Loss and gain functions for CBR retrieval

Castro, Juan Luis; Navarro, María G.; Sánchez, José Ignacio Peláez; Zurita, J. M.

doi:10.1016/j.ins.2009.01.017

Cited by 42 publications

(17 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first three‐degree SD rules are commonly used to determine the relative merits of project alternatives [ Castro et al ., ; Porter and Carey , ; Tung and Yang , ]. The first‐degree stochastic dominance (FSD) rule states that alternative‐ A i dominates A j if

F_{i} (x) \leq F_{j} (x),

for all outcome levels of x , and the strict inequality holds for at least one value of x , where F i ( x ) and F j ( x ) are the CDFs of the two random outcomes X i and X j , respectively.…”

Section: Methodsmentioning

confidence: 99%

Incorporating uncertainty of distribution parameters due to sampling errors in flood‐damage‐reduction project evaluation

Tung

2013

Water Resources Research

View full text Add to dashboard Cite

[1] Epistemic uncertainty is a result of knowledge deficiency about the system. Sampling error exists when limited amounts of hydrologic data are used to estimate a T year event quantile. Both the natural randomness of hydrologic data and the sampling error in design quantile estimation contribute to the uncertainty in flood damage estimation. This paper presents a framework for evaluating a flood-damage-mitigation project in which both the hydrologic randomness and epistemic uncertainty due to sampling error are considered in flood damage estimation. Different risk-based decision-making criteria are used to evaluate project merits based on the mean, standard deviation, and probability distribution of the project net benefits. The results show that the uncertainty of the project net benefits is quite significant. Ignoring the data sampling error will underestimate the potential risk of each project. It can be clearly shown that adding data to existing sample observations leads to improved quality of information, enhanced reliability of the estimators, and reduced sampling error and uncertainty in the project net benefits. Through the proposed framework, the proper length of the extended record for risk reduction can be determined to achieve the required level of acceptable risk.

show abstract

F_{i} (x) \leq F_{j} (x),

for all outcome levels of x , and the strict inequality holds for at least one value of x , where F i ( x ) and F j ( x ) are the CDFs of the two random outcomes X i and X j , respectively.…”

Section: Methodsmentioning

confidence: 99%

Incorporating uncertainty of distribution parameters due to sampling errors in flood‐damage‐reduction project evaluation

Tung

2013

Water Resources Research

View full text Add to dashboard Cite

show abstract

“…For decision under uncertainty, zero risk for any decision is not attainable because any chosen alternative has a certain possibility to be inferior to its competing alternatives. As stated by Castro et al (2009), "Being wrong about alternatives with a lower expected loss is preferable to being wrong about alternatives with a higher expected loss" (p. 1740).…”

Section: Discussionmentioning

confidence: 99%

“…The idea of considering the potential loss and gain as the consequences of disease diagnoses has been applied in the retrieval stage of case-based reasoning (Castro et al 2009). The method aims at choosing the best possible diagnosis that minimizes the potential loss in case the diagnosis turns out to be erroneous.…”

Section: Minimax Eol Criterionmentioning

confidence: 99%

Minimax Expected Opportunity Loss: A New Criterion for Risk-Based Decision Making

Tung

2012

The Engineering Economist

View full text Add to dashboard Cite

A risk measure, expected opportunity loss (EOL), is introduced to quantify the potential loss of making an incorrect choice in risk-based decision making. Different from Savage's (1951) minimax regret principle, EOL can account for the unbounded continuous random outcomes of alternatives and decision makers' acceptable risk. This article studies the effects of the forms of loss function, correlation among outcomes, and the acceptable risk on the ranking results by considering the loss function in the power form. The results show that the loss functions and the outcomes correlations can significantly influence the rankings of alternatives in risk-based decision making.

show abstract

“…For continuous attributes, the similarity13 between the new case and the stored case can be calculated as formula (5). where, n is the number of the attributes; ${\rm sim}\,{\rm (}x_{{\rm i}}^{{\rm stored}} {\rm ,}\,x_{{\rm i}}^{{\rm new}} {\rm )}$ is the similarity of the i th attribute between two cases, the calculation formula is shown as follows.…”

Section: Cbr Prediction Methods For End Temperature Of Molten Steelmentioning

confidence: 99%

End Temperature Prediction of Molten Steel in LF Based on CBR

Wang

et al. 2012

steel research int.

View full text Add to dashboard Cite

In order to improve the temperature control level of molten steel in ladle furnace (LF), a case‐based reasoning (CBR) method has been proposed for predicting end temperature of molten steel in LF. To predict the temperature accurately and efficiently, this paper develops two‐step retrieval approach and the correlation based feature weighting (CFW) method for CBR. And, the study evaluates the prediction effect of CBR method by the experiment of comparison with back propagation neural network (BPNN) model and CBR model. Experimental results show that CBR model achieves better accuracy than BPNN model and the CBR method is effective to predict end temperature of molten steel in LF.

show abstract

Loss and gain functions for CBR retrieval

Cited by 42 publications

References 58 publications

Incorporating uncertainty of distribution parameters due to sampling errors in flood‐damage‐reduction project evaluation

Incorporating uncertainty of distribution parameters due to sampling errors in flood‐damage‐reduction project evaluation

Minimax Expected Opportunity Loss: A New Criterion for Risk-Based Decision Making

End Temperature Prediction of Molten Steel in LF Based on CBR

Contact Info

Product

Resources

About