Pub Date : 2017-04-19DOI: 10.1109/ICWR.2017.7959312
F. Azimzadeh, F. Biabani
The rapid growth of cloud services and the growing user demands on resources have led to the development and popularity of cloud networks. This environment gives users an impression of infinite resources so the resources can be used on demand. Cloud resource providers wish to gain the most efficiency from its own resources. Their main objective is to reduce cost and maximize revenue from providing services for users. Users also desire to minimize their costs and achieve their required efficiency. Proper use of resources in the cloud is a challenge; therefore proper task scheduling is an important issue while responding to the requests in the shortest time requires proper resource management, which enables the handling of many requests with the number of sources identified. Time reduction is one of the main concerns of cloud resource providers, on the other hand, increased reliability leads to more confidence for the users. Time and reliability are two conflicting objectives, thus resource allocation methods with multi-objective optimization that simultaneously consider multiple conflicting objectives are put in use. In this study, the method presented for resource management and task assignment in cloud environment accounts for the optimized state of both time reduction and reliability enhancement for the system.
{"title":"Multi-objective job scheduling algorithm in cloud computing based on reliability and time","authors":"F. Azimzadeh, F. Biabani","doi":"10.1109/ICWR.2017.7959312","DOIUrl":"https://doi.org/10.1109/ICWR.2017.7959312","url":null,"abstract":"The rapid growth of cloud services and the growing user demands on resources have led to the development and popularity of cloud networks. This environment gives users an impression of infinite resources so the resources can be used on demand. Cloud resource providers wish to gain the most efficiency from its own resources. Their main objective is to reduce cost and maximize revenue from providing services for users. Users also desire to minimize their costs and achieve their required efficiency. Proper use of resources in the cloud is a challenge; therefore proper task scheduling is an important issue while responding to the requests in the shortest time requires proper resource management, which enables the handling of many requests with the number of sources identified. Time reduction is one of the main concerns of cloud resource providers, on the other hand, increased reliability leads to more confidence for the users. Time and reliability are two conflicting objectives, thus resource allocation methods with multi-objective optimization that simultaneously consider multiple conflicting objectives are put in use. In this study, the method presented for resource management and task assignment in cloud environment accounts for the optimized state of both time reduction and reliability enhancement for the system.","PeriodicalId":304897,"journal":{"name":"2017 3th International Conference on Web Research (ICWR)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133132083","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 : 2017-04-19DOI: 10.1109/ICWR.2017.7959314
Zeinab Borhanifard, B. Minaei-Bidgoli
With the rapid growth of the internet and the spread of the information contained therein, the volume of information available on the web is more than the ability of users to manage, capture and keep the information up to date. One solution to this problem are personalization and recommender systems. Recommender systems use the comments of the group of users so that, to help people in that group more effectively to identify their favorite items from a huge set of choices. In recent years, the web has seen very strong growth in the use of blogs. Considering the high volume of information in blogs, bloggers are in trouble to find the desired information and find blogs with similar thoughts and desires. Therefore, considering the mass of information for the blogs, a blog recommender system seems to be necessary. In this paper, by combining different methods of clustering and collaborative filtering, personalized recommender system for Persian blogs is suggested.
{"title":"Recommender system for Persian blogs","authors":"Zeinab Borhanifard, B. Minaei-Bidgoli","doi":"10.1109/ICWR.2017.7959314","DOIUrl":"https://doi.org/10.1109/ICWR.2017.7959314","url":null,"abstract":"With the rapid growth of the internet and the spread of the information contained therein, the volume of information available on the web is more than the ability of users to manage, capture and keep the information up to date. One solution to this problem are personalization and recommender systems. Recommender systems use the comments of the group of users so that, to help people in that group more effectively to identify their favorite items from a huge set of choices. In recent years, the web has seen very strong growth in the use of blogs. Considering the high volume of information in blogs, bloggers are in trouble to find the desired information and find blogs with similar thoughts and desires. Therefore, considering the mass of information for the blogs, a blog recommender system seems to be necessary. In this paper, by combining different methods of clustering and collaborative filtering, personalized recommender system for Persian blogs is suggested.","PeriodicalId":304897,"journal":{"name":"2017 3th International Conference on Web Research (ICWR)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132119535","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 : 2017-04-01DOI: 10.1109/ICWR.2017.7959320
Neda Mohammadian, Fakhroddin Noorbehbahani
Despite the increasing use of internet by Iranians, the bounce rates of the e-commerce websites are still high. This is because the e-commerce institutions are not familiar with designing websites based on their own target market preferences. So the purpose of this paper is to identify and to evaluate the effective visual factors for attracting online users. This study has been conducted by an attitude assessment through an online user questionnaire to collect demographic data that influence the user's color preferences and interests. Next, statistical analysis was done through a variety of tests including T-Test, ANOVA-Test and Duncan-Test. These tests are employed to find the relationship between user's demographic features and his/her preferred color on websites. The results of this study can be useful to personalize the websites exploiting the extracted rules of colors.
{"title":"Analyzing users' preferred color on websites based on demographic features","authors":"Neda Mohammadian, Fakhroddin Noorbehbahani","doi":"10.1109/ICWR.2017.7959320","DOIUrl":"https://doi.org/10.1109/ICWR.2017.7959320","url":null,"abstract":"Despite the increasing use of internet by Iranians, the bounce rates of the e-commerce websites are still high. This is because the e-commerce institutions are not familiar with designing websites based on their own target market preferences. So the purpose of this paper is to identify and to evaluate the effective visual factors for attracting online users. This study has been conducted by an attitude assessment through an online user questionnaire to collect demographic data that influence the user's color preferences and interests. Next, statistical analysis was done through a variety of tests including T-Test, ANOVA-Test and Duncan-Test. These tests are employed to find the relationship between user's demographic features and his/her preferred color on websites. The results of this study can be useful to personalize the websites exploiting the extracted rules of colors.","PeriodicalId":304897,"journal":{"name":"2017 3th International Conference on Web Research (ICWR)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123061283","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 : 2017-04-01DOI: 10.1109/ICWR.2017.7959311
Farzaneh Shoeleh, M. Zahedi, M. Farhoodi
Since the use of internet has incredibly increased, it becomes an important source of knowledge about anything for everyone. Therefore, the role of search engine as an effective approach to find information is critical for internet's users. The study of search engine users' behavior has attracted considerable research attention. These studies are helpful in developing more effective search engine and are useful in three points of view: for users at the personal level, for search engine vendors at the business level, and for government and marketing at social society level. These kinds of studies can be done through analyzing the log file of search engine wherein the interactions between search engine and the users are captured. In this paper, we aim to present analyses on the query log of a well-known and most used Persian search engine. Our analyses are presented in three main categories: 1) Stats-based analyses, 2) Temporal- based analyses, and 3) Topic-based analyses. The obtained results are promising. Mobile users often posted queries in weekends, whereas Web users utilize the search engine in workweeks. The majority of queries posted form most-populated cities. Additionally, Iranians are mostly interested in political, social, and economical topics.
{"title":"Search engine pictures: Empirical analysis of a web search engine query log","authors":"Farzaneh Shoeleh, M. Zahedi, M. Farhoodi","doi":"10.1109/ICWR.2017.7959311","DOIUrl":"https://doi.org/10.1109/ICWR.2017.7959311","url":null,"abstract":"Since the use of internet has incredibly increased, it becomes an important source of knowledge about anything for everyone. Therefore, the role of search engine as an effective approach to find information is critical for internet's users. The study of search engine users' behavior has attracted considerable research attention. These studies are helpful in developing more effective search engine and are useful in three points of view: for users at the personal level, for search engine vendors at the business level, and for government and marketing at social society level. These kinds of studies can be done through analyzing the log file of search engine wherein the interactions between search engine and the users are captured. In this paper, we aim to present analyses on the query log of a well-known and most used Persian search engine. Our analyses are presented in three main categories: 1) Stats-based analyses, 2) Temporal- based analyses, and 3) Topic-based analyses. The obtained results are promising. Mobile users often posted queries in weekends, whereas Web users utilize the search engine in workweeks. The majority of queries posted form most-populated cities. Additionally, Iranians are mostly interested in political, social, and economical topics.","PeriodicalId":304897,"journal":{"name":"2017 3th International Conference on Web Research (ICWR)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127970328","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}
Although recent studies have provided a framework for determining factors contributing online retailers' success, they have not been successful in recognizing that customer decision-making process is mostly influenced by internal factors of the websites (e.g. navigation, color and graphics). Although website quality is important, it provides only a subset of the evaluation criteria for service provider. Other features of online retailers can play important roles in influencing customer's response. This study considers external (i.e. reputation) and internal factors (i.e. quality of the website) as factors affecting the customer's opinion about the website of companies offering broadband services in Iran. Structural Equation Modeling (SEM) has been used for data analysis. The findings show that security and confidentiality of data have a significant and positive impact on reputation. Moreover, web design and customer services have a significant positive effect on positive emotions of the customers. In addition, we found that security and confidentiality of data have a significant positive effect on perceived risk, and positive emotions have a significant positive effect on purchase intention. Finally, perceived risk has a positive impact on negative emotions.
{"title":"Sustainable Internet service provider selection: Affected by internal and external factors (quality and reputation)","authors":"Nastaran Hajiheydari, Babak Hazaveh Hesar Maskan, Mahdi Ashkani","doi":"10.1109/ICWR.2017.7959323","DOIUrl":"https://doi.org/10.1109/ICWR.2017.7959323","url":null,"abstract":"Although recent studies have provided a framework for determining factors contributing online retailers' success, they have not been successful in recognizing that customer decision-making process is mostly influenced by internal factors of the websites (e.g. navigation, color and graphics). Although website quality is important, it provides only a subset of the evaluation criteria for service provider. Other features of online retailers can play important roles in influencing customer's response. This study considers external (i.e. reputation) and internal factors (i.e. quality of the website) as factors affecting the customer's opinion about the website of companies offering broadband services in Iran. Structural Equation Modeling (SEM) has been used for data analysis. The findings show that security and confidentiality of data have a significant and positive impact on reputation. Moreover, web design and customer services have a significant positive effect on positive emotions of the customers. In addition, we found that security and confidentiality of data have a significant positive effect on perceived risk, and positive emotions have a significant positive effect on purchase intention. Finally, perceived risk has a positive impact on negative emotions.","PeriodicalId":304897,"journal":{"name":"2017 3th International Conference on Web Research (ICWR)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133281207","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 : 2017-04-01DOI: 10.1109/ICWR.2017.7959324
Parisa Alaei, Fakhroddin Noorbehbahani
With the proliferation of the internet and increased global access to online media, cybercrime is also occurring at an increasing rate. Currently, both personal users and companies are vulnerable to cybercrime. A number of tools including firewalls and Intrusion Detection Systems (IDS) can be used as defense mechanisms. A firewall acts as a checkpoint which allows packets to pass through according to predetermined conditions. In extreme cases, it may even disconnect all network traffic. An IDS, on the other hand, automates the monitoring process in computer networks. The streaming nature of data in computer networks poses a significant challenge in building IDS. In this paper, a method is proposed to overcome this problem by performing online classification on datasets. In doing so, an incremental naive Bayesian classifier is employed. Furthermore, active learning enables solving the problem using a small set of labeled data points which are often very expensive to acquire. The proposed method includes two groups of actions i.e. offline and online. The former involves data preprocessing while the latter introduces the NADAL online method. The proposed method is compared to the incremental naive Bayesian classifier using the NSL-KDD standard dataset. There are three advantages with the proposed method: (1) overcoming the streaming data challenge; (2) reducing the high cost associated with instance labeling; and (3) improved accuracy and Kappa compared to the incremental naive Bayesian approach. Thus, the method is well-suited to IDS applications.
{"title":"Incremental anomaly-based intrusion detection system using limited labeled data","authors":"Parisa Alaei, Fakhroddin Noorbehbahani","doi":"10.1109/ICWR.2017.7959324","DOIUrl":"https://doi.org/10.1109/ICWR.2017.7959324","url":null,"abstract":"With the proliferation of the internet and increased global access to online media, cybercrime is also occurring at an increasing rate. Currently, both personal users and companies are vulnerable to cybercrime. A number of tools including firewalls and Intrusion Detection Systems (IDS) can be used as defense mechanisms. A firewall acts as a checkpoint which allows packets to pass through according to predetermined conditions. In extreme cases, it may even disconnect all network traffic. An IDS, on the other hand, automates the monitoring process in computer networks. The streaming nature of data in computer networks poses a significant challenge in building IDS. In this paper, a method is proposed to overcome this problem by performing online classification on datasets. In doing so, an incremental naive Bayesian classifier is employed. Furthermore, active learning enables solving the problem using a small set of labeled data points which are often very expensive to acquire. The proposed method includes two groups of actions i.e. offline and online. The former involves data preprocessing while the latter introduces the NADAL online method. The proposed method is compared to the incremental naive Bayesian classifier using the NSL-KDD standard dataset. There are three advantages with the proposed method: (1) overcoming the streaming data challenge; (2) reducing the high cost associated with instance labeling; and (3) improved accuracy and Kappa compared to the incremental naive Bayesian approach. Thus, the method is well-suited to IDS applications.","PeriodicalId":304897,"journal":{"name":"2017 3th International Conference on Web Research (ICWR)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124129928","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 : 2017-04-01DOI: 10.1109/ICWR.2017.7959322
S. H. Jafarpour, A. Mahmoudabadi, Azam Andalib
The emergence of electronic commerce led to a situation that many companies tend to take advantage of this space, but the main problem with this type of business is to retain customers and build loyalty in them. Ease of access to other companies in case of dissatisfaction allows customers to quickly refer to other competing companies. Therefore, customer satisfaction is very important. Considering the importance of customer loyalty in this business, in this study the impacts of some affecting factors in electronic loyalty was investigated. This study is using the samples of 378 people obtained from Cochran formula that have been selected from one of the neighborhoods of Tehran called Narmak with a population of 25,000 people and they all had the experience of online shopping. In this study, SPSS software and multivariate regression analysis were used for data analysis. The result of this study showed that the quality of services, website quality, infrastructure and electronic shopping experience in the order of priority has an impact on electronic loyalty. It is worth mentioning that considering the survey results of this research they can be used for obtaining customer satisfaction in e-commerce.
{"title":"The impact of quality of service, website, shopping experience and infrastructure on online customers' loyalty","authors":"S. H. Jafarpour, A. Mahmoudabadi, Azam Andalib","doi":"10.1109/ICWR.2017.7959322","DOIUrl":"https://doi.org/10.1109/ICWR.2017.7959322","url":null,"abstract":"The emergence of electronic commerce led to a situation that many companies tend to take advantage of this space, but the main problem with this type of business is to retain customers and build loyalty in them. Ease of access to other companies in case of dissatisfaction allows customers to quickly refer to other competing companies. Therefore, customer satisfaction is very important. Considering the importance of customer loyalty in this business, in this study the impacts of some affecting factors in electronic loyalty was investigated. This study is using the samples of 378 people obtained from Cochran formula that have been selected from one of the neighborhoods of Tehran called Narmak with a population of 25,000 people and they all had the experience of online shopping. In this study, SPSS software and multivariate regression analysis were used for data analysis. The result of this study showed that the quality of services, website quality, infrastructure and electronic shopping experience in the order of priority has an impact on electronic loyalty. It is worth mentioning that considering the survey results of this research they can be used for obtaining customer satisfaction in e-commerce.","PeriodicalId":304897,"journal":{"name":"2017 3th International Conference on Web Research (ICWR)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121168555","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 : 2017-04-01DOI: 10.1109/ICWR.2017.7959310
M. Zahedi, Behrooz Mansouri, Shiva Moradkhani, M. Farhoodi, F. Oroumchian
In this paper we investigate a Persian search engine log and present a comprehensive analysis of question queries in three levels: structure, click and topic. By analyzing question queries characteristics, we explore behavior of Persian language users. Our experimental results show that question queries length are larger than normal queries. Most of these queries contained question words "How" and "What" and their topics were mainly about health, policy, religion and society.
{"title":"How questions are posed to a search engine? An empiricial analysis of question queries in a large scale Persian search engine log","authors":"M. Zahedi, Behrooz Mansouri, Shiva Moradkhani, M. Farhoodi, F. Oroumchian","doi":"10.1109/ICWR.2017.7959310","DOIUrl":"https://doi.org/10.1109/ICWR.2017.7959310","url":null,"abstract":"In this paper we investigate a Persian search engine log and present a comprehensive analysis of question queries in three levels: structure, click and topic. By analyzing question queries characteristics, we explore behavior of Persian language users. Our experimental results show that question queries length are larger than normal queries. Most of these queries contained question words \"How\" and \"What\" and their topics were mainly about health, policy, religion and society.","PeriodicalId":304897,"journal":{"name":"2017 3th International Conference on Web Research (ICWR)","volume":"11 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113957643","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 : 2017-04-01DOI: 10.1109/ICWR.2017.7959298
Mohsen Arab, M. Hasheminezhad
The discovery and analysis of community structures in networks is very helpful in many fields. Despite existing some well-known quality metrics for detecting and evaluating communities, each of them has its own limitations. In this paper we will discuss deeply these limitations for community detection and evaluation based on the definitions and formulations of these quality metrics.
{"title":"Limitations of quality metrics for community detection and evaluation","authors":"Mohsen Arab, M. Hasheminezhad","doi":"10.1109/ICWR.2017.7959298","DOIUrl":"https://doi.org/10.1109/ICWR.2017.7959298","url":null,"abstract":"The discovery and analysis of community structures in networks is very helpful in many fields. Despite existing some well-known quality metrics for detecting and evaluating communities, each of them has its own limitations. In this paper we will discuss deeply these limitations for community detection and evaluation based on the definitions and formulations of these quality metrics.","PeriodicalId":304897,"journal":{"name":"2017 3th International Conference on Web Research (ICWR)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127489903","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 : 2017-04-01DOI: 10.1109/ICWR.2017.7959309
M. Zavvar, Shole Garavand, Esmaeel Sabbagh, Meysam Rezaei, H. Khalili, M. Zavvar, H. Motameni
Web service combination is an important task performed in different phases of the service-oriented architecture lifecycle. Measuring service quality based on the non-functional characteristics is an exceedingly difficult task. Therefore, this paper presents a Multilayer Perceptron Artificial Neural Network (MLPANN) to provide a method for measuring quality of service in a service-oriented architecture. To improve network performance, Particle Swarm Optimization (PSO) is used to optimize the weights of the network. Finally, our results are compared to those of a combination of Different Evolution (DE) algorithm and MLPANN in terms of Mean Square Error (MSE), Root Mean Square Error (RMSE) and Standard Deviation (STD). The results demonstrate the superiority of the proposed method.
{"title":"Measuring service quality in service-oriented architectures using a hybrid particle swarm optimization algorithm and artificial neural network (PSO-ANN)","authors":"M. Zavvar, Shole Garavand, Esmaeel Sabbagh, Meysam Rezaei, H. Khalili, M. Zavvar, H. Motameni","doi":"10.1109/ICWR.2017.7959309","DOIUrl":"https://doi.org/10.1109/ICWR.2017.7959309","url":null,"abstract":"Web service combination is an important task performed in different phases of the service-oriented architecture lifecycle. Measuring service quality based on the non-functional characteristics is an exceedingly difficult task. Therefore, this paper presents a Multilayer Perceptron Artificial Neural Network (MLPANN) to provide a method for measuring quality of service in a service-oriented architecture. To improve network performance, Particle Swarm Optimization (PSO) is used to optimize the weights of the network. Finally, our results are compared to those of a combination of Different Evolution (DE) algorithm and MLPANN in terms of Mean Square Error (MSE), Root Mean Square Error (RMSE) and Standard Deviation (STD). The results demonstrate the superiority of the proposed method.","PeriodicalId":304897,"journal":{"name":"2017 3th International Conference on Web Research (ICWR)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126597059","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：