Showing 5 results for Membership Function
Seyed Hossein Razavi Hajiagha, Shide Sadat Hashemi, Hannan Amoozad Mahdiraji,
Volume 25, Issue 3 (7-2014)
Abstract
Data envelopment analysis operates as a tool for appraising the relative efficiency of a set of homogenous decision making units. This methodology is applied widely in different contexts. Regarding to its logic, DEA allows each DMU to take its optimal weight in comparison with other DMUs while a similar condition is considered for other units. This feature is a bilabial characteristic which optimizes the performance of units in one hand. This flexibility on the other hand threats the comparability of different units because different weighting schemes are used for different DMUs. This paper proposes a unified model for determination of a common set of weights to calculate DMUs efficiency. This model is developed based on a multi objective fractional linear programming model that considers the original DEA's results as ideal solution and seeks a set of common weights that rank the DMUs and increase the model's discrimination power. Comparison of the proposed method with some of the previously presented models has shown its advantages as a DMUs ranking model.
Abdollah Eshghi, Mehrdad Kargari,
Volume 29, Issue 1 (3-2018)
Abstract
In this paper a fraud detection method is proposed which user behaviors are modeled using two main components namely the un-normal trend analysis component and scenario based component. The extent of deviation of a transaction from his/her normal behavior is estimated using fuzzy membership functions. The results of applying all membership functions on a transaction will then be infused and a final risk is gained which is the basis for decision making in order to block the arrived transaction or not. An optimized threshold for the value of the final risk is estimated in order to make a balance between the fraud detection rate and alarm rate. Although the assessment of such problems are complicated, we show that this method can be useful in application according to several measures and metrics.
Hamiden Abd Elwahed Khalifa, El- Saed Ebrahim Ammar,
Volume 30, Issue 1 (3-2019)
Abstract
Fully fuzzy linear programming is applied to water resources management due to its close connection with human life, which is considered to be of great importance. This paper investigates the decision-making concerning water resources management under uncertainty based on two-stage stochastic fuzzy linear programming. A solution method for solving the problem with fuzziness in relations is suggested to prove its applicability. The purpose of the method is to generate a set of solutions for water resources planning that helps the decision-maker make a tradeoff between economic efficiency and risk violation of the constraints. Finally, a numerical example is given and is approached by the proposed method.
Hamiden Khalifa, E. E. Ammar,
Volume 31, Issue 1 (3-2020)
Abstract
This paper deals with a multi- objective linear fractional programming problem involving probabilistic parameters in the right- hand side of the constraints. These probabilistic parameters are randomly distributed with known means and variances through the use of Uniform and Exponential Distributions. After converting the probabilistic problem into an equivalent deterministic problem, a fuzzy programming approach is applied by defining a membership function. A linear membership function is being used for obtaining an optimal compromise solution. The stability set of the first kind without differentiability corresponding to the obtained optimal compromise solution is determined. A solution procedure for obtaining an optimal compromise solution and the stability set of the first kind is presented. Finally, a numerical example is given to clarify the practically and the efficiency of the study.
Hamiden Khalifa,
Volume 31, Issue 2 (6-2020)
Abstract
This paper aims to study multi- objective assignment (NMOAS) problem with imprecise costs instead of its prices information. The NMOAS problem is considered by incorporating single valued trapezoidal neutrosophic numbers in the elements of cost matrices. After converting the NMOAS problem into the corresponding crisp multiobjective assignment (MOAS) problem based on the score function, an approach to find the most preferred neutrosophic solution is discussed. The approach is used through a weighting Tchebycheff problem which is applied by defining relative weights and ideal targets. The advantage of this approach is more flexible than the standard multi- objective assignment problem, where it allows the decision maker (DM) to choose the targets he is willing. Finally, a numerical example is given to illustrate the utility, effectiveness and applicability of the approach.
