• 제목/요약/키워드: Probabilistic model

검색결과 1,254건 처리시간 0.023초

그룹 가치스코어 모형을 활용한 강수확률예보의 사용자 만족도 효용 분석 (Analysis of Users' Satisfaction Utility for Precipitation Probabilistic Forecast Using Collective Value Score)

  • 윤승철;이기광
    • 경영과학
    • /
    • 제32권4호
    • /
    • pp.97-108
    • /
    • 2015
  • This study proposes a mathematical model to estimate the economic value of weather forecast service, among which the precipitation forecast service is focused. The value is calculated in terms of users' satisfaction or dissatisfaction resulted from the users' decisions made by using the precipitation probabilistic forecasts and thresholds. The satisfaction values can be quantified by the traditional value score model, which shows the scaled utility values relative to the perfect forecast information. This paper extends the value score concept to a collective value score model which is defined as a weighted sum of users' satisfaction based on threshold distribution in a group of the users. The proposed collective value score model is applied to the picnic scenario by using four hypothetical sets of probabilistic forecasts, i.e., under-confident, over-confident, under-forecast and over-forecast. The application results show that under-confident type of forecasts outperforms the others as a measure of the maximum collective value regardless of users' dissatisfaction patterns caused by two types of forecast errors, e.g., miss and false alarm.

탄산화된 RC구조물의 표면보수에 대한 확률론적 LCC 평가 (Probabilistic LCC evaluation for Surface Repair of carbonated RC structure)

  • 이형민;양현민;이한승
    • 대한건축학회논문집:구조계
    • /
    • 제34권2호
    • /
    • pp.41-48
    • /
    • 2018
  • Carbonation is one of the major detrimental factors to the reinforced concrete structures owing to penetration of atmospheric CO2 through the micro pores, thereby it reduces the durability of the concrete. The maintenance periods and cost for concrete according to the coefficient variation of different finishing materials is documented in literature. However, it is required to carry out the systematic and well planned studies. Therefore, keeping them in mind, surface repair was carried out to the carbonated concrete and the maintenance cost was calculated to measure the durability life after repair with different variable. The deterministic and probabilistic methods were applied for durability and repair cost of the concrete. In the existing deterministic model, the cost of repair materials increases significantly when the concrete structure reaches its service life. In present study using a stochastic model, the maintenance period and cost was evaluated. According to obtained results, there was no significant difference in the number of maintenance of the coefficient variation. The initial durability has a great influence on the maintenance time and cost of the structure. Unlike the deterministic model, the probabilistic cost estimating model reduces the number of maintenance to the target service life expectancy.

Probabilistic Modeling of Fish Growth in Smart Aquaculture Systems

  • Jongwon Kim;Eunbi Park;Sungyoon Cho;Kiwon Kwon;Young Myoung Ko
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제17권8호
    • /
    • pp.2259-2277
    • /
    • 2023
  • We propose a probabilistic fish growth model for smart aquaculture systems equipped with IoT sensors that monitor the ecological environment. As IoT sensors permeate into smart aquaculture systems, environmental data such as oxygen level and temperature are collected frequently and automatically. However, there still exists data on fish weight, tank allocation, and other factors that are collected less frequently and manually by human workers due to technological limitations. Unlike sensor data, human-collected data are hard to obtain and are prone to poor quality due to missing data and reading errors. In a situation where different types of data are mixed, it becomes challenging to develop an effective fish growth model. This study explores the unique characteristics of such a combined environmental and weight dataset. To address these characteristics, we develop a preprocessing method and a probabilistic fish growth model using mixed data sampling (MIDAS) and overlapping mixtures of Gaussian processes (OMGP). We modify the OMGP to be applicable to prediction by setting a proper prior distribution that utilizes the characteristic that the ratio of fish groups does not significantly change as they grow. We conduct a numerical study using the eel dataset collected from a real smart aquaculture system, which reveals the promising performance of our model.

지진예측을 위한 확률론적퍼지모형의 개발 (Development of Probabilistic-Fuzzy Model for Seismic Hazard Analysis)

  • 홍갑표
    • 전산구조공학
    • /
    • 제4권3호
    • /
    • pp.107-115
    • /
    • 1991
  • 지진예측을 위한 확률론적퍼지모형을 제안하였다. 제안된 모형은 지진발생에 대하여 무작위성(randomness)과 퍼지니스(fuzziness)를 같이 사용하여, 기존의 확률론에 근거한 지진예측방법을 개선할 수 있도록 하였다. 이 연구의 결과는 (a) 주어진 초과확률에 대한 지반가속도 또는 주어진 지반가속도에 대한 초과확률의 멤버쉽함수와 (b) 멤버쉽함수를 대표할 수 있는 특성값(characteristic value)이다. 확률론적 퍼지모형을 미국 Utah주의 Wasatch Front Range의 자료에 적용하여 서로 다른 연간 초과확률, 최대지반가속도에 대하여 지진도를 작성하였다.

  • PDF

PLDA 모델 적응과 데이터 증강을 이용한 짧은 발화 화자검증 (Short utterance speaker verification using PLDA model adaptation and data augmentation)

  • 윤성욱;권오욱
    • 말소리와 음성과학
    • /
    • 제9권2호
    • /
    • pp.85-94
    • /
    • 2017
  • Conventional speaker verification systems using time delay neural network, identity vector and probabilistic linear discriminant analysis (TDNN-Ivector-PLDA) are known to be very effective for verifying long-duration speech utterances. However, when test utterances are of short duration, duration mismatch between enrollment and test utterances significantly degrades the performance of TDNN-Ivector-PLDA systems. To compensate for the I-vector mismatch between long and short utterances, this paper proposes to use probabilistic linear discriminant analysis (PLDA) model adaptation with augmented data. A PLDA model is trained on vast amount of speech data, most of which have long duration. Then, the PLDA model is adapted with the I-vectors obtained from short-utterance data which are augmented by using vocal tract length perturbation (VTLP). In computer experiments using the NIST SRE 2008 database, the proposed method is shown to achieve significantly better performance than the conventional TDNN-Ivector-PLDA systems when there exists duration mismatch between enrollment and test utterances.

몬테카를로 시뮬레이션을 이용한 LCI data 불활실성 처리 방법론 (A Methodology on Treating Uncertainty of LCI Data using Monte Carlo Simulation)

  • 박지형;서광규
    • 한국정밀공학회지
    • /
    • 제21권12호
    • /
    • pp.109-118
    • /
    • 2004
  • Life cycle assessment (LCA) usually involves some uncertainty. These uncertainties are generally divided in two categories such lack of data and data inaccuracy in life cycle inventory (LCI). This paper explo.es a methodology on dealing with uncertainty due to lack of data in LCI. In order to treat uncertainty of LCI data, a model for data uncertainty is proposed. The model works with probabilistic curves as inputs and with Monte Carlo Simulation techniques to propagate uncertainty. The probabilistic curves were derived from the results of survey in expert network and Monte Carlo Simulation was performed using the derived probabilistic curves. The results of Monte Carlo Simulation were verified by statistical test. The proposed approach should serve as a guide to improve data quality and deal with uncertainty of LCI data in LCA projects.

태양광발전원의 확률론적인 발전비용 산정에 관한 연구 (A Study on Probabilistic Production Costing for Solar Cell Generators)

  • 박정제;최재석
    • 전기학회논문지
    • /
    • 제58권4호
    • /
    • pp.700-707
    • /
    • 2009
  • The application of renewable energy in electric power systems is growing rapidly in order to make provision for the inequality of the climate, the dwindling supplies of coal, oil and natural gas and a further rise in oil prices. Solar cell generators(SCG) is one of the fastest growing renewable energy. This paper presents a methodology on probabilistic production cost simulation of a power system including SCGs. The generated power by SCGs is variable due to the random variation of solar radiation. In order to solve this problem, the SCGs is modeled as multi-state operational model in this paper. Probabilistic production cost of a power system can be calculated by proposed method considering SCGs with multi-state. The results show that the impacts of SCGs added to a power system can be analyzed in view point of production cost using the proposed method.

Probabilistic condition assessment of structures by multiple FE model identification considering measured data uncertainty

  • Kim, Hyun-Joong;Koh, Hyun-Moo
    • Smart Structures and Systems
    • /
    • 제15권3호
    • /
    • pp.751-767
    • /
    • 2015
  • A new procedure is proposed for assessing probabilistic condition of structures considering effect of measured data uncertainty. In this procedure, multiple Finite Element (FE) models are identified by using weighting vectors that represent the uncertainty conditions of measured data. The distribution of structural parameters is analysed using a Principal Component Analysis (PCA) in relation to uncertainty conditions, and the identified models are classified into groups according to their similarity by using a K-means method. The condition of a structure is then assessed probabilistically using FE models in the classified groups, each of which represents specific uncertainty condition of measured data. Yeondae bridge, a steel-box girder expressway bridge in Korea, is used as an illustrative example. Probabilistic condition of the bridge is evaluated by the distribution of load rating factors obtained using multiple FE models. The numerical example shows that the proposed method can quantify uncertainty of measured data and subsequently evaluate efficiently the probabilistic condition of bridges.

인간신뢰도 학습현상 (Human reliability growth in the absolute identification of tones)

  • 박희석;박경수
    • 대한인간공학회지
    • /
    • 제5권2호
    • /
    • pp.11-15
    • /
    • 1986
  • In this paper, we consider the validity of a human probabilistic learning model applied to the perdiction of errors associated with the absolute identification of tones. It is shown that the probabilistic learning model describes the human error process adequately. The model parameters are estimated by two methods which are the method of maximum likelihood, and the method of mement. The MLE version of the model has the better predictive power but the ME version is more readily obtainable and may be more practical.

  • PDF

기분석 어절 사전과 음절 단위의 확률 모델을 이용한 한국어 형태소 분석기 복제 (Cloning of Korean Morphological Analyzers using Pre-analyzed Eojeol Dictionary and Syllable-based Probabilistic Model)

  • 심광섭
    • 정보과학회 컴퓨팅의 실제 논문지
    • /
    • 제22권3호
    • /
    • pp.119-126
    • /
    • 2016
  • 본 논문에서는 어절 단위의 기분석 사전과 음절 단위의 확률 모델을 이용하는 한국어 형태소 분석기가 실용성이 있는지를 검증한다. 이를 위해 기존의 한국어 형태소 분석기 MACH와 KLT2000을 복제하고, 복제된 형태소 분석기의 분석 결과가 MACH와 KLT2000 분석 결과와 얼마나 유사한지 정밀도와 재현율로 평가하는 실험을 하였다. 실험은 1,000만 어절 규모의 세종 말뭉치를 10개의 세트로 나누고 10배수 교차 검증을 하는 방식으로 하였다. MACH의 분석 결과를 정답 집합으로 하고 MACH 복제품의 분석 결과를 평가한 결과 정밀도와 재현율이 각각 97.16%와 98.31%였으며, KLT2000 복제품의 경우에는 정밀도와 재현율이 각각 96.80%와 99.03%였다 분석 속도는 MACH 복제품의 경우 초당 30.8만 어절이며, KLT2000 복제품은 초당 43.6만 어절로 나타났다. 이 실험 결과는 어절 단위의 기분석 사전과 음절 단위의 확률 모델로 만든 한국어 형태소 분석기가 실제 응용에 사용될 수 있을 정도의 성능을 가진다는 것을 보여준다.