.3
• /
• pp.145-153
• /
• 1994

In the fabrication of welded built-up beams, longitudinal deformation occurs due to welding, and this obstructs improvement of productivity and quality. In this study, to estimate the deformation due to welding, a simplified thermal elasto-plastic analysis method is proposed and verified by experiments. From the results of the simplified analysis, it is clarified that deformation coefficients defined in this study are the function of fabrication parameters. Based on this simplified analysis, a method to simulate the fabrication procedures for the built-up beams can be developed.

• Journal of Korean Society of Transportation
• /
• v.23 no.2
• /
• pp.25-36
• /
• 2005

In this study, we suggested a new approach method forecasting distribution demand of urban rail transit usign fuzzy control, with intend to reflect irregularity and various functional relationship between trip length and distribution demand. To establish fuzzy control model and test this model, the actual trip volume(production, attraction and distribution volume) and trip length (space distance between a departure and arrival station) of Daegu subway line 1 were used. Firstly, usign these data we established a fuzzy control model, nd the estimation accuracy of the model was examined and compared with that of generalized gravity model. The results showed that the fuzzy control model was superior to gravity model in accuracy of estimation. Therefore, wwe found that fuzzy control was able to be applied as a effective method to predict the distribution demand of urban rail transit. Finally, to increase the estimation precision of the model, we expect studies that define membership functions and set up fuzzy rules organized with neural networks.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.24 no.4
• /
• pp.467-474
• /
• 2018

The purpose of this study is related to automatic hull-form design for ships operating at two speeds. Research was conducted using a series 60 ($C_B=0.6$) ship as a target, which has the most basic ship hull-form. Hull-form development was pursued from the viewpoint of improving resistance performance. In particular, automatic hull-form design for a ship was performed to improve wave resistance, which is closely related to hull-forms. For this purpose, we developed automatic hull-form design software for ships by combining an optimization technique, resistance prediction technique and hull-form modification technique, appling the software developed to a target ship. A sequential quadratic programming method was used for optimization, and a potential-based panel method was used to predict resistance performance. A Gaussian-type modification function was developed and applied to change the ship hull-form. The software developed was used to design a target ship operating at two different speeds, and the performance of the resulting optimized hull was compared with the results of the original hull. In order to verify the validity of the program developed, experimental results obtained in model tests were compared with calculated values by numerical analysis.

• The Journal of Engineering Geology
• /
• v.20 no.3
• /
• pp.281-295
• /
• 2010

A new, automated apparatus is proposed for calculating the Soil-Water Characteristic Curve (SWCC), representing a simple and easily applied testing device for continuous measurements of the volumetric water content and suction of unsaturated soils. The use of this apparatus helps to avoid the errors that arise when performing experiments. Consequently, the apparatus provides greater accuracy in calculating the SWCC of unsaturated soils. The apparatus is composed of a pressure panel, flow cell, water reservoir, air bubble trap, balance, sample-preparation accessories, and measurement system, among other components. The air pressure can attain 300 kPa, and a general test can be completed in a short time. The apparatus can simply control the drying process and wetting process. The changes in volumetric water content that occur during the drying and wetting processes are shown directly in the SWRC program, in real time. As a case study, we performed an SWCC test of Joomunjin sand (75% relative density) to measure matric suction and volumetric water content during both the drying and wetting processes. The test revealed hysteresis behavior, whereby the water content on the wetting curve is always lower than that on the drying curve for a specific matric suction, during the wetting and drying processes. Based on the test results, SWCCs were estimated using the Brooks and Corey, van Genuchten, and Fredlund and Xing models. The van Genuchten model performed best for the given soil conditions, as it yielded the highest coefficient of determination.