Pub Date : 2006-04-17DOI: 10.1109/SIU.2006.1659780
M. Zeybek, M.M. Tavli, D. Kuntalp, M. Kuntalp
Automation systems are commonly used in various areas nowadays. Thanks to automation systems, which are integrated with Internet technologies, we are able to remotely access and control data in a location-independent manner. Automation systems have also been used in medical applications recently. By the system proposed in this paper, data coming from patients are transferred to a main computer which has a database. By programming the database as desired, data can be accessed and modified any time. Another special feature of this system is its accessibility to the Web server which contains the database over the Internet
{"title":"Web Based Remote Patient Monitoring System","authors":"M. Zeybek, M.M. Tavli, D. Kuntalp, M. Kuntalp","doi":"10.1109/SIU.2006.1659780","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659780","url":null,"abstract":"Automation systems are commonly used in various areas nowadays. Thanks to automation systems, which are integrated with Internet technologies, we are able to remotely access and control data in a location-independent manner. Automation systems have also been used in medical applications recently. By the system proposed in this paper, data coming from patients are transferred to a main computer which has a database. By programming the database as desired, data can be accessed and modified any time. Another special feature of this system is its accessibility to the Web server which contains the database over the Internet","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"60 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":"129327743","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.2006.1659693
Y. Kutlu, Y. Isler, D. Kuntalp
In this work, the spikes in the electroencephalogram (EEG) signals are analyzed by using artificial neural networks (ANN). Multiple layer perceptron (MLP) networks utilizing between 3 and 15 hidden neurons are used in the network architecture. For training the MLP network backpropagation algorithm, backpropagation with adaptive learning rate, Levenberg-Marquardt (LM) algorithm, early stopping and regularization methods are used. Principal components of feature vectors obtained from 41 consecutive sample values of each peak are used for training the networks. Performances of classifiers are examined for two cases depending on both sensitivity-specificity and sensitivity-selectivity properties
{"title":"Detection of Spikes with Multiple Layer Perceptron Network Structures","authors":"Y. Kutlu, Y. Isler, D. Kuntalp","doi":"10.1109/SIU.2006.1659693","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659693","url":null,"abstract":"In this work, the spikes in the electroencephalogram (EEG) signals are analyzed by using artificial neural networks (ANN). Multiple layer perceptron (MLP) networks utilizing between 3 and 15 hidden neurons are used in the network architecture. For training the MLP network backpropagation algorithm, backpropagation with adaptive learning rate, Levenberg-Marquardt (LM) algorithm, early stopping and regularization methods are used. Principal components of feature vectors obtained from 41 consecutive sample values of each peak are used for training the networks. Performances of classifiers are examined for two cases depending on both sensitivity-specificity and sensitivity-selectivity properties","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"1 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":"130353306","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.2006.1659879
G. Bush, President George Bush, G. Bush
We propose a method to associate names and faces for querying people in large news photo collections. On the assumption that a person's face is likely to appear when his/her name is mentioned in the caption, first all the faces associated with the query name are selected. Among these faces, there could be many faces corresponding to the queried person in different conditions, poses and times, but there could also be other faces corresponding to other people in the caption or some non-face images due to the errors in the face detection method used. However, in most cases, the number of corresponding faces of the queried person will be large, and these faces will be more similar to each other than to others. When the similarities of faces are represented in a graph structure, the set of most similar faces will be the densest component in the graph. In this study, we propose a graph-based method to find the most similar subset among the set of possible faces associated with the query name, where the most similar subset is likely to correspond to the faces of the queried person
{"title":"Finding Faces in News Photos Using Both Face and Name Information","authors":"G. Bush, President George Bush, G. Bush","doi":"10.1109/SIU.2006.1659879","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659879","url":null,"abstract":"We propose a method to associate names and faces for querying people in large news photo collections. On the assumption that a person's face is likely to appear when his/her name is mentioned in the caption, first all the faces associated with the query name are selected. Among these faces, there could be many faces corresponding to the queried person in different conditions, poses and times, but there could also be other faces corresponding to other people in the caption or some non-face images due to the errors in the face detection method used. However, in most cases, the number of corresponding faces of the queried person will be large, and these faces will be more similar to each other than to others. When the similarities of faces are represented in a graph structure, the set of most similar faces will be the densest component in the graph. In this study, we propose a graph-based method to find the most similar subset among the set of possible faces associated with the query name, where the most similar subset is likely to correspond to the faces of the queried person","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"61 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":"126698449","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.2006.1659882
Oya Celiktutan, I. Avcibas, B. Sankur, N. P. Ayerden, C. Capar
In this paper, we focus on blind source cell-phone identification problem. The main idea is that proprietary interpolation algorithm (involved due to the structure of color filter array [CFA]) leaves footprints in the form of correlations across adjacent bit planes of images. For this purpose, we explore a set of binary similarity measures, image quality measures and higher order wavelet statistics in conjunction with KNN and SVM classifiers to identify the originating cell-phone. We provide identification results among 9 different brand cell-phone cameras
{"title":"Source Cell-phone Identification","authors":"Oya Celiktutan, I. Avcibas, B. Sankur, N. P. Ayerden, C. Capar","doi":"10.1109/SIU.2006.1659882","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659882","url":null,"abstract":"In this paper, we focus on blind source cell-phone identification problem. The main idea is that proprietary interpolation algorithm (involved due to the structure of color filter array [CFA]) leaves footprints in the form of correlations across adjacent bit planes of images. For this purpose, we explore a set of binary similarity measures, image quality measures and higher order wavelet statistics in conjunction with KNN and SVM classifiers to identify the originating cell-phone. We provide identification results among 9 different brand cell-phone cameras","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"12 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":"124156428","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.2006.1659825
C.B. Akgul, B. Sankur, Y. Yemez, F. Schmitt
In this work, we propose a computational framework for histogram-based 3D shape descriptors. Our method is based on evaluating the density of a shape function defined over the surface of 3D model using Gaussian modeling. The proposed approach has a better shape description ability compared to other competitor histogram-based approaches. We illustrate this assertion in a content-based 3D model retrieval application
{"title":"A New Computational Framework for 3D Shape Descriptors","authors":"C.B. Akgul, B. Sankur, Y. Yemez, F. Schmitt","doi":"10.1109/SIU.2006.1659825","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659825","url":null,"abstract":"In this work, we propose a computational framework for histogram-based 3D shape descriptors. Our method is based on evaluating the density of a shape function defined over the surface of 3D model using Gaussian modeling. The proposed approach has a better shape description ability compared to other competitor histogram-based approaches. We illustrate this assertion in a content-based 3D model retrieval application","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"121 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":"121452092","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.2006.1659903
E. Imre, A. Alatan, S. Knorr, T. Sikora
In this study, an algorithm is proposed to solve the multi-frame structure from motion (MFSfM) problem for monocular video sequences in dynamic scenes. The algorithm uses the epipolar criterion to segment the features belonging to the independently moving objects. Once the features are segmented, the corresponding objects are reconstructed individually by using a sequential algorithm, which is also capable prioritizing the frame pairs with respect to their reliability and information content, thus achieving a fast and accurate reconstruction through efficient processing of the available data. A tracker is utilized to increase the baseline distance between views and to improve the F-matrix estimation, which is beneficial to both the segmentation and the 3D structure estimation processes. The experimental results demonstrate that our approach has the potential to effectively deal with the multi-body MFSfM problem in a generic video sequence
{"title":"Prioritized Sequential 3D Reconstruction in Video Sequences of Dynamic Scenes","authors":"E. Imre, A. Alatan, S. Knorr, T. Sikora","doi":"10.1109/SIU.2006.1659903","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659903","url":null,"abstract":"In this study, an algorithm is proposed to solve the multi-frame structure from motion (MFSfM) problem for monocular video sequences in dynamic scenes. The algorithm uses the epipolar criterion to segment the features belonging to the independently moving objects. Once the features are segmented, the corresponding objects are reconstructed individually by using a sequential algorithm, which is also capable prioritizing the frame pairs with respect to their reliability and information content, thus achieving a fast and accurate reconstruction through efficient processing of the available data. A tracker is utilized to increase the baseline distance between views and to improve the F-matrix estimation, which is beneficial to both the segmentation and the 3D structure estimation processes. The experimental results demonstrate that our approach has the potential to effectively deal with the multi-body MFSfM problem in a generic video sequence","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"83 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":"124027827","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.2006.1659699
H.C. Akakin, B. Sankur
In this paper we introduced an automatic landmarking method for near-frontal face images based on DCT coefficients. The face information is provided as 480times640 gray-level images with 3D scene depth data. Range data is used to eliminate the background data from the face. The proposed facial landmarking algorithm uses a coarse-to-fine searching algorithm. In coarse level the images are downsampled to 80times60 pixels resolution. Both in coarse and fine levels SVM classifiers are trained using the DCT coefficients extracted from the manually landmarked training data. Coarse level candidate facial points are searched within the whole face image. Once the candidate locations are established, we revert back to the higher resolution image and refine the accuracy by using search windows around the coarse landmark locations
{"title":"DCT Based Facial Feature Extraction","authors":"H.C. Akakin, B. Sankur","doi":"10.1109/SIU.2006.1659699","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659699","url":null,"abstract":"In this paper we introduced an automatic landmarking method for near-frontal face images based on DCT coefficients. The face information is provided as 480times640 gray-level images with 3D scene depth data. Range data is used to eliminate the background data from the face. The proposed facial landmarking algorithm uses a coarse-to-fine searching algorithm. In coarse level the images are downsampled to 80times60 pixels resolution. Both in coarse and fine levels SVM classifiers are trained using the DCT coefficients extracted from the manually landmarked training data. Coarse level candidate facial points are searched within the whole face image. Once the candidate locations are established, we revert back to the higher resolution image and refine the accuracy by using search windows around the coarse landmark locations","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"9 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":"127746250","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.2006.1659765
S. Baykut, T. Akgul, S. Ergintav
In this study, we model the daily recordings of the GPS (global positioning system) data, and examine the noise characteristics of its residual signal (which is the difference between the real data and the model.) Here, two main problems are studied: The first one is the issue of selecting proper model parameters that are fitted to GPS data. Note that, at this step, some critical preprocessing issues are also addressed. The second issue is to assess the noise characteristics of the GPS residual signal which is very critical for accurate estimation of the parameters. It is assumed that GPS residual signals consist of time independent white noise and time-dependent colored noise components. Here, we propose a wavelet based method to estimate the amount of mixture of white and colored noise portions, plus the self-similarity index of the colored noise. Our proposed method is tested on the synthetic data and giving promising results. Later, a total of 60 GPS recordings from 20 stations are analyzed by this promising method. It is shown that the colored noise portions in the GPS residual signals can be modeled by so-called the flicker noise with the self similarity index of approximately "1"
{"title":"GPS Data Modeling and GPS Noise Analysis","authors":"S. Baykut, T. Akgul, S. Ergintav","doi":"10.1109/SIU.2006.1659765","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659765","url":null,"abstract":"In this study, we model the daily recordings of the GPS (global positioning system) data, and examine the noise characteristics of its residual signal (which is the difference between the real data and the model.) Here, two main problems are studied: The first one is the issue of selecting proper model parameters that are fitted to GPS data. Note that, at this step, some critical preprocessing issues are also addressed. The second issue is to assess the noise characteristics of the GPS residual signal which is very critical for accurate estimation of the parameters. It is assumed that GPS residual signals consist of time independent white noise and time-dependent colored noise components. Here, we propose a wavelet based method to estimate the amount of mixture of white and colored noise portions, plus the self-similarity index of the colored noise. Our proposed method is tested on the synthetic data and giving promising results. Later, a total of 60 GPS recordings from 20 stations are analyzed by this promising method. It is shown that the colored noise portions in the GPS residual signals can be modeled by so-called the flicker noise with the self similarity index of approximately \"1\"","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"22 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":"127836498","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.2006.1659863
O. Polat, T. Yıldırım
This paper presents an approach for the recognition of similar objects automatically. In the recognition system, colour features were extracted from two dimensional (2-D) pose images of every 3-D object given and the classification of the objects was realized by using these feature vectors in general regression neural networks-GRNN. The system has been simulated with eight different objects having similar shapes and high recognition rate was obtained. The ability of recognizing many undefined objects after training with low number of samples is important property of this system
{"title":"Recognition of 3-D Similar Objects by GRNN","authors":"O. Polat, T. Yıldırım","doi":"10.1109/SIU.2006.1659863","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659863","url":null,"abstract":"This paper presents an approach for the recognition of similar objects automatically. In the recognition system, colour features were extracted from two dimensional (2-D) pose images of every 3-D object given and the classification of the objects was realized by using these feature vectors in general regression neural networks-GRNN. The system has been simulated with eight different objects having similar shapes and high recognition rate was obtained. The ability of recognizing many undefined objects after training with low number of samples is important property of this system","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"25 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":"128080854","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.2006.1659775
E. Yilmaz, M. O. Sunay
We consider capacity analysis of power controlled multiple-input multiple-output (MIMO) systems for multiple-access channels (MAC) where receivers are equipped with diversity combiners such as maximum ratio combiner (MRC), equal gain combiner (EGC) and selection combiners (SC). Moreover, it is shown here by simulations that at high signal-to-noise ratios (SNR) cut-off parameter, gamma, converges to 1/K, where K is the number of users. Numerical results for frequency-flat Rayleigh fading channels with a specific number of antennas for each user using different receiver combining techniques are shown in ergodic capacity-user numbers and ergodic capacity-SNR graphs and the results are commented
{"title":"Power Controlled MIMO-MAC Capacity With Diversity Combining","authors":"E. Yilmaz, M. O. Sunay","doi":"10.1109/SIU.2006.1659775","DOIUrl":"https://doi.org/10.1109/SIU.2006.1659775","url":null,"abstract":"We consider capacity analysis of power controlled multiple-input multiple-output (MIMO) systems for multiple-access channels (MAC) where receivers are equipped with diversity combiners such as maximum ratio combiner (MRC), equal gain combiner (EGC) and selection combiners (SC). Moreover, it is shown here by simulations that at high signal-to-noise ratios (SNR) cut-off parameter, gamma, converges to 1/K, where K is the number of users. Numerical results for frequency-flat Rayleigh fading channels with a specific number of antennas for each user using different receiver combining techniques are shown in ergodic capacity-user numbers and ergodic capacity-SNR graphs and the results are commented","PeriodicalId":415037,"journal":{"name":"2006 IEEE 14th Signal Processing and Communications Applications","volume":"1 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":"125804647","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：