Pub Date : 2006-04-17DOI: 10.1109/SIU.2006.1659827
H. Meral, B. Sankur, A. S. Ozsoy
Text watermarking is a recent subject of natural language processing aimed to the content security and authentication information of the text documents. This study explores possible text watermarking tools for Turkish language. Various watermarking tools such as changes of morphological and syntactic structures, and swapping of synonyms and punctuations are investigated and their relative performance measured
{"title":"Watermarking Tools for Turkish Texts","authors":"H. Meral, B. Sankur, A. S. Ozsoy","doi":"10.1109/SIU.2006.1659827","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659827","url":null,"abstract":"Text watermarking is a recent subject of natural language processing aimed to the content security and authentication information of the text documents. This study explores possible text watermarking tools for Turkish language. Various watermarking tools such as changes of morphological and syntactic structures, and swapping of synonyms and punctuations are investigated and their relative performance measured","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"188 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114008763","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 : 2006-04-17DOI: 10.1109/SIU.2006.1659899
N. O. Unverdi, O. Turkmen
Optical sensors, one of the principal components of optical communications, are studied, classified and their working principles are explained. The components of optical fiber sensors are discussed and their characteristics evaluated. The Mach-Zehnder interferometric sensor, an optical fiber sensor largely used in physics, chemistry and biomedical applications is assessed, its phase variation analyzed in the light of the theory of elasticity, and critical parameters are determined for increasing the sensitivity of the sensor
{"title":"Propagation Analysis in Optical Fiber Interferometric Sensors","authors":"N. O. Unverdi, O. Turkmen","doi":"10.1109/SIU.2006.1659899","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659899","url":null,"abstract":"Optical sensors, one of the principal components of optical communications, are studied, classified and their working principles are explained. The components of optical fiber sensors are discussed and their characteristics evaluated. The Mach-Zehnder interferometric sensor, an optical fiber sensor largely used in physics, chemistry and biomedical applications is assessed, its phase variation analyzed in the light of the theory of elasticity, and critical parameters are determined for increasing the sensitivity of the sensor","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"160 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131534503","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 : 2006-04-17DOI: 10.1109/SIU.2006.1659685
A. Ozen, B. Soysal, I. Kaya, I. Altas
While data speed provided by communication technologies and the data speed required for multimedia applications are competing with each other, the importance of OFDM technology, which has less intersymbol interference influences that occur in the channel, has been increasing. Deep fadings occurred as a result of multipath propagation because some sub carriers that loses its information as well as fading in a non-recoverable degree, and consequently results in a poorer system performance. Since the training speed of LMS algorithm used in estimation of channel coefficients in time domain for OFDM based systems is not generally sufficient to achieve the desired performance levels in training time defined by standards, a fuzzy logic based algorithm is adapted to get a faster performance. An application of fuzzy logic based high performance LMS algorithm for OFDM systems is investigated in this paper. The aim of the proposed method is to produce the required fuzzy rule base and fuzzy subsets for fuzzy logic controller in order to speed up the LMS algorithm. The generations of fuzzy rules are based on the comparison of estimated signal by equalizer or channel output. The obtained results of simulations show that the LMS algorithm based on fuzzy logic (F-LMS) increases the performance in OFDM systems significantly and converges to the performance of the RLS algorithm
{"title":"Production of Time Domain Fuzzy Control Rules for Channel Estimation and Equalization in OFDM Based Communication Systems","authors":"A. Ozen, B. Soysal, I. Kaya, I. Altas","doi":"10.1109/SIU.2006.1659685","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659685","url":null,"abstract":"While data speed provided by communication technologies and the data speed required for multimedia applications are competing with each other, the importance of OFDM technology, which has less intersymbol interference influences that occur in the channel, has been increasing. Deep fadings occurred as a result of multipath propagation because some sub carriers that loses its information as well as fading in a non-recoverable degree, and consequently results in a poorer system performance. Since the training speed of LMS algorithm used in estimation of channel coefficients in time domain for OFDM based systems is not generally sufficient to achieve the desired performance levels in training time defined by standards, a fuzzy logic based algorithm is adapted to get a faster performance. An application of fuzzy logic based high performance LMS algorithm for OFDM systems is investigated in this paper. The aim of the proposed method is to produce the required fuzzy rule base and fuzzy subsets for fuzzy logic controller in order to speed up the LMS algorithm. The generations of fuzzy rules are based on the comparison of estimated signal by equalizer or channel output. The obtained results of simulations show that the LMS algorithm based on fuzzy logic (F-LMS) increases the performance in OFDM systems significantly and converges to the performance of the RLS algorithm","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127716271","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 : 2006-04-17DOI: 10.1109/SIU.2006.1659758
V. Ozkaner, T. Kayikçioglu
In this study, a Markov model for gating kinetics of sodium channel currents in dissociated cerebellar Purkinje neurons is developed. The model is based on voltage-clamped, resurgent and action potential evoked currents, known as macroscopic currents. It is different from previously developed models. In this model, some modifications are made in the number of states and channel rate constants. The model parameters are determined using trial and error procedure to minimizing the error between model responses and three experimental data sets. The developed sodium channel model reproduces quantitatively all features of the experimental data sets, with minor discrepancies
{"title":"A Markov Model Developed For Sodium Channel Currents In Cerebellar Purkinje Neurons","authors":"V. Ozkaner, T. Kayikçioglu","doi":"10.1109/SIU.2006.1659758","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659758","url":null,"abstract":"In this study, a Markov model for gating kinetics of sodium channel currents in dissociated cerebellar Purkinje neurons is developed. The model is based on voltage-clamped, resurgent and action potential evoked currents, known as macroscopic currents. It is different from previously developed models. In this model, some modifications are made in the number of states and channel rate constants. The model parameters are determined using trial and error procedure to minimizing the error between model responses and three experimental data sets. The developed sodium channel model reproduces quantitatively all features of the experimental data sets, with minor discrepancies","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"182 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134311668","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 : 2006-04-17DOI: 10.1109/SIU.2006.1659705
T. Sonmez
The purpose of this paper is to analyze data association problem in sonar applications. Bearings only tracking algorithms are used because the range information is distorted in water. A method is proposed to associate detections with established sonar tracks using the distribution of the received signal. Using a single detection when two target's bearings are close to each other, may result in poor tracking capability. Splitting a single detection from two targets is a new method which has the potential to keep weaker target's track alive. This method is compared with PDA (probabilistic data association) filters. Monte Carlo simulation results are also given
{"title":"Splitting Algorithm for Cases with Single Detection from Sonar Data for Two Tracks","authors":"T. Sonmez","doi":"10.1109/SIU.2006.1659705","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659705","url":null,"abstract":"The purpose of this paper is to analyze data association problem in sonar applications. Bearings only tracking algorithms are used because the range information is distorted in water. A method is proposed to associate detections with established sonar tracks using the distribution of the received signal. Using a single detection when two target's bearings are close to each other, may result in poor tracking capability. Splitting a single detection from two targets is a new method which has the potential to keep weaker target's track alive. This method is compared with PDA (probabilistic data association) filters. Monte Carlo simulation results are also given","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134465731","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 : 2006-04-17DOI: 10.1109/SIU.2006.1659859
O.S. Sarac, V. Atalay, R. Atalay
Representation of amino-acid sequences constitutes the key point in classification of proteins into functional or structural classes. The representation should contain the biologically meaningful information hidden in the primary sequence of the protein. Conserved or similar subsequences are strong indicators of functional and structural similarity. In this study we present a feature mapping that takes into account the models of the subsequences of protein sequences. An expectation-maximization algorithm along with an HMM mixture model is used to cluster and learn the models of subsequences of a given set of proteins
{"title":"A Novel Model-based Method for Feature Extraction from Protein Sequences for Classification","authors":"O.S. Sarac, V. Atalay, R. Atalay","doi":"10.1109/SIU.2006.1659859","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659859","url":null,"abstract":"Representation of amino-acid sequences constitutes the key point in classification of proteins into functional or structural classes. The representation should contain the biologically meaningful information hidden in the primary sequence of the protein. Conserved or similar subsequences are strong indicators of functional and structural similarity. In this study we present a feature mapping that takes into account the models of the subsequences of protein sequences. An expectation-maximization algorithm along with an HMM mixture model is used to cluster and learn the models of subsequences of a given set of proteins","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"480 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133048622","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 : 2006-04-17DOI: 10.1109/SIU.2006.1659769
M. Karar, K. Gulec, A. Carkacioglu
In this paper, we have been developing a system that searches Web pages for various depths based on predefined strings within given time intervals. Problems encountered during development and their solutions are discussed. It is observed that the number of Web pages found increased proportionally to the number of strings searched, where the quality of the found pages did not increase as well as the number of strings increased. Consequently, it became a necessity to add artificial intelligence methods to evaluate the quality of Web pages found. Thus, Web pages found by searching the Internet sites can be ranked so that pages in interest are selected automatically
{"title":"Searching Web Pages Based on Predefined Strings","authors":"M. Karar, K. Gulec, A. Carkacioglu","doi":"10.1109/SIU.2006.1659769","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659769","url":null,"abstract":"In this paper, we have been developing a system that searches Web pages for various depths based on predefined strings within given time intervals. Problems encountered during development and their solutions are discussed. It is observed that the number of Web pages found increased proportionally to the number of strings searched, where the quality of the found pages did not increase as well as the number of strings increased. Consequently, it became a necessity to add artificial intelligence methods to evaluate the quality of Web pages found. Thus, Web pages found by searching the Internet sites can be ranked so that pages in interest are selected automatically","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134154635","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 : 2006-04-17DOI: 10.1109/SIU.2006.1659821
M. Bastan, Pinar Duygulu
We propose a new approach to object recognition problem motivated by the availability of large annotated image and video collections. Similar to translation from one language to another, this approach considers the object recognition problem as the translation of visual elements to words. The visual elements represented in feature space are first categorized into a finite set of blobs. Then, the correspondences between the blobs and the words are learned using a method adapted from statistical machine translation. Finally, the correspondences, in the form of a probability table, are used to predict words for particular image regions (region naming), for entire images (auto-annotation), or to associate the automatically generated speech transcript text with the correct video frames (video alignment). Experimental results are presented on TRECVID 2004 data set, which consists of about 150 hours of news videos associated with manual annotations and speech transcript text.
{"title":"Object Recognition and Auto-annotation In News Videos","authors":"M. Bastan, Pinar Duygulu","doi":"10.1109/SIU.2006.1659821","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659821","url":null,"abstract":"We propose a new approach to object recognition problem motivated by the availability of large annotated image and video collections. Similar to translation from one language to another, this approach considers the object recognition problem as the translation of visual elements to words. The visual elements represented in feature space are first categorized into a finite set of blobs. Then, the correspondences between the blobs and the words are learned using a method adapted from statistical machine translation. Finally, the correspondences, in the form of a probability table, are used to predict words for particular image regions (region naming), for entire images (auto-annotation), or to associate the automatically generated speech transcript text with the correct video frames (video alignment). Experimental results are presented on TRECVID 2004 data set, which consists of about 150 hours of news videos associated with manual annotations and speech transcript text.","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"462 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131796204","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 : 2006-04-17DOI: 10.1109/SIU.2006.1659713
E. Ayaz, A. Ozturk, S. Seker
The purpose of this paper is to extract features from vibration signals measured from induction motors subjected to accelerated bearing fluting aging. The signals taken from accelerometers placed near to process end bearing were first combined using simple sensor fusion method and then spectral analysis and time-scale analysis were performed. Fused vibration signals were decomposed into several scales using continuous wavelet transform analysis and selected scales was further investigated to get detailed information relating to bearing damage features. And also the advantage of the continuous wavelet transform over Fourier transform was emphasized in terms of getting the bearing damage between 2-4 kHz and this frequency band was interpreted as a joint feature for both of the healthy and aged motor cases. And also, the transfer function to indicate the bearing damage was represented
{"title":"A Study on Continuous Wavelet Transform for Fault Detection in Electric Motors","authors":"E. Ayaz, A. Ozturk, S. Seker","doi":"10.1109/SIU.2006.1659713","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659713","url":null,"abstract":"The purpose of this paper is to extract features from vibration signals measured from induction motors subjected to accelerated bearing fluting aging. The signals taken from accelerometers placed near to process end bearing were first combined using simple sensor fusion method and then spectral analysis and time-scale analysis were performed. Fused vibration signals were decomposed into several scales using continuous wavelet transform analysis and selected scales was further investigated to get detailed information relating to bearing damage features. And also the advantage of the continuous wavelet transform over Fourier transform was emphasized in terms of getting the bearing damage between 2-4 kHz and this frequency band was interpreted as a joint feature for both of the healthy and aged motor cases. And also, the transfer function to indicate the bearing damage was represented","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133403003","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 : 2006-04-17DOI: 10.1109/SIU.2006.1659880
E.S. Ugurlu, G. Biricik
In Q-learning, the aim is to reach the goal by using state and action pairs. When the goal is set as a big reward, the optimal path is found as soon as the reward accumulated reaches its highest value. Upon modification of the start and goal points, the information concerning how to reach the goal becomes useless even if the environment does not change. In this study, Q-learning is improved by making the usage of the past data possible. To achieve this, action probabilities for certain start and goal points are found and a neural network is trained with those values to estimate the action probabilities for other start and goal points. A radial basis function network is used as neural network for it can support local representation and can learn fast when there is a few number of inputs. When Q-learning is run with the found action probabilities, an increase in speed is observed in reaching the goal
{"title":"Q-Learning with Probability Based Action Policy","authors":"E.S. Ugurlu, G. Biricik","doi":"10.1109/SIU.2006.1659880","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659880","url":null,"abstract":"In Q-learning, the aim is to reach the goal by using state and action pairs. When the goal is set as a big reward, the optimal path is found as soon as the reward accumulated reaches its highest value. Upon modification of the start and goal points, the information concerning how to reach the goal becomes useless even if the environment does not change. In this study, Q-learning is improved by making the usage of the past data possible. To achieve this, action probabilities for certain start and goal points are found and a neural network is trained with those values to estimate the action probabilities for other start and goal points. A radial basis function network is used as neural network for it can support local representation and can learn fast when there is a few number of inputs. When Q-learning is run with the found action probabilities, an increase in speed is observed in reaching the goal","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133205705","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：