Pub Date : 2015-11-01DOI: 10.1109/KBEI.2015.7436191
Ahmad Pouramini, Amine Naseri
Treebanks are essential resources for both data-driven approaches to natural language processing (NLP) and empirical linguistic researches. Developing these resources is time- and cost-consuming and requires specialized expertise. Therefore, they should be designed to be reused for different purposes. Currently, there are several dependency treebanks for some languages which are annotated in CoNLL format. For some languages, such as Persian, they are the few available linguistic resources. These treebanks are more suitable for the input of data-driven parsers, and querying linguistic data in them is not easy. In recent years, XML has been widely used for formatting treebanks, and there are various tools available for querying and annotating a linguistic croups in this format. In this paper, we present a tool for converting a dependency treebank in CoNLL format to an appropriate XML format. We designed the XML scheme to be particularly suitable for writing linguistic queries in XQuery syntax.
{"title":"The XMLization of a dependency treebank in CoNLL format for evaluating linguistic queries using XQuery","authors":"Ahmad Pouramini, Amine Naseri","doi":"10.1109/KBEI.2015.7436191","DOIUrl":"https://doi.org/10.1109/KBEI.2015.7436191","url":null,"abstract":"Treebanks are essential resources for both data-driven approaches to natural language processing (NLP) and empirical linguistic researches. Developing these resources is time- and cost-consuming and requires specialized expertise. Therefore, they should be designed to be reused for different purposes. Currently, there are several dependency treebanks for some languages which are annotated in CoNLL format. For some languages, such as Persian, they are the few available linguistic resources. These treebanks are more suitable for the input of data-driven parsers, and querying linguistic data in them is not easy. In recent years, XML has been widely used for formatting treebanks, and there are various tools available for querying and annotating a linguistic croups in this format. In this paper, we present a tool for converting a dependency treebank in CoNLL format to an appropriate XML format. We designed the XML scheme to be particularly suitable for writing linguistic queries in XQuery syntax.","PeriodicalId":168295,"journal":{"name":"2015 2nd International Conference on Knowledge-Based Engineering and Innovation (KBEI)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133865244","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 : 2015-11-01DOI: 10.1109/KBEI.2015.7436082
Mojgan Esna Ashari, M. Zekri, M. Askari
Diabetes is known as the sixth leading cause of death in the world leading to kidney and cardiovascular diseases as well. As a result, controlling the disease is of particular importance. To control blood glucose level in diabetes mellitus type I, insulin must be injected into the body. This injection must be strictly controlled - any excessive increase in insulin injection can cause human death. Various controllers have been introduced to control diabetes type I with their own disadvantages. Diabetic patient model used in previous methods is not in compliance with physiological data, uncertainties are not considered in the model, or the controller has a very limited range of stability. In this paper, a Nonlinear Model Predictive Controller is introduced which not only resolves previous problems like lack of consideration of model uncertainty, sharp drop in blood glucose, and low stability, but also specifies insulin injection dosage based on blood glucose level momentarily so that.
{"title":"Control of the blood glucose level in diabetic patient using predictive controller and delay differential equation","authors":"Mojgan Esna Ashari, M. Zekri, M. Askari","doi":"10.1109/KBEI.2015.7436082","DOIUrl":"https://doi.org/10.1109/KBEI.2015.7436082","url":null,"abstract":"Diabetes is known as the sixth leading cause of death in the world leading to kidney and cardiovascular diseases as well. As a result, controlling the disease is of particular importance. To control blood glucose level in diabetes mellitus type I, insulin must be injected into the body. This injection must be strictly controlled - any excessive increase in insulin injection can cause human death. Various controllers have been introduced to control diabetes type I with their own disadvantages. Diabetic patient model used in previous methods is not in compliance with physiological data, uncertainties are not considered in the model, or the controller has a very limited range of stability. In this paper, a Nonlinear Model Predictive Controller is introduced which not only resolves previous problems like lack of consideration of model uncertainty, sharp drop in blood glucose, and low stability, but also specifies insulin injection dosage based on blood glucose level momentarily so that.","PeriodicalId":168295,"journal":{"name":"2015 2nd International Conference on Knowledge-Based Engineering and Innovation (KBEI)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133967930","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 : 2015-11-01DOI: 10.1109/KBEI.2015.7436190
M. Hashemi, R. Rafeh
Classification and sentiment analysis and research is one of the most important issues in recent times, especially in the realm of language is Persian. Identify the user sentiments about an issue through a process of expressing a sense of individual and output data analysis work is in the context of Hijab of natural language processing and computational linguistics, artificial intelligence is a subsidiary. The need to categorize and production data sources in our field and that's the dress code, according to the news raised in this context and user reaction to the news texts, to provide a data set with an algorithm that on it has been implemented. The algorithm proposed in this study using text mining techniques and algorithms applied weight to words and try to identify the type of polarization of the comments gathered from official sites built in 1000. Analysis on the words in the comments feature has been conducted. It focused on the importance of the word in a sentence.
{"title":"Using of emotion mining techniques for opinions analysis on the issue of Hijab","authors":"M. Hashemi, R. Rafeh","doi":"10.1109/KBEI.2015.7436190","DOIUrl":"https://doi.org/10.1109/KBEI.2015.7436190","url":null,"abstract":"Classification and sentiment analysis and research is one of the most important issues in recent times, especially in the realm of language is Persian. Identify the user sentiments about an issue through a process of expressing a sense of individual and output data analysis work is in the context of Hijab of natural language processing and computational linguistics, artificial intelligence is a subsidiary. The need to categorize and production data sources in our field and that's the dress code, according to the news raised in this context and user reaction to the news texts, to provide a data set with an algorithm that on it has been implemented. The algorithm proposed in this study using text mining techniques and algorithms applied weight to words and try to identify the type of polarization of the comments gathered from official sites built in 1000. Analysis on the words in the comments feature has been conducted. It focused on the importance of the word in a sentence.","PeriodicalId":168295,"journal":{"name":"2015 2nd International Conference on Knowledge-Based Engineering and Innovation (KBEI)","volume":"284 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116099702","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 : 2015-11-01DOI: 10.1109/KBEI.2015.7436090
Mehrnaz Bahrieh, A. Fakharzadeh
A mathematical model can appropriately describe the metastatic growth process in bones, which is regarded as a cancer case. This article proposes to describe a dynamic model for bone metastas by a system of partial differential equations. Based on the interaction between osteoclasts, cancer cells, PTHrP, OPG, RANKL cells and the other relations therein, This model describe the manner in which osteoclasts resorb the bone to make place for growing cancer cells. Here, tumor growth during ninety days of appearance and for different locations of bone of a patient has been set out by numerical simulations that make use of the finite difference method. Moreover, tumor density throughout the bone after ninety days has been also investigated.
{"title":"A survey on bone metastasis by finite difference method","authors":"Mehrnaz Bahrieh, A. Fakharzadeh","doi":"10.1109/KBEI.2015.7436090","DOIUrl":"https://doi.org/10.1109/KBEI.2015.7436090","url":null,"abstract":"A mathematical model can appropriately describe the metastatic growth process in bones, which is regarded as a cancer case. This article proposes to describe a dynamic model for bone metastas by a system of partial differential equations. Based on the interaction between osteoclasts, cancer cells, PTHrP, OPG, RANKL cells and the other relations therein, This model describe the manner in which osteoclasts resorb the bone to make place for growing cancer cells. Here, tumor growth during ninety days of appearance and for different locations of bone of a patient has been set out by numerical simulations that make use of the finite difference method. Moreover, tumor density throughout the bone after ninety days has been also investigated.","PeriodicalId":168295,"journal":{"name":"2015 2nd International Conference on Knowledge-Based Engineering and Innovation (KBEI)","volume":"518 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116246214","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 : 2015-11-01DOI: 10.1109/KBEI.2015.7436021
G. D'Antona
This paper presents three engineering applications concerning power system where knowledge uncertainty is managed properly in order to be able to control the process appropriately. The three examples reported are very different from each other especially for what concerns the complexity of the process involved, the time available for the decision process and for the cost of the uncertainty supervision system.
{"title":"Knowledge uncertainty supervision in automatic control and measurements","authors":"G. D'Antona","doi":"10.1109/KBEI.2015.7436021","DOIUrl":"https://doi.org/10.1109/KBEI.2015.7436021","url":null,"abstract":"This paper presents three engineering applications concerning power system where knowledge uncertainty is managed properly in order to be able to control the process appropriately. The three examples reported are very different from each other especially for what concerns the complexity of the process involved, the time available for the decision process and for the cost of the uncertainty supervision system.","PeriodicalId":168295,"journal":{"name":"2015 2nd International Conference on Knowledge-Based Engineering and Innovation (KBEI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125323778","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 : 2015-11-01DOI: 10.1109/KBEI.2015.7436212
Zeinab S. Jalali, Alireza Rezvanian, M. Meybodi
In recent years, the data used for analysis of social networks become very huge and restrictive so that it can be used an appropriate and small sampled network of original network for analysis goals. Sampling social network is referred to collect a small subgraph of original network with high property similarities between them. Due to important impact of sampling on the social network analyses, many algorithms have been proposed in the field of network sampling. In this paper, we propose a two-phase algorithm for sampling online social networks. At first phase, our algorithm iteratively constructs several set of minimum spanning trees (MST) of network. In the second phase, the proposed algorithm sorts vertices of MSTs and merge them to form a sampled network. Several simulation experiments are conducted to examine the performance of the proposed algorithm on different networks. The obtained results are compared with counterpart algorithms in terms of KS-test and ND-test. From the results, it can be observed that the proposed algorithm outperforms the existing algorithms.
{"title":"A two-phase sampling algorithm for social networks","authors":"Zeinab S. Jalali, Alireza Rezvanian, M. Meybodi","doi":"10.1109/KBEI.2015.7436212","DOIUrl":"https://doi.org/10.1109/KBEI.2015.7436212","url":null,"abstract":"In recent years, the data used for analysis of social networks become very huge and restrictive so that it can be used an appropriate and small sampled network of original network for analysis goals. Sampling social network is referred to collect a small subgraph of original network with high property similarities between them. Due to important impact of sampling on the social network analyses, many algorithms have been proposed in the field of network sampling. In this paper, we propose a two-phase algorithm for sampling online social networks. At first phase, our algorithm iteratively constructs several set of minimum spanning trees (MST) of network. In the second phase, the proposed algorithm sorts vertices of MSTs and merge them to form a sampled network. Several simulation experiments are conducted to examine the performance of the proposed algorithm on different networks. The obtained results are compared with counterpart algorithms in terms of KS-test and ND-test. From the results, it can be observed that the proposed algorithm outperforms the existing algorithms.","PeriodicalId":168295,"journal":{"name":"2015 2nd International Conference on Knowledge-Based Engineering and Innovation (KBEI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124083163","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 : 2015-11-01DOI: 10.1109/KBEI.2015.7436080
H. Rakhshani, A. Rahati, E. Dehghanian
Protein structure prediction (PSP) is one of the most challenging problems in the field of structural bioinformatics. Determining native conformation of a protein can affect its functions and plays an important role in drug design and disease prediction. Therefore, researchers are trying to come up with different techniques in order to find more precise structures. This study investigates application of cuckoo search (CS) algorithm on the protein folding problem based on AB off-lattice model. Experiments are conducted on a set of protein sequences that are suggested in the literature. For the purpose of evaluation, we used state-of-the-art and recently developed algorithms. Comparison of the statistical results demonstrates that CS outperforms other algorithms in a meaningful way.
{"title":"Cuckoo search algorithm and its application for secondary protein structure prediction","authors":"H. Rakhshani, A. Rahati, E. Dehghanian","doi":"10.1109/KBEI.2015.7436080","DOIUrl":"https://doi.org/10.1109/KBEI.2015.7436080","url":null,"abstract":"Protein structure prediction (PSP) is one of the most challenging problems in the field of structural bioinformatics. Determining native conformation of a protein can affect its functions and plays an important role in drug design and disease prediction. Therefore, researchers are trying to come up with different techniques in order to find more precise structures. This study investigates application of cuckoo search (CS) algorithm on the protein folding problem based on AB off-lattice model. Experiments are conducted on a set of protein sequences that are suggested in the literature. For the purpose of evaluation, we used state-of-the-art and recently developed algorithms. Comparison of the statistical results demonstrates that CS outperforms other algorithms in a meaningful way.","PeriodicalId":168295,"journal":{"name":"2015 2nd International Conference on Knowledge-Based Engineering and Innovation (KBEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130599036","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 : 2015-11-01DOI: 10.1109/KBEI.2015.7436103
Amin Aref, M. Lotfizad
In this paper we introduce an Modified Clipped LMS (MCLMS) algorithm with a variable step size. In the MCLMS algorithm two parameters, the step size and the threshold control the convergence rate of the adaptive filter coefficients and also determine the final mean-square error. The computational complexity decreased dramatically by a large threshold. However, this selection results in a low convergence rate. Since the convergence time is inversely proportional to the step size, a large step size is often selected for fast convergence. But a large step size results in an increased final mean square error. Therefore in this paper we choose a large threshold and propose a variable step size for the MCLMS algorithm. The advantages of this proposed variable step size and a large threshold selection are that the computation complexity is low, final mean square error is low and that the convergence is fast.
{"title":"Variable step size modified clipped LMS algorithm","authors":"Amin Aref, M. Lotfizad","doi":"10.1109/KBEI.2015.7436103","DOIUrl":"https://doi.org/10.1109/KBEI.2015.7436103","url":null,"abstract":"In this paper we introduce an Modified Clipped LMS (MCLMS) algorithm with a variable step size. In the MCLMS algorithm two parameters, the step size and the threshold control the convergence rate of the adaptive filter coefficients and also determine the final mean-square error. The computational complexity decreased dramatically by a large threshold. However, this selection results in a low convergence rate. Since the convergence time is inversely proportional to the step size, a large step size is often selected for fast convergence. But a large step size results in an increased final mean square error. Therefore in this paper we choose a large threshold and propose a variable step size for the MCLMS algorithm. The advantages of this proposed variable step size and a large threshold selection are that the computation complexity is low, final mean square error is low and that the convergence is fast.","PeriodicalId":168295,"journal":{"name":"2015 2nd International Conference on Knowledge-Based Engineering and Innovation (KBEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130821488","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 : 2015-11-01DOI: 10.1109/KBEI.2015.7436208
F. Halataei, A. Kayhani
Humanoid locomotion of biped robots is an interesting research area due to its similarity to human walking. Furthermore, wide application of humanoid locomotion especially in robocup competitions made it more interesting for several researchers in the fields of electronics, mechanics and computer science, although it has its own complexity. This paper proposes a novel approach that optimizes the walking speed and stability for NAO biped robots. This method has been implemented on simulated NAO robot in Robocup 3D simulation environment (rcsssever3d). We have used Artificially Bee Colony (ABC) algorithm in order to achieve full stability and considerable fast walking speed without any external disturbances. Experimental results show that using this approach also, significantly decreased optimization time in order to get optimal values for parameters in our fitness function. At end a comparison has been made between the described optimization solution and GA optimization, while same walking method and foot trajectory formula has been used.
{"title":"Optimizing NAO humanoid walking using ABC algorithm","authors":"F. Halataei, A. Kayhani","doi":"10.1109/KBEI.2015.7436208","DOIUrl":"https://doi.org/10.1109/KBEI.2015.7436208","url":null,"abstract":"Humanoid locomotion of biped robots is an interesting research area due to its similarity to human walking. Furthermore, wide application of humanoid locomotion especially in robocup competitions made it more interesting for several researchers in the fields of electronics, mechanics and computer science, although it has its own complexity. This paper proposes a novel approach that optimizes the walking speed and stability for NAO biped robots. This method has been implemented on simulated NAO robot in Robocup 3D simulation environment (rcsssever3d). We have used Artificially Bee Colony (ABC) algorithm in order to achieve full stability and considerable fast walking speed without any external disturbances. Experimental results show that using this approach also, significantly decreased optimization time in order to get optimal values for parameters in our fitness function. At end a comparison has been made between the described optimization solution and GA optimization, while same walking method and foot trajectory formula has been used.","PeriodicalId":168295,"journal":{"name":"2015 2nd International Conference on Knowledge-Based Engineering and Innovation (KBEI)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121075942","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 : 2015-11-01DOI: 10.1109/KBEI.2015.7436128
P. Kakvand, M. Jaberzadeh, Mohamed Madadpour Inallou, Y. Alborz
This paper outlines the design and manufacture of Unmanned Aircraft Vehicle (UAV) that the require to a separate ground station for data (output data of parameter measurement in rotational and linear motion and image data) processing is completely removed, and all the flying robot operations became autonomously from take-off to the end of the progress to determine the distance towards the objects for obtaining coordinates (current location), calculates the distance from the object and pursues it by on-board process. Played as a result, in addition to reducing errors in data transmission process, the cost will be reduced. A PID controller designed the combined use of feedback in two phases, Flight Controller (IMU module output data and programmed algorithms for spiral movement and distance calculation algorithm by the means of counting sent and received radio pulses) and video data processing, may reduce performance errors in the addressed projects in comparison to other similar smart systems.
{"title":"Smart on-board UAV system: Using computer vision system to find a movable and stationary target","authors":"P. Kakvand, M. Jaberzadeh, Mohamed Madadpour Inallou, Y. Alborz","doi":"10.1109/KBEI.2015.7436128","DOIUrl":"https://doi.org/10.1109/KBEI.2015.7436128","url":null,"abstract":"This paper outlines the design and manufacture of Unmanned Aircraft Vehicle (UAV) that the require to a separate ground station for data (output data of parameter measurement in rotational and linear motion and image data) processing is completely removed, and all the flying robot operations became autonomously from take-off to the end of the progress to determine the distance towards the objects for obtaining coordinates (current location), calculates the distance from the object and pursues it by on-board process. Played as a result, in addition to reducing errors in data transmission process, the cost will be reduced. A PID controller designed the combined use of feedback in two phases, Flight Controller (IMU module output data and programmed algorithms for spiral movement and distance calculation algorithm by the means of counting sent and received radio pulses) and video data processing, may reduce performance errors in the addressed projects in comparison to other similar smart systems.","PeriodicalId":168295,"journal":{"name":"2015 2nd International Conference on Knowledge-Based Engineering and Innovation (KBEI)","volume":"280 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123089537","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：