Data envelopment analysis (DEA) helps the managers to separate and classify the e cient and ine cient units in a homogenous group. DEA is a set of methods inferred from mathematics and other sciences in which the branch of unit ranking can be signi cantly e ective in improving managerial decisions. Although this branch in DEA is considered still young, it has proved its ability in solving some problems like production planning, resource allocation, inventory control, etc. The managers who care about their results quality cannot be indi erent to units ranking. In this article, to rank the units which are under-evaluated,  rstly the decision-making unit (DMU) is removed from the production possibility set (PPS), and then the new PPS is produced. The unit under evaluation is inside or outside of the new PPS. Therefore, to benchmark the under-evaluation DMU to new frontiers, two models are solved. If the removed unit is outside of the new PPS, the  rst model is feasible, and the second model is infeasible. If the removed unit is inside or on the frontier of the new PPS, both models are feasible. The method presented in this article for ranking the under-evaluation units has these characteristics: 1-this model can distinguish Extreme and non-Extreme e cient units and ine cient units. 2-Also, the presented models for ranking DMUs can be changed into a linear model. 3-This method shows stability in changing small or near-zero data. 4-It does not assign a false ranking. The presented methods in this article are able to distinguish the set of Extreme and non-Extreme e cient and ine cient units as well as being able to overcome the common problems in ranking. In this article, suggested models are introduced in 3. 1 which are able to rank all under evaluation units except non-Extreme e cient units, this problem is solved in 3. 2, in other words in 3. 2 all DMUs are ranked.

Super efficiency data envelopment analysis (DEA) model can be used in ranking the performance of efficient decision making units (DMUs). In DEA, non-Extreme efficient units have a super efficiency score one and the existing super efficiency DEA models do not provide a complete ranking about these units. In this paper, we will propose a method for ranking the performance of the Extreme and non-Extreme efficient units.

In this paper, we present two methods to find the strictly efficient and weakly efficient points of multi-objective programming (MOP) problems in which their objective functions are pseudo-convex and their feasible sets are polyhedrons. The obtained efficient solutions in these methods are the Extreme points. Since the pseudo-convex functions are quasi-convex as well, therefore the presented methods can be used to find efficient solutions of the (MOP) problem with the quasi-convex objective functions and the polyhedron feasible set. Two experimental examples are presented.

Identifying the efficient Extreme units in a production possibility set is a very important matter in data envelopment analysis, as these observed, real units have the best performances. In this paper, we proposed a multiple objective programming model, in which the feasible region is the production possibility set under the assumption of variable returns to scale and the objective function consists of input and output variables. As we know, by increasing the dimensions of the problem, the set of efficient points would increase as well; thus, using the multiple objective linear programming problem-solving methods in a decision set would lead to computational problems and it would be much easier to work in the outcome set instead of the decision set. In this research, we show that the efficient points in the outcome set of the suggested multiple objective linear programming problems correspond with the efficient Extreme points in data envelopment analysis. An outer approximation algorithm is presented for production of all efficient Extreme points in the outcome set. This algorithm provides us with the equations for all efficient surfaces. In the outcome set, this algorithm would use few calculations to produce all the Extreme points. Finally, we demonstrate the presented approach through numerical examples.

Data envelopment analysis (DEA) is a mathematical programming method for calculating efficiency of decision making units (DMU). In calculating the efficiency score of units through DEA we may come up with some efficient units. But the question is among these efficient units which of them is better. As we know, it is possible to rank inefficient units through efficiency score; however, for ranking efficient units it is not helpful and other methods should be developed in these regards. To obviate this problem there have been so many attempts in the literature which have their pros and cons. Cross-efficiency method was first introduced by Sexon et al. for ranking efficient units. The major problem of this method is alternative optimal solutions in each model which must be solved for each DMU. Another problem of this method is dependency of obtained solutions on the solution obtained by other units. Another method which has widely been used is super efficiency, presented by Anderson and Petersen. There are several flaws in their suggested method. Infeasibility, instability, dependency of the model on the input and output orientation and non-zero slack variables are the weaknesses of this method which may occur in specific problems. This article is an attempt to present a method which does not have the aforementioned problems and can be utilized to calculate the rank of Extreme efficient units through using the Hit or Miss Monte Carlo method. At the end of the article some examples are made in order to show the efficiency of the presented method.

A B S T R A C T Temperature is one of the climate elements that has fluctuated a lot over time. When these fluctuations increase and decrease more than normal and are placed in the upper and lower regions of the statistical distribution, if continued, it can lead to the creation of heating and cooling waves. The purpose of this study is to analyze the temporal and spatial changes in heating and cooling waves in Iran during a period of 50 years. For this purpose, the temperature of 663 synoptic stations from 1962 to 2004 was obtained from the Esfazari database. Then, in order to complete this database, the daily temperature from 2004 to 2011 was obtained from the Meteorological Organization of the country and added to the aforementioned database. In order to perform calculations and draw maps, Matlab, grads and Surfer software have been used. The results of this study showed that the index of cooling waves and heating waves, while having a direct effect on each other, had an increasing trend in most of the area of Iran. The statistical distribution of the index of cooling waves is more heterogeneous than that of the index of heating waves. So that the spatial variation coefficient for cold waves is 84.22%. Also, the index of cooling waves has more spatial variability. The highest common diffraction of the index of heating and cooling waves has been seen in the northwest, east and along the Zagros mountains. Analysis of the indexes trends show that heat waves have intensified in 65.8% of Iran and the intensity of cold waves has decreased in 48.5% of Iran Extended Abstract Introduction Temperature is one of the major climatic variables, which it has a direct impact on different aspects of human life. It plays an essential role in the growth of crops and is considered a key driver of the biological system(Reicosky et al, 1988). It is associated with several types of Extremes, for example, heat and cold waves which caused human societies maximum damage. Past occurrences of heat waves hitherto had significant impacts on several aspects of society. Have increased Mortality and morbidity. Ecosystems can be affected, as well as increased pressure on infrastructures that support society, such as water, transportation, and energy(Dewce, 2016). The long-term change of Extreme temperatures has a key role in climatic change. The form of statistical distribution and the variability of mean values and also Extreme event indicate a change in the region. It can be a small relative change in the mean as a result of a large change in the probability of Extreme occurrence. Also, the variation in temperature data variance is significantly more important than the mean, for assessing the Extreme occurrence of climate(Toreti and Desiato, 2008). The average surface temperature has increased the world between 0.56 and 0.92 ° C over the past 100 years(IPCC, 2007). Meanwhile, it was in the Middle East, the average daily temperature increased by 0.4-0.5 ° C in decades(Kostopoulou et al, 2014; Tanarhte et al, 2012). Considering that not many studies have been done in the field of spatio-temporal Variations of the heating and cooling waves thresholds in Iran, in this study, the spatio-temporal Variations of the heating and cooling waves thresholds in Iran during 50 years were examined and analyzed.   Methodology The daily temperature from the beginning of the year 21/03/1967 to 19/05/2005 was obtained from the Esfazari database prepared by Dr. Masoudian at the University of Isfahan. In order to increase the time resolution of the mentioned database, the daily temperature of observations from 05/21/2005 to 05/12/2012 has been added to the mentioned database using the same method, and the exact spatial resolution (15 x 15 km) is used as a database. Threshold indices of heating waves are the average numbers between the 95th and 99th percentiles, that is, the Extreme hot threshold to the limit of excessively Extreme hot. For Extreme cool, from the 5th percentile down to zero is used. Of course, a condition was added to these thresholds, which is that these thresholds must be repeated two days in a row. These thresholds were extracted for each day in the 50 years of the study period and used as the original database. In order to analyze the relationship between cooling and heating waves, Pearson's correlation coefficient was used and regression was used to analyze the trend.   Results and discussion The average of cold waves was 5.26 ° C and for the heat waves is 30.20° C. Generally, if the temperature is upper or lower than this threshold, it is considered as hot or cold temperatures. A comparison of the median, mode, and average of cold waves with heat waves shows that the distribution is more heterogeneous for cold waves and its CV is 84.22%. In southern Iran, the average threshold heat waves are higher. This situation can be caused by the effects of subtropical high-pressure radiation, low latitude, and proximity to the sea. Though the threshold is higher in these areas, fewer fluctuations and changes are seen in the area. Heights moderate the temperature so they pose a minimum threshold for heat waves i.e. an iso-threshold of 25 ° C is consistent along the Zagros mountain chains, but in the west and east of Zagros Mountains, the threshold of heat waves is increased. Heat waves have increased in most areas of the country. So nearly 85 percent of the Iran has been an increasing trend, of which 65.8 percent is statistically significant at the 95% confidence level. Still, more areas of the country (60 percent) have a trend between 0.00828 and 0.00161. As can be seen, only 15% of the land area (including the southwest and northwest of the Country) had decreased heat waves. Cold waves, in most parts of the country, have a Positive Trend. However, about 25 percent of the study area's cold waves have a negative trend. they are located in areas higher than Latitude 30°. The largest decline of the wave's trend along the country is highlands. Nowadays, most of the country, has a trend between 0.01494 and 0.00828 ° C, respectively. Conclusion Common changes and effects of heat and cold waves had a direct relationship in many parts of the country. It is remarkable common variance in the East reached 55 percent, according to statistical significance. In some areas of the northwest and southwest, which have been impressive heights, the common variance is 40 percent. This common variance in mountains area has been high values. Investigation of heat waves trend shows that 65.8% of Iran significant positive trend and 7.1% significant negative trend. Also, the cold waves trend has indicated a 48.5% significant positive trend and a 10.8% significant negative trend. Climate change and global warming have changed the frequency and severity of temperature Extremes. The present study, by examining the number of warm waves, concluded that the warm waves have increased in magnitude in 65.8% of the Iran zone. Also, the study of the cold waves trend showed that 48.5 percent of Iran had a positive trend, which means that the amount of temperature in the cold waves increased In other words, the severity of the cold has been reduced And only 10.8 percent of Iran had a negative cold wave trend And it shows the intensity of these waves is reduced.   Funding There is no funding support.   Authors’ Contribution The authors contributed equally to the conceptualization and writing of the article. All of the authors approthe contenttent of the manuscript and agreed on all aspects of the work declaration of competing interest none.   Conflict of Interest The authors declared no conflict of interest.   Acknowledgments  We are grateful to all the scientific consultants of this paper.

Due to the stochastic nature of wind energy, allocating an appropriate investment incentive for wind generation technology (WGT) is a complicated issue. We propose an improvement on the traditional incentive, known as capacity payment mechanism (CPM), to reward the wind generators based on their performance exogenously affected by the wind energy potential of the location where the turbines are installed, and therefore, lead the investments towards locations with more generation potential. In CPM, a part of investment cost of each generator is recovered through fixed payments. However, in our proposal, wind generators are rewarded according to dynamic forecasts of the wind energy potential of the wind farm where they are located. We use an auto-regressive moving average (ARMA) model to forecast the wind speed fluctuations in long-term while capturing the auto-correlation of wind velocity variation in consecutive time intervals. Using the system dynamics (SD) modelling approach a competitive electricity market is designed to examine the efficiency of the proposed incentive. Performing a simulation analysis, we conclude that while a fixed CPM for wind generation can decrease the loss of load durations and average prices in long-term, the proposed improvement can provide quite similar results more efficiently.

The purpose of this study is to utilize a new method for ranking Extreme efficient decision making units (DMUs) based upon the omission of these efficient DMUs from reference set of inefficient and non-Extreme efficient DMUs in data envelopment analysis (DEA) models with constant and variable returns to scale. In this method, an L2-norm is used and it is believed that it doesn't have any existing problems of such methods. Finally, two numerical examples for illustration and comparing the proposed method with other ranking approaches are presented.

Recently, many neural network methods have been proposed for multilabel classification in the literature. One of these recent methods is the Multi-Layer Extreme Learning Machines (ML-ELMs) in which stack auto encoders are used for tuning their weights. However, ML-ELMs suffer from three primary drawbacks: First, input weights and biases are chosen randomly; second, the pseudoinverse solution for calculating output weights will increase the reconstruction error; third, memory and execution time of transformation matrices are proportional to the number of hidden layers. In this paper, Multi-Layer Kernel Extreme Learning Machine (ML-CK-ELM) that uses a linear combination of base kernels in each layer is proposed for multi-label classification. The proposed approach effectively addresses the above-mentioned drawbacks. Furthermore, multi-label classification data are inherently characterized by multi-modal aspects due to a variety of labels assigned to each instance. Applying a combination of different kernels is the added advantage of ML-CK-ELM that implicitly assesses the inherent multi-modal aspects of multi-label data; each kernel can be effectively used to cover one of the modals better than other kernels. The empirical study indicates that ML-CK-ELM shows competitively better performance than other state-of-the-art methods, and experimental results of multilabel datasets verify the feasibility of ML-CK-ELM.