نشریه سیستم های پردازشی و ارتباطی چند رسانه ای هوشمند
سال دوم شماره 1 (پیاپی 3، بهار 1400)

Social networks are exposed to a variety of security problems due to their wide use and popularity. Therefore, identifying unusual activities in social networks is of paramount importance as it helps to obtain significant information about the behavior of unusual users and identify them. One of the important aspects of social network analysis is to check the presence of anomalies. Anomalies in the field of social networks imply irregular and often illegal behavior. A host of methods have been proposed to detect different kinds of anomalies in social networks. According to the employed approach, these methods can be classified into three categories, namely, clustering-based, based on network structure-based, and signal processing-based. In this paper, we extend the graph structure-based approach by introducing and analyzing important graph metrics to detect abnormal activities. Theoretical and experimental evaluation using several large data sets demonstrate that the relationship between the interface node and the number of edges helps to correctly detect and rank the maximum number of anomalies.

The proposed method is a combination of graphical and statistical theory. First, various metrics and graph structures are calculated, and then statistical methods are used to identify and analyze unusual structures (stars and clusters).

Statistical and visual analysis shows that the area covered by the curve is maximum for the interface (B) compared to the number of edges (E). The results show that the proxy is a scale that can correctly detect many abnormalities. It can also be said that the relationship between the (B) and the (E) helps to predict most anomalies.

In this research, a structure-based method was presented by using graph criteria to predict abnormalities. The curve fitting method based on the graph structure was extended to detect anomalies using the combination of new graph criteria. It was observed that the relationship between the interface and the edges helped to predict a large number of anomalies that were either misclassified or missed by the Oddball method and the ABC relationship to E. The abnormality scores assigned to the nodes help predict the degree of anomalies and rank the nodes according to their irrational behavior.

Today, the dramatic growth of infertility in different societies and the need to investigate each of the factors resulting from the inability of men and women to create and exacerbate, is not hidden from anyone. Meanwhile, WHO statistics show a rapid increase in male fertility factors to about 50 percent; Which indicates the high importance of morphological analysis of sperm, as one of the most important and fundamental steps in semen analysis, to perform artificial insemination. In this article, an attempt has been made to extract the characteristics of different parts of sperm (such as head, vacuole and acrosome) using a semi-supervisory learning method called ladder network, and then, by classifying them into two groups of normal and abnormal sperms, we will succeed in selecting the appropriate sperm in order to participate in the process of artificial insemination. The present study by applying changes and improving various factors, especially input noise, has obtained good results in the analysis of low-resolution images without coloring. The study of the proposed model for all three sperm sections (head, vacuole and acrosome) succeeded, despite low quality images, achieving impressive results of more than 70% for the head and acrosome and more than 80% for the vacuole.

Knowledge extraction is one of the most significant problems of data mining. The principles raised in if-then format can be turned into real numbers in each section- as values which could be included in dataset. The suggested method in the present dissertation is application of decision tree algorithms, clustering and forum rules for extraction of final rules. In the suggested method, extraction of rules is defined as an optimization problem and objective was obtaining a rule of high confidence, generalization and understandability. The suggested algorithm for extraction of rules was obtained from and tested based on a dataset of educational failure of 256 art school students living in Zanjan. The results suggested that the j48 algorithm in decision tree and accuracy of 0.95 is the choice for the dataset of educational failure. Data clustering was done by K-Main algorithm with confidence coefficient of 0.95. After all, obtaining rules of high confidence coefficient was done based on forum rules from Apriori algorithm for the whole datasets. The results of present study could be used for inhibition of educational failure of students, improved quality of relationship of parents and authorities with students and enhancing the education they receive.

Obsessive-Compulsive Disorder (OCD) is a chronic mental and social disease that is prevalent in about 2 to 3% of the human population leading to cognitive impairments and affected quality of patient's life. Therefore, a reliable and timely diagnosis can help psychiatrists in better treating or controlling this disease. Previous studies have demonstrated interdependence impairments between different brain regions in patients with OCD. Hence, this study has provided a new approach based on the decomposition of signals into intrinsic components and extraction of differential transient changes in amplitude envelope and phase spectra of the EEG signal recorded during Flanker tasks. The proposed algorithm has been evaluated using 19 healthy subjects and 11 patients by the Support Vector Machine (SVM) classifier. The obtained results have confirmed the capability of the proposed method in diagnosing the disease with high accuracy of 93.89% using amplitude differential information of the electroencephalogram signal. In comparison between different regions, the statistical features extracted from the frontal lobe, the frontal-parietal network, and the inter-hemispheric features have offered better detection ability.

In this research, a numerical method based on Jacobi polynomials is introduced for solving nonlinear fractional pantograph differential equations with boundary conditions. First, the differential equation is presented as an equivalent Volterra-Fredholm integral equation. Then, Jacobi polynomials and Gauss-Jacobi quadrature formula together with the Newton-Cotes collocation points are used in order to transform the obtained integral equation into a system of nonlinear algebraic equations. Finally, by considering some examples and computing the L^"2" and L^∞ errors, the efficiency and accuracy of the proposed method are shown.- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

Essentially resource sharing and dynamic workloads in recent e-learning systems causes resource contention between users and performance loss in these systems. Existence of these efficiency fluctuations and loss of service quality in such environments threatens the performance of applications and proper implementation of related services and the provision of the integrated functions. Performance awareness as a key solution is able to protect workloads from the negative impacts. The lack of such infrastructure is currently causing the performance fluctuations and poor service quality in such systems. The purpose of the present study is to take steps to compensate such deficiencies and the most important achievements is to develop a performance-aware cloud infrastructure for e-learning systems. The proposed cloud infrastructure is not dependent on specific execution mechanism and contrary to existing viewpoints, is independent from the service level and actors, supervises the performance across the whole cloud computing stack, dynamically. The results of implementation and evaluation of different implementation scenarios illustrate the superiority of the proposed infrastructure and the improvement in related performance criteria.