Context and Goal: Forecast is one of the important tools in the hands of managers for strategic decision making. Shipping with all the benefits, but also injuries and significant losses associated with traffic accidents cause mortality and severe damage to life and property and the heavy consequences of social, economic, cultural and human societies is seriously threatened, which is important for future studies in the field of traffic accidents Method: In this study, using gray system GM (1, 1), gray circulation model RGM (1, 1), gray model FGM (1, 1), remained the same model, ARIMA time series model and the harmonic pattern As well as the use of statistical data the number of victims of traffic accidents in the province between March 2009 and February 2016, To predict the number of victims referred to the coroner province between 2017 and 2020 is discussed. For the ACCURACY of prediction ACCURACY indicator gauge is used. Findings and Conclusion: Mean absolute percent error for models GM, RGM, FGM, changes survivor, Arima and harmonics to predict the number of patients referred to the 0. 10, 0. 07, 0. 12, 0. 14, 0. 13 and 0. 15, respectively, indicating a more accurate method of RGM the anticipated number of patients referred to the coroner in the province of Zanjan. According to the results of the reference in the province RGM number of victims is declining. And the number of victims in the years 1398 to 2894 will reach people. the RGM, the best method to predict the number of disaster victims referred to legal medicine of Zanjan province compared to other methods of case study in this research, and managers and experts to predict with high ACCURACY can be used this way. Reducing the number of disaster victims referred to legal medicine represents the improvement of driving tips and actions and nested in the province is that we can continue with this approach to reduce the number of accidents and disaster more help.

The non-parametric regression method of K-nearest neighbour (K-NN) has been used in a variety of eco-hydrological issues. In this study, some techniques are presented to improve the ACCURACY of the K-NN method in FORECASTING the accumulated 9-month inflow of Zayandeh-rud dam in Iran, from winter to the end of the following summer. The improving techniques considered at current study include: 1) selection of the best data pre-processing functions, 2) selecting the best number of neighbour, 3) selecting the best distance functions, 4) specifying the best weights of predictors at distance functions, and 5) Adding the ability of extrapolation to K-NN using a simple method. Final results show that the use of mentioned techniques can improve the ACCURACY of K-NN’s forecast meaningfully. The results of goodness-of-fit criteria for the optimized K-NN in comparison with a regular K-NN can present an increase of 31% at correlation coefficient (from 65% to 96%), a decrease from 31 to 8 at volume error, and finally a drop from 54 to 25 at root mean square error.

Predicting the path of pollution in the marine area is one of the most important concerns for those involved in environmental studies. In this paper, we have discussed the capabilities of using the data assimilation method in the FVCOM numerical model in FORECASTING the movement path of a surface drifter in the Strait of Hormuz. Initially, the FVCOM model was implemented for particle tracking by using environmental data in the Strait of Hormuz. Then tidal gages data of the Strait of Hormuz were assimilated in the numerical model using the nudging method. The results of the two runs were compared with field measurements data using statistical parameters such as bias and correlation coefficient. Statistical analysis and visual comparisons depicted the ability of data assimilation in optimizing the model water level outputs and reducing the differences between drifter location and model results and also the rate of the distance between them.

Autumn precipitation FORECASTING plays a key role in agricultural planning especially rainfed farming feasibility studies. In this study, model fusion technique has been used in order to increase the ACCURACY of autumn precipitation forecast. Based on two teleconnection signals of SOI and NINO 3.4 as predictors, five models including; Artificial Neural Network (ANN), Generalized Regression Neural Network (GRNN), Support Vector Regression (SVR), K-Nearest Neighbor (KNN), and Linear Regression (LR) with optimized structure have been implemented as individual rainfall FORECASTING models (IPFMs) in Seimareh subbasin of Karkheh basin, IRAN. In order to combine the IPFMs, the ordered weighted aggregation strategy (OWA) has been performed in which, two weighting methods including Orness and Orlike methods have been used and assessed for determining the weights of IPFMs. The results of this study showed that the forecasted rainfall obtained from two methods of OWA model fusion strategy has more ACCURACY comparing to individual FORECASTING models. Moreover, application of the Orlike method did a quite better job than Orness method. Besides, comparing the results of the OWA strategy methods with two other strategies viz model fusion with artificial neural network and selecting the best IPFM revealed that both Orness and Orlike methods are performing more precisely than two other strategies in FORECASTING rainfall.

AbstractIn the present study, the researcher uses meta-analysis to investigate how the size of the company affects the ACCURACY of earnings FORECASTING. In the first step, referring to the available domestic and foreign scientific and research databases, the keywords of company size and ACCURACY of earnings FORECASTING and meta-analysis method were searched and a number of articles in Persian and English from 2010 to 2021 about this relationship were found. In the next step, in order to calculate the size of the study effect, the researcher first standardizes all the results of the articles and identifies them so that they can be compared and combined. The results of the present study using the statistical combination of the results of previous studies in the field of examining the effect of company size on the ACCURACY of earnings FORECASTING showed that the fixed effects model is valid and significant and states that company size has a significant effect on the ACCURACY of earnings FORECASTING. Also, tests of homogeneity of research showed that the studies of the present study are completely homogeneous

In this paper, a new histogram-based method is introduced to make object detectors resistant to hostile attacks. In the following, this method was applied to two object detector models, YOLOV5 and FRCNN, and in this way, two models resistant to attacks were introduced. In order to verify the performance of the mentioned models, we performed the adversarial training process of these models with three targeted attacks TOG-vanishing, TOG-mislabeling, and TOG-fabrication and one untargeted attack, DAG. We have checked the efficiency of the introduced models on two data sets MSCOCO and PASCAL VOC, which are among the most famous data sets in the field of object recognition. The results show that this method, in addition to improving the adversarial ACCURACY, also improves the clean ACCURACY of the object detector models to some extent. The average clean ACCURACY of the YOLOv5-n model for the PASCAL VOC dataset, if adversarial attacks are applied to it, in the case where no defense method is applied, is 85.5%, and in the case where the histogram method is applied, the average ACCURACY is equal to with 87.36%. In the YOLOv5-n model, according to the results, the best adversarial ACCURACY of this model, which has increased compared to other models, is in TOG-vanishing and TOG-fabrication attacks, which are 48% and 52.36%, respectively.

Various methods have recently been proposed to predict essential economic and non-economic variables. Each FORECASTING method has its own advantages and disadvantages based on the nature of the input data. Box-Jenkins and Halt-Winters methods are among the new approaches for increasing the ACCURACY of FORECASTING results. Therefore, this research aimed to predict OPEC average oil price data for June 2022 to May 2024 based on the data from 2003 to 2022 using Box-Jenkins and Holt-Winters methodology with a single variable. The errors of Box-Jenkins methodology, among the time series, processes ARIMA 5.1.5, ARIMA 4.1.5, ARIMA 3.1.5, and ARIMA 5.1.3 have the best ACCURACY with MSE of 61.86, 63.21, 63.29, and 63.62, respectively. The ACCURACY of the Holt-Winters method was not appropriately compared to the time series method due to the nature of the data.

Hydrological time-series is a time-dependent hydrological variable that finding the model of changes and predicting is the most important goal of time-series analysis. The purpose of this study is to simultaneously study the characteristics of time series and their prediction and the important parameters of the GEP for high-precision predictions in the training and validation. In this study, groundwater depth time-series of Chamchamal plain station located in Kermanshah province with a 12-year period and mountainous climate and the monthly time-series of Alaska temperature with a 50-year period and cold and dry climate have been used. Genexprotools5. 0 software has been used to model time-series by GEP. The results of studying with GEP showed that the periodicity of data properties that existed in the time series of temperature caused correlation results above 90% in different stages of training and validation. So that the effect of different parameters of GEP is less than 10% in improving results. On the other hand, by examining the time-series of groundwater depth, which lacks periodicity and has a descending ACF shape, the prediction results of the GEP with any effective expression parameter, R more than 44% in the validation wasn't obtained. This means that the time-series preprocessing has a greater impact on the prediction results. So that by eliminating the semester, the prediction results in all stages of modeling are significantly reduced. In this case, the best R for the validation is 50%.