mohammadreza hassanzadeh

Malware is one of the constant challenges of the modern world, which has particular importance due to the harm it causes to users. In the last decade, there has been a great increase in malware number and complexity that caused the current security tools and methods not able to defend against. Visualizing binary content of malware and searching for malicious elements among suspicious image patterns is one of the new methods that have achieved high progress and efficiency in the last decade thanks to deep learning algorithms. In this research, by combining various ideas that exist in the field of malware image analysis, a suitable algorithm has been presented for classifying malware into their corresponding families. Visualizing the binary content of the malware executable file, applying the GIST descriptor and classifying the extracted features using the SVM classifier forms the proposed algorithm of this research, which can achieve the same results as previous researches by using traditional machine learning methods and obtain average classification accuracy of 99.72 and 99.16% on Malimg and Microsoft datasets.

When dealing with a road accident and reconstructing the scene, one of the main parameters is the speed of the vehicle at the time of the accident. In the past, the speed of vehicles at the time of collision or before the collision was determined based on the effect of the remaining brake line. In the last decade, cars have been equipped with anti-lock braking system (ABS). However, many of the mentioned methods are not able to solve the problem of speed determination, and the need to provide new methods of speed calculation seems necessary.

The load dynamics of the seat belt, which is used as a means to limit the movement of people inside the car during sudden deceleration, has been used to calculate the speed of the car according to the change in the shape of the belt and the corresponding movement of the person.

The findings of the research indicate that the use of seat belts reduces the probability of death and other types of injuries compared to drivers and passengers who do not use seat belts. In addition, as the weight of the driver increases, the speed of the vehicle in which the seat belt breaks at the moment of impact with the fixed obstacle decreases.

The proposed method for determining the speed of the vehicle allows the court, judges, research institutions and investigators to have a correct assessment of the actions of the people involved in the accident.

In recent years, convolutional neural networks (CNNs) have been increasingly used in various applications of machine vision. CNNs simulate the function of the brain's visual cortex and have a powerful structure for analyzing visual images. However, the diversity of digital images, their content, and their features necessitate that CNN networks are specially designed, and their parameters are carefully adjusted to achieve higher efficiency in any classification problem. In this regard, in many previous studies, researchers have attempted to increase the efficiency of the CNNs by setting their adjustable parameters more accurately.

New method In this study, we presented a novel initializing method for the kernels of the first convolutional layer of the CNN networks. We designed a filter bank with specialized kernels and used them in the first convolution layer of the proposed models. These kernels, compared to the random kernels in traditional CNNs, extract more effective features from the input images without increasing the computational cost of the network, and improve the classification accuracy by covering all the important characteristics.

The dataset used in this paper was the MNIST database of handwritten digits. We examined the performance of CNN networks when three different types of kernels were used in their first convolution layer. The first group of kernels had constant coefficients; the second group had random coefficients, and finally, the kernels of the third group were specially designed to extract a wide range of image features. Our experiments on a single-layer CNN network with three types of kernels (constant numbers, random numbers, and filter-bank) showed the average classification accuracy of MNIST images in 50 times of network training to be 74.94%, 86.47%, and 91.89%, respectively, and for a three-layer CNN network, 88.82%, 96.16%, and 99.14%, respectively. Comparison with existing methods Compared to the kernels with randomized coefficients, the use of specialized kernels in the first convolution layer of the CNN networks has several important advantages: 1) They can be designed to extract all important features of the input images, 2) They can be designed more effectively based on the problem in hand, 3) They cause the training to start from a more appropriate point, and in this way, the speed of training and the classification accuracy of the network increase.

This study provides a novel method for initializing kernels in convolution layers of CNN networks to enhance their performance in image classification works. Our results show that compared to random kernels, the kernels used in the proposed models extract more effective features from the images at different frequencies and increase the classification accuracy by starting the training algorithm from a more appropriate point, without increasing the computational cost. Therefore, it can be concluded that the initial coefficients of the convolution layer kernels are effective on the classification accuracy of CNN networks, and by using more effective kernels in the convolution layers, these networks can be made specific to the problem and, in this way, increase the efficiency of the network.

Many studies have been conducted based on field data collected to determine the effects of weather on traffic flow characteristics. However, there are limitations to field data studies that make it difficult to comprehensively assess the impact of weather conditions, especially unusual weather conditions, on traffic flow characteristics. According to traffic police statistics, in the last decade, speeding has been identified as the main cause of accidents on freeways, and therefore speed limits will be the most common retaliatory action by traffic police to prevent these cases. However, few studies have focused on the issue of speed limits in sandstorm conditions that reduce visibility and reduce pavement friction; Therefore, the purpose of this study is to develop a prototype of speed limit theory for roads in sandstorm conditions. For this purpose, in this study, samples of porous asphalt were prepared in the laboratory of Yazd University and after spreading the sandstorm (sandstorm around the desert roads of Yazd province) the amount of friction was measured by the English pendulum test. In general, the results show that the friction rate decreases by about 8.4% when the sandstorm blows due to the scattering of sand particles on the asphalt surface, and consequently the safe speed must be reduced. For example, in a steady field of view (Lv) and a slope (i) of 250 Lv and i = 100% safe speed is also reduced by about 10%. In such a situation, speed limits by electronic signs and traffic police can effectively prevent accidents.

Binge eating disorder (BED) is one of the most common eating disorders. Numerous factors such as aggression, rumination, anger, and anger rumination are associated with BED. The main purpose of this study was to investigate the effectiveness of schema therapy on anger rumination and aggression in men with binge eating disorder.

 This quasi-experimental study was a pre-test and post-test design with a control group. The statistical population consisted of all men with BED who are members of the Mashhad Overeaters Anonymous (OA) association in 2020. Twenty four of them were selected by convenience sampling method and randomly placed in two groups (experiment and control groups). Pre-test was performed for both groups, including anger rumination scale (ARS) and aggression questionnaire (AQ). The control group did not receive any intervention. Post-test was completed for both groups and the results were analyzed by multivariate analysis of covariance.

The results showed that schema therapy reduces anger rumination and aggression in people with BED in the experimental group compared to the control group. (p <.01).

Based on the results of the present study, it can be said that therapists can use this treatment to reduce anger rumination and aggression in people with BED.

Road accidents cause many damages in the country every year, which is sometimes impossible to compensate for their consequences, so identifying the variables affecting accidents and planning to solve them in terms of priorities is inevitable, so this study was conducted to identify and rank road and environment factors in road accidents.

This research is applied in terms of purpose and in terms of nature, descriptive-analytical and quantitative in terms of methodology. The statistical population of the study consisted of 50 experts, experts and civil professors of road construction projects in Khorramabad city who have sufficient information and skills in this field, data collection tools, a researcher-made questionnaire and to ensure its validity from the viewpoints of professors and for reliability of the questionnaire, Cronbach's alpha coefficient was used and analysis and ranking of variables were done by BWD method.

According to the findings, six indicators affecting the incidence of road accidents were identified and extracted in two dimensions. And the quality of the road ranked first, the existence of the valley and the screw ranked second, temperature and frost ranked third, the low width of the road ranked fourth, the storm and the presence of dust ranked fifth and snow and rain ranked sixth.

If appropriate and targeted planning priority is done in order to resolve the identified defects, we will see a reduction in road accidents and fatalities along khorramabad-Boroujerd route.

Transportation and communication arteries have been the source of many positive and negative events throughout human history. Traffic accidents and the resulting injuries, which threaten the lives of many people around the world and annually about 1.2 million people in the world are killed in road accidents and more than 50 million people suffer serious injuries, including these events It is negative. The present study is in order to analyze the causes of the occurrence of these traffic accidents on the outskirts of cities in 1397 in the city of Mashhad.

This research is applied in terms of purpose and qualitative research method (directional content analysis). The statistical population includes all the chiefs and deputies of police experts in accident affairs of the country, who were selected from 21 people based on snowball sampling. The method of gathering field information and its tools are in-depth semi-structured interviews to achieve theoretical saturation. Due to the quality of the work, the analysis method is simultaneously collected, encoded, compressed, isolated and summarized and encrypted. Then by creating the categories, the themes using the software version 18 Max. کیو.دی. It was calculated and analyzed.

Forecasting and prevention, comprehensive management, infrastructure, prevailing conditions in the suburbs and safety are the main causes of traffic accidents in the suburbs of Mashhad and in this regard, some suggestions were presented at the end.

One of the reasons for many traffic accidents is the delay in seeing the obstacle. The city of Khorramabad, due to having many intersections, old alleys and boulevards with dense and unsuitable plants on its outskirts, is facing many problems due to visual barriers. The purpose of this study is to investigate the effect of sight barriers on accidents

The method of the present research is applied in terms of purpose, descriptive-analytical, and quantitative in terms of nature and method of implementation. In this study, some intersections, boulevards and side streets that are similar in terms of traffic volume and geometric features, but one of them has a visual impairment and the other does not, have been selected and compared in pairs. The data collection tool in this research is the information of the existing accidents and the com form of the accident sketches drawn by the accident expert officers in 1397 in the traffic police of Khorramabad.

The results of this study have shown that there is a significant effect between the presence of visual barriers on the side of the road and the increase of accidents. more than.

Because removing visual barriers is one of the low-cost measures to increase traffic safety in the city of Khorramabad, so the municipality can prevent accidents largely by removing the visual barriers more carefully and strictly.

One of the major concerns of big cities is the high volume of traffic, the use of public transport, more safety and a proven solution to this problem. For reasons that are addressed in this research, many people are interested in using motorcycles at city level. The purpose of this research is to investigate the causes of citizens' tendency to use motorcycles instead of using public transportation in Qom. By interviewing the experts, the variables that influenced the use of motorcycles were determined; variables include: economic factors, factors related to the quality of infrastructure, factors related to urban traffic, and the lack of culture for the use of public transport. In this research, a descriptive-survey method was used to investigate the hypotheses and answer the research questions. The statistical population of this study includes off-road motorcyclists whose motorcycles were seized in the past month; a sample size of 341 people was determined using Morgan's table. A researcher-made questionnaire was used to collect required data in this research. A confirmatory factor analysis test and then structural equation model were used for validity of the questionnaire. SPSS software was used to analyze the collected data and to investigate the hypotheses of the research. After analyzing the data, all four hypotheses were confirmed with 95% confidence. That is, variables of economic factors, factors related to the quality of infrastructure, factors related to urban traffic and the lack of culture of using public transportation affect the tendency of citizens to use motorcycles in Qom.

Eight accident points have been identified in District 2 of Greater Tehran Municipality, with numerous cases of accidents occurring in different forms at these eight points. There were 9 deaths, 225 fatalities and 1353 fatalities in 1986. The main purpose of this study was to evaluate the effect of geometric corrections performed on accident points on the accident rate and to what extent the corrected impacts on accident, death and injury accidents. The purpose of this study was to describe descriptive-documentary research based on the type of purpose of applied research and in terms of the method of work performed. For this purpose, the accident analysis points were analyzed and the evaluations carried out in the area 2 of Tehran. In order to investigate the effectiveness of accident corrections in the year 2017 and 2018, information and statistics from the Greater Tehran Road Police (COM Form 114) have been examined to identify the major features and trends of accidents (decreasing or incremental) in the corrected accident locations. It was estimate 97 compared to 96. As a result, we have seen a reduction in the number of fatal and surgical accidents, but no significant change in the number of injuries.

The Increasingly increasing traffic on the streets and highways has become one of the problems of small and large cities. Experts have resorted to electronic systems and equipment for traffic control to address this problem. The data collection is the basis of the formation of a transport system. Having the right traffic information is effective in designing and implementing smart transportation plans and can be programmed to solve traffic problems and improve the current structure. Vehicle detectors or detectors are part of intelligent transportation systems that detect the presence or passage of a vehicle. There are a number of identifiers across the country. The most important and most active  of them are the induction ring (loop), radar, image. Each of these identifiers has their own characteristics that can be evaluated and prioritized. The purpose of this study is to investigate the effectiveness of smart transportation system identifiers on traffic regulation.

This study was conducted to determine the effectiveness and its impact on traffic management using a structured qualitative method. The survey is conducted through interviews with skilled experts who work directly with them.

Eight basic questions were approved by professors and experts and were asked from experts and specialists who work directly with identifiers. Summing up the experts' opinions showed that all three indicators have a direct and 100% impact on traffic management and transportation regulation.

Regarding on the type of work and purpose of organizations of utilizing these identifiers, the most effective were respectively the image detector for video surveillance of passages, radar detector for speed control and the loop detector for counting vehicles and smart intersections

Due to the increasing number of personal vehicles in Mashhad and the problems that arise in this regard, a study has been conducted to investigate the factors affecting the efficiency of personal passenger car plans. Therefore, the main issue of this study is to investigate the factors affecting the efficiency of traffic planning in Mashhad with emphasis on the plan of dealing with personal passengers. The main purpose of this research is to identify and explain the effective factors of the plan of dealing with personal passengers in Mashhad. The research method of this research is applied, in terms of purpose, and in terms of quantitative methods of data collection, it is a descriptive-explanatory survey. As many as 321 individuals were selected and evaluated using a questionnaire developed by the researcher. The results of this study show how traffic regulations are implemented, timely and sufficient information, how police interact with personal passenger drivers, drivers' practical commitment to the plan and rules and regulations, and the role of effective and responsible agencies in the implementation of the plan. Dealing with personal travelers plays an important role in the effectiveness of the plan for dealing with personal travelers in Mashhad.

Ensemble of classifiers is one of the famous methods to increase accuracy of Classifiers. Bagging, boosting and Error Correcting Output Codes (ECOC) are some of common methods to ensemble of classifiers. In this paper a new method for ensemble of Classifiers based on double combination is proposed and accuracy of this method in compare with other existing methods is evaluated for different datasets. Numerical results indicated that this method increases classifying accuracy in many cases comparing with other existing methods.