Pub Date : 2021-03-03DOI: 10.1109/CSICC52343.2021.9420628
S. Azadifar, A. Ahmadi
Identifying disease genes from a large number of candidate genes by laboratory methods is very costly and time consuming, so it is necessary to prioritize disease candidate genes before laboratory work. Recently, many gene prioritization methods have been proposed using various datasets such as gene ontology and protein-protein interaction, which are often based on text mining, machine learning, and random walk methods. Due to the good performance and increasing use of deep graph networks in the representation of graph problems, in this study, a method based on graph convolutional networks has been developed to represent the graph on the protein-protein interaction. The results show that the proposed method is effective and the performance of the proposed method better than other methods in some cases.
{"title":"A New Disease Candidate Gene Prioritization Method Using Graph Convolutional Networks","authors":"S. Azadifar, A. Ahmadi","doi":"10.1109/CSICC52343.2021.9420628","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420628","url":null,"abstract":"Identifying disease genes from a large number of candidate genes by laboratory methods is very costly and time consuming, so it is necessary to prioritize disease candidate genes before laboratory work. Recently, many gene prioritization methods have been proposed using various datasets such as gene ontology and protein-protein interaction, which are often based on text mining, machine learning, and random walk methods. Due to the good performance and increasing use of deep graph networks in the representation of graph problems, in this study, a method based on graph convolutional networks has been developed to represent the graph on the protein-protein interaction. The results show that the proposed method is effective and the performance of the proposed method better than other methods in some cases.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122664488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-03DOI: 10.1109/CSICC52343.2021.9420565
Benyamin Eslami, Morteza Biabani, Mohsen Shekarisaz, N. Yazdani
Cloud data centers play a significant role in providing services needed by users in a quick way. Recent studies show that, traffic patterns in data centers have a special importance to be improved, since they have significant effects on various aspects such as congestion, overall energy consumption and service response time. The traffic patterns inside a cloud data center have two categories: North-South and East-West. The former one is the outside-inside and inside-outside traffic, Whereas, the latter is the traffic among Virtual Machines (VMs) within data centers. Previous studies have shown that the East-West traffic pattern is multiple times larger than the North-South one. This leads data centers to experience congestion and packet loss in the core layer of their topology. Common cause of large traffic patterns is that, VMs of service chains are scattered within the data center in different racks, so that, it causes lots of packet injection into the data center. In this paper, we propose a heuristic algorithm to place VMs of a service chain in a closer proximity of each other to improve the East-West traffic pattern by reducing response time of services and also data centers’ overall energy consumption. The simulation results compared to the state-of-the-art method demonstrate about 18% improvement in response time for users’ requests and 10% of total energy consumption reduction in the data center.
{"title":"PERMUTE: Response Time and Energy Aware Virtual Machine Placement for Cloud Data Centers","authors":"Benyamin Eslami, Morteza Biabani, Mohsen Shekarisaz, N. Yazdani","doi":"10.1109/CSICC52343.2021.9420565","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420565","url":null,"abstract":"Cloud data centers play a significant role in providing services needed by users in a quick way. Recent studies show that, traffic patterns in data centers have a special importance to be improved, since they have significant effects on various aspects such as congestion, overall energy consumption and service response time. The traffic patterns inside a cloud data center have two categories: North-South and East-West. The former one is the outside-inside and inside-outside traffic, Whereas, the latter is the traffic among Virtual Machines (VMs) within data centers. Previous studies have shown that the East-West traffic pattern is multiple times larger than the North-South one. This leads data centers to experience congestion and packet loss in the core layer of their topology. Common cause of large traffic patterns is that, VMs of service chains are scattered within the data center in different racks, so that, it causes lots of packet injection into the data center. In this paper, we propose a heuristic algorithm to place VMs of a service chain in a closer proximity of each other to improve the East-West traffic pattern by reducing response time of services and also data centers’ overall energy consumption. The simulation results compared to the state-of-the-art method demonstrate about 18% improvement in response time for users’ requests and 10% of total energy consumption reduction in the data center.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128564175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-03DOI: 10.1109/CSICC52343.2021.9420574
Shayan Ramazi, A. Nadian-Ghomsheh
Zero-Shot Learning (ZSL) is an emerging learning paradigm that addresses the problem of recognizing unseen classes during training. Several studies have shown ZSL can be improved using synthetic samples of unseen classes, usually generated with a GAN and conditioned on some high- level descriptions of the desired class. This paper proposes a new generative adversarial network architecture to improve synthetic feature generation by applying a ranking step at training time. We combined two classifiers' results at the zeroshot classification step to ensure improved classification accuracy. Then we evaluated the proposed architecture using the widely used dataset AWA. Our results show an improvement of classification accuracy of 2.3% in ZSL setting and 0.15% in GZSL setting compared to the state-of-the-art.
{"title":"Ranking Synthetic Features for Generative Zero-Shot Learning","authors":"Shayan Ramazi, A. Nadian-Ghomsheh","doi":"10.1109/CSICC52343.2021.9420574","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420574","url":null,"abstract":"Zero-Shot Learning (ZSL) is an emerging learning paradigm that addresses the problem of recognizing unseen classes during training. Several studies have shown ZSL can be improved using synthetic samples of unseen classes, usually generated with a GAN and conditioned on some high- level descriptions of the desired class. This paper proposes a new generative adversarial network architecture to improve synthetic feature generation by applying a ranking step at training time. We combined two classifiers' results at the zeroshot classification step to ensure improved classification accuracy. Then we evaluated the proposed architecture using the widely used dataset AWA. Our results show an improvement of classification accuracy of 2.3% in ZSL setting and 0.15% in GZSL setting compared to the state-of-the-art.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117065579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-03DOI: 10.1109/CSICC52343.2021.9420585
F. Faraji, F. Lotfi, M. Majdolhosseini, M. Jafarian, H. Taghirad
As a critical part of any security system, identity recognition has become paramount among researchers. In this regard, several methods are presented while considering various sensors and data. In particular, gait data yields rich information about a person, including some exclusive moving patterns which can be utilized to distinguish between different individuals. On the other hand, convolutional neural networks are proved to be applicable for structured data, especially images. In this article, 12 markers are considered in gathering the gait data, each representing a lower-body joint location. Then, utilizing the gait data in a 2D tensor form, three different convolutional neural networks are trained to recognize the identities. Taking light architectures into account, this approach is implementable in realtime application. The obtained result shows the promising capability of the proposed method being used in identity recognition.
{"title":"Identity Recognition based on Convolutional Neural Networks Using Gait Data","authors":"F. Faraji, F. Lotfi, M. Majdolhosseini, M. Jafarian, H. Taghirad","doi":"10.1109/CSICC52343.2021.9420585","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420585","url":null,"abstract":"As a critical part of any security system, identity recognition has become paramount among researchers. In this regard, several methods are presented while considering various sensors and data. In particular, gait data yields rich information about a person, including some exclusive moving patterns which can be utilized to distinguish between different individuals. On the other hand, convolutional neural networks are proved to be applicable for structured data, especially images. In this article, 12 markers are considered in gathering the gait data, each representing a lower-body joint location. Then, utilizing the gait data in a 2D tensor form, three different convolutional neural networks are trained to recognize the identities. Taking light architectures into account, this approach is implementable in realtime application. The obtained result shows the promising capability of the proposed method being used in identity recognition.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117127005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-03DOI: 10.1109/CSICC52343.2021.9420622
Moein Raeisi, Amir Soltany Mahboob
The increasing number of vehicles, followed by traffic congestion, has posed a great challenge to the optimal control of traffic for human societies. Therefore, in order to achieve sustainable development in the field of integrated urban management, control of transportation networks is inevitable. The proper method for optimal traffic control should certainly be adaptable in order to be able to manage urban traffic that has a dynamic, complex and changeable nature. In this regard, the method of reinforcement learning that does not require a mathematical model of the environment is very important. In this paper, an intelligent method for controlling urban traffic based on reinforcement learning is presented in which a 4-way intersection is modeled with two different scenarios for low and high traffic congestion. The results obtained after repeated experiments of implementing the proposed method and also its improved model on the mentioned intersection show that the amount of travel time delay has been reduced compared to the usual fixed time methods. After comparing with the two fixed time methods, the waiting time of vehicles at the intersection is 15% and 86% improved for the scenario with low and high traffic congestion respectively, compared to the first method and 37% and 16% compared to the second method.
{"title":"Intelligent Control of Urban Intersection Traffic Light Based on Reinforcement Learning Algorithm","authors":"Moein Raeisi, Amir Soltany Mahboob","doi":"10.1109/CSICC52343.2021.9420622","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420622","url":null,"abstract":"The increasing number of vehicles, followed by traffic congestion, has posed a great challenge to the optimal control of traffic for human societies. Therefore, in order to achieve sustainable development in the field of integrated urban management, control of transportation networks is inevitable. The proper method for optimal traffic control should certainly be adaptable in order to be able to manage urban traffic that has a dynamic, complex and changeable nature. In this regard, the method of reinforcement learning that does not require a mathematical model of the environment is very important. In this paper, an intelligent method for controlling urban traffic based on reinforcement learning is presented in which a 4-way intersection is modeled with two different scenarios for low and high traffic congestion. The results obtained after repeated experiments of implementing the proposed method and also its improved model on the mentioned intersection show that the amount of travel time delay has been reduced compared to the usual fixed time methods. After comparing with the two fixed time methods, the waiting time of vehicles at the intersection is 15% and 86% improved for the scenario with low and high traffic congestion respectively, compared to the first method and 37% and 16% compared to the second method.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131153172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-03DOI: 10.1109/CSICC52343.2021.9420570
Arefeh Esmaili, Saeed Farzi
Nowadays, with the pervasiveness of social networks among the people, the possibility of publishing incorrect information has increased more than before. Therefore, detecting fake news and users who publish this incorrect information is of great importance. This paper has proposed a system based on combining context-user and context-network features with the help of a conditional generative adversarial network for balancing the data set to detect users who publish incorrect information in the Persian language on Twitter. Moreover, by conducting numerous experiments, the proposed system in terms of evaluation metrics compared to its competitors, has produced good performance results in detecting fake users.
{"title":"Effective synthetic data generation for fake user detection","authors":"Arefeh Esmaili, Saeed Farzi","doi":"10.1109/CSICC52343.2021.9420570","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420570","url":null,"abstract":"Nowadays, with the pervasiveness of social networks among the people, the possibility of publishing incorrect information has increased more than before. Therefore, detecting fake news and users who publish this incorrect information is of great importance. This paper has proposed a system based on combining context-user and context-network features with the help of a conditional generative adversarial network for balancing the data set to detect users who publish incorrect information in the Persian language on Twitter. Moreover, by conducting numerous experiments, the proposed system in terms of evaluation metrics compared to its competitors, has produced good performance results in detecting fake users.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"2015 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130596278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-03DOI: 10.1109/CSICC52343.2021.9420576
A. Razavi, A. Kosari
In this paper, the optimal low thrust planar orbit transfer problem is solved utilizing a fuzzy optimal control algorithm. Firstly, dynamic equations are presented in a discretized form, then all the design variables and constraints are transformed to fuzzy space, while minimizing the performance index and also satisfying transversallity conditions. Applying the concept of membership functions based on expert experience, the designed cost function associated with operational constraints are transformed to fuzzy relations through specific membership functions. Applying Bellman-Zadeh approach, the optimal control problem can be converted to a parameter optimization. Combining the performance index and problem’s constraints in a scalar function, necessary optimality conditions are achieved in a form of nonlinear algebraic equations. Finally, to solve this set of equations, the gradient-based method is used. In comparison with the exact form of the problem, the efficiency of the proposed algorithm is highlighted in terms of time and accuracy. In the fuzzy optimal control, a control designer could take advantage of determining the allowed limit for cost function. This algorithm could be successfully extended to fixed state or fixed control problems which is time-consuming in scope of the classical optimal control.
{"title":"Fuzzy Optimal Control Approach in Low-Thrust Orbit Transfer Problem","authors":"A. Razavi, A. Kosari","doi":"10.1109/CSICC52343.2021.9420576","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420576","url":null,"abstract":"In this paper, the optimal low thrust planar orbit transfer problem is solved utilizing a fuzzy optimal control algorithm. Firstly, dynamic equations are presented in a discretized form, then all the design variables and constraints are transformed to fuzzy space, while minimizing the performance index and also satisfying transversallity conditions. Applying the concept of membership functions based on expert experience, the designed cost function associated with operational constraints are transformed to fuzzy relations through specific membership functions. Applying Bellman-Zadeh approach, the optimal control problem can be converted to a parameter optimization. Combining the performance index and problem’s constraints in a scalar function, necessary optimality conditions are achieved in a form of nonlinear algebraic equations. Finally, to solve this set of equations, the gradient-based method is used. In comparison with the exact form of the problem, the efficiency of the proposed algorithm is highlighted in terms of time and accuracy. In the fuzzy optimal control, a control designer could take advantage of determining the allowed limit for cost function. This algorithm could be successfully extended to fixed state or fixed control problems which is time-consuming in scope of the classical optimal control.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133071233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-03DOI: 10.1109/CSICC52343.2021.9420606
M. Hemati, M. Shajari
In recent years, the blockchain that is the basis of Bitcoin has received much attention. However, the blockchain also faces many challenges, such as security and scalability, which have been the subject of recent researches. Much work has been done to solve the scalability problem in blockchain; one of these methods is sharding. This method is based on dividing the network into different groups and validating transactions in parallel. These methods use traditional consensus algorithms. One of the problems in this regard is the incentive that should be provided for nodes to participate in these consensus algorithms. In this paper, Repchain, one of the existing methods in this field, is examined, and the problems that this method has is analyzed. Next, it is proved that the proposed method causes the network nodes not to follow the protocol and also causes collusion between network nodes.
{"title":"Analysis of incentive mechanism in Repchain","authors":"M. Hemati, M. Shajari","doi":"10.1109/CSICC52343.2021.9420606","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420606","url":null,"abstract":"In recent years, the blockchain that is the basis of Bitcoin has received much attention. However, the blockchain also faces many challenges, such as security and scalability, which have been the subject of recent researches. Much work has been done to solve the scalability problem in blockchain; one of these methods is sharding. This method is based on dividing the network into different groups and validating transactions in parallel. These methods use traditional consensus algorithms. One of the problems in this regard is the incentive that should be provided for nodes to participate in these consensus algorithms. In this paper, Repchain, one of the existing methods in this field, is examined, and the problems that this method has is analyzed. Next, it is proved that the proposed method causes the network nodes not to follow the protocol and also causes collusion between network nodes.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122213860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-03DOI: 10.1109/CSICC52343.2021.9420566
Faezeh Goumeh, A. Barforoush
A wide range of industries is facing a fundamental change: digital transformation. The banking industry is no exception. However, despite such transformation being underway, there is a lack of frameworks and tools to help banking providers navigate such radical change. This article presents a new framework: the digital maturity model for digital banking providers. The model aims to offer a structured view of digital transformation specific to the context and challenges of digital banking. That can be used as a standard to help digital Banking providers benchmark themselves against peers or themselves as they advance their transformation. This article begins with a review of digital banking. A new definition of digital banking was introduced. Digital transformation and digital maturity, and after that, the previous models were investigated. And finally, a new model specific to digital banking in Iran.
{"title":"A Digital Maturity Model for digital banking revolution for Iranian banks","authors":"Faezeh Goumeh, A. Barforoush","doi":"10.1109/CSICC52343.2021.9420566","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420566","url":null,"abstract":"A wide range of industries is facing a fundamental change: digital transformation. The banking industry is no exception. However, despite such transformation being underway, there is a lack of frameworks and tools to help banking providers navigate such radical change. This article presents a new framework: the digital maturity model for digital banking providers. The model aims to offer a structured view of digital transformation specific to the context and challenges of digital banking. That can be used as a standard to help digital Banking providers benchmark themselves against peers or themselves as they advance their transformation. This article begins with a review of digital banking. A new definition of digital banking was introduced. Digital transformation and digital maturity, and after that, the previous models were investigated. And finally, a new model specific to digital banking in Iran.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124327054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-03DOI: 10.1109/CSICC52343.2021.9420601
F. Torgheh, M. Keyvanpour, B. Masoumi, S. V. Shojaedini
In the modern world, social media are extensively used for the purpose of communication, business and education. Although ease of use and simple accessibility to social media has expanded their applications, but unfortunately, they are associated with potential dangers which may negatively influence users. As main item, the publication of fake news can negatively affect various aspects of life (political, social, economic, etc.), therefore researchers have studied various methods to address the fake news detection. One way to check and detect fake news is to use the available features in news propagation path, news publisher and users. In this paper, an attempt has been made to investigate fake news detection based on these features and a proposed deep neural network model.
{"title":"A Novel Method for Detecting Fake news: Deep Learning Based on Propagation Path Concept","authors":"F. Torgheh, M. Keyvanpour, B. Masoumi, S. V. Shojaedini","doi":"10.1109/CSICC52343.2021.9420601","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420601","url":null,"abstract":"In the modern world, social media are extensively used for the purpose of communication, business and education. Although ease of use and simple accessibility to social media has expanded their applications, but unfortunately, they are associated with potential dangers which may negatively influence users. As main item, the publication of fake news can negatively affect various aspects of life (political, social, economic, etc.), therefore researchers have studied various methods to address the fake news detection. One way to check and detect fake news is to use the available features in news propagation path, news publisher and users. In this paper, an attempt has been made to investigate fake news detection based on these features and a proposed deep neural network model.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123676631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：