مجله محاسبات و سامانه های توزیع شده
سال پنجم شماره 2 (پیاپی 10، پاییز و زمستان 1401)

In this study, a tunable laser source was designed and simulated using OptiSystem software, based on credible similar articles analysis, by using a laser pump and a Raman amplifier. The simulation results showed that tunable laser sources based on fiber Bragg gratings can be used for monitoring targeted devices up to a distance of 300 kilometers from the monitoring station. Moreover, by serially placing fiber Bragg gratings and using a multi-wavelength, the reflected signals were transmitted through a single-mode fiber for monitoring at the transmission station. In the conducted experiments, it was feasible to obtain a reasonable output power from fiber Bragg grating sensors using a 1-watt 980-nanometer laser source. Therefore, remote control and monitoring can be performed at far distances from the monitoring station. Consequently, the hypotheses of the study, including the design of tunable laser sources and their use in fiber Bragg grating sensors, the use of tunable laser sources in advanced long-range sensors, and the design and simulation of tunable laser sources based on various fiber Bragg gratings in advanced long-range sensors, were confirmed.

In the real world, all available data are not definitive and are considered based on quality. Based on the nature of the data, fuzzy linear programming has been proposed. Solving these types of issues is one of the important discussions. In this article, a method to obtain the optimal solution of fuzzy linear programming (FLP) problems with coefficients of triangular fuzzy numbers by using the properties of triangular fuzzy numbers is presented. Using the proposed method, it is easy to obtain the fuzzy optimal solution for the FLP problem according to the real world events. To check the advantages and application of the introduced method, a numerical example is given.

SDN architecture has become popular nowadays due to the abstract view that it provides. Due to the centralized network Controller in SDN, Most of the processing load is on the controller. This centralized controller has made this architecture a great target to DDoS attacks. Over the few past decades, many detection methods has been proposed; but with increased traffic and complexity of DDoS attacks, researchers aimed to utilize the data plane processing power. One of the most effective methods that has been proposed, is the P4 technology. With P4, we can utilize the processing power of the data plane devices in detection and prevention procedure of DDoS attacks on SDN; which will result the reduction of controller overhead and more flexibility data plane devices. In this research, we proposed a detection and prevention model that utilizes machine learning techniques along with implementation of P4 switches to detect slow-rate DDoS attacks on SDN. The ONOS controller has been used for implementation of this model. The goal of proposing this model, is to use programmable P4 switches in detection procedure, in order to minimize the controller overhead. The procedure of extracting feature values for machine learning models, will result processing overhead for the controller, but with implementing this procedure with P4 switches on data plane and local processing of packets in the switch, the controller overhead will be minimized. The proposed model has been analyzed in terms of detection time, bandwidth consumption and CPU utilization of the controller. In compare to the normal SDN, the results shows about 60 seconds improvement in detection time, about 50% less overhead on bandwidth consumption and CPU utilization in proposed method. The results show that implementation of P4 data plane, with programming the data plane devices, will have significant effects on detection of slow-rate DDoS attacks and processing load of the controller in SDN.

With the evolution of the Internet of Things, the exchange of information is accompanied by secure encryption. Due to the development of classical computers to quantum computers in the near future and the emergence of quantum attacks, the need to securely encrypt information and maintain security against it has increased. In this research, along with the introduction of lattices, the detailed and comprehensive encryption plan based on the NTRU lattice, the complete design of the encryption and decryption of which took years, and a complete presentation of the geometric drawing of the NTRU encryption, public and private key generation, and its decryption are made. In the following, network-based authentication and how to prove the security of encrypted information against quantum attacks and the speed of encryption and decryption of the plan compared to the similar introduced plans are concluded.

Intrusion detection is followed with special importance in computer systems research and is used to help system security managers to detect intrusion and attack. The importance of anomaly detection is due to the fact that anomalies in data are important information that can be used in a wide range of application areas. Intrusion detection methods are used in many application domains and each domain requires a different method. In this research, a method for improving intrusion detection in computer networks is presented using stream data based on neural network. OeSNN-UAD network is used to present the proposed method and it has input and output layers that produce a candidate output neuron for each new data. The input layer of this network contains GRF and input neurons, which GRFs are used to filter the input data. In the proposed method, the ELM algorithm is used to improve the learning process of the OeSNN-UAD network, and this algorithm has improved the communication between the two layers by being placed between the input and output layers in the OeSNN-UAD network.The simulation of the proposed method was done in MATLAB software. In the first experiment, the effect of ELM in the proposed method was investigated based on the criteria of accuracy, readability, F score, BA, MCC on data classification, and in the second experiment, the effect of the Wsize parameter on the final performance of the proposed method was investigated, and the optimal results It gave a good result.

The issue of customer knowledge management for organizations is important in terms of gaining more active participation of the customer in the realization or development of new products and services. Providing customized products and improving the quality of products and services is not possible without successful customer knowledge management. However, organizations face many problems in customer knowledge management, in this study, organizational, human and technological challenges of customer knowledge management are investigated. Then, the stages and obstacles to the development of customer knowledge management in organizations are discussed, and finally, the main process of customer knowledge management is described. The results of this study can be used by researchers and experts in this field to evaluate the common stages of customer knowledge management in any organization and the challenges that organizations may face when developing customer knowledge management, now and in the future.

Universities and educational institutions collect and store a huge amount of data, such as personal and educational information of students. The huge growth of electronic data in universities points to the fact that by using data analysis methods, it is possible to achieve desirable results in the fields of education and research. One of the main challenges of the educational environment is the success rate of students. There is the issue of what are the most important characteristics of students to predict their academic progress and which algorithm is more suitable for making this prediction, and if appropriate results are obtained in the analysis of academic progress, how can managers plan better based on it. In this article, all the possible characteristics of students in an educational institution, collection and some data mining algorithms as well as a proposed method have been implemented on the data and the results have been obtained, checked and compared with each other based on the criteria of Accuracy, Recall and Precision. The decision tree showed the lowest accuracy with 0.864 and the proposed method showed the highest accuracy with 0.935. Also, the most important features that are effective in the academic progress of students were identified. By using this prediction, managers can also remove the obstacles and provide the ground for the progress of students.

With the advancement of technology and the significant use of the Internet by individuals and groups, advertisements in this field have expanded explosively, so that all kinds of methods for mass distribution of these advertisements to Internet users in the form of e-mail have been encountered. And this causes problems for Internet users. One of these problems is the presence of spam emails which Spam email is one of the most common negative features suffering the owner of an email address. Although existing technologies cannot eliminate unwanted spams, some existing methods can reduce their number. By definition, spam is an electronic version of "useless mails." Spam refers to unwanted and unsolicited e-mails. Such e-mails are not necessarily directly related to the virus, meaning that messages sent from valid sources may also be included in this class. This study proposes a new method based on improving the multilayer perceptron artificial neural network using the shuffled frog leaping algorithm to realize this objective. The shuffled frog leaping algorithm is used to find the best features, and the artificial multilayer perceptron neural network is used to detect spam emails based on the best features. The simulation results prove that the shuffled frog leaping algorithm has significantly improved the multilayer perceptron artificial neural network compared to the artificial neural network based on the radial base function.

Due to the COVID-19 pandemic, there have been significant changes in different aspects of education around the world, including the testing process. Online testing carried out without any supervision replaced the traditional evaluation processes. However, their lack of validity as a result of the increased possibility of cheating among the students concerns educators about the results' authenticity. In such cases, providing additional processes to check the results is a necessary step to administer safer online tests. In this research, a process with high accuracy is proposed. This process is able to detect fraud based on data mining techniques. It consists of several steps, including the use of statistical methods, similarity criteria, student grades, K-nearest neighbor algorithms, artificial neural network, and support vector machine. In this process, scoring has been done for each stage of the operation, and the final statement to judge whether the cheating ever occurred or not will be based on the sum score of each stage. The process uses the results of the students' exam evaluation in order to identify abnormal scores in exams, and the recommender system is able to detect students' cheating with 99.98% accuracy. The results show that the proposed online test system has t