Pub Date : 2020-12-22DOI: 10.1109/IKT51791.2020.9345626
M. Dadfarnia, Ali Alemi Matinpour, M. Abdoos
In recent years, there is remarkable growing concern for marketing team to retain their customers. This can be achieved by predicting accurately ahead of time, whether a terminal for buying is valuable in the foreseeable future or not. This paper presents the application of Deep Neural Network in the issue of classifying the payment terminals in different branches of Parsian bank specifically. The paper uses real data for classifying various payment terminals in 6 classes of terminal by a 5 layer deep neural network and RFM model. The empirical results reveal that utilizing the deep network generate significantly better accuracy in comparison with other popular methods.
{"title":"Churn Prediction in Payment Terminals Using RFM model and Deep Neural Network","authors":"M. Dadfarnia, Ali Alemi Matinpour, M. Abdoos","doi":"10.1109/IKT51791.2020.9345626","DOIUrl":"https://doi.org/10.1109/IKT51791.2020.9345626","url":null,"abstract":"In recent years, there is remarkable growing concern for marketing team to retain their customers. This can be achieved by predicting accurately ahead of time, whether a terminal for buying is valuable in the foreseeable future or not. This paper presents the application of Deep Neural Network in the issue of classifying the payment terminals in different branches of Parsian bank specifically. The paper uses real data for classifying various payment terminals in 6 classes of terminal by a 5 layer deep neural network and RFM model. The empirical results reveal that utilizing the deep network generate significantly better accuracy in comparison with other popular methods.","PeriodicalId":382725,"journal":{"name":"2020 11th International Conference on Information and Knowledge Technology (IKT)","volume":"190 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124317932","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 : 2020-12-22DOI: 10.1109/IKT51791.2020.9345613
Omid Mohammadi Kia, Mahmood Neshati, M. S. Alamdari
Searching for new information requires talking to the system. In this research, an Open-domain Conversational information search system has been developed. This system has been implemented using the TREC CAsT 2019 track, which is one of the first attempts to build a framework in this area. According to the user's previous questions, the system firstly completes the question (using the first and the previous question in each turn) and then classifies it (based on the question words). This system extracts the related answers according to the rules of each question. In this research, a simple yet effective method with high performance has been used, which on average, extracts 20% more relevant results than the baseline.
{"title":"Open-Domain question classification and completion in conversational information search","authors":"Omid Mohammadi Kia, Mahmood Neshati, M. S. Alamdari","doi":"10.1109/IKT51791.2020.9345613","DOIUrl":"https://doi.org/10.1109/IKT51791.2020.9345613","url":null,"abstract":"Searching for new information requires talking to the system. In this research, an Open-domain Conversational information search system has been developed. This system has been implemented using the TREC CAsT 2019 track, which is one of the first attempts to build a framework in this area. According to the user's previous questions, the system firstly completes the question (using the first and the previous question in each turn) and then classifies it (based on the question words). This system extracts the related answers according to the rules of each question. In this research, a simple yet effective method with high performance has been used, which on average, extracts 20% more relevant results than the baseline.","PeriodicalId":382725,"journal":{"name":"2020 11th International Conference on Information and Knowledge Technology (IKT)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130823483","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 : 2020-12-22DOI: 10.1109/IKT51791.2020.9345638
Farhoud Jafari Kaleibar, M. Abbaspour
In recent years, the development of the Internet of things has also extended to transportation networks, affecting smart transportation networks. There are many vehicles in the city that do not use their resources (storage, processing and bandwidth) and therefore there is a good potential to use these resources as a cloud. However, the mobility of vehicles poses a challenge in providing and receiving services available in the cloud. On the other hand, service requests are not predictable and require the use of dynamic approaches for service provisioning. In this paper, we try to reduce the effect of these challenges by modeling the existing problem with the customized mathematical model of maximum coverage, and by using the approximate heuristic algorithm in this field. The simulation performed by the heuristic algorithm shows an improvement in terms of service delivery rate and resource efficiency compared to the random allocation mode.
{"title":"An approach to model the optimal service provisioning in vehicular cloud networks","authors":"Farhoud Jafari Kaleibar, M. Abbaspour","doi":"10.1109/IKT51791.2020.9345638","DOIUrl":"https://doi.org/10.1109/IKT51791.2020.9345638","url":null,"abstract":"In recent years, the development of the Internet of things has also extended to transportation networks, affecting smart transportation networks. There are many vehicles in the city that do not use their resources (storage, processing and bandwidth) and therefore there is a good potential to use these resources as a cloud. However, the mobility of vehicles poses a challenge in providing and receiving services available in the cloud. On the other hand, service requests are not predictable and require the use of dynamic approaches for service provisioning. In this paper, we try to reduce the effect of these challenges by modeling the existing problem with the customized mathematical model of maximum coverage, and by using the approximate heuristic algorithm in this field. The simulation performed by the heuristic algorithm shows an improvement in terms of service delivery rate and resource efficiency compared to the random allocation mode.","PeriodicalId":382725,"journal":{"name":"2020 11th International Conference on Information and Knowledge Technology (IKT)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133165084","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 : 2020-12-22DOI: 10.1109/IKT51791.2020.9345635
Armin Salimi-Badr, Mohammadreza Hashemi
In this paper, a neural approach based on using Long-Short Term Memory (LSTM) neural networks is proposed to diagnose patients suffering from PD. In this study, it is shown that the temporal patterns of the gait cycle are different for healthy persons and patients. Therefore, by using a recurrent structure like LSTM, able to analyze the dynamic nature of the gait cycle, the proposed method extracts the temporal patterns to diagnose patients from healthy persons. Utilized data to extract the temporal shapes of the gait cycle are based on changing vertical Ground Reaction Force (vGRF), measured by 16 sensors placed in the soles of shoes worn by each subject. To reduce the number of data dimensions, the sequences of corresponding sensors placed in different feet are combined by subtraction. This method analyzes the temporal pattern of time-series collected from different sensors, without extracting special features representing statistics of different parts of the gait cycle. Finally, by recording and presenting data from 10 seconds of subject walking, the proposed approach can diagnose the patient from healthy persons with an average accuracy of 97.66%, and the total F1 score equal to 97.78%.
{"title":"A Neural-Based Approach to Aid Early Parkinson's Disease Diagnosis","authors":"Armin Salimi-Badr, Mohammadreza Hashemi","doi":"10.1109/IKT51791.2020.9345635","DOIUrl":"https://doi.org/10.1109/IKT51791.2020.9345635","url":null,"abstract":"In this paper, a neural approach based on using Long-Short Term Memory (LSTM) neural networks is proposed to diagnose patients suffering from PD. In this study, it is shown that the temporal patterns of the gait cycle are different for healthy persons and patients. Therefore, by using a recurrent structure like LSTM, able to analyze the dynamic nature of the gait cycle, the proposed method extracts the temporal patterns to diagnose patients from healthy persons. Utilized data to extract the temporal shapes of the gait cycle are based on changing vertical Ground Reaction Force (vGRF), measured by 16 sensors placed in the soles of shoes worn by each subject. To reduce the number of data dimensions, the sequences of corresponding sensors placed in different feet are combined by subtraction. This method analyzes the temporal pattern of time-series collected from different sensors, without extracting special features representing statistics of different parts of the gait cycle. Finally, by recording and presenting data from 10 seconds of subject walking, the proposed approach can diagnose the patient from healthy persons with an average accuracy of 97.66%, and the total F1 score equal to 97.78%.","PeriodicalId":382725,"journal":{"name":"2020 11th International Conference on Information and Knowledge Technology (IKT)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124348325","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 : 2020-12-22DOI: 10.1109/IKT51791.2020.9345627
Zohre Nasiri Zarandi, I. Sharifi
Cyber-physical systems(cps) have made significant progress in many dynamic applications due to the integration between physical processes, computational resources, and communication capabilities. However, cyber-attacks are a major threat to these systems. Unlike faults that occurs by accidents cyber-physical systems, cyber-attacks occur intelligently and stealthy. Some of these attacks which are called deception attacks, inject false data from sensors or controllers, and also by compromising with some cyber components, corrupt data, or enter misinformation into the system. If the system is unaware of the existence of these attacks, it won't be able to detect them, and performance may be disrupted or disabled altogether. Therefore, it is necessary to adapt algorithms to identify these types of attacks in these systems. It should be noted that the data generated in these systems is produced in very large number, with so much variety, and high speed, so it is important to use machine learning algorithms to facilitate the analysis and evaluation of data and to identify hidden patterns. In this research, the CPS is modeled as a network of agents that move in union with each other, and one agent is considered as a leader, and the other agents are commanded by the leader. The proposed method in this study is to use the structure of deep neural networks for the detection phase, which should inform the system of the existence of the attack in the initial moments of the attack. The use of resilient control algorithms in the network to isolate the misbehave agent in the leader-follower mechanism has been investigated. In the presented control method, after the attack detection phase with the use of a deep neural network, the control system uses the reputation algorithm to isolate the misbehave agent. Experimental analysis shows us that deep learning algorithms can detect attacks with higher performance that usual methods and can make cyber security simpler, more proactive, less expensive and far more effective.
{"title":"Detection and Identification of Cyber-Attacks in Cyber-Physical Systems Based on Machine Learning Methods","authors":"Zohre Nasiri Zarandi, I. Sharifi","doi":"10.1109/IKT51791.2020.9345627","DOIUrl":"https://doi.org/10.1109/IKT51791.2020.9345627","url":null,"abstract":"Cyber-physical systems(cps) have made significant progress in many dynamic applications due to the integration between physical processes, computational resources, and communication capabilities. However, cyber-attacks are a major threat to these systems. Unlike faults that occurs by accidents cyber-physical systems, cyber-attacks occur intelligently and stealthy. Some of these attacks which are called deception attacks, inject false data from sensors or controllers, and also by compromising with some cyber components, corrupt data, or enter misinformation into the system. If the system is unaware of the existence of these attacks, it won't be able to detect them, and performance may be disrupted or disabled altogether. Therefore, it is necessary to adapt algorithms to identify these types of attacks in these systems. It should be noted that the data generated in these systems is produced in very large number, with so much variety, and high speed, so it is important to use machine learning algorithms to facilitate the analysis and evaluation of data and to identify hidden patterns. In this research, the CPS is modeled as a network of agents that move in union with each other, and one agent is considered as a leader, and the other agents are commanded by the leader. The proposed method in this study is to use the structure of deep neural networks for the detection phase, which should inform the system of the existence of the attack in the initial moments of the attack. The use of resilient control algorithms in the network to isolate the misbehave agent in the leader-follower mechanism has been investigated. In the presented control method, after the attack detection phase with the use of a deep neural network, the control system uses the reputation algorithm to isolate the misbehave agent. Experimental analysis shows us that deep learning algorithms can detect attacks with higher performance that usual methods and can make cyber security simpler, more proactive, less expensive and far more effective.","PeriodicalId":382725,"journal":{"name":"2020 11th International Conference on Information and Knowledge Technology (IKT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130001927","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 : 2020-12-22DOI: 10.1109/IKT51791.2020.9345611
Behzad Soleimani Neysiani, S. Doostali, S. M. Babamir, Zahra Aminoroaya
Duplicate bug report detection (DBRD) is a famous problem in software triage systems like Bugzilla. It is vital to update the internal machine learning (ML) models of DBRD for real-world usage and continuous query of new bug reports. The training phase of ML algorithms is time-consumable and dependent on the training dataset volume. Instance-based learning (IbL) is an ML technique that reduces the number of samples in the training dataset to achieve fast learning for the incremental database. This research introduces a hybrid approach using clustering and straight forward sampling to improve the runtime and validation performance of DBRD. Two bug report datasets of Android and Mozilla Firefox are used to evaluate the proposed approach. The experimental evaluation shows acceptable results and improvement in both runtime and validation performance of DBRD versus the traditional approach without IbL.
{"title":"Fast Duplicate Bug Reports Detector Training using Sampling for Dimension Reduction: Using Instance-based Learning for Continous Query in Real-World","authors":"Behzad Soleimani Neysiani, S. Doostali, S. M. Babamir, Zahra Aminoroaya","doi":"10.1109/IKT51791.2020.9345611","DOIUrl":"https://doi.org/10.1109/IKT51791.2020.9345611","url":null,"abstract":"Duplicate bug report detection (DBRD) is a famous problem in software triage systems like Bugzilla. It is vital to update the internal machine learning (ML) models of DBRD for real-world usage and continuous query of new bug reports. The training phase of ML algorithms is time-consumable and dependent on the training dataset volume. Instance-based learning (IbL) is an ML technique that reduces the number of samples in the training dataset to achieve fast learning for the incremental database. This research introduces a hybrid approach using clustering and straight forward sampling to improve the runtime and validation performance of DBRD. Two bug report datasets of Android and Mozilla Firefox are used to evaluate the proposed approach. The experimental evaluation shows acceptable results and improvement in both runtime and validation performance of DBRD versus the traditional approach without IbL.","PeriodicalId":382725,"journal":{"name":"2020 11th International Conference on Information and Knowledge Technology (IKT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127444887","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 : 2020-12-22DOI: 10.1109/IKT51791.2020.9345630
V. Dehnavi, M. Shafiee
In recent years, artificial intelligent has been widely used as expert systems. In this paper, an intelligent system is provided for determining the risk of cardiovascular diseases. At first, a neuro-fuzzy network is used for risk prediction which the input of this network includes patient's data such as blood pressure, blood sugar, heart rate, number of cigarettes per day, and age, and the output of this network indicates the risk of cardiovascular disease for patients over the next 10 years. In this article, by using genetic algorithm (GA), the features for determining the patient's condition were reduced from 16 to 6 and least-squares algorithm is used to determine the linear network's parameters and, the improved grasshopper optimization algorithm is used to optimize the nonlinear parameters of fuzzy sets. Finally, the proposed network and algorithm are validated by using patient's data which was obtained from patients in Framingham. The results show that the network and algorithm are acceptable.
{"title":"The risk prediction of heart disease by using neuro-fuzzy and improved GOA","authors":"V. Dehnavi, M. Shafiee","doi":"10.1109/IKT51791.2020.9345630","DOIUrl":"https://doi.org/10.1109/IKT51791.2020.9345630","url":null,"abstract":"In recent years, artificial intelligent has been widely used as expert systems. In this paper, an intelligent system is provided for determining the risk of cardiovascular diseases. At first, a neuro-fuzzy network is used for risk prediction which the input of this network includes patient's data such as blood pressure, blood sugar, heart rate, number of cigarettes per day, and age, and the output of this network indicates the risk of cardiovascular disease for patients over the next 10 years. In this article, by using genetic algorithm (GA), the features for determining the patient's condition were reduced from 16 to 6 and least-squares algorithm is used to determine the linear network's parameters and, the improved grasshopper optimization algorithm is used to optimize the nonlinear parameters of fuzzy sets. Finally, the proposed network and algorithm are validated by using patient's data which was obtained from patients in Framingham. The results show that the network and algorithm are acceptable.","PeriodicalId":382725,"journal":{"name":"2020 11th International Conference on Information and Knowledge Technology (IKT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116165949","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 : 2020-12-22DOI: 10.1109/IKT51791.2020.9345633
MohammadMohsen Jadidi, Pegah Moslemi, Saeed Jamshidiha, Iman Masroori, A. Mohammadi, V. Pourahmadi
Vaccination is an effective method for prevention of infectious diseases, but when the number of available vaccines is limited, it is not possible to vaccinate everyone in a society. In this paper, a two-step model is proposed to distribute a limited number of vaccines among the people of a society, in a way that would disrupt the transmission chain of the infectious disease most efficiently. In the first step, the vaccines are allocated to different communities in the society (e.g. cities in a country), and in the second step, the individuals whose vaccination removes the greatest number of transmission routes for the infection are identified in concordance with the regulations of international health organizations. In the second step, contact data is obtained from cellular networks and Bluetooth signals, and a graph-based modeling scheme is utilized in conjunction with a combined susceptibility metric specifically designed for selection of these individuals. The simulations indicate that a 30 % drop in infection rate compared to random vaccination could be achieved.
{"title":"Targeted Vaccination for COVID-19 Using Mobile Communication Networks","authors":"MohammadMohsen Jadidi, Pegah Moslemi, Saeed Jamshidiha, Iman Masroori, A. Mohammadi, V. Pourahmadi","doi":"10.1109/IKT51791.2020.9345633","DOIUrl":"https://doi.org/10.1109/IKT51791.2020.9345633","url":null,"abstract":"Vaccination is an effective method for prevention of infectious diseases, but when the number of available vaccines is limited, it is not possible to vaccinate everyone in a society. In this paper, a two-step model is proposed to distribute a limited number of vaccines among the people of a society, in a way that would disrupt the transmission chain of the infectious disease most efficiently. In the first step, the vaccines are allocated to different communities in the society (e.g. cities in a country), and in the second step, the individuals whose vaccination removes the greatest number of transmission routes for the infection are identified in concordance with the regulations of international health organizations. In the second step, contact data is obtained from cellular networks and Bluetooth signals, and a graph-based modeling scheme is utilized in conjunction with a combined susceptibility metric specifically designed for selection of these individuals. The simulations indicate that a 30 % drop in infection rate compared to random vaccination could be achieved.","PeriodicalId":382725,"journal":{"name":"2020 11th International Conference on Information and Knowledge Technology (IKT)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126674925","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 : 2020-12-22DOI: 10.1109/IKT51791.2020.9345636
Masoumeh Hashemi, Mehdi Sakhaei-nia, Morteza Yousef Sanati
AUTHaaS is a solution for various problems in an enterprise involving different software systems, each of which have a different authentication mechanism. Multiple usernames and passwords for a user, different security vulnerabilities for each software, and possible changes to the authentication mechanism are some of these problems. The solutions proposed for AUTHaaS are based on SOA. As communication in SOA is synchronous, the authentication process can confront problems if the authentication service is delayed for any reason. It is the purpose of this paper to answer these problems. In this paper, a security architecture is proposed for AUTHaaS through enterprise application integration. The core of the integration solution is the Enterprise Service Bus (ESB) technology. Proposed ESB-based architecture allows the user to authenticate only once for using different systems. Once the user is successfully authenticated for an application, other applications receive events through the ESB that indicate the user has successfully authenticated. So they do not need to be authenticated again by the authentication service for further access. The results show that after the 500th request, i.e. the second request of each user, the response time is reduced by 50% and the number of visits to the authentication server for subsequent requests of users will be zero.
{"title":"An ESB-based Architecture for Authentication as a Service Through Enterprise Application Integration","authors":"Masoumeh Hashemi, Mehdi Sakhaei-nia, Morteza Yousef Sanati","doi":"10.1109/IKT51791.2020.9345636","DOIUrl":"https://doi.org/10.1109/IKT51791.2020.9345636","url":null,"abstract":"AUTHaaS is a solution for various problems in an enterprise involving different software systems, each of which have a different authentication mechanism. Multiple usernames and passwords for a user, different security vulnerabilities for each software, and possible changes to the authentication mechanism are some of these problems. The solutions proposed for AUTHaaS are based on SOA. As communication in SOA is synchronous, the authentication process can confront problems if the authentication service is delayed for any reason. It is the purpose of this paper to answer these problems. In this paper, a security architecture is proposed for AUTHaaS through enterprise application integration. The core of the integration solution is the Enterprise Service Bus (ESB) technology. Proposed ESB-based architecture allows the user to authenticate only once for using different systems. Once the user is successfully authenticated for an application, other applications receive events through the ESB that indicate the user has successfully authenticated. So they do not need to be authenticated again by the authentication service for further access. The results show that after the 500th request, i.e. the second request of each user, the response time is reduced by 50% and the number of visits to the authentication server for subsequent requests of users will be zero.","PeriodicalId":382725,"journal":{"name":"2020 11th International Conference on Information and Knowledge Technology (IKT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133080270","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 : 2020-12-22DOI: 10.1109/IKT51791.2020.9345621
F. Ebadifard, S. M. Babamir, Fatemeh Labafiyan
The problem of task scheduling on VMs is selecting appropriate resources for a task so that its associated tasks have already been executed. Since the workflow contains a set of tasks, the likelihood of failure increases with the failure of a task throughout the workflow. The allocation of tasks on virtual machines with higher reliability improves workflow-scheduling efficiency. Therefore, Trust relationship is an important factor of resource allocation and job scheduling, and in this paper, we have presented a good method to estimate the trust of virtual machines on which the workflow is run. In addition to the trust, which is an important factor in the workflow scheduling, there are other criteria for the satisfaction of service providers and customers. By increasing the number of requests and the diversity of virtual machines as well as the contradiction between objectives, finding the optimal Pareto front is more challenging. Therefore, multi-objective evolutionary algorithms face a large space of permutations to find an optimal tradeoff of objectives. In this paper, we present a multi-objective workflow-scheduling algorithm using MVO algorithm with the aim of increasing diversity and convergence, so that the proposed method can consider QoS requirements for service providers and customers simultaneously.
{"title":"A Multi Objective & Trust-Based Workflow Scheduling Method in Cloud Computing based on the MVO Algorithm","authors":"F. Ebadifard, S. M. Babamir, Fatemeh Labafiyan","doi":"10.1109/IKT51791.2020.9345621","DOIUrl":"https://doi.org/10.1109/IKT51791.2020.9345621","url":null,"abstract":"The problem of task scheduling on VMs is selecting appropriate resources for a task so that its associated tasks have already been executed. Since the workflow contains a set of tasks, the likelihood of failure increases with the failure of a task throughout the workflow. The allocation of tasks on virtual machines with higher reliability improves workflow-scheduling efficiency. Therefore, Trust relationship is an important factor of resource allocation and job scheduling, and in this paper, we have presented a good method to estimate the trust of virtual machines on which the workflow is run. In addition to the trust, which is an important factor in the workflow scheduling, there are other criteria for the satisfaction of service providers and customers. By increasing the number of requests and the diversity of virtual machines as well as the contradiction between objectives, finding the optimal Pareto front is more challenging. Therefore, multi-objective evolutionary algorithms face a large space of permutations to find an optimal tradeoff of objectives. In this paper, we present a multi-objective workflow-scheduling algorithm using MVO algorithm with the aim of increasing diversity and convergence, so that the proposed method can consider QoS requirements for service providers and customers simultaneously.","PeriodicalId":382725,"journal":{"name":"2020 11th International Conference on Information and Knowledge Technology (IKT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130078295","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：