Pub Date : 2016-09-07DOI: 10.1109/IKT.2016.7777781
Marzieh Raoufnezhad, M. Kahani, Yaghoob Maharati
As the number of researcher increases, the amount of information related to research activities grows rapidly. As a result, the management of this information for better retrieval and analysis has become an important issue. Many data models abroad and within Iran have been developed to address this issue. In this paper, after comparing some of these models, a new ontology based data model is proposed. The evaluation results show that the proposed method increases the performance and the organization of research information management compared to the existing methods.
{"title":"An ontology based data model for Iranian research information","authors":"Marzieh Raoufnezhad, M. Kahani, Yaghoob Maharati","doi":"10.1109/IKT.2016.7777781","DOIUrl":"https://doi.org/10.1109/IKT.2016.7777781","url":null,"abstract":"As the number of researcher increases, the amount of information related to research activities grows rapidly. As a result, the management of this information for better retrieval and analysis has become an important issue. Many data models abroad and within Iran have been developed to address this issue. In this paper, after comparing some of these models, a new ontology based data model is proposed. The evaluation results show that the proposed method increases the performance and the organization of research information management compared to the existing methods.","PeriodicalId":205496,"journal":{"name":"2016 Eighth International Conference on Information and Knowledge Technology (IKT)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131258319","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 : 2016-09-01DOI: 10.1109/IKT.2016.7777785
Mostafa Mohammadpour, M. Ghorbanian, S. Mozaffari
An improved AdaBoost algorithm based on optimizing search in sample space is presented. Working with data in large scale need more time to compare samples for finding a threshold in the AdaBoost algorithm when using decision stump as a weak classifier. We used PSO algorithm to evolve and select best feature in sample space for a weak classifier to reduce time. The experiment results show that with applying PSO to the decision stump, time consuming of the AdaBoost algorithm has been improved than base Adaboost. As a result, using evolutionary algorithms in such problems which have large scale, can reduce searching time for finding best solution and increase performance of algorithms in hand.
{"title":"AdaBoost performance improvement using PSO algorithm","authors":"Mostafa Mohammadpour, M. Ghorbanian, S. Mozaffari","doi":"10.1109/IKT.2016.7777785","DOIUrl":"https://doi.org/10.1109/IKT.2016.7777785","url":null,"abstract":"An improved AdaBoost algorithm based on optimizing search in sample space is presented. Working with data in large scale need more time to compare samples for finding a threshold in the AdaBoost algorithm when using decision stump as a weak classifier. We used PSO algorithm to evolve and select best feature in sample space for a weak classifier to reduce time. The experiment results show that with applying PSO to the decision stump, time consuming of the AdaBoost algorithm has been improved than base Adaboost. As a result, using evolutionary algorithms in such problems which have large scale, can reduce searching time for finding best solution and increase performance of algorithms in hand.","PeriodicalId":205496,"journal":{"name":"2016 Eighth International Conference on Information and Knowledge Technology (IKT)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115629620","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 : 2016-09-01DOI: 10.1109/IKT.2016.7777791
Ahmad Taghinezhad, S. Pashazadeh
Consistency is one of the key challenges in replicated distributed systems (DSs). Data centric and client centric are two main categories of consistency models. Monotonic read (MR) is one of the client centric consistency models that guarantees consistency from view point of a single client in terms of access to replicated data store. This consistency model guarantees that when a process reads a value of data item, it never sees a value older than the one it saw in previous read. Petri net is one of the formal methods to analyze behavioral properties of concurrent systems. In this paper a novel model of MR consistency DS and its analysis using coloured Petri nets is introduced. This model enables us to study that a given history is valid history for MR consistent DS or not. Proposed model using developed functions that are used for model checking can prove this and present a scenario that MR consistent DS can produce given history. By analysis of SSG of model we can prove that proposed model do not have true deadlocks and therefore proposed model is correct.
{"title":"Modelling and analysis of the monotonic read consistent distributed system using coloured Petri net","authors":"Ahmad Taghinezhad, S. Pashazadeh","doi":"10.1109/IKT.2016.7777791","DOIUrl":"https://doi.org/10.1109/IKT.2016.7777791","url":null,"abstract":"Consistency is one of the key challenges in replicated distributed systems (DSs). Data centric and client centric are two main categories of consistency models. Monotonic read (MR) is one of the client centric consistency models that guarantees consistency from view point of a single client in terms of access to replicated data store. This consistency model guarantees that when a process reads a value of data item, it never sees a value older than the one it saw in previous read. Petri net is one of the formal methods to analyze behavioral properties of concurrent systems. In this paper a novel model of MR consistency DS and its analysis using coloured Petri nets is introduced. This model enables us to study that a given history is valid history for MR consistent DS or not. Proposed model using developed functions that are used for model checking can prove this and present a scenario that MR consistent DS can produce given history. By analysis of SSG of model we can prove that proposed model do not have true deadlocks and therefore proposed model is correct.","PeriodicalId":205496,"journal":{"name":"2016 Eighth International Conference on Information and Knowledge Technology (IKT)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124406309","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 : 2016-09-01DOI: 10.1109/IKT.2016.7777784
Mahboobeh Soleimanpour, Ali K. Hamze
The study of embedded structure of communities in social and information networks is an extensive studies in this domain and vast variety of community detection methods have been proposed. In this paper we proposed a distributed approach for local and overlapping community detection based on the game theory. In our method, each node is a player and there is an iterative cycle in which players can play their best action from a given set of actions periodically in their turn. Each player decides to become member of a community which has the best influence on it in order to maximize its utility function. According to players' decisions communities will be formed gradually. Therefore, when the game process reaches the Nash equilibrium, the community emerges. We evaluate our method on some common datasets to indicate the performance and sufficiency of it.
{"title":"A game-theoretic approach for locally detecting overlapping communities in social networks","authors":"Mahboobeh Soleimanpour, Ali K. Hamze","doi":"10.1109/IKT.2016.7777784","DOIUrl":"https://doi.org/10.1109/IKT.2016.7777784","url":null,"abstract":"The study of embedded structure of communities in social and information networks is an extensive studies in this domain and vast variety of community detection methods have been proposed. In this paper we proposed a distributed approach for local and overlapping community detection based on the game theory. In our method, each node is a player and there is an iterative cycle in which players can play their best action from a given set of actions periodically in their turn. Each player decides to become member of a community which has the best influence on it in order to maximize its utility function. According to players' decisions communities will be formed gradually. Therefore, when the game process reaches the Nash equilibrium, the community emerges. We evaluate our method on some common datasets to indicate the performance and sufficiency of it.","PeriodicalId":205496,"journal":{"name":"2016 Eighth International Conference on Information and Knowledge Technology (IKT)","volume":"274 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124422898","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 : 2016-09-01DOI: 10.1109/IKT.2016.7777769
Mohsen Gorzin, F. Parand, Mahsa Hosseinpoorpia, Seyed Ashkan Madine
Recommender Systems (RS) are turned into remarkable tools in electronics commerce (e-commerce) in a way that they effectively find items which are suitable for user's interests. Techniques such as collaborative filtering and content-based filtering are designed for RS. One of the novel methods to recommend appropriate items is using the Ordered Weighted Averaging (OWA) operators to fuzzify the output of RS [1]. OWA is one of the decision-making methods capable of considering the priorities and mental evaluations of a decision-maker. Furthermore it has the ability to assess the measure of orness and include the computation in final decision. This article aims at presenting methods that have been proposed to combine RS and OWA operators and also at proposing the implementation and development of these two methods in future.
{"title":"A survey on ordered weighted averaging operators and their application in recommender systems","authors":"Mohsen Gorzin, F. Parand, Mahsa Hosseinpoorpia, Seyed Ashkan Madine","doi":"10.1109/IKT.2016.7777769","DOIUrl":"https://doi.org/10.1109/IKT.2016.7777769","url":null,"abstract":"Recommender Systems (RS) are turned into remarkable tools in electronics commerce (e-commerce) in a way that they effectively find items which are suitable for user's interests. Techniques such as collaborative filtering and content-based filtering are designed for RS. One of the novel methods to recommend appropriate items is using the Ordered Weighted Averaging (OWA) operators to fuzzify the output of RS [1]. OWA is one of the decision-making methods capable of considering the priorities and mental evaluations of a decision-maker. Furthermore it has the ability to assess the measure of orness and include the computation in final decision. This article aims at presenting methods that have been proposed to combine RS and OWA operators and also at proposing the implementation and development of these two methods in future.","PeriodicalId":205496,"journal":{"name":"2016 Eighth International Conference on Information and Knowledge Technology (IKT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129460193","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 : 2016-09-01DOI: 10.1109/IKT.2016.7777786
Farhad Mohamad Kazemi, W. Banzhaf, Minglun Gong
Human recognition through walking styles is among the newest of biometric methods. By using this biometric, individuals can be identified, distantly, even at low visibility. Our aim is to provide such ability for a computer system. In other words, we intend to extract appropriate features through processing video images that can reflect individuals' identity. In order to set up such a system, we have used Fourier, Wavelet, and Multi-wavelet transforms. Using images from the USF dataset version 1.7, the results obtained indicate that SA4 Multi-wavelet transforms prove more efficient in extracting suitable features than Fourier and wavelet transforms, and combined with one-versus-one Support Vector Machine, they can provide a 85.7 % recognition accuracy rate. Our proposed method shows higher accuracy and precision compared to other frequency based methods.
{"title":"Human recognition through walking styles by multiwavelet transform","authors":"Farhad Mohamad Kazemi, W. Banzhaf, Minglun Gong","doi":"10.1109/IKT.2016.7777786","DOIUrl":"https://doi.org/10.1109/IKT.2016.7777786","url":null,"abstract":"Human recognition through walking styles is among the newest of biometric methods. By using this biometric, individuals can be identified, distantly, even at low visibility. Our aim is to provide such ability for a computer system. In other words, we intend to extract appropriate features through processing video images that can reflect individuals' identity. In order to set up such a system, we have used Fourier, Wavelet, and Multi-wavelet transforms. Using images from the USF dataset version 1.7, the results obtained indicate that SA4 Multi-wavelet transforms prove more efficient in extracting suitable features than Fourier and wavelet transforms, and combined with one-versus-one Support Vector Machine, they can provide a 85.7 % recognition accuracy rate. Our proposed method shows higher accuracy and precision compared to other frequency based methods.","PeriodicalId":205496,"journal":{"name":"2016 Eighth International Conference on Information and Knowledge Technology (IKT)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134452591","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 : 2016-09-01DOI: 10.1109/IKT.2016.7777777
M. Daneshvar, H. Veisi
Recently Recurrent Neural Networks (RNNs) have shown impressive performance in sequence classification tasks. In this paper we apply Long Short-Term Memory (LSTM) network on Persian phoneme recognition. For years Hidden Markov Model (HMM) was the dominant technique in speech recognition system but after introducing LSTM, RNNs outperformed HHM-based methods. We apply LSTM and deep LSTM on FARSDAT speech database and find that both LSTM and deep LSTM outperforms HMM in Persian phoneme recognition. Our evaluation show that deep LSTM achieves 17.55% error in FARSDAT phoneme recognition on test set which to our knowledge is the best recorded result.
{"title":"Persian phoneme recognition using long short-term memory neural network","authors":"M. Daneshvar, H. Veisi","doi":"10.1109/IKT.2016.7777777","DOIUrl":"https://doi.org/10.1109/IKT.2016.7777777","url":null,"abstract":"Recently Recurrent Neural Networks (RNNs) have shown impressive performance in sequence classification tasks. In this paper we apply Long Short-Term Memory (LSTM) network on Persian phoneme recognition. For years Hidden Markov Model (HMM) was the dominant technique in speech recognition system but after introducing LSTM, RNNs outperformed HHM-based methods. We apply LSTM and deep LSTM on FARSDAT speech database and find that both LSTM and deep LSTM outperforms HMM in Persian phoneme recognition. Our evaluation show that deep LSTM achieves 17.55% error in FARSDAT phoneme recognition on test set which to our knowledge is the best recorded result.","PeriodicalId":205496,"journal":{"name":"2016 Eighth International Conference on Information and Knowledge Technology (IKT)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131586351","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 : 2016-09-01DOI: 10.1109/IKT.2016.7777773
M. Jahantigh, M. Erfani, N. Daneshpour, Nargess Orojlou
Since text mining saves a large amount of information in text format, it has a very high potential application. One of the main applications of text mining is to classify texts in subject order. In this paper, we tried to propose a aarianew method in order to increase classification accuracy and efficiency, by considering different methods of Persian text classification. We used a number of 5330 news of Hamshahri data collection, for classification. In pre-processing of texts for removing stop words, we proposed a new method by using entropy of words. To extract the feature, word frequencies, and Tf-idf methods have been used. K nearest neighbor algorithm, Naive Bayes classification, and mixture of classifiers, have been used to classify texts, by using combinational classification and mixture of experts. Implementation of proposed method has caused a 15 percent improvement comparing to the previous works done on this data collection, by presenting entropy in pre-processing and also mixture of classifiers. In the best condition, scientific and cultural news has gained 96.36 percent classification accuracy.
{"title":"Presenting an improved combination for classification of Persian texts","authors":"M. Jahantigh, M. Erfani, N. Daneshpour, Nargess Orojlou","doi":"10.1109/IKT.2016.7777773","DOIUrl":"https://doi.org/10.1109/IKT.2016.7777773","url":null,"abstract":"Since text mining saves a large amount of information in text format, it has a very high potential application. One of the main applications of text mining is to classify texts in subject order. In this paper, we tried to propose a aarianew method in order to increase classification accuracy and efficiency, by considering different methods of Persian text classification. We used a number of 5330 news of Hamshahri data collection, for classification. In pre-processing of texts for removing stop words, we proposed a new method by using entropy of words. To extract the feature, word frequencies, and Tf-idf methods have been used. K nearest neighbor algorithm, Naive Bayes classification, and mixture of classifiers, have been used to classify texts, by using combinational classification and mixture of experts. Implementation of proposed method has caused a 15 percent improvement comparing to the previous works done on this data collection, by presenting entropy in pre-processing and also mixture of classifiers. In the best condition, scientific and cultural news has gained 96.36 percent classification accuracy.","PeriodicalId":205496,"journal":{"name":"2016 Eighth International Conference on Information and Knowledge Technology (IKT)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117191217","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 : 2016-09-01DOI: 10.1109/IKT.2016.7777782
F. Kheirkhah, H. R. Sadegh Mohammadi, A. Shahverdi
Proper recognition of microscopic sperm cells in video images is an important step in diagnosis and treatment of male infertility. The small sizes of the sperm cells make their segmentation and detection an important stage in the microscopic images analysis. Histogram-based thresholding schemes are one of the common approaches for this purpose. This paper proposes a non-linear amplitude compression transform method applied as a pre-processing stage for histogram-based thresholding algorithms. The results of conducted experiments verify the higher performance of the proposed scheme when used with Kittler method compared to its utilization with the other competitive algorithms in most cases for this application.
{"title":"Histogram non-linear transform for sperm cells image detection enhancement","authors":"F. Kheirkhah, H. R. Sadegh Mohammadi, A. Shahverdi","doi":"10.1109/IKT.2016.7777782","DOIUrl":"https://doi.org/10.1109/IKT.2016.7777782","url":null,"abstract":"Proper recognition of microscopic sperm cells in video images is an important step in diagnosis and treatment of male infertility. The small sizes of the sperm cells make their segmentation and detection an important stage in the microscopic images analysis. Histogram-based thresholding schemes are one of the common approaches for this purpose. This paper proposes a non-linear amplitude compression transform method applied as a pre-processing stage for histogram-based thresholding algorithms. The results of conducted experiments verify the higher performance of the proposed scheme when used with Kittler method compared to its utilization with the other competitive algorithms in most cases for this application.","PeriodicalId":205496,"journal":{"name":"2016 Eighth International Conference on Information and Knowledge Technology (IKT)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116074762","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 : 2016-09-01DOI: 10.1109/IKT.2016.7777767
Mostafa Mohammadpour, M. Ghorbanian, S. Mozaffari
Classifying electroencephalogram (EEG) signal in Brain Computer Interface (BCI) is a useful methods to analysis different organs of human body and it can be used for communicate with the outside world and controlling external device. Accuracy classification of extracted features from EEG signals is a problem which many researcher try to improve it. Although many methods for extracting feature and classifying EEG signal have been proposed and developed, many of them suffer from extracting less accurate data from EEG signals. In this work, four signal feature extraction and three ensemble learning method have been reviewed and performances of classification techniques are compared for motor imagery task.
{"title":"Comparison of EEG signal features and ensemble learning methods for motor imagery classification","authors":"Mostafa Mohammadpour, M. Ghorbanian, S. Mozaffari","doi":"10.1109/IKT.2016.7777767","DOIUrl":"https://doi.org/10.1109/IKT.2016.7777767","url":null,"abstract":"Classifying electroencephalogram (EEG) signal in Brain Computer Interface (BCI) is a useful methods to analysis different organs of human body and it can be used for communicate with the outside world and controlling external device. Accuracy classification of extracted features from EEG signals is a problem which many researcher try to improve it. Although many methods for extracting feature and classifying EEG signal have been proposed and developed, many of them suffer from extracting less accurate data from EEG signals. In this work, four signal feature extraction and three ensemble learning method have been reviewed and performances of classification techniques are compared for motor imagery task.","PeriodicalId":205496,"journal":{"name":"2016 Eighth International Conference on Information and Knowledge Technology (IKT)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122651804","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：