Pub Date : 2012-04-18DOI: 10.1109/SIU.2012.6204531
Engin Karacan, E. Kılıç
In this study, a novel methodology based on Support Vector Machine (SVM) is proposed. In the proposed method, the sigma value belonging to the radial based function which is being used as the kernel function for the support vector machine is computed by using an adaptive mechanism. By this means, a new kind of SVM which can be defined as “Adaptive SVM” (ASVM) is proposed, and smart diagnosis of the breast cancer is aimed. During the training and test phases of this newly designed smart system, the prognostic breast cancer dataset which is provided from University of California is used. It is observed that the novel methodology which is firstly proposed in this study has a correct classification rate of 94.29% on the prognostic breast cancer dataset.
{"title":"Diagnosis of breast cancer with an innovative adaptive Support Vector Machine","authors":"Engin Karacan, E. Kılıç","doi":"10.1109/SIU.2012.6204531","DOIUrl":"https://doi.org/10.1109/SIU.2012.6204531","url":null,"abstract":"In this study, a novel methodology based on Support Vector Machine (SVM) is proposed. In the proposed method, the sigma value belonging to the radial based function which is being used as the kernel function for the support vector machine is computed by using an adaptive mechanism. By this means, a new kind of SVM which can be defined as “Adaptive SVM” (ASVM) is proposed, and smart diagnosis of the breast cancer is aimed. During the training and test phases of this newly designed smart system, the prognostic breast cancer dataset which is provided from University of California is used. It is observed that the novel methodology which is firstly proposed in this study has a correct classification rate of 94.29% on the prognostic breast cancer dataset.","PeriodicalId":256154,"journal":{"name":"2012 20th Signal Processing and Communications Applications Conference (SIU)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114301890","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 : 2012-04-18DOI: 10.1109/SIU.2012.6204476
Erdinç Uzun, Hayri Volkan Agun, T. Yerlikaya
Via information extraction techniques, web pages are able to generate datasets for various studies such as natural language processing, and data mining. However, nowadays the uninformative sections like advertisement, menus, and links are in increase. The cleaning of web pages from uninformative sections, and extraction of informative content has become an important issue. In this study, we present an decision tree learning approach over DOM based features which aims to clean the uninformative sections and extract informative content in three classes: title, main content, and additional information. Through this approach, differently from previous studies, the learning model for the extraction of the main content constructed on DIV and TD tags. The proposed method achieved 95.58% accuracy in cleaning uninformative sections and extraction of the informative content. Especially for the extraction of the main block, 0.96 f-measure is obtained.
{"title":"Web content extraction by using decision tree learning","authors":"Erdinç Uzun, Hayri Volkan Agun, T. Yerlikaya","doi":"10.1109/SIU.2012.6204476","DOIUrl":"https://doi.org/10.1109/SIU.2012.6204476","url":null,"abstract":"Via information extraction techniques, web pages are able to generate datasets for various studies such as natural language processing, and data mining. However, nowadays the uninformative sections like advertisement, menus, and links are in increase. The cleaning of web pages from uninformative sections, and extraction of informative content has become an important issue. In this study, we present an decision tree learning approach over DOM based features which aims to clean the uninformative sections and extract informative content in three classes: title, main content, and additional information. Through this approach, differently from previous studies, the learning model for the extraction of the main content constructed on DIV and TD tags. The proposed method achieved 95.58% accuracy in cleaning uninformative sections and extraction of the informative content. Especially for the extraction of the main block, 0.96 f-measure is obtained.","PeriodicalId":256154,"journal":{"name":"2012 20th Signal Processing and Communications Applications Conference (SIU)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121653063","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 : 2012-04-18DOI: 10.1109/SIU.2012.6204538
Mehmet Kabasakal, C. Toker
In this paper, feature based modulation classifiers are investigated for AM, DSB, LSB, USB and FM analog modulations methods. Instantaneous phase, magnitude and spectrum of the signals to be classified are used for the calculation of the key features. At the decision step decision tree, minimum distance classifier and support vector machines are used. Then the performance of the developed classifiers is assessed through computer simulations and the decision tree classifier is realized on an USRP software radio platform.
{"title":"Investigation of automatic analog modulation classification algorithms","authors":"Mehmet Kabasakal, C. Toker","doi":"10.1109/SIU.2012.6204538","DOIUrl":"https://doi.org/10.1109/SIU.2012.6204538","url":null,"abstract":"In this paper, feature based modulation classifiers are investigated for AM, DSB, LSB, USB and FM analog modulations methods. Instantaneous phase, magnitude and spectrum of the signals to be classified are used for the calculation of the key features. At the decision step decision tree, minimum distance classifier and support vector machines are used. Then the performance of the developed classifiers is assessed through computer simulations and the decision tree classifier is realized on an USRP software radio platform.","PeriodicalId":256154,"journal":{"name":"2012 20th Signal Processing and Communications Applications Conference (SIU)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126378934","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 : 2012-04-18DOI: 10.1109/SIU.2012.6204834
T. Özkurt, M. Butz, A. Schnitzler
Traditional analysis of brain signals is often realized under assumptions such as stationarity, linearity, predetermined frequency bands and basis functions. These strong assumptions imposed on brain signals might cause distortions leading to improper results. This study adapts a data-driven approach called `empirical mode decomposition' in order to avoid unrealistic assumptions and minimize the parameter space. In this respect, we confront with the issues of band range determination and coherent source localization. Magnetoencephalographic (MEG) data and local field potentials (LFP) acquired from a Parkinson disease patient are used to demonstrate the use of the suggested methods.
{"title":"Adaptive determination of brain oscillatory activity","authors":"T. Özkurt, M. Butz, A. Schnitzler","doi":"10.1109/SIU.2012.6204834","DOIUrl":"https://doi.org/10.1109/SIU.2012.6204834","url":null,"abstract":"Traditional analysis of brain signals is often realized under assumptions such as stationarity, linearity, predetermined frequency bands and basis functions. These strong assumptions imposed on brain signals might cause distortions leading to improper results. This study adapts a data-driven approach called `empirical mode decomposition' in order to avoid unrealistic assumptions and minimize the parameter space. In this respect, we confront with the issues of band range determination and coherent source localization. Magnetoencephalographic (MEG) data and local field potentials (LFP) acquired from a Parkinson disease patient are used to demonstrate the use of the suggested methods.","PeriodicalId":256154,"journal":{"name":"2012 20th Signal Processing and Communications Applications Conference (SIU)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125998113","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 : 2012-04-18DOI: 10.1109/SIU.2012.6204764
Nurpinar Akdeniz, H. Tora
This study evaluates the implementation of Balanced Contrast Limited Adaptive Histogram Equalization (BCLAHE) for infrared images (IR) on an embedded platform. The aim was to achieve real time performance for the operator display target application. The system configured for this aim is a dual processor media application device OMAP3530, which consists of an ARM and a DSP processor. System is configured so that hardware sources are used efficiently and various performance improvement techniques are investigated. Performance analysis is done over IR images with different dynamic range.
{"title":"Real time infrared image enhancement","authors":"Nurpinar Akdeniz, H. Tora","doi":"10.1109/SIU.2012.6204764","DOIUrl":"https://doi.org/10.1109/SIU.2012.6204764","url":null,"abstract":"This study evaluates the implementation of Balanced Contrast Limited Adaptive Histogram Equalization (BCLAHE) for infrared images (IR) on an embedded platform. The aim was to achieve real time performance for the operator display target application. The system configured for this aim is a dual processor media application device OMAP3530, which consists of an ARM and a DSP processor. System is configured so that hardware sources are used efficiently and various performance improvement techniques are investigated. Performance analysis is done over IR images with different dynamic range.","PeriodicalId":256154,"journal":{"name":"2012 20th Signal Processing and Communications Applications Conference (SIU)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134514551","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 : 2012-04-18DOI: 10.1109/SIU.2012.6204768
Kadir Eraltay, Yakup S. Özkazanç
This paper reports some of our studies concerning the countermeasures against FMCW radars. Generation and the effects of noise jamming and deceptive jamming signals on FMCW radars are studied via detailed simulation models.
{"title":"Jamming of FMCW radars","authors":"Kadir Eraltay, Yakup S. Özkazanç","doi":"10.1109/SIU.2012.6204768","DOIUrl":"https://doi.org/10.1109/SIU.2012.6204768","url":null,"abstract":"This paper reports some of our studies concerning the countermeasures against FMCW radars. Generation and the effects of noise jamming and deceptive jamming signals on FMCW radars are studied via detailed simulation models.","PeriodicalId":256154,"journal":{"name":"2012 20th Signal Processing and Communications Applications Conference (SIU)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133904043","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 : 2012-04-18DOI: 10.1109/SIU.2012.6204603
Berk Ozer, A. Altintas, G. Moral, O. Arikan
In this study, Particle Swarm Optimization(PSO) is proposed for change point (edge) detection on noisy ramped signals. By taking moving averages between detected edges, noise on ramped signals is filtered and desired piecewise constant signals are acquired. It is required to detect edges in the immediate vicinity of actual edges. Performance of PSO is measured by the difference between estimated and actual position of edges. It is not possible to satisfy such a condition by standard PSO. Hence, in this work, two modifications to standard PSO are proposed: “PSO with uniformly distributed position vectors” and “Cascading PSO”. Throughout this work, all implementations are done on real signals which indicate generated powers by plants.
{"title":"Piecewise constant line fitting on noisy ramped signals by Particle Swarm Optimization","authors":"Berk Ozer, A. Altintas, G. Moral, O. Arikan","doi":"10.1109/SIU.2012.6204603","DOIUrl":"https://doi.org/10.1109/SIU.2012.6204603","url":null,"abstract":"In this study, Particle Swarm Optimization(PSO) is proposed for change point (edge) detection on noisy ramped signals. By taking moving averages between detected edges, noise on ramped signals is filtered and desired piecewise constant signals are acquired. It is required to detect edges in the immediate vicinity of actual edges. Performance of PSO is measured by the difference between estimated and actual position of edges. It is not possible to satisfy such a condition by standard PSO. Hence, in this work, two modifications to standard PSO are proposed: “PSO with uniformly distributed position vectors” and “Cascading PSO”. Throughout this work, all implementations are done on real signals which indicate generated powers by plants.","PeriodicalId":256154,"journal":{"name":"2012 20th Signal Processing and Communications Applications Conference (SIU)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133969819","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 : 2012-04-18DOI: 10.1109/SIU.2012.6204652
Caglar Oflazoglu, S. Yıldırım
An emerging trend in human-computer interaction technology is to design spoken interfaces that facilitate more natural interaction between a user and a computer. Being able to detect the user's affective state during interaction is one of the key steps toward implementing such interfaces. In this study, anger recognition from Turkish speech using acoustic information is explored. The relative importance of acoustic feature categories in anger recognition is examined. Results show that logarithmic power of Mel-frequency bands, mel frequency cepstral coefficients and perceptual linear predictive coefficients are relatively more important than other acoustic categories in the context of anger recognition. Results also show that unweighted recall of 75.8% is obtained when correlation based feature selection method and Naive Bayes classifier are used.
{"title":"Anger recognition in Turkish speech using acoustic information","authors":"Caglar Oflazoglu, S. Yıldırım","doi":"10.1109/SIU.2012.6204652","DOIUrl":"https://doi.org/10.1109/SIU.2012.6204652","url":null,"abstract":"An emerging trend in human-computer interaction technology is to design spoken interfaces that facilitate more natural interaction between a user and a computer. Being able to detect the user's affective state during interaction is one of the key steps toward implementing such interfaces. In this study, anger recognition from Turkish speech using acoustic information is explored. The relative importance of acoustic feature categories in anger recognition is examined. Results show that logarithmic power of Mel-frequency bands, mel frequency cepstral coefficients and perceptual linear predictive coefficients are relatively more important than other acoustic categories in the context of anger recognition. Results also show that unweighted recall of 75.8% is obtained when correlation based feature selection method and Naive Bayes classifier are used.","PeriodicalId":256154,"journal":{"name":"2012 20th Signal Processing and Communications Applications Conference (SIU)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126587930","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 : 2012-04-18DOI: 10.1109/SIU.2012.6204586
S. Oztürk, Ö. C. Gürol, B. Sankur, B. Acar, Mehmet Güney
This paper presents the estimation of the vergence region, which is defined by the set of zero disparity points on the stereo images, in the form of the best border line separating the positive and negative disparities, by using a sparse disparity map. Sparse disparities are summed along radiating directions and the best direction to separate the sparse map is found by means of the metrics defined over the resultant sum function. The resulting border line points correspond to the points which will be perceived on the screen when the scene is displayed in three dimensions. This method requires the use of the stereo images with a certain spatial distribution of disparities, where the positive and negative disparities are grouped together.
{"title":"Vergence region estimation from sparse disparity map","authors":"S. Oztürk, Ö. C. Gürol, B. Sankur, B. Acar, Mehmet Güney","doi":"10.1109/SIU.2012.6204586","DOIUrl":"https://doi.org/10.1109/SIU.2012.6204586","url":null,"abstract":"This paper presents the estimation of the vergence region, which is defined by the set of zero disparity points on the stereo images, in the form of the best border line separating the positive and negative disparities, by using a sparse disparity map. Sparse disparities are summed along radiating directions and the best direction to separate the sparse map is found by means of the metrics defined over the resultant sum function. The resulting border line points correspond to the points which will be perceived on the screen when the scene is displayed in three dimensions. This method requires the use of the stereo images with a certain spatial distribution of disparities, where the positive and negative disparities are grouped together.","PeriodicalId":256154,"journal":{"name":"2012 20th Signal Processing and Communications Applications Conference (SIU)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133091441","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 : 2012-04-18DOI: 10.1109/SIU.2012.6204628
Gonca Bulur, A. Şahin
A new Ground Penetrating Radar (GPR) system, which is a combination of Optical Fiber Sensor (OFS), GPR and optical communication link, is developed to determine the depth and the position of the buried circular cylinder. Optical Fiber Sensor offers the advantage of Electromagnetic Interference (EMI) immunity and low amplification noise. In this study the electric field distribution at the OFS caused by the Continuous Radio Wave (CRW), which is transmitted from the GPR antenna, is obtained mathematically and its corresponding OFS output voltage measurement is simulated. Various plots are obtained by changing the depth of the cylinder and the operation frequency of the system. Plots exhibit a relation between x axis displacement and measured OFS voltages, and the resultant interference fringe patterns are analyzed. The depth and the position of the cylinder can be determined using interference fringe patterns.
{"title":"Determination of depth and position of buried objects with Optical Fiber Sensor integrated Ground Penetrating Radar","authors":"Gonca Bulur, A. Şahin","doi":"10.1109/SIU.2012.6204628","DOIUrl":"https://doi.org/10.1109/SIU.2012.6204628","url":null,"abstract":"A new Ground Penetrating Radar (GPR) system, which is a combination of Optical Fiber Sensor (OFS), GPR and optical communication link, is developed to determine the depth and the position of the buried circular cylinder. Optical Fiber Sensor offers the advantage of Electromagnetic Interference (EMI) immunity and low amplification noise. In this study the electric field distribution at the OFS caused by the Continuous Radio Wave (CRW), which is transmitted from the GPR antenna, is obtained mathematically and its corresponding OFS output voltage measurement is simulated. Various plots are obtained by changing the depth of the cylinder and the operation frequency of the system. Plots exhibit a relation between x axis displacement and measured OFS voltages, and the resultant interference fringe patterns are analyzed. The depth and the position of the cylinder can be determined using interference fringe patterns.","PeriodicalId":256154,"journal":{"name":"2012 20th Signal Processing and Communications Applications Conference (SIU)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132658414","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：