International Journal Information and Communication Technology Research
Volume:12 Issue: 4, Autumn 2020

One of the biggest amounts of energy consumption in the telecommunications industry is related to energy consumption in data centers, which cause high costs imposed on companies that are interested in having data centers, so without using appropriate methods for reducing energy consumption instead of environmental problems It will also create many cost for companies. Today, companies choose and operate a variety of methods to optimize energy consumption in their data centers. In this research, we have tried to use new methods in architecture called changes in building morphology to reduce energy consumption in office and building applications in the construction of data centers to beautify the facade of the building, the required energy consumption to reduce the brightness and cooling of the data center. In this study, the effect of morphology design on energy consumption and costs in data centers will be investigated. Also, based on the hypotheses, a conceptual model has been considered to better understand the subject. The analysis of statistical data of this research was done with SPSS 25 and LISREL 8.5 software.

Vehicular ad-hoc networks (VANETs), as a result of today's vehicles equipped with different wireless technology, have been attracting interest for their potential roles in many fields such as emergency, safety, and intelligent transport system. However, the development of a reliable routing protocol to route data packets between vehicles is still a challenging task due to the high mobility, lack of fixed infrastructure, and obstacles. One technique to tackle this challenge is using machine learning. In this paper, we have proposed a protocol applying  multi-agent reinforcement learning (MARL) as a technique that enables groups of reinforcement learning agents to solve system optimization problems online in dynamic, decentralized networks. Our protocol is based on a model-based reinforcement learning method which has a higher convergence speed compared to the model-free one. To form the needed model for MARL, we have developed a Fuzzy Logic (FL) system that evaluates the quality of links between neighbor nodes based on parameters such as velocity and connection quality. The performance of the proposed protocol is studied by extensive simulation with respect to various metrics such as delivery ratio, delay, and overhead. The results obtained show significant improvement of VANETs performance in terms of these metrics.

The objective of this study was to develop a technique for differentiation of two instantaneous audio signals recorded concurrently by two microphones. To achieve this objective, a signal was first subjected to Short Time Fourier Transform (STFT), then each frequency bin was processed individually by a two-phase technique consisting of an estimation of orthogonalization matrix and rotation matrix in that order. The proposed method introduces a new geometric approach to the separation of sparse signals. In fact, it introduces two new steps for the general BSS technique. In fact, these two steps are presented in this paper instead of the whitening and rotating steps in blind speech separation algorithms. This paper separates audio sources in difficult situations with significant improvements in algorithm performance. Therefore, the experiments were performed in difficult conditions, such as when the microphones are collinear, short distances of microphones and having short sources. Therefore, the experiments were performed in difficult conditions. Performance of the proposed method was evaluated by a number of numerical examples. The experiments were performed using the Roosim simulator, and the results showed that the proposed algorithm is a simple and useful solution for separating two speech signals recorded with two microphones.

In recent years, image retargeting (IR) problem has been discussed as one of the challenging topics in the field of image processing in different applied domains. In this paper, a multi operators hybrid method is proposed (IR-WCO2C) to improve performance of a IR system, which performed in three sub-systems. At first, the identification precision of important regions is enhanced using a feature extraction technique based on wavelet coefficients (WC) then identified the saliency map of images. In second sub-system, this saliency map is used to improve performance of seam carving process instead of the saliency map identified by conventional methods. Finally, the act of operator selection is improved using metaheuristic techniques to optimize the process of operators combination. Comparing the proposed method and conventional methods, it is observed that accuracy of IR-WCO2C method is higher than understudy methods in different stages of the IR process.

Today, different groups of people use social media in their businesses and normal daily activities specially for accessing news and their favorite information in various fields. Facing with huge amounts of information and news in social media makes different challenges for the users. One of the main challenges of the users is distinguishing valid news and information from invalid and fake ones. Fake news means low quality news containing inaccurate or invalid information. Because of the fast and widely spread of the news in social media, they may have very destructive effects on the user's social behavior. Therefore, the fake news should be identified and banned as soon as possible.  To overcome the challenge of identifying fake news, in this manuscript a method is introduced to use profile features of the users and some features of the tweets in twitter to determine the possibility of a tweet being fake. This method also uses ordered weighted averaging as a data fusion method to increase the accuracy of the detection. To determine the effectiveness of the presented method, some experiments are designed based on the known datasets from twitter. The evaluations of the results of these experiments indicate effectiveness of the proposed method.

 Most of the data on the web is in the form of natural language, but natural language is highly ambiguous, especially when it comes to the frequent occurrence of entities. The goal of entity linking is to find entity mentions and link them to their corresponding entities in an external knowledge base. Recently, FarsBase was introduced as the first Persian knowledge base with nearly 750,000 entities. This research suggested one of the first end-to-end unsupervised entity linking systems specifically for Persian, using context and graph-based features to rank candidate entities. To evaluate the proposed method, we used the first Persian entity-linking dataset created by crawling social media text from some popular Telegram channels. The ParsEL results show that the F-Score of the input data set is 87.1% and is comparable to any other entity-linking system that supports Persian.