• 한국융합학회논문지
• /
• 제13권1호
• /
• pp.23-30
• /
• 2022

냉동 컨테이너의 고장은 큰 비용의 손실을 야기하지만, 현재 냉동 컨테이너의 알람 체계는 효율성이 떨어진다. 기존에 냉동 시스템의 시뮬레이션 데이터를 활용한 연구는 존재하지만, 냉동 컨테이너의 실제 운영 데이터를 활용한 연구는 부족하다. 이에 본 연구는 실제 냉동 컨테이너 운영 데이터를 활용하여 고장 원인을 분류하였다. 실제 데이터에서는 데이터 불균형이 발생하였으며 ENN-SMOTE, 클래스 가중치를 둔 Logistic 회귀분석과 본 연구에서 개발한 2-stage 알고리즘을 비교하여 데이터 불균형문제를 해결하였다. 2-stage 알고리즘은 XGboost, LGBoost, DNN을 사용하여 첫 번째 단계에서는 고장 및 정상을 분류하고, 두 번째 단계에서는 고장의 원인을 분류하는 알고리즘이다. 2-stage 알고리즘에서 LGBoost를 사용한 모델이 99.16%의 정확도로 가장 우수하였다. 본 연구는 데이터 불균형을 해결하기 위해 2-stage 알고리즘을 활용한 최종모델을 제안하며 이는 다른 산업에도 활용할 수 있을 것으로 사료된다.

• 대한조선학회논문집
• /
• 제43권3호
• /
• pp.362-374
• /
• 2006

Currently, all design information of a hull structure is being first defined on 2D drawings not 3D CAD model at the initial ship design stage and then transferred to following design stages through the 2D drawings. This is caused by the past design practice, limitation on time, and lack of hull structural CAD systems supporting the initial design stage. As a result, the following design tasks such as the process planning and scheduling are being manually performed using the 2D drawings. For solving this problem, a data structure supporting the initial design stage is proposed and a prototype system is developed based on the data structure. The applicability of the system is demonstrated by applying it to various examples. The results show that the system can be effectively used for generating the 3D CAD model of the hull structure at the initial design stage.

• 산업기술연구
• /
• 제29권A호
• /
• pp.101-110
• /
• 2009

Due to frequent occurrence of a localized torrential downpour caused by global warming and change of outflow tendency caused by rapid urbanization and industrialization, risk analysis must be carried out in levee design with uncertainty. In this study, reliability analysis was introduced to quantitatively evaluate the overtopping risk of levee by the uncertainty. First of all, breaking function was established as a function of flood stage and height of levee. All variables of breaking function were considered as random variables following any distribution functions, and the risk was defined as the possibility that the flood stage is formed higher than height of levee. The risk evaluation model was developed with AFDA (Approximate Full Distribution Approach). The flood stage computed by 2-D numerical model FESWMS-2DH was used as input data for the model of levee risk evaluation. Risk for levee submergence were quantitatively presented for levee of Wol-Song-Cheon.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권2호
• /
• pp.632-657
• /
• 2022

Detecting web attacks is a major challenge, and it is observed that the use of simple models leads to low sensitivity or high false positive problems. In this study, we aim to develop a robust two-stage deep learning based stacked ensemble web application firewall. Normal and abnormal classification is carried out in the first stage of the proposed WAF model. The classification process of the types of abnormal traffics is postponed to the second stage and carried out using an integrated stacked ensemble model. By this way, clients' requests can be served without time delay, and attack types can be detected with high sensitivity. In addition to the high accuracy of the proposed model, by using the statistical similarity and diversity analyses in the study, high generalization for the ensemble model is achieved. Within the study, a comprehensive, up-to-date, and robust multi-class web anomaly dataset named GAZI-HTTP is created in accordance with the real-world situations. The performance of the proposed WAF model is compared to state-of-the-art deep learning models and previous studies using the benchmark dataset. The proposed two-stage model achieved multi-class detection rates of 97.43% and 94.77% for GAZI-HTTP and ECML-PKDD, respectively.

• 한국의학물리학회지:의학물리
• /
• 제2권2호
• /
• pp.175-182
• /
• 1991

본 논문은 인공폐의 설계및 임상진단을 위한 허파기능의 연구 및 호흡생리의 요체인 폐모세 혈관내 혈액의 Hb와 가스상 산소의 비선형 결합특성을 규명할 수 있는 새로운 산소포화 모델을 전기적 등가회로에 기초하여 유도하였다. 새로이 유도된 산소포화 모텔은 종래의 모델에 비해 훨씬 간단하고, 광범위한 pH 및 각 생리 parameter 등의 변동에도 정확히 적용될 수 있었을 뿐 아니라, 결합반응과 등가인 2단 및 4단 RC 전기적 등가회로의 Simulation 결과로 부터, Hb 와 산소의 비선형 결합특성은 2단계의 복합 반응으로 취급하는 것이 타당함을 확인하였다.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1993년도 추계학술대회발표논문집; 서강대학교, 서울; 25 Sep. 1993
• /
• pp.175-184
• /
• 1993

Modeling the production process is a necessary and essential aspect of the production planning. This paper introduces a theoretical model of the multi-stage production process. A multi-stage production process is regarded as a network of interrelated production activities which use system exogenous inputs of goods in production and the intermediate products transfers between activities to produce final products. Our model is characterized by (1) a few of the production-related assumptions and (2) two types of elements "goods and activities" that are represented in terms of the network terminology. This model is different from the another multi-stage production models, so-called production network models in relation to the production-theoretical concept. It is not based on the concept of the production correspondence and the activity production functions, but the technology model of Koopmans. Koopmans.

• 디지털콘텐츠학회 논문지
• /
• 제5권2호
• /
• pp.151-156
• /
• 2004

본 논문에서는 인터넷에서의 트래픽 엔지니어링을 수행하기 위한 프로세스 모델을 제시한다. 프로세스 모델은 4 단계로 이루어지는데, 첫번째 단계는 네트워크의 운용을 지배하는 적절한 제어정책을 정의하고 두 번째 단계는 운용 네트워크로부터의 측정 데이터를 얻는 과정이다. 세 번째 단계에서는 네트워크 상태를 분석하고 트래픽 부하를 산출하며, 마지막 단계에서는 네트워크의 성능을 최적화하는데 이와 같은 프로세스 모델의 4 단계는 연속적으로 반복되는 프로세스 모델이다.

• 디지털융복합연구
• /
• 제12권1호
• /
• pp.539-548
• /
• 2014

이 연구의 목적은 수업모형 관련 논문을 연구시기별, 연구주제별, 수업모형별, 학교급별, 교과목별로 분류하여 연구동향을 확인하기 위한 것이다. 연구대상의 표집기간은 1977년부터 2013년 3월까지로 설정했으며, 최종 586개의 연구논문을 토대로 분석을 진행하였다. 수업모형 연구의 변천사를 시기별 세 단계로 구분하였다. 제1기(1977년~1996년), 제2기(1997년~2006년), 제3기(2007년~2013년)이며, 제1기에 8%에서 제2기에 51%로, 제2기에 비약적으로 증가했다. 세 시기에 걸쳐 가장 많이 연구된 주제는 '설계 및 개발'이었으며, 연구가 가장 활발한 수업모형군은 '교과 교육과정지향'인 것으로 나타났다. 교과별로 보면, '범교과' 연구가 다른 교과에 비해 상대적으로 활발히 진행되고 있었다. 이러한 결과들을 바탕으로 향후 수업모형의 국내 연구 방향에 대해 제안하였다.

• 대한치과교정학회지
• /
• 제51권2호
• /
• pp.77-85
• /
• 2021

Objective: To evaluate the accuracy of a multi-stage convolutional neural network (CNN) model-based automated identification system for posteroanterior (PA) cephalometric landmarks. Methods: The multi-stage CNN model was implemented with a personal computer. A total of 430 PA-cephalograms synthesized from cone-beam computed tomography scans (CBCT-PA) were selected as samples. Twenty-three landmarks used for Tweemac analysis were manually identified on all CBCT-PA images by a single examiner. Intra-examiner reproducibility was confirmed by repeating the identification on 85 randomly selected images, which were subsequently set as test data, with a two-week interval before training. For initial learning stage of the multi-stage CNN model, the data from 345 of 430 CBCT-PA images were used, after which the multi-stage CNN model was tested with previous 85 images. The first manual identification on these 85 images was set as a truth ground. The mean radial error (MRE) and successful detection rate (SDR) were calculated to evaluate the errors in manual identification and artificial intelligence (AI) prediction. Results: The AI showed an average MRE of 2.23 ± 2.02 mm with an SDR of 60.88% for errors of 2 mm or lower. However, in a comparison of the repetitive task, the AI predicted landmarks at the same position, while the MRE for the repeated manual identification was 1.31 ± 0.94 mm. Conclusions: Automated identification for CBCT-synthesized PA cephalometric landmarks did not sufficiently achieve the clinically favorable error range of less than 2 mm. However, AI landmark identification on PA cephalograms showed better consistency than manual identification.

• 한국식품조리과학회지
• /
• 제30권6호
• /
• pp.687-694
• /
• 2014

The purpose of this study was to investigate the salt-related dietary behaviors according to the stage of change model in middle school students from the Gyeongsangbuk-do area. Data were collected from, a total of 253 male and 210 female middle school students through. Self-reporting questionnaire. By stage of salt-related dietary behaviors, the 'Pre-contemplation stage' was comprised of 57.3%, the 'Contemplation stage' of 12.2%, the 'Preparation stage' of 7.4% and the 'Action stage' of 23.2% of students. There were significant differences in the stage of change according to the experience with salt-related nutrition education (p<0.05), wherein differences according to gender and parent's education were not observed. In the salt-related dietary behaviors, there were significant differences according to gender (p<0.05), pocket money (p<0.01), and the stage of change (p<0.001). Males had higher salt-related dietary behavior scores than females, while students who had more pocket money also had higher scores, and the action group had lower scores than the other groups. Among the 10 items of salt-related dietary behaviors, only 4 showed above the average score (2.92/5.00), including behaviors of liking kimchi, completely consuming snacks and instant foods, and drinking the broth of soups. The salt-related dietary score of males was higher than females, while the action group's score was lower than the other stages.