The basic FDH model is to ensure that efficiency evaluations are effected from only actually observed performances. That introduced in input-oriented or output-oriented only. In this paper, we propose a FDH model in input-output orientation, simultaneously. 

Hydrological modelling is usually used as a tool for predicting watershed hydrological response by water resources planners in flood forecasting and water resources management. Identification of the Nash-cascade model parameters as a practical model in simulation of flood hydrograph is very important in watersheds with limited data. The aim of this study was determining the Nash model response to variations of input parameters ranges (number of reservoirs and storage coefficient), and best subset combination to simulate unit hydrograph in the Jafar-Abad watershed, Golestan Province. The forty three rainfall-runoff events were used to derive that index unit hydrograph of the study area using S-curve technique. Then, the response of the Nash model results output was assessed considering random generated n, and k parameters through 3220 synthetic simulation and model efficiency was assesses using Nash-sutcliffe criteria. The results showed that the model has produced acceptable results in different values of n, and k input parameters and the model efficiency were more than 0. 6 with ranges of 10-30 for n parameter and 0. 01-3 subset of k values. The response of the Nash model in higher k and low n value subsets, showed the perfect simulation results. Also the results indicates that the storage coefficient parameter had an effective influence on determination of optimal input model combination, while a suitable model results is possible in different values on (n) number of reservoirs. In conclusion, identification of a precise value for the storage coefficient can greatly improve the simulation results. The results and the used approach can be used to determine the optimal model response regarding input parameters in similar ungauged watersheds.

A novel approach to the problem of regression modeling for fuzzy input-output data is introduced. In order to estimate the parameters of the model, a distance on the space of interval-valued quantities is employed. By minimizing the sum of squared errors, a class of regression models is derived based on the interval-valued data obtained from the a-level sets of fuzzy input-output data. Then, by integrating the obtained parameters of the interval-valued regression models, the optimal values of parameters for the main fuzzy regression model are estimated. Numerical examples and comparison studies are given to clarify the proposed procedure, and to show the performance of the proposed procedure with respect to some common methods.

Distributed Denial of Service (DDoS) attacks are among the primary concerns in internet security today. Machine learning can be exploited to detect such attacks. In this paper, a multi-layer perceptron model is proposed and implemented using deep machine learning to distinguish between malicious and normal traffic based on their behavioral patterns. The proposed model is trained and tested using the CICDDoS2019 dataset. To remove irrelevant and redundant data from the dataset and increase learning accuracy, feature selection is used to select and extract the most effective features that allow us to detect these attacks. Moreover, we use the grid search algorithm to acquire optimum values of the model’s hyperparameters among the parameters’ space. In addition, the sensitivity of accuracy of the model to variations of an input parameter is analyzed. Finally, the effectiveness of the presented model is validated in comparison with some state-of-the-art works.

To evaluate the effect of nitrogen and water withholding in vegetative growth stage of corn on efficacy of nicosulfuron and 2,4-D+ MCPA an experiment was conducted as a factorial arrangement in a randomized complete block design with three replications at Tarbiat Modares University in 2017. The first factor contained four treatments including application of nicosulfuron, 2,4-D+ MCPA, weed free and weed infested as control. The second factor consisted of normal irrigation and water withholding from 4 to 8 leaf stage. Third factor contained either urea application or no fertilizer application. Normal irrigation and nitrogen fertilizer application significantly increased nicosulfuron and 2,4-D+ MCPA efficacy in weed control and total weed dry weight decreased to 341 and 361 g.m-2 respectively compared 1370 g.m-2 as weed infested. Nicosulfuron and 2,4-D+ MCPA reduced weed total dry weight significantly under irrigation withholding. Grain yield increased with application of nitrogen and nicosulfuron. Grain yield was higher with application of 2,4-D+ MCPA than nicosulfuron without nitrogen application under irrigation withholding. Application of nicosulfuron with nitrogen application provided satisfactory weed control and increased grain yield.

BACKGROUND AND OBJECTIVES: Air quality in some developing countries is dominated by particulate matter, especially those with size 10 micrometers and smaller or PM10. They can be inhaled and sometimes can get deep into lungs,some may even get into bloodstream and cause serious health problems. Therefore, future PM10 concentration forecasting is important for early prevention and in urban development planning, which is crucial for developing cities. This paper presents the development of PM10 forecasting model using nonlinear autoregressive with exogenous input model. METHODS: To improve performance of nonlinear autoregressive with exogenous input model, principal component analysis is used prior to the model for variable selection. The first stage of principal component analysis involves Scree plot, which determines the number of principal components based on explained variance. This is then followed by selecting variables using a rotated component matrix, based on their strength of contribution towards variation of PM10 concentration. To test the model, PM10 data in Kota Kinabalu from 2003 –,2010 was used. Neural network models are developed using this data by varying number of input variables with the inclusion of temporal variables. The developed forecasting models are evaluated using data PM10 in the city from 2011 to 2012. Four performance indicators, namely root mean square error, mean absolute error, index of agreement and fractional bias are reported. FINDINGS: Results from principal component analysis show that five variables including wind direction index, relative humidity, ambient temperature, concentration of nitrogen dioxide and concentration of ozone strongly contribute to the variation of PM10 concentration. By using these variables together with temporal variables as input in the nonlinear autoregressive with exogenous input models, the resultant model shows good forecasting performance, with root mean square error of 7. 086±, 0. 873 μ, g/m3. The selection of significant variables helps in reducing input variables inside the forecast model without degrading its forecast performance. CONCLUSION: This model shows very promising performance in forecasting PM10 concentration in Kota Kinabalu as it requires fewer input variables and does not require variable transformation.