خلاصة:
The classification of fuzzy uncertain data is considered one of the most challenging issues in data analysis. In spite of the significance of fuzzy data in mathematical programming, the development of the analytical methods of fuzzy data is slow. Therefore, the current study proposes a new fuzzy data classification method based on fuzzy data envelopment analysis (DEA) which can handle streaming data. The new method is tested by simulated data and the results indicate its effectiveness in facing uncertain data and variable conditions.
ملخص الجهاز:
Fuzzy Data Envelopment Analysis for Classification of Streaming Data Alireza Alinezhad Associate Professor, Faculty of industrial and mechanical engineering, Qazvin branch, Islamic Azad University, Qazvin, Iran E-mail address: alinezhad_ir@yahoo.
Therefore, the current study proposes a new fuzzy data classification method based on fuzzy data envelopment analysis (DEA) which can handle streaming data.
Keywords: Fuzzy Data Envelopment Analysis, Mathematical Programming; Classification; Fuzzy Streaming Data Introduction Classification is assigning a class or category to a data (position) based on a predetermined function or model.
The border of classes 1 and 2 based on frontier points and the data of Table 1 Classification of Uncertain Fuzzy Data Using Data Envelopment Analysis Assuming that the value of jth ( ) characteristic related to ith data ( ) is a trapezoidal fuzzy number in the form of , the pattern of linear programming model appropriate to a DEA problem will be in the form of Equation 4.
The border of classes 1 and 2 based on frontier points and the data of Table 4 Classification of Fuzzy Streaming Data Using DEA The new framework, which is used to classify fuzzy data using data envelopment analysis, is illustrated in Figure 4.
As it is shown in the figure, first, DEA problems are solved to identify boundary areas based ranges, we determine the label of the new data in accordance with the classification to which they belong.
87 Results This study developed a model of the data classification in the form of a Data Envelopment Analysis (DEA) problem based on the trapezoidal fuzzy uncertain data.