Pub Date : 2016-06-23DOI: 10.1109/SIU.2016.7495943
S. Ay, Yavuz Selim Dogan, Seyfullah Alver, Cetin Kaya
Thanks to the proliferation of Internet, a lot of data are produced by both Web sites and personal users. The documents are required to be classified in terms of their content in order to reach the necessary information fast and correctly from produced data. One of the biggest difficulties in document classification systems is detection of attribute that represent the classes in best way. In this research, a new attribute method is presented by using a Genetic Algorithm for document classification problem. This proposed method is tested on 450 documents that are from 6 different categories collected from a news portal that broadcasts online. According to experimental results 93% of success is achieved with the proposed method.
{"title":"A novel attribute weighting method with genetic algorithm for document classification","authors":"S. Ay, Yavuz Selim Dogan, Seyfullah Alver, Cetin Kaya","doi":"10.1109/SIU.2016.7495943","DOIUrl":"https://doi.org/10.1109/SIU.2016.7495943","url":null,"abstract":"Thanks to the proliferation of Internet, a lot of data are produced by both Web sites and personal users. The documents are required to be classified in terms of their content in order to reach the necessary information fast and correctly from produced data. One of the biggest difficulties in document classification systems is detection of attribute that represent the classes in best way. In this research, a new attribute method is presented by using a Genetic Algorithm for document classification problem. This proposed method is tested on 450 documents that are from 6 different categories collected from a news portal that broadcasts online. According to experimental results 93% of success is achieved with the proposed method.","PeriodicalId":427250,"journal":{"name":"2016 24th Signal Processing and Communication Application Conference (SIU)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130793157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-23DOI: 10.1109/SIU.2016.7495769
Abdullah H. Ozcan, C. Ünsalan
Automated object detection in remotely sensed data has gained wide application areas due to increased sensor resolution. In this study, we propose a novel building detection method using high resolution DSM data and true orthophoto image. In the proposed method, DSM feature points and NDVI are obtained. Then, they are used for spatial voting to generate a building probability map. Local maxima of this map are used as seed points for segmentation. For this purpose, a morphology based segmentation method is proposed. This way, buildings are detected from DSM data. We tested our method on ISPRS semantic labeling dataset and obtained promising results.
{"title":"Building detection with spatial voting and morphology based segmentation","authors":"Abdullah H. Ozcan, C. Ünsalan","doi":"10.1109/SIU.2016.7495769","DOIUrl":"https://doi.org/10.1109/SIU.2016.7495769","url":null,"abstract":"Automated object detection in remotely sensed data has gained wide application areas due to increased sensor resolution. In this study, we propose a novel building detection method using high resolution DSM data and true orthophoto image. In the proposed method, DSM feature points and NDVI are obtained. Then, they are used for spatial voting to generate a building probability map. Local maxima of this map are used as seed points for segmentation. For this purpose, a morphology based segmentation method is proposed. This way, buildings are detected from DSM data. We tested our method on ISPRS semantic labeling dataset and obtained promising results.","PeriodicalId":427250,"journal":{"name":"2016 24th Signal Processing and Communication Application Conference (SIU)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129702586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-23DOI: 10.1109/SIU.2016.7495834
Cansu Özkan, Seda Doğan, T. Uğur, M. Aksahin, A. Erdamar
The diagnosis of the epilepsy diseases are made by physicians with analyzing the electroencephalography (EEG) records. The epilepsy diseases can be determined with observing the main properties of before and on-time seizure signals in time and frequency domain. Physicians are evaluating the results after some necessary scoring on EEG records. However, this evaluation is specialistic, time consuming processes and also may subjective results. At this point, to allow detection of epilepsy diseases, a decision support system can give more objective results to the physicians for diagnosing. The subject of the study is automatically diagnosing the epilepsy diseases on EEG signals. In the proposed study, analyses of EEG signals in time and frequency domain were done and features of diseases were obtained. As a result, using artificial neural network (ANN) and obtained features, a decision support system is realized to diagnose the epilepsy. The specificity and the sensitivity of the algorithm are 94% and 66% respectively.
{"title":"Detection of epilepsy disease from EEG signals with artificial neural networks","authors":"Cansu Özkan, Seda Doğan, T. Uğur, M. Aksahin, A. Erdamar","doi":"10.1109/SIU.2016.7495834","DOIUrl":"https://doi.org/10.1109/SIU.2016.7495834","url":null,"abstract":"The diagnosis of the epilepsy diseases are made by physicians with analyzing the electroencephalography (EEG) records. The epilepsy diseases can be determined with observing the main properties of before and on-time seizure signals in time and frequency domain. Physicians are evaluating the results after some necessary scoring on EEG records. However, this evaluation is specialistic, time consuming processes and also may subjective results. At this point, to allow detection of epilepsy diseases, a decision support system can give more objective results to the physicians for diagnosing. The subject of the study is automatically diagnosing the epilepsy diseases on EEG signals. In the proposed study, analyses of EEG signals in time and frequency domain were done and features of diseases were obtained. As a result, using artificial neural network (ANN) and obtained features, a decision support system is realized to diagnose the epilepsy. The specificity and the sensitivity of the algorithm are 94% and 66% respectively.","PeriodicalId":427250,"journal":{"name":"2016 24th Signal Processing and Communication Application Conference (SIU)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134039712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-23DOI: 10.1109/SIU.2016.7496211
D. G. Duru, A. Duru
In the last few decades, the relationship between the mental workload and electrophysiological measurements are being studied. The aim of this study is to measure the electrophysiological responses of the autonomic and central nervous system to the increased mental workload. In this concept, backwards counting paradigm is used to increase the mental workload while the brain electrical activity (EEG), hearth rate variability (HRV) and electrodermal activity has been measured synchronously. During the increased mental workload, EEG alpha band suppression and increased EDA were observed. On the other hand, hearth rate variability has not been changed with respect to paradigm.
{"title":"Investigation of electrophysiological features during mental workload paradigm","authors":"D. G. Duru, A. Duru","doi":"10.1109/SIU.2016.7496211","DOIUrl":"https://doi.org/10.1109/SIU.2016.7496211","url":null,"abstract":"In the last few decades, the relationship between the mental workload and electrophysiological measurements are being studied. The aim of this study is to measure the electrophysiological responses of the autonomic and central nervous system to the increased mental workload. In this concept, backwards counting paradigm is used to increase the mental workload while the brain electrical activity (EEG), hearth rate variability (HRV) and electrodermal activity has been measured synchronously. During the increased mental workload, EEG alpha band suppression and increased EDA were observed. On the other hand, hearth rate variability has not been changed with respect to paradigm.","PeriodicalId":427250,"journal":{"name":"2016 24th Signal Processing and Communication Application Conference (SIU)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116983094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-23DOI: 10.1109/SIU.2016.7496165
Ahmet Cakiroglu
Joint Probabilistic Data Association Filter (JPDAF) is an algorithm for overcoming the measurement-to-track association problem in multi-target tracking systems. JPDAF requires that the number of targets being tracked is a foreknown, constant parameter. Therefore, targets exiting and entering into the field of view reduces the tracking performance of JPDAF. In this work, an algorithm which makes it possible to use JPDAF for tracking variable number of targets is presented.
{"title":"Tracking variable number of targets with Joint Probabilistic Data Association Filter","authors":"Ahmet Cakiroglu","doi":"10.1109/SIU.2016.7496165","DOIUrl":"https://doi.org/10.1109/SIU.2016.7496165","url":null,"abstract":"Joint Probabilistic Data Association Filter (JPDAF) is an algorithm for overcoming the measurement-to-track association problem in multi-target tracking systems. JPDAF requires that the number of targets being tracked is a foreknown, constant parameter. Therefore, targets exiting and entering into the field of view reduces the tracking performance of JPDAF. In this work, an algorithm which makes it possible to use JPDAF for tracking variable number of targets is presented.","PeriodicalId":427250,"journal":{"name":"2016 24th Signal Processing and Communication Application Conference (SIU)","volume":"2015 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128049381","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-23DOI: 10.1109/SIU.2016.7496127
Ozlem Tugfe Demir, T. E. Tuncer
In this paper, multi-group multicasting scenario is considered where single antenna sources transmit their own information to different groups of users with the help of single antenna relays. Users have energy harvesting capability, i.e., a part of the received signal is used for information decoding while the rest is used for energy harvesting. Beamforming is performed by the relays which use amplify-and-forward protocol. The design of complex relay coefficients and power splitting ratios for the users is studied and the resulting nonconvex optimization problem is converted into a form suitable for quadratically constrained quadratic programming. In this paper, phase-only beamforming is also considered and both problems are solved iteratively.
{"title":"Relay-assisted beamforming for multicast systems with energy harvesting capability","authors":"Ozlem Tugfe Demir, T. E. Tuncer","doi":"10.1109/SIU.2016.7496127","DOIUrl":"https://doi.org/10.1109/SIU.2016.7496127","url":null,"abstract":"In this paper, multi-group multicasting scenario is considered where single antenna sources transmit their own information to different groups of users with the help of single antenna relays. Users have energy harvesting capability, i.e., a part of the received signal is used for information decoding while the rest is used for energy harvesting. Beamforming is performed by the relays which use amplify-and-forward protocol. The design of complex relay coefficients and power splitting ratios for the users is studied and the resulting nonconvex optimization problem is converted into a form suitable for quadratically constrained quadratic programming. In this paper, phase-only beamforming is also considered and both problems are solved iteratively.","PeriodicalId":427250,"journal":{"name":"2016 24th Signal Processing and Communication Application Conference (SIU)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131372521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-23DOI: 10.1109/SIU.2016.7495827
Eyyup Temlioglu, M. Dag, Ridvan Gurcan
Ground Penetrating Radar (GPR) senses dielectric discontinuities below the surface. Thus, it can detect low-metal and non-metal landmines. However, it detects not only landmines but also all objects under the ground and therefore, false alarm rates of GPR are very high. Powerful feature based algorithms are necessary to reduce false alarm rates and to distinguish landmine from clutter that causes false alarms. In this paper, Binary Robust Independent Elementary Features (BRIEF), Edge Histogram Descriptor (EHD), Histogram of Oriented Gradients (HOG), Scale Invariant Feature Transform (SIFT) and Speeded Up Robust Features (SURF) feature extraction methods are implemented to landmine detection problem. The methods are compared with extended data sets collected from different soil types by using surrogate landmines and other objects. Receiver Operating Characteristic (ROC) curves are calculated for comparison of methods and it is shown that the HOG outperforms other methods.
{"title":"Comparison of feature extraction methods for landmine detection using Ground Penetrating Radar","authors":"Eyyup Temlioglu, M. Dag, Ridvan Gurcan","doi":"10.1109/SIU.2016.7495827","DOIUrl":"https://doi.org/10.1109/SIU.2016.7495827","url":null,"abstract":"Ground Penetrating Radar (GPR) senses dielectric discontinuities below the surface. Thus, it can detect low-metal and non-metal landmines. However, it detects not only landmines but also all objects under the ground and therefore, false alarm rates of GPR are very high. Powerful feature based algorithms are necessary to reduce false alarm rates and to distinguish landmine from clutter that causes false alarms. In this paper, Binary Robust Independent Elementary Features (BRIEF), Edge Histogram Descriptor (EHD), Histogram of Oriented Gradients (HOG), Scale Invariant Feature Transform (SIFT) and Speeded Up Robust Features (SURF) feature extraction methods are implemented to landmine detection problem. The methods are compared with extended data sets collected from different soil types by using surrogate landmines and other objects. Receiver Operating Characteristic (ROC) curves are calculated for comparison of methods and it is shown that the HOG outperforms other methods.","PeriodicalId":427250,"journal":{"name":"2016 24th Signal Processing and Communication Application Conference (SIU)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116655870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-05-16DOI: 10.1109/SIU.2016.7495860
S. Guney, Murat Bilen
In this study, a robot with different maneuvras is followed with different estimation algorithms. The mobile robot has acted first linear, then maneuver and finally linear again. It's speed is constant through the way. Standard Kalman Filter, Adaptive Kalman Filter, Extended Kalman Filter and Interacting Multiple Model consist of multiple model Kalman Filter combined of linear and non-linear model are used to follow the act of the robot. The results of these estimations are compared with each other. Multiple model Kalman Filter is the best estimation algorithm among them for this motion model.
{"title":"The comparison of estimation algorithms for mobile robot navigation","authors":"S. Guney, Murat Bilen","doi":"10.1109/SIU.2016.7495860","DOIUrl":"https://doi.org/10.1109/SIU.2016.7495860","url":null,"abstract":"In this study, a robot with different maneuvras is followed with different estimation algorithms. The mobile robot has acted first linear, then maneuver and finally linear again. It's speed is constant through the way. Standard Kalman Filter, Adaptive Kalman Filter, Extended Kalman Filter and Interacting Multiple Model consist of multiple model Kalman Filter combined of linear and non-linear model are used to follow the act of the robot. The results of these estimations are compared with each other. Multiple model Kalman Filter is the best estimation algorithm among them for this motion model.","PeriodicalId":427250,"journal":{"name":"2016 24th Signal Processing and Communication Application Conference (SIU)","volume":"185 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115422882","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-05-16DOI: 10.1109/SIU.2016.7495737
Meltem Kurt PehlIvanoõlu, N. Duru
Developing technology threaten to the information security and privacy. Today, for data transfer in a private and secure environment, the use of encryption methods or cryptographic systems are inevitable. In this study WHT (Walsh-Hadamard Transform) that is used, one of the transforms that used image processing techniques such as attribute extraction on image files, text analysis, filtering, compression. Image pixel values obtained at the end of transformation encrypt with AES (Advanced Encryption Standard) encryption algorithm. Using encryption pixel values encrypted txt file was obtained.
{"title":"Encryption of Walsh Hadamard Transform applied images with the AES encryption algorithm","authors":"Meltem Kurt PehlIvanoõlu, N. Duru","doi":"10.1109/SIU.2016.7495737","DOIUrl":"https://doi.org/10.1109/SIU.2016.7495737","url":null,"abstract":"Developing technology threaten to the information security and privacy. Today, for data transfer in a private and secure environment, the use of encryption methods or cryptographic systems are inevitable. In this study WHT (Walsh-Hadamard Transform) that is used, one of the transforms that used image processing techniques such as attribute extraction on image files, text analysis, filtering, compression. Image pixel values obtained at the end of transformation encrypt with AES (Advanced Encryption Standard) encryption algorithm. Using encryption pixel values encrypted txt file was obtained.","PeriodicalId":427250,"journal":{"name":"2016 24th Signal Processing and Communication Application Conference (SIU)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123067403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-05-16DOI: 10.1109/SIU.2016.7495704
Abbas Memiş, F. Karabiber
In this paper, we present face recognition systems, which are performed by using appearance based methods on mobile environment face images, and their comparative performance analysis. In proposed systems, face detection process is performed by using Haar-like features and cascade classifiers on mobile environment face images. Color space transformation, dimensional normalization and histogram equalization operations are performed on detected face images as pre-processing steps. Principal Component Analysis, Fisher's Linear Discriminant Analysis and Local Binary Pattern Histograms methods are used to extract facial features. K-nearest neighbor classifier is employed for the performance analysis of implemented methods. Accuracy, precision, recall and F-measure values are measured and compared in performance evaluations of selected facial recognition methods on various dimensionally normalized face images. Experimental results obtained using MOBIO face database show that Local Binary Pattern Histograms method has high success rates on mobile environment images.
{"title":"Face recognition on mobile environment images using appearance based methods","authors":"Abbas Memiş, F. Karabiber","doi":"10.1109/SIU.2016.7495704","DOIUrl":"https://doi.org/10.1109/SIU.2016.7495704","url":null,"abstract":"In this paper, we present face recognition systems, which are performed by using appearance based methods on mobile environment face images, and their comparative performance analysis. In proposed systems, face detection process is performed by using Haar-like features and cascade classifiers on mobile environment face images. Color space transformation, dimensional normalization and histogram equalization operations are performed on detected face images as pre-processing steps. Principal Component Analysis, Fisher's Linear Discriminant Analysis and Local Binary Pattern Histograms methods are used to extract facial features. K-nearest neighbor classifier is employed for the performance analysis of implemented methods. Accuracy, precision, recall and F-measure values are measured and compared in performance evaluations of selected facial recognition methods on various dimensionally normalized face images. Experimental results obtained using MOBIO face database show that Local Binary Pattern Histograms method has high success rates on mobile environment images.","PeriodicalId":427250,"journal":{"name":"2016 24th Signal Processing and Communication Application Conference (SIU)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116905129","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：