دانشنامه تحول دیجیتال
سال دوم شماره 4 (پیاپی 5، زمستان 1400)

The Internet of Vehicles (IoV) is an emerging concept in Intelligent Transportation Systems (ITS) that aims to improve pedestrian and driver safety and traffic monitoring, But the IoV is vulnerable to various attacks. Therefore, security in the IoV is a serious issue because it directly affects the lives of the users. One of the most important attacks in the IoV is the Denial of Service (DoS) attack, which prevents access to the services of IoV and most importantly causes traffic and road accidents and the safety of users. endangers Therefore, a solution based on deep learning is proposed to detect DoS attacks in the IoV. The proposed model consists of a 10-layer convolutional neural network that can effectively detect different types of denial of service attacks. The performance of the proposed model is evaluated with real and new VDoS-LRS dataset. Experimental results show that the proposed intrusion detection system has reached a 100% accuracy rate.

The aim of the research is to determine the effect of the e-learning system on high-level thinking skills and self-regulated learning skills of students with the mediating role of interest in learning. The present research is applied in terms of purpose and descriptive-correlational in terms of method. The total number of the statistical population of the research included 1755 skilled, technical and professional students (girls and boys) of the second secondary school in Mahmoud Abad city, who were randomly selected based on the Morgan table of 315 people. Research tools include questionnaires related to electronic education system from Userlen (2010), interest in learning questionnaire, taken from the research of Betacherji (2001) and Mathieson (1991) and Ruka et al. (2006), high-level thinking skill questionnaire from Abdi et al. (2013) and the self-regulation learning skill questionnaire from Bouffard et al. (1995) that the validity (face and content) and reliability of the questionnaires indicated the appropriate validity and reliability of the measurement tool. To analyze the data, structural equation test and factor analysis were used using spss_26 and pls_3 software. The results of the research confirmed the effect of the electronic education system on high-level thinking skills and self-regulated learning skills with a mediating role of interest in learning among male and female technical and vocational second secondary students in Mahmoud Abad city.

The purpose of this study is to Investigating the factors affecting the digital entrepreneurial marketing ecosystem in the insurance industry (Case study: Tehran Province Insurance Company). In this regard, while reviewing the concepts of digital entrepreneurial marketing ecosystem and online insurance sales using structural equation modeling method, the model of digital entrepreneurial marketing ecosystem was presented. The statistical population of this study includes employees and customers of Tehran Insurance Company, whose number is unlimited and the sample size has been calculated using Morgan table equal to 384 people. A questionnaire was used to collect data in this study. Its validity was confirmed as content validity by experts and structure validity was confirmed by confirmatory factor analysis in SPSS and Smart-PLS2 software and its reliability was confirmed using Cronbach's alpha coefficient. Has been. In order to analyze the data in this study, Kolmogorov-Smirnov test was used to test the normality and the path analysis test was used to confirm the hypotheses. The results showed that market-oriented, innovation-oriented, entrepreneurship-oriented and customer-centric components are effective components in the digital entrepreneurial marketing ecosystem for online insurance sales.

The current research was conducted with the aim of heatmap technology applications in the field of online business and the relationship between the use of this technology and the performance of online businesses. Also, the current research has been analyzed using mixed research methodology (qualitative-quantitative). In the first stage, to investigate the applications of heatmap technology in the field of business, interviews were conducted with 10 experts and senior managers in the field of online technologies. country, and using the qualitative content analysis method, a questionnaire was designed, which is the basis of quantitative research. The statistical population related to the quantitative study was 300 managers and owners of online businesses, which was determined using the appropriate sample size method for modeling structural equations. The sampling method in the implementation of the quantitative study was simple random sampling. Data analysis was done using structural equation modeling method by Lisrel software. The results indicate the relationship between the applications of heat map technology, including the recognition of customer behavior patterns, increasing website visits, and improving the overall performance of online businesses in the three concepts of effectiveness, profitability, and customer satisfaction. Based on the findings of the present research, it can be said that the use of heatmap technology in tracking website performance improves the overall performance of online businesses.

This article is an investigation of some problems of modeling, expression of characteristics and analysis of Complex Dynamic Systems (CDS) using Fuzzy Cognitive Maps (FCM). Efficient analysis and control of CDS is impossible without a formal model of the system. The key problem of CDS and control theory is to develop methods to qualitatively analyze the dynamics and behavior of such systems and to construct efficient control algorithms for their efficient operation. Most qualitative description of the parameters of complex dynamic systems inevitably leads to ambiguity, complexity and uncertainty. Reasons for using Fuzzy Cognitive Maps (FCM) in CDS modeling are presented. FCMs provide an opportunity to generate new knowledge based on system applications and address the need to address the uncertainties, ambiguities, and inaccuracies associated with real CDS problems. In this study, the basic principles of FCM are briefly presented and then the NHL algorithm for training the FCM model and adjusting these weights. With fuzzy expressions and converting qualitative data into quantitative, a presentation and an example about the factors affecting the phenomenon of divorce were presented. The example results are promising, further development of CDS modeling and control using soft computing methods.

Diabetes is a group of metabolic disorders that are the result of untreated high blood glucose greatly. Early diagnosis and continued control of this disease can reduce its effectsTherefore, providing a method for timely diagnosis of this disease is of great importance. Until now, researchers have made many efforts to provide machine learning methods to diagnose diabetes. But most of these models are either based on simple machine learning methods or based on the assumption that the available diabetes data are balanced. Both cases are factors of their complete failure. Therefore, considering the existing challenges as well as the importance of timely diagnosis of diabetes, in this research, a diabetes diagnosis model based on deep recurrent neural networks and SMOTE oversampling algorithm is presented. In this model, several pre-processing steps including quantification of missing values, removal of outlier data and then oversampling have been performed. Three deep recurrent neural networks with three recurrent hidden units including LSTM, GRU and BiLSTM have been used to diagnose diabetes. The results of the model presented on the Pima database received from the UCI repository indicate that the average accuracy in 10 different runs in LSTM, GRU and BiLSTM is 91.21%, 89.61% and 90.99%, respectively. The recurrent network with GRU unit has achieved the highest accuracy of 93.74% on average in 10 different executions. The results of the proposed model show that deep neural networks have a much more successful performance in diabetes diagnosis compared to traditional machine learning methods.