• 제목/요약/키워드: Cost-Loss Model

검색결과 297건 처리시간 0.027초

불균형 데이터를 갖는 냉동 컨테이너 고장 판별 및 원인 분석을 위한 기계학습 모형 개발 (Development of machine learning model for reefer container failure determination and cause analysis with unbalanced data)

  • 이희원;박성호;이승현;이승재;이강배
    • 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.

타공형 스트레이너의 압력강하 예측을 위한 다공성모델링 (Porous modeling for the prediction of pressure drop through a perforated strainer)

  • 정일선;박재현;배재환;강상모
    • Journal of Advanced Marine Engineering and Technology
    • /
    • 제37권4호
    • /
    • pp.358-367
    • /
    • 2013
  • 본 논문에서는 타공판으로 구성된 필터의 전부 또는 일부를 다공성 매질로 대체하고 Forchheimer 법칙에 따라 판의 수직방향과 횡방향으로 손실계수를 부과하여 스트레이너를 지나는 유동의 압력 강하량를 정확히 예측할 수 있는 다공성모델링 기법을 적용하고 그 유효성을 확인하였다. 먼저 간단한 파이프 유동 해석을 통하여 수직방향 손실계수를 구하였다. 이어 필터 내에 반복되는 타공판 형상과 유동손실특성을 공유할 수 있는 단위주기 형상을 설정하고, 설정된 단위형상에 대하여 원형과 다공성모델 수치모사를 각각 수행한 후, 얻어진 두 결과를 서로 비교하여 횡방향 손실계수를 구하였다. 적용된 다공성모델링 기법을 검증하기 위하여 스트레이너 전체형상에 대하여 다공성모델 수치모사를 수행하였으며, 그 해석결과를 원형 수치모사 결과와 직접 비교하였다. 비교 결과, 다공성모델링 기법은 압력 강하량과 유동특성을 비교적 정확히 예측하였으며 계산비용과 직결되는 노드 수는 약 3~4배 정도 줄일 수 있었다.

Rate control to reduce bitrate fluctuation on HEVC

  • Yoo, Jonghun;Nam, Junghak;Ryu, Jiwoo;Sim, Donggyu
    • IEIE Transactions on Smart Processing and Computing
    • /
    • 제1권3호
    • /
    • pp.152-160
    • /
    • 2012
  • This paper proposes a frame-level rate control algorithm for low delay video applications to reduce the fluctuations in the bitrate. The proposed algorithm minimizes the bitrate fluctuations in two ways with minimal coding loss. First, the proposed rate control applies R-Q model to all frames including the first frame of every group of pictures (GOP) except for the first one of a sequence. Conventional rate control algorithms do not use any R-Q models for the first frame of each GOP and do not estimate the generated-bit. An unexpected output rate result from the first frame affects the remainder of the pictures in the rate control. Second, a rate-distortion (R-D) cost is calculated regardless of the hierarchical coding structure for low bitrate fluctuations because the hierarchical coding structure controls the output bitrate in rate distortion optimization (RDO) process. The experimental results show that the average variance of per-frame bits with the proposed algorithm can reduce by approximately 33.8% with a delta peak signal-to-noise ratio (PSNR) degradation of 1.4dB for a "low-delay B" coding structure and by approximately 35.7% with a delta-PSNR degradation of 1.3dB for a "low-delay P" coding structure, compared to HM 8.0 rate control.

  • PDF

Routing Decision with Link-weight Calculating Function in WDM Switching Networks

  • Charoenphetkul, Pongnatee;Thipchaksurat, Sakchai;Varakulsiripunth, Ruttikorn
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 2004년도 ICCAS
    • /
    • pp.1346-1349
    • /
    • 2004
  • In this paper, we have proposed the new link-weight calculating function using for routing decision in WDM networks. The proposed link-weight calculating functions includes following factors those are available wavelengths per link, distance loss, total wavelengths, and limited wavelength conversion. The calculated link-weight is applied into the algorithm of routing decision in order to determine the available lightpath that qualifies user requests. The objective is to improve the performance of wavelengths assignment with fast determining the suitable lightpath by using the proposed link-weights calculating function. The analytical model of WDM switching networks is introduced for numerical analysis. The link-weight calculating function is performed. Finally, the performance of proposed algorithm is displayed with numerical results in term of the blocking probability, the probability that connection requests from users are rejected due to there are no available lightpath to be assigned for them. It is also shown that the blocking probability is varied in depending on the number of available wavelengths and the degree of wavelength conversion. The numerical results also show that the proposed link-weight calculating function is more cost-effective choice for the routing decision in WDM switching networks.

  • PDF

Early Coding Unit-Splitting Termination Algorithm for High Efficiency Video Coding (HEVC)

  • Goswami, Kalyan;Kim, Byung-Gyu;Jun, Dongsan;Jung, Soon-Heung;Choi, Jin Soo
    • ETRI Journal
    • /
    • 제36권3호
    • /
    • pp.407-417
    • /
    • 2014
  • A new-generation video coding standard, named High Efficiency Video Coding (HEVC), has recently been developed by JCT-VC. This new standard provides a significant improvement in picture quality, especially for high-resolution videos. However, one the most important challenges in HEVC is time complexity. A quadtree-based structure is created for the encoding and decoding processes and the rate-distortion (RD) cost is calculated for all possible dimensions of coding units in the quadtree. This provides a high encoding quality, but also causes computational complexity. We focus on a reduction scheme of the computational complexity and propose a new approach that can terminate the quadtree-based structure early, based on the RD costs of the parent and current levels. Our proposed algorithm is compared with HEVC Test Model version 10.0 software and a previously proposed algorithm. Experimental results show that our algorithm provides a significant time reduction for encoding, with only a small loss in video quality.

수요예측에 오차를 고려한 신뢰도 지수 산정에 관한 연구 (A STUDY ON THE GENERATING SYSTEM RELIABILITY INDEX EVALUATION WITH CONSIDERING THE LOAD FORECASTING UNCERTAINTY)

  • 송길영;김용하;차준;오광해
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 1991년도 하계학술대회 논문집
    • /
    • pp.402-405
    • /
    • 1991
  • This paper represents a new method for computing reliability indices by using Large Deviation method which is one of the probabilistic production cost simulations. The reliability measures are based on the models used for the loads and for the generating unit failure states. In computing these measures it has been tacitly assumed that the values of all parameters in the models are precisely known. In fact, however, some of these values must often be chosen with a considerable degree of uncertainty involved. This is particularly true for the forecast peak loads in the load model, where there is an inherent uncertainty in the method of forecasting, which are frequently based on insufficient statistics. In this paper, the effect of load forecasting uncertainty on the LOLP(Loss of Load Probability), is investigated. By applying the Large Deviation method to the IEEE Rilability Test System, it is verified that the proposed method is generally very accurate and very fast for computing system reliability indices.

  • PDF

Improvement of Zinc Coating Weight Control for Transition of Target Change

  • Chen, Chien-Ming;Lin, Jeng-Hwa;Hsu, Tse-Wei;Lin, Rui-Rong
    • Corrosion Science and Technology
    • /
    • 제9권3호
    • /
    • pp.105-108
    • /
    • 2010
  • The product specification of the Continuous Hot Dip Galvanizing Line (CGL) changes and varies constantly with different customers' requirements, especially in the zinc coating weight which is from 30 to 150 g/$m^2$ on each side. Since the coating weight of zinc changes often, it is very important to reduce time spent in the transfer of target values changed for low production cost and yield loss. The No.2 CGL in China Steel Corporation (CSC) has improved the control of the air knife which is designed by Siemens VAI. CSC proposed an experiment design which is an $L_9(3^4)$ orthogonal array to find the relations between zinc coating weight and the process parameters, such as the line speed, air pressure, gap of air knife and air knife position. A non-linear regression formula was derived from the experimental results and applied in the mathematical model. A new air knife feedforward control system, which is coupled with the regression formula, the air knife control system and the process computer, is implemented into the line. The practical plant operation results have been presented to show the transfer time is obviously shortened while zinc coating weight target changing and the product rejected ratio caused by zinc coating weight out of specification is significantly reduced from 0.5% to 0.15 %.

UCP 600 합리성 행위기준의 적용방식 : 서류검토기간의 효율과 형평의 균형 (A Study on the Application of Reasonableness in UCP600 : Striking a Fair Balance between Efficiency and Equity)

  • 김기선
    • 무역상무연구
    • /
    • 제57권
    • /
    • pp.111-135
    • /
    • 2013
  • This study analyzes some important spin-off effects of the provision, UCP600 Article 14(6), through the methodology of the expected utility maximization theory based on the state-contingent commodities model. Some technical implications of this study are as follows. First, the risk-averse beneficiary will choose to present his documents more than 5 days before expiry date by paying a higher risk premium (so-called cure period) for full assurance to cure documentary discrepancies, if expressed economically, he pursues loss reducing activities to the point where the expected marginal product of his activities is less than its marginal cost. Secondly, where the effectiveness of securing cure period is uncertain, the risk-averse beneficiary will choose to present documents just on the expiry date without securing any cure period by paying no risk premium. This study finally suggests the safe harbor standard should be optimal solution only if it is supplemented by the hidden reasonableness standard for balancing the conflicts of interest between beneficiaries and banks.

  • PDF

자동차 대체연료의 상호호환성 연구 (A Study on Compatibility of Vehicle Using Alternative Fuels)

  • 이택희;강승진
    • 전기학회논문지P
    • /
    • 제61권2호
    • /
    • pp.74-81
    • /
    • 2012
  • The purpose of this study provides the theoretical model for protecting the economic and social loss from the current alternative fuel vehicle which is developed without compatibility and senseless one's own through verifying the statistical significant by method of measuring analysis. The market scale of alternative fuel vehicle depends on customer's and station's expectation about the number of potential vehicle users. It is very difficult for vehicle manufacturer to make a decision on the standard alternative fuel vehicle as it might reduce profit and market share. Accordingly, the development of alternative fuel vehicle should have manufacturer confident on the potential profit in the future. Moreover, if we decide to use the non-standard fuel after we started to use the standard fuel, it would take a huge cost comparing with starting to use the standard fuel only. As a result, once one of companies starts to provide the non-standard fuel service, it is getting more difficult to use the standard fuel going forward. Consequently, we may review the possibility of choice on the standard fuel before the vehicle manufacturer starts service with non-standard fuel.

양식어장 보호를 위한 원격감시시스템의 구축방안에 관한 연구 (A Study on Remote Monitoring System for Protecting Aquaculture Farms)

  • 김철승;정중식;박성현
    • 해양환경안전학회지
    • /
    • 제10권2호
    • /
    • pp.55-60
    • /
    • 2004
  • 국민소득 증가에 따라 고급해산물의 수요가 늘어나고 있으며, 어패류 및 해조류를 포함하는 양식어업은 국내어업에 대한 총수입중 $50.6\%$를 차지하고 있는 어가의 주 소득원 중의 하나이다. 최근 국내어장에서 불규칙하게 발생하는 어패류 도난사건의 피해액은 매년 건당 수십만에서 수천만원 이상으로 증가하고 있는 실정이다. 본 연구에서는 국내 영세어가에 적용할 수 있는 양식어장 보호를 위한 레이더 감시시스템의 모델을 제안하고, 시스템의 구축방안을 제시하였다. 국외에서 양식어장보호 감시시스템이 개발된 바가 있지만 구축비용이 고가이므로 국내 영세어가에 적용하기에는 어렵다.

  • PDF