گراف

Open Access Article

1 - Document Clustering Based On Ontology and Fuzzy Approach
Maryam Amiri hasan khatan Lo

Data mining, also known as knowledge discovery in database, is the process to discover unknown knowledge from a large amount of data. Text mining is to apply data mining techniques to extract knowledge from unstructured text. Text clustering is one of important techniqu More

Data mining, also known as knowledge discovery in database, is the process to discover unknown knowledge from a large amount of data. Text mining is to apply data mining techniques to extract knowledge from unstructured text. Text clustering is one of important techniques of text mining, which is the unsupervised classification of similar documents into different groups. The most important steps in document clustering are how documents are represented and the measurement of similarities between them. By giving a new ontological representation and a similarity measure, this research focuses on improving the performance of text clustering. The text clustering algorithm has been investigated in three aspects: ontological representation of documents, documents similarity measure, fuzzy inference system to measuring the final similarities. Ultimately, the clustering is carried out by bottom-up hierarchical clustering. In the first step, documents are represented as ontological graph according to domain knowledge. In contrast to keywords method, this method is based on domain concepts and represents a document as subgraph of domain ontology. The extracted concepts of document are the graph nodes. Weight is measured for each node in terms of concept frequency. The relation between documents’ concepts specifies the graph edges and the scope of the concepts’ relation determines the edge’s weight. In the second step, a new similarity measure has been presented proportional to the ontological representation. For each document, main and detailed concepts and main edges are determined. The similarity of each couple of documents is computed in three amounts and according to these three factors. In the third step, the fuzzy inference system with three inputs and one output has been designed. Inputs are the similarities of main concepts, detailed concepts and the main edges of two documents and the output is final similarities of the two documents. In final step, a bottom-up hierarchical clustering algorithm is used to clustering the documents according to final similarity matrix. In order to evaluate, the offered method has been compared with the results of Naïve Bayes method and ontology based algorithms. The results indicate that the proposed method improves the precision, recall, F-measure and accuracy and produces more meaningful results. Manuscript profile

Open Access Article

2 - طراحی سیستم گراف‌کاوی برای شناسایی مشتریان وفادار
Roya Nasiri

Manuscript profile

Open Access Article

3 - تعبیه ی هندسی درخت درنقاط داخل یک چندضلعی با حداقل تعداد خم
Hooman Tahayori

In this paper we consider to embed a tree T with N vertices on a set of N points inside a simple polygon on n vertices and the goal is to minimize the number of bends. The main idea of our algorithm is modeling the problem into graph matching problem and uses the graph More

In this paper we consider to embed a tree T with N vertices on a set of N points inside a simple polygon on n vertices and the goal is to minimize the number of bends. The main idea of our algorithm is modeling the problem into graph matching problem and uses the graph matching algorithms. We apply the concept of error-correction transformation and find the appropriate cost function then we perform the graph matching with the minimum cost for minimizing the number of bends. The time complexity of the proposed algorithm is found to be O (N2n+N4). Manuscript profile

Open Access Article

4 - Investigating the Effects of Hardware Parameters on Power Consumptions in SPMV Algorithms on Graphics Processing Units (GPUs)
Farshad Khunjush

Although Sparse matrix-vector multiplication (SPMVs) algorithms are simple, they include important parts of Linear Algebra algorithms in Mathematics and Physics areas. As these algorithms can be run in parallel, Graphics Processing Units (GPUs) has been considered as on More

Although Sparse matrix-vector multiplication (SPMVs) algorithms are simple, they include important parts of Linear Algebra algorithms in Mathematics and Physics areas. As these algorithms can be run in parallel, Graphics Processing Units (GPUs) has been considered as one of the best candidates to run these algorithms. In the recent years, power consumption has been considered as one of the metrics that should be taken into consideration in addition to performance. In spite of this importance, to the best of our knowledge, studies on power consumptions in SPMVs algorithms on GPUs are scarce. In this paper, we investigate the effects of hardware parameters on power consumptions in SPMV algorithms on GPUs. For this, we leverage the possibility of setting the GPU’s parameters to investigate the effects of these parameters on power consumptions. These configurations have been applied to different formats of Sparse Matrices, and the best parameters are selected for having the best performance per power metric. Therefore, as the results of this study the settings can be applied in running different Linear Algebra algorithms on GPUs to obtain the best performance per power. Manuscript profile

Open Access Article

5 - Geometric embedding of the tree in points inside a polygon with minimum number of bends
akram sepehri alireza bagheri

In this article, we intend to embed a tree with N nodes on N points inside a polygon with n vertices. This embedding should be in such a way that the number of bends in the resulting tree is minimized. The main idea of the new algorithm is to model the problem as a gr More

In this article, we intend to embed a tree with N nodes on N points inside a polygon with n vertices. This embedding should be in such a way that the number of bends in the resulting tree is minimized. The main idea of the new algorithm is to model the problem as a graph matching problem and use algorithms It is graph matching that leads to the examination of the link distance problem and the path with the minimum number of links, then by using the concept of error correction and finding a suitable cost function and using the graph analysis method, graph matching is done. We do it with minimal cost to minimize the number of bends and the algorithm has a computational complexity of O(N2n+N4). Manuscript profile

Open Access Article

6 - Investigating the Effect of Hardware Parameters Adjustments on Energy Consumption in Thin Matrix Multiplication Algorithm on GPUs
mina ashouri Farshad Khunjush

Multiplication of thin algorithmic matrices is a simple but very important part of linear and scientific algebra programs in mathematics and physics, and due to its parallel nature, GPUs are one of the most suitable and important options. To select its executive platfor More

Multiplication of thin algorithmic matrices is a simple but very important part of linear and scientific algebra programs in mathematics and physics, and due to its parallel nature, GPUs are one of the most suitable and important options. To select its executive platform. In recent years, due to the emphasis of researchers to consider energy consumption as one of the main design goals along with efficiency, very little effort has been made to improve the energy consumption of this algorithm on the GPU. In this article, this issue is addressed from the perspective of energy efficiency in efficiency obtained. Utilizing the configuration capability introduced in modern GPUs, by statistically examining the behavior of this algorithm when using different thin matrix storage formats and different hardware settings for more than 200 matrices Slim example, the best configuration settings for the thin matrix multiplication algorithm with different storage formats on the GPU are obtained. This configuration for each storage format is selected to give the best configuration in all samples tested. Manuscript profile

Open Access Article

7 - دندانهای کشیده شده: دور ریختنی یا اتو گرافت فوری استخوانی؟
Azin Tavakoli

Extracted teeth are always considered as waste or debris. Tooth extraction is the most performed procedure in dentistry following cleaning and prophylaxis in small animals. The first indication of tooth extraction is advanced periodontal disease which the teeth attachme More

Extracted teeth are always considered as waste or debris. Tooth extraction is the most performed procedure in dentistry following cleaning and prophylaxis in small animals. The first indication of tooth extraction is advanced periodontal disease which the teeth attachments loss occurs and the teeth could not be saved. Other indications include jaw and teeth fracture. In sever and refractory stomatitis, one of the recommended treatment is extraction of either rostral or even all teeth. Therefore, lots of extracted teeth as tissue similar to bone is available. In this article the role of extracted teeth in bone defects as readily available bone graft and regarded existed studies in literature will be reviewed. Manuscript profile

Open Access Article

8 - The aware genetic algorithm of the best member, applied to graph coloring and metric-dimension of the graph problems
mahmood amintoosi Hashem Ezzati

Genetic algorithm is one of the most famous methods for solving Combinatorial Optimization Problems. It had various applications in different field of studies such as Electronics, Computer Science and Mathematics and still has. In this algorithm, the population members More

Genetic algorithm is one of the most famous methods for solving Combinatorial Optimization Problems. It had various applications in different field of studies such as Electronics, Computer Science and Mathematics and still has. In this algorithm, the population members which contribute for producing the next generation are selected according to their fitness values. The combination of the members is through Crossover Operator; And in some versions a few of the best members migrate to the next generation directly. Normally, the weak members of population may participate to the next generation. In this study, the combination operators are aware of the best member of generation; Only those child which are as good as the best member, are allowed to form the next generation. The proposed method is applied on graph coloring and finding metric-dimension of graph problems. The results are compared with the common genetic algorithm. Experimental results shows the superior performance of the proposed method in comparison to common genetic algorithm. Manuscript profile

Open Access Article

9 - Improving Efficiency of Finding Frequent Subgraphs in Graph Stream Using gMatrix Summarization
masoud kazemi Seyed Hossein Khasteh hamidreza rokhsati

In many real-world frameworks, dealing with huge domains of nodes and online streaming edges are unavoidable. Transportation systems, IP networks and developed social medias are quintessential examples of such scenarios. One of the most important open problems while dea More

In many real-world frameworks, dealing with huge domains of nodes and online streaming edges are unavoidable. Transportation systems, IP networks and developed social medias are quintessential examples of such scenarios. One of the most important open problems while dealing with massive graph streams are finding frequent sub-graph. There are some approaches such as count-min for storing the frequent nodes, however performing these methods will result in inaccurate modelling of structures based on the main graph. Having said that, gMatrix is one of the recently developed approaches which can fairly save the important properties of the main graph. In this approach, different hash functions are utilized to store the basis of streams in the main graph. As a result, having the reverse of the hash functions will be extremely useful in calculation of the frequent subgraph. Though gMatrix mainly suffer from two problems. First, they are not really accurate due to high compression rate of the main graph and second, the complexity of returning a query is high. In this thesis, we have presented a new approach based on gMatrix which can reduce the amount of memory usage as well as returning the queries in less amount of time. The main contribution of the introduced approach is to reduce the dependency among the hash functions. This will result in less conflicts while creating the gMatrix later. In this study we have used Cosine Similarity in order to estimate the amount of dependency and similarity among hash functions. Our experimental results prove the higher performance in terms of algorithm and time complexity. Manuscript profile

Open Access Article

10 - Use of conditional generative adversarial network to produce synthetic data with the aim of improving the classification of users who publish fake news
arefeh esmaili Saeed Farzi

For many years, fake news and messages have been spread in human societies, and today, with the spread of social networks among the people, the possibility of spreading false information has increased more than before. Therefore, detecting fake news and messages has bec More

For many years, fake news and messages have been spread in human societies, and today, with the spread of social networks among the people, the possibility of spreading false information has increased more than before. Therefore, detecting fake news and messages has become a prominent issue in the research community. It is also important to detect the users who generate this false information and publish it on the network. This paper detects users who publish incorrect information on the Twitter social network in Persian. In this regard, a system has been established based on combining context-user and context-network features with the help of a conditional generative adversarial network (CGAN) for balancing the data set. The system also detects users who publish fake news by modeling the twitter social network into a graph of user interactions and embedding a node to feature vector by Node2vec. Also, by conducting several tests, the proposed system has improved evaluation metrics up to 11%, 13%, 12%, and 12% in precision, recall, F-measure and accuracy respectively, compared to its competitors and has been able to create about 99% precision, in detecting users who publish fake news. Manuscript profile

Open Access Article

11 - A Neighbor-based Link Prediction Method for Bipartite Networks
Golshan Sondossi alireza saebi S. Alireza hashemi G.

Social network analysis’ link prediction has a diverse range of applications in different areas of science. Bipartite networks are a kind of complex network, which can be used to describe various real-world phenomena. In this article, a link prediction method for bipart More

Social network analysis’ link prediction has a diverse range of applications in different areas of science. Bipartite networks are a kind of complex network, which can be used to describe various real-world phenomena. In this article, a link prediction method for bipartite network is presented. Uni-partite link prediction methods are not effective and efficient enough to be applied to bipartite networks. Thus, to solve this problem, distinct methods specifically designed for bipartite networks are required. The proposed method is neighbor based and consisted of measures of such. Classic uni-partite link prediction measures are redefined to be compatible with bipartite network. Subsequently, these modified measures are used as the basis of the presented method, which in addition to simplicity, has high performance rates and is superior to other neighbor-based methods by 15% in average. Manuscript profile

Open Access Article

12 - The model of the network of technology development in Web 5 based on the principles of soft technology development
Sasan Azimi

10.52547/jstpi.20983.17.68.42

A couple of technologies are growing extraordinarily and pervasive much faster and more widely than usual. Investigate their trend of development shows that their growth path is not only linear, but these technologies, years after their invention and birth, have a littl More

A couple of technologies are growing extraordinarily and pervasive much faster and more widely than usual. Investigate their trend of development shows that their growth path is not only linear, but these technologies, years after their invention and birth, have a little story and limited success, but suddenly jump and advance on a global scale. Examining the main reasons and bases of this growth shows that there are general rules in development while applying in the case of technology, lead to rapid development. This paper briefly discusses such technologies. The generations Web as a comprehensive and close case to the subject of this article - the network of technology development - are discussed. Understanding the pillar foundations of this launchpad and modeling it for the technology development network, provides the infrastructure for systematic acceleration in technology development. In this paper, the definition of each of these basic concepts is presented in accordance with the technology development network, and the implementation manner is mentioned. Manuscript profile

Open Access Article

13 - User recommendation in Telegram messenger by graph analysis and mathematical modeling of users' behavior
Davod Karimpour Mohammad Ali Zare Chahooki Ali Hashemi

Recommender systems on social networks and websites have been developed to reduce the production and processing of queries. The purpose of these systems is to recommend users various items such as books, music, and friends. Users' recommendation on social networks and i More

Recommender systems on social networks and websites have been developed to reduce the production and processing of queries. The purpose of these systems is to recommend users various items such as books, music, and friends. Users' recommendation on social networks and instant messengers is useful for users to find friends and for marketers to find new customers. On social networks such as Facebook, finding target users for marketing is an integrated feature, but in instant messengers such as Telegram and WhatsApp, it is not possible to find the target community. In this paper, by using graph and modeling the intergroup behavior of users and also defining features related to groups, a method for recommending Telegram users has been presented. The proposed method consists of 8 steps and each step can be considered a separate method for user recommendation. The data used in this paper is a real data set including more than 900,000 supergroups and 120 million Telegram users crawled by the Idekav system. Evaluation of the proposed method on high-quality groups showed an average reduction in error by 0.0812 in RMSE and 0.128 in MAE. Manuscript profile

Open Access Article

14 - An overview of the molecular template polymer sensor based on graphene quantum dots
seyed mohammad reza milani hoseini parizad mohammadnejad elaheh jabbari

An important part of molecular markers identification has been performed by sophisticated laboratory methods. What is visible today is referred to exploit the achievements and combine them as new available technologies. To accomplish this gold, we need to develop techno More

An important part of molecular markers identification has been performed by sophisticated laboratory methods. What is visible today is referred to exploit the achievements and combine them as new available technologies. To accomplish this gold, we need to develop technologies of 1 to 100 nm to help imagine and sense the interactions between the receptors and specific components. Graphene quantum dots have been developed with easy production methods, biocompatibility, and low toxicity and have been applicable in all fields. This type of quantum dots contains carboxylic acid functional groups on their surfaces, which are interchangeable with other functional groups and have a high solubility in water. It also makes them appropriate for functionalizing with various organic materials such as polymers. Molecular imaging is a fast and accurate method for molecule detection and it is one of the most important methods for molecule detection and quantification. Molecularly imprinted polymer based on graphene quantum dots have being had high-performance applications in most fields of detection and measurement, due to their high selectivity and sensitivity as well as solubility in aqueous media. Manuscript profile

Open Access Article

15 - An Efficient Bread First Search Algorithm on CPU and GPU
P. Keshavarzi H. Deldari S. Abrishami

Graphs are powerful data representations used in enormous computational domains. In graph-based applications, a systematic exploration of graph such as a breath first search often is a fundamental component in the processing of the vast data sets. In this paper we prese More

Graphs are powerful data representations used in enormous computational domains. In graph-based applications, a systematic exploration of graph such as a breath first search often is a fundamental component in the processing of the vast data sets. In this paper we presented a hybrid method that in each level of processing of graph chooses the best implementation of algorithms implemented on CPU or GPU, while avoid poor performance on low and high degree graphs. Our method shows improved performance over the current state-of-the-art implementation and our results proves it. Manuscript profile

Open Access Article

16 - A Parallel Bacterial Foraging Optimization Algorithm implementation on GPU
A. Rafiee S. M. Mosavi

Bacterial foraging algorithm is one of the population-based optimization algorithms that used for solving many search problems in various branches of sciences. One of the issues discussed today is parallel implementation of population-based optimization algorithms on Gr More

Bacterial foraging algorithm is one of the population-based optimization algorithms that used for solving many search problems in various branches of sciences. One of the issues discussed today is parallel implementation of population-based optimization algorithms on Graphic Processor Units. Due to the low speed of bacterial foraging algorithm in the face of complex problem and also lack the ability to solve large-scale problems by this algorithm, Implementation on the graphics processor is a suitable solution to cover the weaknesses of this algorithm. In this paper, we proposed a parallel version of bacterial foraging algorithm which designed by CUDA and has ability to run on GPUs. The performance of this algorithm is evaluated by using a number of famous optimization problems in comparison with the standard bacterial foraging optimization algorithm. The results show that Parallel Algorithm is faster and more efficient than standard bacterial foraging optimization algorithm. Manuscript profile

Open Access Article

17 - Proposing a New Method for Acquiring Skills in Reinforcement Learning with the Help of Graph Clustering
M. Davoodabadi Farahani N. Mozayani

Reinforcement learning is atype of machine learning methods in which the agent uses its transactions with the environment to recognize the environment and to improve its behavior.One of the main problems of standard reinforcement learning algorithms like Q-learning is t More

Reinforcement learning is atype of machine learning methods in which the agent uses its transactions with the environment to recognize the environment and to improve its behavior.One of the main problems of standard reinforcement learning algorithms like Q-learning is that they are not able to solve large scale problems in a reasonable time. Acquiring skills helps to decompose the problem to a set of sub-problems and to solve it with hierarchical methods. In spite of the promising results of using skills in hierarchical reinforcement learning, it has been shown in some previous studies that based on the imposed task, the effect of skills on learning performance can be quite positive. On the contrary, if they are not properly selected, they can increase the complexity of problem-solving. Hence, one of the weaknesses of previous methods proposed for automatically acquiring skills is the lack of a systematic evaluation method for each acquired skill. In this paper, we propose new methods based on graph clustering for subgoal extraction and acquisition of skills. Also, we present new criteria for evaluating skills, with the help of which, inappropriate skills for solving the problem are eliminated. Using these methods in a number of experimental environments shows a significant increase in learning speed. Manuscript profile

Open Access Article

18 - Human Activity Recognition using Switching Structure Model
Mohammad Mahdi Arzani M. Fathy Ahmad Akbari

To communicate with people interactive systems often need to understand human activities in advance. However, recognizing activities in advance is a very challenging task, because people perform their activities in different ways, also, some activities are simple while More

To communicate with people interactive systems often need to understand human activities in advance. However, recognizing activities in advance is a very challenging task, because people perform their activities in different ways, also, some activities are simple while others are complex and comprised of several smaller atomic sub-activities. In this paper, we use skeletons captured from low-cost depth RGB-D sensors as high-level descriptions of the human body. We propose a method capable of recognizing simple and complex human activities by formulating it as a structured prediction task using probabilistic graphical models (PGM). We test our method on three popular datasets: CAD-60, UT-Kinect, and Florence 3D. These datasets cover both simple and complex activities. Also, our method is sensitive to clustering methods that are used to determine the middle states, we evaluate test different clustering, methods. Manuscript profile

Open Access Article

19 - Evaluating Schottky-Barrier-Type GNRFETs-Based Static Flip-Flop Characteristic under Manufacturing Process Parameters Variations
Erfan Abbasian Morteza Gholipour

Graphene nanoribbon field-effect transistors (GNRFETs) have emerged as encouraging replacement candidate for traditional silicon-based transistor in next-generation technology. Since GNRFETs’ channel is about a few nanometers, impact of manufacturing process variations More

Graphene nanoribbon field-effect transistors (GNRFETs) have emerged as encouraging replacement candidate for traditional silicon-based transistor in next-generation technology. Since GNRFETs’ channel is about a few nanometers, impact of manufacturing process variations on circuits’ performance is very large. In this paper, impact of manufacturing process variations such as oxide thickness, channel length, and number of dimer lines on schottky-barrier-type GNRFETs (SB-GNRFETs)-based static flip-flop characteristics such as delay, power, and energy-delay-product (EDP) is evaluated and analyzed. Furthermore, Monte-Carlo (MC) simulations have been performed for statistical analysis of these variations. With change in the oxide thickness from its nominal value to 1.15 nm, the propagation delay and EDP are increased by 31.57% and 60.62%, respectively. Also, the channel length variation has the least effect on flip-flop characteristic. The propagation delay and EDP are increased by 315.48 % and 204.79%, respectively, when the number of dimer lines increases by one from its nominal value. The results obtained from MC simulations show that the oxide thickness variations lead to spread of 2.46, 1.57 and 2.39 times higher than the number of dimer lines variations in histogram distribution of flip-flop characteristic. Manuscript profile

Open Access Article

20 - Investigating the Influence of Number of Carbon Atoms Along the Width of Graphene Nanoribbon on the current of a Graphene Single Electron Transistor
D. Dideban Vahideh Khademhosseini

A single electron transistor is a nanoscale device comprised of three metallic electrodes and one island or quantum dot. The island can made of carbon nano materials like a graphene nanoribbon. The number of carbon atoms along the width of the graphene nanoribbon affect More

A single electron transistor is a nanoscale device comprised of three metallic electrodes and one island or quantum dot. The island can made of carbon nano materials like a graphene nanoribbon. The number of carbon atoms along the width of the graphene nanoribbon affect on the speed of transistor operation and coulomb blockade region. In this research, the current for a single electron transistor utilizing a graphene nanoribbon island is modeled. The impact of several parameters on the transistor current is investigated including the number of carbon atoms along the width, length of nanoribbon, and the applied gate voltage. The modeling results show that increasing the number of carbon atoms along the width of the nanoribbon results in reduced coulomb blockade region. Moreover, reducing the length of nanoribbon and increasing the applied gate voltage cause a decrease in the zero current range of the transistor. Increasing the number of atoms along the width of three islands also gives a boost in the electron tunneling region and thus, the transistor performance will be improved. Manuscript profile

Open Access Article

21 - Computing Colored Average Degree of Graphs in Sublinear Time
Mohammad Ali Abam محمدرضا بهرامی

Graphs are common data structures which widely used for information storage and retrieval. Occasionally some vertices of a graph contain specific features or information, which we value in their effect. We consider modeling this effect formally, and we devise two super- More

Graphs are common data structures which widely used for information storage and retrieval. Occasionally some vertices of a graph contain specific features or information, which we value in their effect. We consider modeling this effect formally, and we devise two super-fast algorithms to approximate the colored average degree. In the first method, we assume the information of each vertex is available; hence, the provided algorithm works with a 2+ϵ approximation factor. Eventually, we waive this assumption and find another algorithm with the same approximation factor, which computes the answer in the sublinear expected time. Manuscript profile

Open Access Article

22 - Improving On-Off Current Ratio (Ion/Ioff) in Schottky-Barrier-Type Graphene Nanoribbon FETs
Morteza Gholipour

Schottky-barrier-type graphene nanoribbon transistors (SB-GNRFET), despite their prominent characteristics compared to conventional transistors, have a relatively high off-current and a low Ion/Ioff ratio. In this paper, a new structure of SB-GNRFET is presented in whic More

Schottky-barrier-type graphene nanoribbon transistors (SB-GNRFET), despite their prominent characteristics compared to conventional transistors, have a relatively high off-current and a low Ion/Ioff ratio. In this paper, a new structure of SB-GNRFET is presented in which the gate of the transistor is divided into two parts. A constant voltage is connected to the gate located on the drain side, and the gate located on the source side is the main gate of the transistor. The proposed SB-GNRFET is simulated using non-equilibrium Green functions-based numerical simulator under different geometric and physical characteristics and in biases. The simulation results show Ion/Ioff ratio improvement of up to 6.7-fold at VDS = 0.8 V. At this voltage the ratio has increased from 1.2 in the normal SB-GNRFET transistor to 8.01 in the new transistor and the off current has been reduced from 5 µA to 0.7 µA. Also at VDS = 0.6 V, as the supply voltage, the Ion/Ioff ratio increased from 3.97 to 15.8 and the off current decreased from 0.63 µA to 0.16 µA. Manuscript profile

Open Access Article

23 - A New Algorithm Based on Distributed Learning Automata for Solving Stochastic Linear Optimization Problems on the Group of Permutations
mohammadreza mollakhalili meybodi masoumeh zojaji

In the present research, a type of permutation optimization was introduced. It is assumed that the cost function has an unknown probability distribution function. Since the solution space is inherently large, solving the problem of finding the optimal permutation is com More

In the present research, a type of permutation optimization was introduced. It is assumed that the cost function has an unknown probability distribution function. Since the solution space is inherently large, solving the problem of finding the optimal permutation is complex and this assumption increases the complexity. In the present study, an algorithm based on distributed learning automata was presented to solve the problem by searching in the permutation answer space and sampling random values. In the present research, in addition to the mathematical analysis of the behavior of the proposed new algorithm, it was shown that by choosing the appropriate values of the parameters of the learning algorithm, this new method can find the optimal solution with a probability close to 100% and by targeting the search using the distributed learning algorithms. The result of adopting this policy is to decrease the number of samplings in the new method compared to methods based on standard sampling. In the following, the problem of finding the minimum spanning tree in the stochastic graph was evaluated as a random permutation optimization problem and the proposed solution based on learning automata was used to solve it. Manuscript profile

Open Access Article

24 - Improving Register File Access Latency Tolerance in GPUs by Value Reproduction
Rahil Barati Mohammad Sadrosadati حمید سربازی آزاد

Large register files reduce the performance and energy overhead of memory accesses by improving the thread-level parallelism and reducing the number of data movements from the off-chip memory. Recently, the latency-tolerant register file (LTRF) is proposed to enable hig More

Large register files reduce the performance and energy overhead of memory accesses by improving the thread-level parallelism and reducing the number of data movements from the off-chip memory. Recently, the latency-tolerant register file (LTRF) is proposed to enable high-capacity register files with low power and area cost. LTRF is a two-level register file in which the first level is a small fast register cache, and the second level is a large slow main register file. LTRF uses a near-perfect register prefetching mechanism that warp registers are prefetched from the main register file to the register file cache before scheduling the warp and hiding the register prefetching latency by the execution of other active warps. LTRF specifies the working set of the warps by partitioning the control flow graph into several prefetch subgraphs, called register-interval. LTRF imposes some performance overhead due to warp stall during the register prefetching. Reducing the number of register-intervals can greatly mitigate this overhead, and improve the effectiveness of LTRF. A register-interval is a subgraph of the control flow graph (CFG) where it has to be a single-entry subgraph with a limited number of registers. We observe that the second constrain contributes more in reducing the size of register-intervals. Increasing the number of registers inside the register-interval cannot address this problem as it imposes huge performance and power overhead during the register prefetching process. In this paper, we propose a register-interval-aware re-production mechanism at compile-time to increase register-interval size without increasing the number of registers inside it. Our experimental results show that our proposal improves the effectiveness of LTRF by 29%, and LTRF’s performance by about 18% (about 30% improvement over baseline GPU architecture). Moreover, our proposal reduces GPU energy and power consumption by respectively 38% and 15%, on average. Manuscript profile

Open Access Article

25 - A New Measure for Partitioning of Block-Centric Graph Processing Systems
Masoud Sagharichian Morteza Alipour Langouri

Block-centric graph processing systems have received significant attention in recent years. To produce the required partitions, most of these systems use general-purpose partitioning methods. As a result, the performance of them has been limited. To face this problem, s More

Block-centric graph processing systems have received significant attention in recent years. To produce the required partitions, most of these systems use general-purpose partitioning methods. As a result, the performance of them has been limited. To face this problem, special partitioning algorithms have been proposed by researchers. However, these methods focused on traditional partitioning measures like the number of cutting-edges and the load-balance. In return, the power of block-centric graph processing systems is due to unique characteristics that are focused on the design of them. According to basic and important characteristics of these systems, in this paper two new measures are proposed as partitioning goals. To the best of our knowledge, the proposed method is the first work that considers the diameter and size of the high-level graph as optimization factors for partitioning purposes. The evaluation of the proposed method over real graphs showed that we could significantly reduce the diameter of the high-level graph. Moreover, the number of cutting-edges of the proposed method are very close to Metis, one of most popular centralized partitioning methods. Since the number of required supersteps in block-centric graph processing systems mainly depends on the diameter of the high-level graph, the proposed method can significantly improve the performance of these systems. Manuscript profile

Open Access Article

26 - Sonic wave velocity estimation using intelligent system and multi resolution graph base clustering: A case study from one of Iranian south field
مرتضی نوری مینا کریمی خالدی

Abstract Compressional and shear velocity are two fundamental parameters, which have many applications in petrophysical, geophysical, and geomechanical operations. These two parameters can be obtained using Dipole Sonic Imaging tool (DSI), but unfortunately this tool More

Abstract Compressional and shear velocity are two fundamental parameters, which have many applications in petrophysical, geophysical, and geomechanical operations. These two parameters can be obtained using Dipole Sonic Imaging tool (DSI), but unfortunately this tool is run just in few wells of a field. Therefore it is important to predict compressional and shear velocity indirectly from the other conventional well logs that have good correlation with these parameters in wells without these logs. Classical methods to predict the mentioned parameters are utilizing correlations and regression analysis. However, the best tool is intelligent systems including Artificial Neural Network, Fuzzy Logic, Adaptive Neuro Fuzzy Inference System, and Multi resolution graph base clustering for performing such tasks. In this paper 1321 data points from Kangan and Dalan formations which have compressional and shear velocity are used. These data are divided into two groups: 995 and 326 data points were used for construction of intelligent systems and model testing, respectively. The results showed that despite differences in concept, all of the intelligent techniques were successful for estimation of compressional and shear velocities. The Multi resolution graph base clustering. The method had the best performance among the others due to precise clustering the data points. Using this method, the compressional and shear velocity were correlated with correlation factor of 0.9505 and 0.9407, respectively. The developed model does not incorporate depth or lithological data as a part of the inputs to the network. This means that utilized methodology is applicable to any field. Manuscript profile

Open Access Article

27 - Comparative study between Rock-Eval pyrolysis and biomarkers parameters: A case study of Horn Valley Siltstone source rock in central- Australia
مهدی شیری سید رضا موسوی حرمی محمد رضا رضائی

In this study 44 Sedimentary rock samples from the Amadeus Basin, in southern portion of the Northern Territory, Australia, were analyzed by two well-proven organic geochemical methods: Rock-Eval (RE) pyrolysis and gas chromatography–mass spectrometry (GC–MS) analysis. More

In this study 44 Sedimentary rock samples from the Amadeus Basin, in southern portion of the Northern Territory, Australia, were analyzed by two well-proven organic geochemical methods: Rock-Eval (RE) pyrolysis and gas chromatography–mass spectrometry (GC–MS) analysis. These techniques were used to obtain independent parameters on organic matter composition, its thermal maturity, and environment of deposition. This study reveals a close concordance between Rock-Eval pyrolysis data and polycyclic biomarkers parameters such as steranes. RE pyrolysis in conjunction with GC–MS analysis show that the Amadeus Basin sediments contain a variable but notable organic-rich facies in the Horn Valley siltstone and prove an unequivocal evidence for Type-II organic matter, which lies dominantly to the peak stage of the conventional oil window (end of diagenesis-middle of catagenesis). The case study from the Amadeus Basin shows that these methods remain undoubtedly suitable for a good assessment of the petroleum potential of source rocks and rapid geochemical characterization of sedimentary organic matter, and can be used in other similar basins. Manuscript profile

Open Access Article

28 - Reservoir Evaluation of the Kangan Formation based on petrophysical and petrographic studies in one of Persian Gulf fields
سید نظام الدین طبیبی حسین اصیلیان مهابادی بهرام موحد حسن حاجی حسنلو

The Early Triassic Kangan Formation is the main reservoir in the Persian Gulf. In this study reservoir rock types were recognized according to lithology, rock fabric, geometry and amount of porosity. Therefore, 7 reservoir rock types were determined: - Anhydrite without More

The Early Triassic Kangan Formation is the main reservoir in the Persian Gulf. In this study reservoir rock types were recognized according to lithology, rock fabric, geometry and amount of porosity. Therefore, 7 reservoir rock types were determined: - Anhydrite without reservoir quality, - limy– dolomite with mud dominated fabric without reservoir quality, - limy– dolomite with mud dominated fabric and an average reservoir quality, -limy– dolomite with mud dominated fabric and good reservoir quality, - dolomite with crystalline fabric and low reservoir quality, - limestone with grain dominated fabric with an average reservoir quality and - dolomite with crystaline fabric with a good reservoir quality. Based on petrophysical logs(Gamma ray, sonic, neutron & density), 5 reservoir units and 6 non – reservoir units were identified. Reservoir units are mainly formed of porous grain dominated limestone ,crystalline dolomite and mud dominated fabric dolomite, and non – reservoir units include anhydrite and limy dolomite without porosity. Petrophysical and petrographical studies indicate that moldic, intercrystaline and interparticle porosities are the most effective porosities in the reservoir units of this formation, whereas others like vuggy , fracture and intraparticle porosities have minor role in reservoir quality. Manuscript profile

Open Access Article

29 - Biomarker study of Asmari Reservoir oil in the oil fields situated in N.E. Dezful Embayment
علیرضا بنی اسد

Masjid-e-Solyman, Haft kel, Par-e-Siah and Naft Safid are productive oil fields which are located in mountain front of NE Dezful Embayment. In this research, in order to Geochemical correlation and Petroleum Systems determination of Asmari oils, a few oil samples were s More

Masjid-e-Solyman, Haft kel, Par-e-Siah and Naft Safid are productive oil fields which are located in mountain front of NE Dezful Embayment. In this research, in order to Geochemical correlation and Petroleum Systems determination of Asmari oils, a few oil samples were subjected to biomarker studies by GC and GC-MS techniques. Review of biomarkers fingerprints indicate two petroleum systems probably are active in studied oilfields. A major petroleum system that has controlled the hydrocarbon generation, migration and accumulation in all studied oilfields and a younger petroleum system, which has caused mixture of oils with another source in Masjed-Soleyman and Par-e-Siah oilfields, Biomarkers fingerprints, Steranes, Hopanes in addition to the main petroleum system. parameters, Pristane to Phytane ratios and also n- alkane's distributions among the studied oils, indicate that the Asamri oils were produced mainly from a marine and marine-carbonate source rock(s), which has been deposited in an anoxic conditions, with kerogen mainly of Type II with little contribution of terrestrial Kerogen (Type III) and oil samples has a maturity about early oil window without any severe biodegradation. 13C isotope values distribution, presence of Oleannane biomarker and slightly differences - mainly from lithological aspects and maturation levels of oils - of Masjid-Soleyman and Par-e-Siah Oils, reveal that, the mixed oils in these two reservoirs have been probably produced from two source rocks, a younger source rock namely Pabdeh Formation (Middle Eocene and Early Oligocene) with less importance of Kazhdumi Formation (Albian) which is the main source rock Manuscript profile

Open Access Article

30 - Biomarker study of Asmari Reservoir oil in the oil fields situated in N.E. Dezful Embayment
Mahmud Memariani Ali reza Bani asad

Masjid-e-Solyman, Haft kel, Par-e-Siah and Naft Safid are productive oil fields which are located in mountain front of NE Dezful Embayment. In this research, in order to Geochemical correlation and Petroleum Systems determination of Asmari oils, a few oil samples were s More

Masjid-e-Solyman, Haft kel, Par-e-Siah and Naft Safid are productive oil fields which are located in mountain front of NE Dezful Embayment. In this research, in order to Geochemical correlation and Petroleum Systems determination of Asmari oils, a few oil samples were subjected to biomarker studies by GC and GC-MS techniques. Review of biomarkers fingerprints indicate two petroleum systems probably are active in studied oilfields. A major petroleum system that has controlled the hydrocarbon generation, migration and accumulation in all studied oilfields and a younger petroleum system, which has caused mixture of oils with another source in Masjed-Soleyman and Par-e-Siah oilfields, Biomarkers fingerprints, Steranes, Hopanes in addition to the main petroleum system. parameters, Pristane to Phytane ratios and also n- alkane's distributions among the studied oils, indicate that the Asamri oils were produced mainly from a marine and marine-carbonate source rock(s), which has been deposited in an anoxic conditions, with kerogen mainly of Type II with little contribution of terrestrial Kerogen (Type III) and oil samples has a maturity about early oil window without any severe biodegradation. 13C isotope values distribution, presence of Oleannane biomarker and slightly differences - mainly from lithological aspects and maturation levels of oils - of Masjid-Soleyman and Par-e-Siah Oils, reveal that, the mixed oils in these two reservoirs have been probably produced from two source rocks, a younger source rock namely Pabdeh Formation (Middle Eocene and Early Oligocene) with less importance of Kazhdumi Formation (Albian) which is the main source rock. Manuscript profile

Open Access Article

31 - Stock Price Movement Prediction Using Directed Graph Attention Network
Alireza Jafari Saman Haratizadeh

Prediction of the future behavior of the stock market has always attracted researchers' attention as an important challenge in the field of machine learning. In recent years deep learning methods have been successfully applied in this domain to improve prediction perfor More

Prediction of the future behavior of the stock market has always attracted researchers' attention as an important challenge in the field of machine learning. In recent years deep learning methods have been successfully applied in this domain to improve prediction performance. Previous studies have demonstrated that aggregating information from related stocks can improve the performance of prediction. However, the capacity of modeling the stocks relations as directed graphs and the power of sophisticated graph embedding techniques such as Graph Attention Networks have not been exploited so far for prediction in this domain. In this work, we introduce a framework called DeepNet that creates a directed graph representing how useful the data from each stock can be for improving the prediction accuracy of any other stocks. DeepNet then applies Graph Attention Network to extract a useful representation for each node by aggregating information from its neighbors, while the optimal amount of each neighbor's contribution is learned during the training phase. We have developed a novel Graph Attention Network model called DGAT that is able to define unequal contribution values for each pair of adjacent nodes in a directed graph. Our evaluation experiments on the Tehran Stock Exchange data show that the introduced prediction model outperforms the state-of-the-art baseline algorithms in terms of accuracy and MCC measures. Manuscript profile

Open Access Article

32 - Community Detection in Complex Dynamic Networks Based on Graph Embedding and Clustering Ensemble
Majid Mohammadpour Seyedakbar Mostafavi وحید رنجبر

Special conditions of wireless sensor networks, such as energy limitation, make it essential to accelerate the convergence of algorithms in this field, especially in the distributed compressive sensing (DCS) scenarios, which have a complex reconstruction phase. This pap More

Special conditions of wireless sensor networks, such as energy limitation, make it essential to accelerate the convergence of algorithms in this field, especially in the distributed compressive sensing (DCS) scenarios, which have a complex reconstruction phase. This paper presents a DCS reconstruction algorithm that provides a higher convergence rate. The proposed algorithm is a distributed primal-dual algorithm in a bidirectional incremental cooperation mode where the parameters change with time. The parameters are changed systematically in the convex optimization problems in which the constraint and cooperation functions are strongly convex. The proposed method is supported by simulations, which show the higher performance of the proposed algorithm in terms of convergence rate, even in stricter conditions such as the small number of measurements or the lower degree of sparsity. Manuscript profile

Open Access Article

33 - -
Farzad Mehrjo

-

- Manuscript profile

Open Access Article

34 - Video Summarization Using a Clustering Graph Neural Networks
Mahsa RahimiResketi Homayun Motameni Ebrahim Akbari Hossein Nematzadeh

The increase of cameras nowadays, and the power of the media in people's lives lead to a staggering amount of video data. It is certain that a method to process this large volume of videos quickly and optimally becomes especially important. With the help of video summar More

The increase of cameras nowadays, and the power of the media in people's lives lead to a staggering amount of video data. It is certain that a method to process this large volume of videos quickly and optimally becomes especially important. With the help of video summarization, this task is achieved and the film is summarized into a series of short but meaningful frames or clips. This study tried to cluster the data by an algorithm (K-Medoids) and then with the help of a convolutional graph attention network, temporal and graph separation is done, then in the next step with the connection rejection method, noises and duplicates are removed, and finally summarization is done by merging the results obtained from two different graphical and temporal steps. The results were analyzed qualitatively and quantitatively on three datasets SumMe, TVSum, and OpenCv. In the qualitative method, an average of 88% accuracy rate in summarization and 31% error rate was achieved, which is one of the highest accuracy rates compared to other methods. In quantitative evaluation, the proposed method has a higher efficiency than the existing methods. Manuscript profile

Open Access Article

35 - Permeability improvement calculated from Stoneley-FZI method in Kangan reservoir, one of Iran's gas fields
hossein rezaie yegane doost

10.61186/ispg.38526.11.22.39

Permeability in fluid flow is for a porous rock, which is exactly what causes the problem. core analysis and well testing are two most commonly used methods of permeability measurement, but in-vitro measurement of permeability by applying core analysis on all wells in a More

Permeability in fluid flow is for a porous rock, which is exactly what causes the problem. core analysis and well testing are two most commonly used methods of permeability measurement, but in-vitro measurement of permeability by applying core analysis on all wells in a specific field is very time consuming and costly and even impossible when dealing with Horizontal wells. Wells testing, on the other hand, is not cost-effective for reasons such as; High costs and zero production during the testing process. Therefore, thanks to their low cost, comprehensiveness and availability, permeability estimation methods developed according to conventional logs land DSI diagrams are of critical importance. Taking this into account, in the present study, permeability was first estimated using multi-resolution graph-based clustering (MRGC) and the results were compared with permeability rates obtained from core analysis. In the second stage, permeability was measured by ST-FZI method and the results were compared with permeability rates obtained from core analysis. In the third stage, the multi-resolution graph-based clustering (MRGC) method was used to improve the permeability calculated by the ST-FZI method and overcome the reservoir heterogeneity. First the flow units were identified, and then the ST-FZI method was applied on each flow unit to calculate permeability and finally the calculated permeabilities were combined to obtain an accurate permeability graph of the studied well. The correlation coefficients of permeability rates estimated via core analysis in the multi-resolution graph-based clustering method (R2 = 77), ST-FZI method (R2 = 47) and improved method (R2 = 84) were measured. The afore-mentioned method was able to improve the permeability calculated in the previous step by 37% and was recognized as the best permeability measurement method in the Kangan reservoir of the well subjected to study. Manuscript profile

Open Access Article

36 - Graphene‑based composite membranes for nanofiltration: performances and future perspectives
Farzad Mehrjo

Nanofiltration is one of the most widely used membrane processes for water purification with high practical value because of a large number of chemical species that are separated through this process. Usually, for nanofiltration, high energy–con- suming operations are i More

Nanofiltration is one of the most widely used membrane processes for water purification with high practical value because of a large number of chemical species that are separated through this process. Usually, for nanofiltration, high energy–con- suming operations are involved including the generation of enough pressure for the rejection of jumps and lower molecular weight chemicals at the surface of the membrane. Recent developments in the synthesis of nanocomposite membranes with graphene and graphene derivatives have led to an increase in energy requirements and the increase in membranes perfor- mances. In the present review, we have presented the recent advances in the field of graphene-based composite membranes for nanofiltration with applications for both types of based solvents—aqueous solutions and organic solvents. The presentation will be focused especially on the performances of membranes and applications of these materials for the rejection of salts (Na+, Mg2+), heavy metals (Li2+), and lower molecular weight organic compounds (methylene blue, Congo red, Direct Red, Methyl orange, Reactive green 13, etc.). Modern synthesis methods like interfacial polymerization for obtaining thin-film composite nanofiltration membranes are also presented. Nanofiltration is one of the most widely used membrane processes for water purification with high practical value because of a large number of chemical species that are separated through this process. Manuscript profile

Open Access Article

37 - Investigating the reservoir quality of Sarvk formation using multi-resolution graph-based and comparing it with petrographic data in an oilfield of Dezful Embayment
Seyedeh Akram Jooybari Payman Rezaee Majid Mehdipour

Sarvak Formation is one of the important carbonate reservoirs in Dezful Embayment. In order to evaluate the reservoir quality of this formation in one of the Dezful Embayment fields, multi-resolution graph-based method was used and compared with petrographic findings. T More

Sarvak Formation is one of the important carbonate reservoirs in Dezful Embayment. In order to evaluate the reservoir quality of this formation in one of the Dezful Embayment fields, multi-resolution graph-based method was used and compared with petrographic findings. The findings showed that the Sarvak formation in the studied field consists of 8 microfacies belonging to the sub-environments of the lagoon, carbonate bar, middle ramp and outer ramp, which were deposited in a homoclinal ramp environment. The main diagenesis processes affecting this reservoir include cementation, dissolution, fracture, stylolitization, and dolomitization. The results of multi-resolution graph-based analysis led to the identification of 3 electrofacies, EF1 electrofacies had the weakest reservoir parameters and EF3 facies had the best reservoir status. The majority of EF1 microfacies are grainstone microfacies and the majority of EF3 microfacies correspond to wackstone and packstone microfacies. Based on this, it seems that the lagoon sub-environment has a better reservoir condition than other sub-environments, especially the carbonate bar, and this is an important sign of the different performance of diagenesis processes in these sub-environments. In a vertical trend, the highest volume of hydrocarbon column is in the EF3 electrofacies and the lowest is EF1. In general, it can be stated that the use of multi-resolution graph-based analysis and comparison with petrographic findings is a suitable solution for accurate evaluation of the reservoir quality of carbonate reservoirs. Manuscript profile

Open Access Article

38 - Community Detection in Bipartite Networks Using HellRank Centrality Measure
Ali Khosrozadeh Ali Movaghar Mohammad Mehdi Gilanian Sadeghi Hamidreza Mahyar

Community structure is a common and important feature in many complex networks, including bipartite networks. In recent years, community detection has received attention in many fields and many methods have been proposed for this purpose, but the heavy consumption of ti More

Community structure is a common and important feature in many complex networks, including bipartite networks. In recent years, community detection has received attention in many fields and many methods have been proposed for this purpose, but the heavy consumption of time in some methods limits their use in large-scale networks. There are methods with lower time complexity, but they are mostly non-deterministic, which greatly reduces their applicability in the real world. The usual approach that is adopted to community detection in bipartite networks is to first construct a unipartite projection of the network and then communities detect in that projection using methods related to unipartite networks, but these projections inherently lose information. In this paper, based on the bipartite modularity measure that quantifies the strength of partitions in bipartite networks and using the HellRank centrality measure, a quick and deterministic method for community detection from bipartite networks directly and without need to projection, proposed. The proposed method is inspired by the voting process in election activities in the social society and simulates it. Manuscript profile

Open Access Article

39 - Survey on the Applications of the Graph Theory in the Information Retrieval
Maryam Piroozmand Amir Hosein Keyhanipour Ali Moeini

Due to its power in modeling complex relations between entities, graph theory has been widely used in dealing with real-world problems. On the other hand, information retrieval has emerged as one of the major problems in the area of algorithms and computation. As graph- More

Due to its power in modeling complex relations between entities, graph theory has been widely used in dealing with real-world problems. On the other hand, information retrieval has emerged as one of the major problems in the area of algorithms and computation. As graph-based information retrieval algorithms have shown to be efficient and effective, this paper aims to provide an analytical review of these algorithms and propose a categorization of them. Briefly speaking, graph-based information retrieval algorithms might be divided into three major classes: the first category includes those algorithms which use a graph representation of the corresponding dataset within the information retrieval process. The second category contains semantic retrieval algorithms which utilize the graph theory. The third category is associated with the application of the graph theory in the learning to rank problem. The set of reviewed research works is analyzed based on both the frequency as well as the publication time. As an interesting finding of this review is that the third category is a relatively hot research topic in which a limited number of recent research works are conducted. Manuscript profile

Open Access Article

40 - Development and application of graphene silk solar panel concept in smart bus station design
Kianoosh Hosseinian Seyed Majid Keshavarz

With the continuous growth of the population, with the expansion of the urban area. Human activities and behaviors waste limited resources, a large number of these personal vehicles occupy our roads, also causing various environmental problems. With the increasing aware More

With the continuous growth of the population, with the expansion of the urban area. Human activities and behaviors waste limited resources, a large number of these personal vehicles occupy our roads, also causing various environmental problems. With the increasing awareness of environmental protection, green travel has gradually become a way of travel for people living in big cities. Convenience and environmental protection are the main advantages of public transport, but unfortunately, the performance, service and environment of many bus stations are not comfortable and friendly. Therefore, the smart bus station was born, it can not only provide real-time bus information, but also provide a safe and comfortable waiting space. However, with the improvement of service functions, the problem of energy consumption has become increasingly prominent. Energy supply through solar panels can naturally be a sustainable energy source for smart bus stations, but many studies have shown that solar panels themselves are not environmentally friendly, regardless of their materials and recyclability. The author's research revealed that relevant studies have confirmed that spraying an aqueous solution containing carbon nanotubes or graphene on mulberry leaves to feed silkworms doubles the strength of silk spit and the conductivity of carbonized silk is 10 times higher. In addition, robotic fiber spinning technology allows silkworms to independently complete the production of silk objects without killing the silkworms. Through research on graphene silk materials and robotic fiber spinning technology, this paper proposes a biologically independent solution for the production of graphene silk thin film solar panels to seek to solve the problem of solar panel pollution in the smart station. Manuscript profile

Open Access Article

41 - Improving Opinion Aspect Extraction Using Domain Knowledge and Term Graph
Mohammadreza Shams Ahmad Baraani Mahdi Hashemi

With the advancement of technology, analyzing and assessing user opinions, as well as determining the user's attitude toward various aspects, have become a challenging and crucial issue. Opinion mining is the process of recognizing people’s attitudes from textual commen More

With the advancement of technology, analyzing and assessing user opinions, as well as determining the user's attitude toward various aspects, have become a challenging and crucial issue. Opinion mining is the process of recognizing people’s attitudes from textual comments at three different levels: document-level, sentence-level, and aspect-level. Aspect-based Opinion mining analyzes people’s viewpoints on various aspects of a subject. The most important subtask of aspect-based opinion mining is aspect extraction, which is addressed in this paper. Most previous methods suggest a solution that requires labeled data or extensive language resources to extract aspects from the corpus, which can be time consuming and costly to prepare. In this paper, we propose an unsupervised approach for aspect extraction that uses topic modeling and the Word2vec technique to integrate semantic information and domain knowledge based on term graph. The evaluation results show that the proposed method not only outperforms previous methods in terms of aspect extraction accuracy, but also automates all steps and thus eliminates the need for user intervention. Furthermore, because it is not reliant on language resources, it can be used in a wide range of languages. Manuscript profile

Open Access Article

42 - Community Detection in Bipartite Networks Using HellRank Centrality Measure
Ali Khosrozadeh movaghar movaghar Mohammad Mehdi Gilanian Sadeghi Hamidreza Mahyar

Community structure is a common and important feature in many complex networks, including bipartite networks. In recent years, community detection has received attention in many fields and many methods have been proposed for this purpose, but the heavy consumption of ti More

Community structure is a common and important feature in many complex networks, including bipartite networks. In recent years, community detection has received attention in many fields and many methods have been proposed for this purpose, but the heavy consumption of time in some methods limits their use in large-scale networks. There are methods with lower time complexity, but they are mostly non-deterministic, which greatly reduces their applicability in the real world. The usual approach that is adopted to community detection in bipartite networks is to first construct a unipartite projection of the network and then communities detect in that projection using methods related to unipartite networks, but these projections inherently lose information. In this paper, based on the bipartite modularity measure that quantifies the strength of partitions in bipartite networks and using the HellRank centrality measure, a quick and deterministic method for community detection from bipartite networks directly and without need to projection, proposed. The proposed method is inspired by the voting process in election activities in the social society and simulates it. Manuscript profile

Open Access Article

43 - Survey on the Applications of the Graph Theory in the Information Retrieval
Maryam Piroozmand Amir Hosein Keyhanipour Ali Moeini

Due to its power in modeling complex relations between entities, graph theory has been widely used in dealing with real-world problems. On the other hand, information retrieval has emerged as one of the major problems in the area of algorithms and computation. As graph- More

Due to its power in modeling complex relations between entities, graph theory has been widely used in dealing with real-world problems. On the other hand, information retrieval has emerged as one of the major problems in the area of algorithms and computation. As graph-based information retrieval algorithms have shown to be efficient and effective, this paper aims to provide an analytical review of these algorithms and propose a categorization of them. Briefly speaking, graph-based information retrieval algorithms might be divided into three major classes: the first category includes those algorithms which use a graph representation of the corresponding dataset within the information retrieval process. The second category contains semantic retrieval algorithms which utilize the graph theory. The third category is associated with the application of the graph theory in the learning to rank problem. The set of reviewed research works is analyzed based on both the frequency as well as the publication time. As an interesting finding of this review is that the third category is a relatively hot research topic in which a limited number of recent research works are conducted. Manuscript profile

List of Articles گراف

Rimag

Links

Related Centers

Technical Support

Official pages