نشریه فناوری اطلاعات و ارتباطات ایران
سال پانزدهم شماره 57 (پاییز و زمستان 1402)

Among the most commonly diagnosed cancers, melanoma is the second leading cause of cancer-related death. A growing number of people are becoming victims of melanoma. Melanoma is also the most malignant and rare form of skin cancer. Advanced cases of the disease may cause death due to the spread of the disease to internal organs. The National Cancer Institute reported that approximately 99,780 people were diagnosed with melanoma in 2022, and approximately 7,650 died. Therefore, this study aims to develop an optimization algorithm for predicting melanoma patients' survival.

This applied research was a descriptive-analytical and retrospective study. The study population included patients with melanoma cancer identified from the National Cancer Research Center at Shahid Beheshti University between 2008 and 2013, with a follow-up period of five years. An optimization model was selected for melanoma survival prognosis based on the evaluation metrics of data mining algorithms.

A neural network algorithm, a Naïve Bayes network, a Bayesian network, a combination of decision tree and Naïve Bayes network, logistic regression, J48, and ID3 were selected as the models used in the national database. Statistically, the studied neural network outperformed other selected algorithms in all evaluation metrics.

The results of the present study showed that the neural network with a value of 0.97 has optimal performance in terms of reliability. Therefore, the predictive model of melanoma survival showed a better performance both in terms of discrimination power and reliability. Therefore, this algorithm was proposed as a melanoma survival prediction model.

In recent years, with the advancement of automotive electronics and the development of modern vehicles with the help of embedded systems and portable equipment, in-vehicle networks such as the controller area network (CAN) have faced new security risks. Since the CAN bus lacks security systems such as authentication and encryption to deal with cyber-attacks, the need for an intrusion detection system to detect attacks on the CAN bus seem to be very necessary. In this paper, a deep adversarial neural network (DACNN) is proposed to detect various types of security intrusions in CAN buses. For this purpose, the DACNN method, which is an extension of the CNN method using adversarial learning, detects intrusion in three stages; In the first stage, CNN acts as a feature descriptor and the main features are extracted, and in the second stage, the discriminating classifier classifies these features and finally, the intrusion is detected using the adversarial learning. In order to show the efficiency of the proposed method, a real open source dataset was used in which the CAN network traffic on a real vehicle during message injection attacks is recorded on a real vehicle. The obtained results show that the proposed method performs better than other machine learning methods in terms of false negative rate and error rate, which is less than 0.1% for DoS and drive gear forgery attack and RPM forgery attack while this rate is less than 0.5% for fuzzy attack.

The purpose of this research is to present the framework of the national plan for transparency and information release. The research employs an integrated approach (qualitative and quantitative) and grounded theory as its research methodology. In the qualitative part، with an in-depth and exploratory review of upstream laws and documents، models، theories، plans، and white papers of different countries related to transparency and information release، data analysis was done until theoretical saturation through three stages of open، axial، and selective coding. To acquire the dimensions، components، and subcomponents of this framework، 129 concepts were extracted from 620 primary codes، which were reduced to 593 secondary codes by removing the duplicated elements. Finally، 24 subcategories were placed under the five main components based on the paradigm model. In the quantitative section، the results of the analysis of the questionnaire indicated that، from a validity standpoint، the total value of the questionnaire، in different dimensions، was between 0.87 and 0.92، and the reliability coefficient was between 0.73 and 0.78. Based on data analysis، the establishment of a supranational management institution for transparency and information release، the precise determination of exceptions، network governance، demanding transparency، adherence to frameworks، maximum disclosure and support for legitimate disclosure، and the establishment of a data governance center are among the subcategories emphasized in this framework.

The purpose of this research is to identify the drivers, obstacles and consequences of digital entrepreneurship in Iran's road freight transportation industry. The statistical society of this research in the qualitative part was made up of 20 experts in this field who were selected using theoretical saturation. In the quantitative part, using Cochran's formula and cluster sampling method, 170 employees of this industry were selected as samples. In order to collect data, a semi-structured interview was used in the qualitative part and a researcher-made questionnaire was used in the quantitative part, whose validity and reliability were checked and confirmed. In the data analysis, systematic literature review and coding and Maxqda software were used in the qualitative part, and inferential statistics and SPSS and Lisrel software were used in the quantitative part. Finally, 9 indicators in 4 driver factors, 11 indicators in 3 obstacle factors and 55 indicators in 8 consequence categories were extracted and prioritized using factor analysis. The result of this research shows that the political component is a priority as a driver and political obstacles are a priority as an obstacle. Therefore, the role of the government in this field is very important.

Application of cloud computing in different datacenters around the world has led to generation of more co2 gas. In addition, energy and throughput are the two most important issues in this field. This paper has presented an energy and throughput-aware algorithm for scheduling of compressed-instance workflows in things-internet by cluster processing in cloud. A method is presented for scheduling cloud workflows with aim of optimizing energy, throughput, and latency. In the proposed method, time and energy consumption has been improved in comparison to previous methods by creating distance parameters, clustering inputs, and considering real execution time. In WSTMOS method by considering special parameters and real execution time, we managed to reach the optimized objective function. Moreover, in the proposed method parameter of time distance of tasks to virtual machines for reduction of number of migration in virtual machines was applied. In WSTMOS method by organizing the workflow inputs to low, medium and heavy groups and also by distributing appropriate load on more suitable servers for processors threshold, we accomplished to optimize energy and cost. Energy consumption was reduced by 4.8 percent while the cost was cut down by 4.4 percent using this method in comparison to studied method. Finally, average delay time, power and workload are optimized in comparison to previous methods.

Recommender systems can predict future user requests and then generate a list of the user's favorite pages. In other words, recommender systems can obtain an accurate profile of users' behavior and predict the page that the user will choose in the next move, which can solve the problem of the cold start of the system and improve the quality of the search. In this research, a new method is presented in order to improve recommender systems in the field of the web, which uses the DBSCAN clustering algorithm to cluster data, and this algorithm obtained an efficiency score of 99%. Then, using the Page rank algorithm, the user's favorite pages are weighted. Then, using the SVM method, we categorize the data and give the user a combined recommender system to generate predictions, and finally, this recommender system will provide the user with a list of pages that may be of interest to the user. The evaluation of the results of the research indicated that the use of this proposed method can achieve a score of 95% in the recall section and a score of 99% in the accuracy section, which proves that this recommender system can reach more than 90%. It detects the user's intended pages correctly and solves the weaknesses of other previous systems to a large extent.

As technology develops, institutions and organizations provide many services electronically and intelligently over the Internet. The police, as an institution that provides services to people and other institutions, aims to make its services smarter. Various electronic and intelligent systems have been offered in this regard. Because these systems lack authentication, many services that can be provided online require a visit to +10 police stations. Budget and equipment limitations for face-to-face responses, limitations of the police force and their focus on essential issues, a lack of service offices in villages and a limited number of service offices in cities, and the growing demand for online services, especially in crisis situations like Corona disease, electronic authentication is becoming increasingly important. This article reviews electronic authentication and its necessity, liveness detection methods and face recognition which are two of the most important technologies in this area. In the following, we present an efficient method of face recognition using deep learning models for face matching, as well as an interactive liveness detection method based on Persian speech recognition. A final section of the paper presents the results of testing these models on relevant data from this field.

In most of the studies, the direct effects of the ICT sector have been discussed, but the indirect effects (spillover) and how to measure them have not been addressed. This issue is on the agenda of this article. For this purpose, while determining the territory of the digital economy, the gross value of the core of the country's digital economy has been estimated.

In this article, using the Solow growth model, the spillover effects of the core of the digital economy (ICT) have been estimated for the period of 2002-2019.

The results imply that in the period under review, according to the elasticity of labor productivity relative to the share of net capital formation of the ICT sector in the national economy (about 0.3), the spillover effects of the digital economy core have increased from 210 thousand billion Rials in 2015 to 279 thousand billion of Rials in 2019.

The retail market industry is one of the industries that affects the economies of countries, the life of which depends on the level of satisfaction and trust of customers to buy from these markets. In such a situation, the retail market industry is trying to provide conditions for customer feedback and interaction with retailers based on web pages and online platforms. Because the analysis of published opinions play a role not only in determining customer satisfaction but also in improving products. Therefore, in recent years, sentiment analysis techniques in order to analyze and summarize opinions, has been considered by researchers in various fields, especially the retail market industry.

As an emerging technological field, artificial intelligence has received increasing attention from companies and governments. The development of artificial intelligence both at business and country levels depends on knowing the current situation. This paper identifies the artifacts and producers presented in this field and maps them to transformational levels. Products/services and producers are achieved through capabilities provided by artificial intelligence. Then, based on the classification methodology and meta-characteristics, the transformational levels of the artifacts of Iran's artificial intelligence ecosystem have been extracted. 562 products/services were identified, which were offered by 112 companies. Machine vision and natural language processing have been at the top of the technologies used, with 44 and 27 percent of the products allocated to them, respectively. Artifacts and producers were classified into seven transformative levels: individual, organization, industry, electronic chip/hardware, society, platform, code/algorithm/library, and infrastructure. Iran's artificial intelligence productions have not grown in a balanced way. The three levels of platform, code/algorithm/library, and infrastructure as the main generator of other artificial intelligence products/services have had the lowest amount of production. It is suggested that a specialized marketplace for the supply of artificial intelligence application programming interfaces should be put on the agenda to stimulate the formation of the ecosystem.

The Arabic language has a very rich and complex morphology, which is very useful for the analysis of the Arabic language, especially in traditional Arabic texts such as historical and religious texts, and helps in understanding the meaning of the texts. In the morphological data set, the variety of labels and the number of data samples helps to evaluate the morphological methods, in this research, the morphological dataset that we present includes about 22, 3690 words from the book of Sharia alIslam, which have been labeled by experts, and this dataset is the largest in terms of volume and The variety of labels is superior to other data provided for Arabic morphological analysis. To evaluate the data, we applied the Farasa system to the texts and we report the annotation quality through four evaluation on the Farasa system.

Due to the increasing use of industrial Internet of Things (IIoT) systems, one of the most widely used security mechanisms is intrusion detection system (IDS) in the IIoT. In these systems, deep learning techniques are increasingly used to detect attacks, anomalies or intrusions. In deep learning, the most important challenge for training neural networks is determining the hyperparameters in these networks. To overcome this challenge, we have presented a hybrid approach to automate hyperparameter tuning in deep learning architecture by eliminating the human factor. In this article, an IDS in IIoT based on convolutional neural networks (CNN) and recurrent neural network based on short-term memory (LSTM) using metaheuristic algorithms of particle swarm optimization (PSO) and Whale (WOA) is used. This system uses a hybrid method based on neural networks and metaheuristic algorithms to improve neural network performance and increase detection rate and reduce neural network training time. In our method, considering the PSO-WOA algorithm, the hyperparameters of the neural network are determined automatically without the intervention of human agent. In this paper, UNSW-NB15 dataset is used for training and testing. In this research, the PSO-WOA algorithm has use optimized the hyperparameters of the neural network by limiting the search space, and the CNN-LSTM neural network has been trained with this the determined hyperparameters. The results of the implementation indicate that in addition to automating the determination of hyperparameters of the neural network, the detection rate of are method improve 98.5, which is a good improvement compared to other methods.

Nowadays, Cloud computing has many applications due to various services. On the other hand, due to rapid growth, resource constraints and final costs, Cloud computing faces with several challenges such as load balancing. The purpose of load balancing is management of the load distribution among the processing nodes in order to have the best usage of resources while having minimum response time for the users’ requests. Several methods for load balancing in Cloud computing have been proposed in the literature. The shuffled frog leaping algorithm for load balancing is a dynamic, evolutionary, and inspired by nature. This paper proposed a modified rapid shuffled frog leaping algorithm (R-SFLA) that converge the defective evolution of frogs rapidly. In order to evaluate the performance of R-SFLA, it is compared to Shuffled Frog Leaping Algorithm (SFLA) and Augmented Shuffled Frog Leaping Algorithm (ASFLA) by the overall execution cost, Makespan, response time, and degree of imbalance. The simulation is performed in CloudSim, and the results obtained from the experiments indicated that the proposed algorithm acts more efficient compared to other methods based on the above mentioned factors.

Variations in telecommunication channels is a challenge of the wireless communication which makes the channel estimation and equalization a noteworthy issue. In OFDM systems, some subcarriers can be considered as pilots for channel estimation. In the pilot-aided channel estimation procedure, interpolation is an essential step to achieve channel response in data subcarriers. Choosing the best interpolation method has been the subject of various researches, because there is no interpolator as the best method in all conditions, and their performance depends on the fading model, signal-to-noise ratio and pilot overhead ratio. In this paper, the effect of different interpolation methods on the quality of DVB-T2 broadcast links is evaluated. A simulation platform is prepared in which different channel models are defined according to the real-world measurements. The interpolation is performed by five widely-used methods (nearest neighbor, linear, cubic, spline, and Makima) for different pilot ratios. After channel equalization by the results of the interpolator, the bit error rate is calculated as the main criterion for evaluation and comparison. The rules of selecting the appropriate interpolator in different conditions is presented. It is generally concluded that for fading scenarios close to flat fading or high pilot overhead ratio, the simple interpolators such as linear interpolator are proper choices. But in harsh conditions, i.e. severe frequency-selective fading channels or low pilot overhead ratio, the more complicated interpolators such as cubic and spline methods yield better results. The amount of improvements and differences are quantified in this study.

Today, e-commerce is rapidly expanding as a way of doing business in the modern world due to its advantages and benefits. The purpose of this study is to extract dimensions and criteria for providing electronic trust arrangements in B2C services, improving the internal processes of the business environment, and also determining the importance and priority of each criterion to ensure electronic trust in order to gain the trust and satisfaction of the customer. A mixed method of research is employed includes: litrature review, field study and opinion gathering alongside of statistical techniques. The statistical population includes all expert customers of online stores in the city of Tehran, among which random sampling has been done. Questions in the context of the electronic trust and provision of e-business services and their priority in relation to each other, are discussed through inferential statistics. The results of the data analysis show that there is a meaningful relationship between the 12 criteria identified and customer's trust. The results obtained in the context of the conceptual framework show the impact of three dimensions of psychological, technical and legal, according to the criteria and indicators of electronic trust

In this paper, a model based on meta-heuristic algorithms for optimal allocation of IoT resources based on fog calculations is proposed. In the proposed model, the user request is first given to the system as a workflow; For each request, the resource requirements (processing power, storage memory, and bandwidth) are first extracted. This component determines the requested traffic status of the application in terms of real-time. If the application is not real-time and is somewhat resistant to latency, the request will be referred to the cloud environment, but if the application needs to respond promptly and is sensitive to latency, it will be dealt with as a fog calculation. It will be written to one of the Cloudletes. In this step, in order to select the best solution in allocating resources to serve the users of the IoT environment, the ant milk optimization algorithm was used. The proposed method is simulated in MATLAB software environment and to evaluate its performance, five indicators of fog cells energy consumption, response time, fog cell imbalance, latency and bandwidth have been used. The results show that the proposed method reduces the energy consumption, latency rate in fog cells, bandwidth consumption rate, load balance rate and response time compared to the base design (ROUTER) 22, 18, 12, 22 and 47, respectively. Percentage has improved.

Generally, in performing technical projects, especially in the field of information and communication technology, the most important criterion for handing over the project is having technical capabilities, and less attention is paid to the communication skills of project managers, such as having emotional intelligence. Lack of attention to this issue seems to reduce the effectiveness of team communication and thus lead to project failure. The aim of this study was to measure the effect of emotional intelligence of project managers on the effectiveness of team communication in the projects of the Institute of Communication and Information Technology. The method of the present research is descriptive-analytical of correlation type, the statistical population of which consists of project managers and members of the project teams of the Research Institute of Communication and Information Technology. The statistical population includes 19 project teams that have been selected by census method. Data collection tools are Bar-On Emotional Intelligence Questionnaire and Senior Questionnaire to evaluate the effectiveness of project team communication. Pearson correlation coefficient, multivariate regression and imaginary variable regression and dependent t-test were used to analyze the data. The results show that the emotional intelligence of project managers affects effective communication in the project team. However, only interpersonal skills, interpersonal skills, and adaptability can predict effective communication within the project team, and the dimensions of general mood and stress management do not affect these relationships

The cellular base stations are communication devices that ensure the connection in the world. Nevertheless, they are usually installed in remote places. This paper, studied the energy procurement of a cellular base stations in an independent microgrid with a hydrogen-based energy storage system, photovoltaic (PV) system, electric vehicles and a diesel generator. A new mixed-integer nonlinear programming model was used to deal with nonlinearities of the system components. The paper studied different uncertainties, such as the connection rate in cellular base stations, the driver of the electric vehicle, and PV generation, using stochastic programming method. The potency of the proposed method was studied in different case studies. The results prove that smart electric vehicle chargers reduce the risks and also cost/emission objective functions. The usage of this model can reduce the emissions as much as 18.60%.