Pub Date : 2011-06-15DOI: 10.1109/INISTA.2011.5946056
Onder Kirli, M. B. Gulmezoglu
In this paper, new techniques have been introduced for revealing the individual features of a person's handwriting pattern to facilitate text-independent off-line writer identification. These techniques are aimed at designing a dynamic model which can be formalized according to any handwritten text line. Various combinations of the extracted features are applied to three well known classifiers for evaluating the contribution of features to the correct identification rate. The K-NN, GMM, and Normal Density Discriminant Function (NDDF) Bayes classifiers are used in the present identification model. The experimental studies are conducted on the IAM database containing 650 writers. The performance of the extracted features is also analyzed with respect to number of writers in the query. The remarkable identification rates obtained from the three classifiers clearly indicate that the proposed feature extraction techniques can be effectively used in writer identification systems.
{"title":"Writer identification from handwriting text lines","authors":"Onder Kirli, M. B. Gulmezoglu","doi":"10.1109/INISTA.2011.5946056","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946056","url":null,"abstract":"In this paper, new techniques have been introduced for revealing the individual features of a person's handwriting pattern to facilitate text-independent off-line writer identification. These techniques are aimed at designing a dynamic model which can be formalized according to any handwritten text line. Various combinations of the extracted features are applied to three well known classifiers for evaluating the contribution of features to the correct identification rate. The K-NN, GMM, and Normal Density Discriminant Function (NDDF) Bayes classifiers are used in the present identification model. The experimental studies are conducted on the IAM database containing 650 writers. The performance of the extracted features is also analyzed with respect to number of writers in the query. The remarkable identification rates obtained from the three classifiers clearly indicate that the proposed feature extraction techniques can be effectively used in writer identification systems.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122969037","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946128
K. Ozkan, C. Topal, C. Akinlar
Contours are the most common feature used in the shape detection and recognition applications. Contours in digital images constitute of consecutive pixels, thus they can be represented with chain codes by encoding the relative positions of the pixels forming that contour. Sharp transitions on chain coded contour information correspond to the corners or notches of the 2D shape enclosed by that contour. Moreover, useful information about geometric structures and orientations of the shapes can be gathered by examining the distributions and moments of the chain codes. Despite their profitable properties, chain codes are not robust against the rotation. Because contours are exposed to quantization while they are being digitized, same geometric shape may have different chain code representations. Another downside about the chain codes is the difficulty of their extraction from real images in an efficient manner. In this study, we propose a novel real-time corner detection method by extracting the chain codes by Edge Drawing (ED) method and after processing them with the trilateral filtering.
{"title":"Corner detection via trilateral filtering of chain codes","authors":"K. Ozkan, C. Topal, C. Akinlar","doi":"10.1109/INISTA.2011.5946128","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946128","url":null,"abstract":"Contours are the most common feature used in the shape detection and recognition applications. Contours in digital images constitute of consecutive pixels, thus they can be represented with chain codes by encoding the relative positions of the pixels forming that contour. Sharp transitions on chain coded contour information correspond to the corners or notches of the 2D shape enclosed by that contour. Moreover, useful information about geometric structures and orientations of the shapes can be gathered by examining the distributions and moments of the chain codes. Despite their profitable properties, chain codes are not robust against the rotation. Because contours are exposed to quantization while they are being digitized, same geometric shape may have different chain code representations. Another downside about the chain codes is the difficulty of their extraction from real images in an efficient manner. In this study, we propose a novel real-time corner detection method by extracting the chain codes by Edge Drawing (ED) method and after processing them with the trilateral filtering.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125271134","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946094
C. Ozdemir, B. Diri
Web-Ear is an information retrieval system in which anyone can search "What person X told about the topic Y" on the internet or in the database of the system. If the search is made on the internet, first the system submits a query to Google search engine and retrieves a set of information. In order to isolate speech portions of retrieved data, an extraction process is required to be performed according to pre-defined rules set by regular expressions, and only after then we have the data that we want to present to the user.
{"title":"Web-Ear, an information retrieval system that uses reported speech expressions in Turkish","authors":"C. Ozdemir, B. Diri","doi":"10.1109/INISTA.2011.5946094","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946094","url":null,"abstract":"Web-Ear is an information retrieval system in which anyone can search \"What person X told about the topic Y\" on the internet or in the database of the system. If the search is made on the internet, first the system submits a query to Google search engine and retrieves a set of information. In order to isolate speech portions of retrieved data, an extraction process is required to be performed according to pre-defined rules set by regular expressions, and only after then we have the data that we want to present to the user.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"73 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114392080","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946171
Umut Orhan, M. Hekim, Mahmut Ozer, Ivo Provaznik
In this paper, the equal frequency discretization (EFD) based probability density approach was proposed to be used in the diagnosis of epilepsy from electroencephalogram (EEG) signals. For this aim, EEG signals were decomposed by using the discrete wavelet discretization (DWT) method into subbands, the coefficients in each subband were discretized to several intervals by EFD method, and the probability density of each subband of each EEG segment was computed according to the number of coefficients in discrete intervals. Then, two probability density functions were defined by means of the curve fitting over the probability densities of the sets of both healthy subjects and epilepsy patients. EEG signals were classified by applying the mean square error (MSE) criterion to these functions. The result of the classification was evaluated by using the ROC analysis, which indicated 82.50% success in the diagnosis of epilepsy. As a result, the EFD based probability density approach may be considered as an alternative way to diagnose epilepsy disease on EEG signals.
{"title":"Epilepsy diagnosis using probability density functions of EEG signals","authors":"Umut Orhan, M. Hekim, Mahmut Ozer, Ivo Provaznik","doi":"10.1109/INISTA.2011.5946171","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946171","url":null,"abstract":"In this paper, the equal frequency discretization (EFD) based probability density approach was proposed to be used in the diagnosis of epilepsy from electroencephalogram (EEG) signals. For this aim, EEG signals were decomposed by using the discrete wavelet discretization (DWT) method into subbands, the coefficients in each subband were discretized to several intervals by EFD method, and the probability density of each subband of each EEG segment was computed according to the number of coefficients in discrete intervals. Then, two probability density functions were defined by means of the curve fitting over the probability densities of the sets of both healthy subjects and epilepsy patients. EEG signals were classified by applying the mean square error (MSE) criterion to these functions. The result of the classification was evaluated by using the ROC analysis, which indicated 82.50% success in the diagnosis of epilepsy. As a result, the EFD based probability density approach may be considered as an alternative way to diagnose epilepsy disease on EEG signals.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"692 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125507788","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946146
H. Zenk, Osman Zenk, A. Akpinar
With two different regions of a Load Frequency control of power systems using fuzzy logic-based controller are examined. With a load of any change in the frequency of the power system investigated how affected. Then Fuzzy Logic Controller (FLC) changes, such as what is observed in using the system. The system has two different control area power system small signal model in Matlab / Simulink computer simulation program was created. FLC in the control and Integral Controller has been using the system. This produces two different results are compared with the controller.
{"title":"Two different power control system load-frequency analysis using fuzzy logic controller","authors":"H. Zenk, Osman Zenk, A. Akpinar","doi":"10.1109/INISTA.2011.5946146","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946146","url":null,"abstract":"With two different regions of a Load Frequency control of power systems using fuzzy logic-based controller are examined. With a load of any change in the frequency of the power system investigated how affected. Then Fuzzy Logic Controller (FLC) changes, such as what is observed in using the system. The system has two different control area power system small signal model in Matlab / Simulink computer simulation program was created. FLC in the control and Integral Controller has been using the system. This produces two different results are compared with the controller.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128783748","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946096
Cagri Toraman, F. Can, Seyit Kocberber
In news portals, text category information is needed for news presentation. However, for many news stories the category information is unavailable, incorrectly assigned or too generic. This makes the text categorization a necessary tool for news portals. Automated text categorization (ATC) is a multifaceted difficult process that involves decisions regarding tuning of several parameters, term weighting, word stemming, word stopping, and feature selection. In this study we aim to find a categorization setup that will provide highly accurate results in ATC for Turkish news portals. We also examine some other aspects such as the effects of training dataset set size and robustness issues. Two Turkish test collections with different characteristics are created using Bilkent News Portal. Experiments are conducted with four classification methods: C4.5, KNN, Naive Bayes, and SVM (using polynomial and rbf kernels). Our results recommends a text categorization template for Turkish news portals and provides some future research pointers.
{"title":"Developing a text categorization template for Turkish news portals","authors":"Cagri Toraman, F. Can, Seyit Kocberber","doi":"10.1109/INISTA.2011.5946096","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946096","url":null,"abstract":"In news portals, text category information is needed for news presentation. However, for many news stories the category information is unavailable, incorrectly assigned or too generic. This makes the text categorization a necessary tool for news portals. Automated text categorization (ATC) is a multifaceted difficult process that involves decisions regarding tuning of several parameters, term weighting, word stemming, word stopping, and feature selection. In this study we aim to find a categorization setup that will provide highly accurate results in ATC for Turkish news portals. We also examine some other aspects such as the effects of training dataset set size and robustness issues. Two Turkish test collections with different characteristics are created using Bilkent News Portal. Experiments are conducted with four classification methods: C4.5, KNN, Naive Bayes, and SVM (using polynomial and rbf kernels). Our results recommends a text categorization template for Turkish news portals and provides some future research pointers.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121172259","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946084
Dilara Torunoglu, Erhan Cakirman, M. Ganiz, S. Akyokuş, M. Gurbuz
Preprocessing is an important task and critical step in information retrieval and text mining. The objective of this study is to analyze the effect of preprocessing methods in text classification on Turkish texts. We compiled two large datasets from Turkish newspapers using a crawler. On these compiled data sets and using two additional datasets, we perform a detailed analysis of preprocessing methods such as stemming, stopword filtering and word weighting for Turkish text classification on several different Turkish datasets. We report the results of extensive experiments.
{"title":"Analysis of preprocessing methods on classification of Turkish texts","authors":"Dilara Torunoglu, Erhan Cakirman, M. Ganiz, S. Akyokuş, M. Gurbuz","doi":"10.1109/INISTA.2011.5946084","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946084","url":null,"abstract":"Preprocessing is an important task and critical step in information retrieval and text mining. The objective of this study is to analyze the effect of preprocessing methods in text classification on Turkish texts. We compiled two large datasets from Turkish newspapers using a crawler. On these compiled data sets and using two additional datasets, we perform a detailed analysis of preprocessing methods such as stemming, stopword filtering and word weighting for Turkish text classification on several different Turkish datasets. We report the results of extensive experiments.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116679263","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946162
H. Erdem, O. T. Altinoz
This study presents the application of the optimized Fixed Frequency Sliding Mode (FFSM) Controller for a Synchronous Buck Converter. The sliding coefficient of the controller, which affects the controller performance, is optimized by using Particle Swarm Optimization (PSO). In order to analysis the performance of the optimized controller, a DC-DC Buck converter which has a variable structure and nonlinear model is used as a test-bed. The controller design procedure and optimization approach are presented in details. Simulation and hardware implementation results are provided to demonstrate the performance of the optimized controller under load and line variations.
{"title":"Implementation of PSO-based fixed frequency sliding mode controller for buck converter","authors":"H. Erdem, O. T. Altinoz","doi":"10.1109/INISTA.2011.5946162","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946162","url":null,"abstract":"This study presents the application of the optimized Fixed Frequency Sliding Mode (FFSM) Controller for a Synchronous Buck Converter. The sliding coefficient of the controller, which affects the controller performance, is optimized by using Particle Swarm Optimization (PSO). In order to analysis the performance of the optimized controller, a DC-DC Buck converter which has a variable structure and nonlinear model is used as a test-bed. The controller design procedure and optimization approach are presented in details. Simulation and hardware implementation results are provided to demonstrate the performance of the optimized controller under load and line variations.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116713964","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946081
Selcuk Kilnc, M. Yalçin, S. Ozoguz
CMOS realization of a one-dimensional cellular neural network containing twenty cells is presented. The network consists of relaxation oscillators and it has been designed to generate autowaves. The layout design of the circuit has been done in the Cadence environment. The test results of the fabricated chip are included.
{"title":"CMOS realization of a cellular neural network generating autowaves","authors":"Selcuk Kilnc, M. Yalçin, S. Ozoguz","doi":"10.1109/INISTA.2011.5946081","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946081","url":null,"abstract":"CMOS realization of a one-dimensional cellular neural network containing twenty cells is presented. The network consists of relaxation oscillators and it has been designed to generate autowaves. The layout design of the circuit has been done in the Cadence environment. The test results of the fabricated chip are included.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"30 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125697861","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 : 2011-06-15DOI: 10.1109/INISTA.2011.5946110
A. Ilker, M. Kose, G. Ergin, Özlem Terzi
In this study, flow estimation models has been developed with artificial neural networks (ANN) method which is one of the artificial intelligence techniques. The various ANN models are developed by using different input combinations consisting of flow data of Söğütlühan (1535), Yamula (1501) and Bulakbaşi (1539) stations and compared with measured monthly flow. The coefficient of determination (R2) and root mean square error (RMSE) are used as performance criteria to compare results. According to these criteria, the model which has flow values in t-1 time of 1501, 1539 and 1535 stations, and in t time of 1501 and 1539 stations has the highest R2 of 0.98 and 0.97 for training and testing set, respectively.
{"title":"An artificial neural networks approach to monthly flow estimation","authors":"A. Ilker, M. Kose, G. Ergin, Özlem Terzi","doi":"10.1109/INISTA.2011.5946110","DOIUrl":"https://doi.org/10.1109/INISTA.2011.5946110","url":null,"abstract":"In this study, flow estimation models has been developed with artificial neural networks (ANN) method which is one of the artificial intelligence techniques. The various ANN models are developed by using different input combinations consisting of flow data of Söğütlühan (1535), Yamula (1501) and Bulakbaşi (1539) stations and compared with measured monthly flow. The coefficient of determination (R2) and root mean square error (RMSE) are used as performance criteria to compare results. According to these criteria, the model which has flow values in t-1 time of 1501, 1539 and 1535 stations, and in t time of 1501 and 1539 stations has the highest R2 of 0.98 and 0.97 for training and testing set, respectively.","PeriodicalId":301397,"journal":{"name":"2011 International Symposium on Innovations in Intelligent Systems and Applications","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126040939","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：