Majlesi Journal of Multimedia Processing
Volume:6 Issue: 1, Mar 2017

Plagiarism, a scientific misbehavior, has turned into a serious problem for researchers and publishers due to increasing and easy access to web-based scientific resources. Plagiarism includes using the scientific content of other documents without referencing the sources and is performed as copy the content directly or copy and change it. Most of the research in different fields are performed well in dealing with direct plagiarism, however, indirect plagiarism is often challenging for them. It is beneficial to study the preceding researches and find their strengths and weaknesses in order to find new ideas for future works. The present paper studies some of the plagiarism methods and a number of researches conducted in the area so far.

The mortality from coronary heart disease is much higher than those from natural events. The World Health Organization (WHO) estimates that around 17 million deaths are due to heart and artery attacks. It should be noted that coronary heart disease is one of the main causes of mortality in advanced and developed countries such as Iran. Several methods have been proposed for the estimation and recognition of the risk of heart attacks, each of which has several advantages and disadvantages. Some disadvantages are as follows: low accuracy in the diagnosis of risk factors for coronary artery disease, time costs for selecting appropriate features, large number of diagnostic parameters, and the possibility of error. In this paper, we evaluate some of these methods and their advantages and disadvantages. The main scope is to review the methods and their advantages and disadvantages.

To recognize the societies in complex networks, Iso Fdp algorithm has used the combination of IsoMap algorithm so as to reduce the linear dimensions and clustering algorithm based on FDP density. One of the problems of this method is selecting the clusters’ centers or societies using the decision graph. The reason is that it would face problems in overlapped societies. Hence, the current study has investigated a method to overcome the problem. To this end, non-parametric clustering algorithm of Meanshift was used for clustering. Unlike the FDP algorithm, the suggested algorithm does not need to determine the cluster`s centers. Moreover, this algorithm has tried to solve the problem of cluster overlapping and membership problem of nods in each cluster through defining the vector of nods membership degree. Additionally, it has tried to choose the maximum difference to determine the clusters` centers and different weighing to their neighbors through defining different kernel functions. In this research for investigating the suggested method and the previous methods, 5 graphs of real networks of Football, Dolphins, Les Miserable and artificial ones like LFR and GN were used. In addition, for evaluating the results, NMI and Modularity criteria were used. The results of experiments using the above criteria on real and artificial networks indicated that the suggested method of recognizing the societies in comparison to the previous methods had remarkably improved.

In the modern world a huge amount of data is being produced every second and a considerable percentage of them are images that need to be processed and analyzed. One of the critical challenges in this aspect is image recovery. The process of image recovery should be done automatically by the machines which is the process of recognition of images concepts and assigning homological labels to them. In order to discover the hidden concepts in the images, one should achieve high level concepts using the low-level features, which is a difficult task. A variety of techniques are proposed to solve this problem that usually use combination of different algorithms. In this paper we review and compare various popular and modern image annotation techniques.

Road accidents in Iran account for a large volume of injuries and mortality, which have a lot of financial losses for society. Therefore, recognizing driver's sleepiness can have a great effect in reducing these injuries. One of the ways to detect fatigue and distraction is the use of surveillance systems from the driver's face. In this paper, a driver's face monitoring system is designed to estimate the driver's consciousness by extracting signs of tiredness and distraction from the eye area. These characteristics are then processed by the KNN algorithm and the RBF network in order to estimate the amount of distraction of the driver's senses. The results of the experiments on the images in the actual environment show that the proposed method has a very good accuracy. In terms of implementing the algorithm, the accuracy of the proposed system is 95.7%.