Pub Date : 2021-03-03DOI: 10.1109/CSICC52343.2021.9420562
Davod Karimpour, M. Z. Chahooki, Ali Hashemi
Over the past decade, social networks and messengers have found a special place in the creation and development of businesses. User recommendation is a very important feature in social networks that has attracted the attention of many users to these environments. Using this system in an instant messenger environment is very useful. Telegram is a cloud-based messenger with more than 400 million monthly active users. Telegram is used as a social network in Iran, but does not offer the most widely used features of social networks, such as recommending users. This feature is important for marketers to find target audience. This paper presents a hybrid filtering-based algorithm to recommend Telegram users. This method combines the membership graph of users with the profile of groups. The membership graph, models users based on their membership in groups. Also, the profile of each group includes the name and description of the group. We have created a bag of words for each group based on natural language processing methods to combine it with the membership graph. After combination process, users are recommended based on the list of groups obtained. The data used in this study is the information of more than 120 million users and 900,000 supergroups in Telegram. This data is obtained through Telegram API by Idekav system. The evaluation of the proposed method has been done separately on two categories of specialized supergroups. Each category includes 25 specialized supergroups in Telegram. Selected supergroups for evaluation have between 2,000 and 10,000 members. Experimental results show the integrity of the model and error reduction in RMSE.
{"title":"User recommendation based on Hybrid filtering in Telegram messenger","authors":"Davod Karimpour, M. Z. Chahooki, Ali Hashemi","doi":"10.1109/CSICC52343.2021.9420562","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420562","url":null,"abstract":"Over the past decade, social networks and messengers have found a special place in the creation and development of businesses. User recommendation is a very important feature in social networks that has attracted the attention of many users to these environments. Using this system in an instant messenger environment is very useful. Telegram is a cloud-based messenger with more than 400 million monthly active users. Telegram is used as a social network in Iran, but does not offer the most widely used features of social networks, such as recommending users. This feature is important for marketers to find target audience. This paper presents a hybrid filtering-based algorithm to recommend Telegram users. This method combines the membership graph of users with the profile of groups. The membership graph, models users based on their membership in groups. Also, the profile of each group includes the name and description of the group. We have created a bag of words for each group based on natural language processing methods to combine it with the membership graph. After combination process, users are recommended based on the list of groups obtained. The data used in this study is the information of more than 120 million users and 900,000 supergroups in Telegram. This data is obtained through Telegram API by Idekav system. The evaluation of the proposed method has been done separately on two categories of specialized supergroups. Each category includes 25 specialized supergroups in Telegram. Selected supergroups for evaluation have between 2,000 and 10,000 members. Experimental results show the integrity of the model and error reduction in RMSE.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"245 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":"127748794","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/CSICC52343.2021.9420604
Ali Beikmohammadi, N. Zahabi
Handwritten digit classification considers one of the crucial subjects in machine vision due to its numerous practical usages in many recognition systems. In this regard, Kannada-MNIST was introduced as a challenging dataset. On the other hand, deep neural networks, especially convolutional neural networks, give us an encouraging promise to solve such a problem. In this paper, as a result, we propose a new hierarchically combination method with the help of two CNN models designed from scratch. The results of this novel approach on the Kannada-MNIST dataset indicate its excellent performance because the accuracy on the training, validation, and test sets are 99.86%, 99.66%, and 99.80%, respectively. Fortunately, this proposed method has been able to overcome all the state-of-the-art solutions with the best performance on this dataset.
{"title":"A Hierarchical Method for Kannada-MNIST Classification Based on Convolutional Neural Networks","authors":"Ali Beikmohammadi, N. Zahabi","doi":"10.1109/CSICC52343.2021.9420604","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420604","url":null,"abstract":"Handwritten digit classification considers one of the crucial subjects in machine vision due to its numerous practical usages in many recognition systems. In this regard, Kannada-MNIST was introduced as a challenging dataset. On the other hand, deep neural networks, especially convolutional neural networks, give us an encouraging promise to solve such a problem. In this paper, as a result, we propose a new hierarchically combination method with the help of two CNN models designed from scratch. The results of this novel approach on the Kannada-MNIST dataset indicate its excellent performance because the accuracy on the training, validation, and test sets are 99.86%, 99.66%, and 99.80%, respectively. Fortunately, this proposed method has been able to overcome all the state-of-the-art solutions with the best performance on this dataset.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"68 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":"127458679","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/CSICC52343.2021.9420609
M. A. Nourian, A. Kusedghi, A. Akbari
Network slicing is a promising approach to meet the diverse requirements of the various use cases in the 5G networks. Hence, the mobile operators are moving forward to leveraging network slicing in order to measure up with the individual service expectations in their networks. Deploying different network slice types requires the global view of the network and the automated orchestration and management of the underlying resources. This is facilitated by utilizing software-defined networking and network function virtualization as the 5G key-enabler technologies. In this paper, we propose a practical network slicing resource management scheme which is comprised of a dynamic, priority-based resource allocation cooperating with an admission control unit. Adopting the proposed dynamic resource allocation would allow the admission control to comply with more NS requests while ensuring the desired requirements of the existing network slices. To validate the effectiveness of such a mechanism in a real environment, we take advantage of the features provided by OpenAirInterface and FlexRAN to efficiently manage multiple isolated network slices. In particular, we evaluate the significance of the network slicing, the isolation degree among created slices, and the effectiveness of the proposed scheme through several practical scenarios.
{"title":"A practical resource management prototype for mobile networks","authors":"M. A. Nourian, A. Kusedghi, A. Akbari","doi":"10.1109/CSICC52343.2021.9420609","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420609","url":null,"abstract":"Network slicing is a promising approach to meet the diverse requirements of the various use cases in the 5G networks. Hence, the mobile operators are moving forward to leveraging network slicing in order to measure up with the individual service expectations in their networks. Deploying different network slice types requires the global view of the network and the automated orchestration and management of the underlying resources. This is facilitated by utilizing software-defined networking and network function virtualization as the 5G key-enabler technologies. In this paper, we propose a practical network slicing resource management scheme which is comprised of a dynamic, priority-based resource allocation cooperating with an admission control unit. Adopting the proposed dynamic resource allocation would allow the admission control to comply with more NS requests while ensuring the desired requirements of the existing network slices. To validate the effectiveness of such a mechanism in a real environment, we take advantage of the features provided by OpenAirInterface and FlexRAN to efficiently manage multiple isolated network slices. In particular, we evaluate the significance of the network slicing, the isolation degree among created slices, and the effectiveness of the proposed scheme through several practical scenarios.","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":"132628987","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/CSICC52343.2021.9420541
Faeze Rasouli, M. Taheri
In this paper, a novel fragile watermarking scheme is proposed for both tamper detection and tampered image recovery based on Hamming code. To serve this purpose, the authentication code (check bits) is computed using Hamming code from data bits. In this work, data bits were selected from the five Most Significant Bits (5_MSB) of the pixel values and authentication code is embedded into the three Least Significant Bits (3LSBs) to preserve image quality. Hamming (7,4) has been extended, in this paper, to (8,5) and is used for embedding, error detection and correction. Each instance of coding is applied on eight pixels (one bit per pixel) located in sufficient far parts of the image. Hence, for tampers smaller than a threshold, the recovery can be done perfectly. According to the experimental results, the proposed method achieves better performance in terms of recovering the tampered areas, compared to state-of-the-art.
{"title":"A New Fragile Watermarking based on Distributed Hamming Code","authors":"Faeze Rasouli, M. Taheri","doi":"10.1109/CSICC52343.2021.9420541","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420541","url":null,"abstract":"In this paper, a novel fragile watermarking scheme is proposed for both tamper detection and tampered image recovery based on Hamming code. To serve this purpose, the authentication code (check bits) is computed using Hamming code from data bits. In this work, data bits were selected from the five Most Significant Bits (5_MSB) of the pixel values and authentication code is embedded into the three Least Significant Bits (3LSBs) to preserve image quality. Hamming (7,4) has been extended, in this paper, to (8,5) and is used for embedding, error detection and correction. Each instance of coding is applied on eight pixels (one bit per pixel) located in sufficient far parts of the image. Hence, for tampers smaller than a threshold, the recovery can be done perfectly. According to the experimental results, the proposed method achieves better performance in terms of recovering the tampered areas, compared to state-of-the-art.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"45 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":"128581674","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/CSICC52343.2021.9420625
M. D. Khomami, Alireza Rezvanian, A. Saghiri, M. Meybodi
The dominating set (DS) problem has noticed the selecting a subset of vertices that every vertex in the graph is either is adjacent to one or more nodes of this subset. The DS with the minimum cardinality is called MDS (minimum dominating set). The MDS problem has several applications in different domains, such as network monitoring, routing, epidemic control and social network. The MDS is known as the NP-Hard problem. Nevertheless, the existing research has focused on the MDS problem to single networks. However, in many real structures, there exist a complex structure involving a set of components combined up by different connections and known as multiplex networks. In this paper, we introduce a learning automaton (LA) based algorithm for find the MDS problem in multiplex networks. In the proposed algorithm, each node of the multiplex network is considered an LA with two actions of a candidate or non-candidate corresponding to the dominating set and non-dominating set. By selecting candidate DS and evaluation mechanisms, the algorithm tries to find a dominating set with the smallest cardinality and as the algorithm proceeds, a candidate solution converges to the optimal solution of the MDS of multiplex networks. With the aid of learning and the behavior of learning automata for finding solution, this algorithm which is present in this paper reduces the number of dominating set, in multiplex networks iteratively. Experimental results demonstrate that in many well-known datasets, the proposed algorithm is efficient with respect to the evaluation measure.
{"title":"Solving Minimum Dominating Set in Multiplex Networks Using Learning Automata","authors":"M. D. Khomami, Alireza Rezvanian, A. Saghiri, M. Meybodi","doi":"10.1109/CSICC52343.2021.9420625","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420625","url":null,"abstract":"The dominating set (DS) problem has noticed the selecting a subset of vertices that every vertex in the graph is either is adjacent to one or more nodes of this subset. The DS with the minimum cardinality is called MDS (minimum dominating set). The MDS problem has several applications in different domains, such as network monitoring, routing, epidemic control and social network. The MDS is known as the NP-Hard problem. Nevertheless, the existing research has focused on the MDS problem to single networks. However, in many real structures, there exist a complex structure involving a set of components combined up by different connections and known as multiplex networks. In this paper, we introduce a learning automaton (LA) based algorithm for find the MDS problem in multiplex networks. In the proposed algorithm, each node of the multiplex network is considered an LA with two actions of a candidate or non-candidate corresponding to the dominating set and non-dominating set. By selecting candidate DS and evaluation mechanisms, the algorithm tries to find a dominating set with the smallest cardinality and as the algorithm proceeds, a candidate solution converges to the optimal solution of the MDS of multiplex networks. With the aid of learning and the behavior of learning automata for finding solution, this algorithm which is present in this paper reduces the number of dominating set, in multiplex networks iteratively. Experimental results demonstrate that in many well-known datasets, the proposed algorithm is efficient with respect to the evaluation measure.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"38 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":"129052472","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/CSICC52343.2021.9420596
A. Foroutannia, Milad Shoryabi, Amirali Alizadeh Anaraki, A. Rowhanimanesh
Swarm robotics is an inspiration from nature and incorporates swarm intelligence to help collective robotics. This recent technology is usually characterized by a swarm of simple, low-cost, and small robots instead of a complicated and expensive robot. Designing optimal and reliable swarm intelligence algorithms require real-world test environments. As a practical solution, physical platforms can efficiently address this issue. In this paper, a programmable physical platform, called SIN, is introduced for swarm robotics. Different design parameters such as communication range, signaling pattern, types of sensors and actuators, cooperation rules, and degree of uncertainty and noise can be simply adjusted by user. The building blocks of each agent has been developed in a modular form to improve the hardware flexibility. To illustrate the efficiency of the proposed platform, a cooperative multi-robot target tracking problem is implemented on this platform as a case study, where the robots interact by artificial attraction-repulsion forces based on short-range and noisy optical communication. The results demonstrate how the details of swarm behaviors such as decentralized aggregation and collective target tracking can be successfully implemented on the proposed platform.
{"title":"SIN: A Programmable Platform for Swarm Robotics","authors":"A. Foroutannia, Milad Shoryabi, Amirali Alizadeh Anaraki, A. Rowhanimanesh","doi":"10.1109/CSICC52343.2021.9420596","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420596","url":null,"abstract":"Swarm robotics is an inspiration from nature and incorporates swarm intelligence to help collective robotics. This recent technology is usually characterized by a swarm of simple, low-cost, and small robots instead of a complicated and expensive robot. Designing optimal and reliable swarm intelligence algorithms require real-world test environments. As a practical solution, physical platforms can efficiently address this issue. In this paper, a programmable physical platform, called SIN, is introduced for swarm robotics. Different design parameters such as communication range, signaling pattern, types of sensors and actuators, cooperation rules, and degree of uncertainty and noise can be simply adjusted by user. The building blocks of each agent has been developed in a modular form to improve the hardware flexibility. To illustrate the efficiency of the proposed platform, a cooperative multi-robot target tracking problem is implemented on this platform as a case study, where the robots interact by artificial attraction-repulsion forces based on short-range and noisy optical communication. The results demonstrate how the details of swarm behaviors such as decentralized aggregation and collective target tracking can be successfully implemented on the proposed platform.","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":"125608252","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/CSICC52343.2021.9420598
M. Zaree, Mohsen Raji
Linear Feedback Shift Registers (LFSR) are extensively used in variety of applications such as Built-In-Self-Test circuits or Pseudo Random Number Generators. Hence, fault tolerant design of LFSR is essential for the applications with high reliability demands. Traditional fault tolerant LFSRs include large number of Single-Point-of-Failures (SPoFs) in which any fault results in the whole system failure. In this paper, a new fault tolerant architecture for LFSR (named as FT-LFSR) is proposed in which the number of SPoFs are significantly reduced compared to the previous ones. To this end, a modified version of Triple Modular Redundancy (TMR) empowered with some extra controlling units for identifying the operational module is used. In addition, a novel metric called Reliability-Area-Factor (RAF) is introduced to evaluate the efficacy of the redundancy-based fault tolerant techniques (such as FT-LFSR) in terms of number of SPoFs and the area overhead. Experimental results show that, the FT-LFSR is resilient to all single transient and permanent faults except in its limited SPoFs and many patterns of multiple faults.
{"title":"FT-LFSR: A Fault Tolerant Architecture for Linear Feedback Shift Registers","authors":"M. Zaree, Mohsen Raji","doi":"10.1109/CSICC52343.2021.9420598","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420598","url":null,"abstract":"Linear Feedback Shift Registers (LFSR) are extensively used in variety of applications such as Built-In-Self-Test circuits or Pseudo Random Number Generators. Hence, fault tolerant design of LFSR is essential for the applications with high reliability demands. Traditional fault tolerant LFSRs include large number of Single-Point-of-Failures (SPoFs) in which any fault results in the whole system failure. In this paper, a new fault tolerant architecture for LFSR (named as FT-LFSR) is proposed in which the number of SPoFs are significantly reduced compared to the previous ones. To this end, a modified version of Triple Modular Redundancy (TMR) empowered with some extra controlling units for identifying the operational module is used. In addition, a novel metric called Reliability-Area-Factor (RAF) is introduced to evaluate the efficacy of the redundancy-based fault tolerant techniques (such as FT-LFSR) in terms of number of SPoFs and the area overhead. Experimental results show that, the FT-LFSR is resilient to all single transient and permanent faults except in its limited SPoFs and many patterns of multiple faults.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"687 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":"123825532","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/CSICC52343.2021.9420612
M. Shabestari, A. Ahmadi
There exist a lot of data associated with psychology, nowadays. Using data mining science, the relation between different subjects including self-esteem, general health, depression, etc. can be detected. Self-esteem is considered a subject of great importance in psychology, since it is one of the most significant factors in favorable human growth which shows how one feels about his worthiness and self-confirmation. Depression is a psychic state which is identified by the person’s unhappiness over time. Mental health, which is a significant moderator in the process of stress, plays a vital role in mitigating stress, increasing health, and improving the quality of life in the society. In order that the level of self-esteem would be measured, special questionnaires are used. Proper and accurate analysis of the questionnaires is one of the challenges of psychology. Several efforts have been made to improve the quality of processing psychological data by using through artificial intelligence. In the present paper, the relation between self-esteem and general health has been analyzed using Coopersmith’s self-esteem questionnaire, Goldberg’s general health questionnaire, clustering algorithms, and semantic data mining techniques. The results have shown that low self-esteem has a weak relationship with three out of four general health subscales; however, there has been a strong relationship with three subscales in high self-esteem levels.
{"title":"Identifying the relationship between human self-esteem and general health using data mining","authors":"M. Shabestari, A. Ahmadi","doi":"10.1109/CSICC52343.2021.9420612","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420612","url":null,"abstract":"There exist a lot of data associated with psychology, nowadays. Using data mining science, the relation between different subjects including self-esteem, general health, depression, etc. can be detected. Self-esteem is considered a subject of great importance in psychology, since it is one of the most significant factors in favorable human growth which shows how one feels about his worthiness and self-confirmation. Depression is a psychic state which is identified by the person’s unhappiness over time. Mental health, which is a significant moderator in the process of stress, plays a vital role in mitigating stress, increasing health, and improving the quality of life in the society. In order that the level of self-esteem would be measured, special questionnaires are used. Proper and accurate analysis of the questionnaires is one of the challenges of psychology. Several efforts have been made to improve the quality of processing psychological data by using through artificial intelligence. In the present paper, the relation between self-esteem and general health has been analyzed using Coopersmith’s self-esteem questionnaire, Goldberg’s general health questionnaire, clustering algorithms, and semantic data mining techniques. The results have shown that low self-esteem has a weak relationship with three out of four general health subscales; however, there has been a strong relationship with three subscales in high self-esteem levels.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"126 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":"130871283","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/CSICC52343.2021.9420553
Fatemeh Rezaimehr, Chitra Dadkhah
Recommender systems help people in finding a particular item based on their preference from a wide range of products in online shopping rapidly. One of the most popular models of recommendation systems is the Collaborative Filtering Recommendation System (CFRS) that recommend the top-K items to active user based on peer grouping user ratings. The implementation of CFRS is easy and it can easily be attacked by fake users and affect the recommendation. Fake users create a fake profile to attack the RS and change the output of it. Different attack types with different features and attacking methods exist in which decrease the accuracy. It is important to detect fake users, remove their rating from rating matrix and recognize the items has been attacked. In the recent years, many algorithms have been proposed to detect the attackers but first, researchers have to inject the attack type into their dataset and then evaluate their proposed approach. The purpose of this article is to develop a tool to inject the different attack types to datasets. Proposed tool constructs a new dataset containing the fake users therefore researchers can use it for evaluating their proposed attack detection methods. Researchers could choose the attack type and the size of attack with a user interface of our proposed tool easily.
{"title":"Injection Shilling Attack Tool for Recommender Systems","authors":"Fatemeh Rezaimehr, Chitra Dadkhah","doi":"10.1109/CSICC52343.2021.9420553","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420553","url":null,"abstract":"Recommender systems help people in finding a particular item based on their preference from a wide range of products in online shopping rapidly. One of the most popular models of recommendation systems is the Collaborative Filtering Recommendation System (CFRS) that recommend the top-K items to active user based on peer grouping user ratings. The implementation of CFRS is easy and it can easily be attacked by fake users and affect the recommendation. Fake users create a fake profile to attack the RS and change the output of it. Different attack types with different features and attacking methods exist in which decrease the accuracy. It is important to detect fake users, remove their rating from rating matrix and recognize the items has been attacked. In the recent years, many algorithms have been proposed to detect the attackers but first, researchers have to inject the attack type into their dataset and then evaluate their proposed approach. The purpose of this article is to develop a tool to inject the different attack types to datasets. Proposed tool constructs a new dataset containing the fake users therefore researchers can use it for evaluating their proposed attack detection methods. Researchers could choose the attack type and the size of attack with a user interface of our proposed tool easily.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"444 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":"132348424","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/CSICC52343.2021.9420572
M. Mohammadi, R. Mokhtari
This paper proposes an equation based on a nonlinear filter for speckle noise removal by introducing a region indicator. The use of Gaussian convolution in the proposed region indicator makes the quality of the edges of the image better than other models. The proposed equation also removes noise well due to having a nonlinear filter while preserving important image details such as edges. Experimental results show that the proposed model can handle speckle noise removal quite well.
{"title":"A Model-Based on Filtration Technique for Speckle Noise Removal from Ultrasound Images","authors":"M. Mohammadi, R. Mokhtari","doi":"10.1109/CSICC52343.2021.9420572","DOIUrl":"https://doi.org/10.1109/CSICC52343.2021.9420572","url":null,"abstract":"This paper proposes an equation based on a nonlinear filter for speckle noise removal by introducing a region indicator. The use of Gaussian convolution in the proposed region indicator makes the quality of the edges of the image better than other models. The proposed equation also removes noise well due to having a nonlinear filter while preserving important image details such as edges. Experimental results show that the proposed model can handle speckle noise removal quite well.","PeriodicalId":374593,"journal":{"name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","volume":"36 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132791181","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：