{"title":"A new diversity technique: Rotation and space diversity","authors":"Ahmet Yilmaz, O. Kucur","doi":"10.1109/SIU.2010.5650456","DOIUrl":"https://doi.org/10.1109/SIU.2010.5650456","url":null,"abstract":"In this work, we propose a new transmit diversity technique which we call rotation and space diversity. In this technique, in-phase and quadrature components of the rotated symbols are transmitted by two transmitter antennas such that they are affected by different fading coefficients and received by single receiver antenna. Error performance of the proposed technique is studied over frequency non-selective slowly Nakagami-m fading channels. Analytical results are validated by the simulations. According to the results, diversity order of the proposed technique is the sum of diversity orders of channels from the transmit antennas to the receive antenna and with this technique error performance of the system is improved significantly.","PeriodicalId":152297,"journal":{"name":"2010 IEEE 18th Signal Processing and Communications Applications Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130919731","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}
{"title":"Named Entity Recognition from Turkish texts","authors":"Faik Erdem Dalkilic, Semih Gelisli, B. Diri","doi":"10.1109/SIU.2010.5653553","DOIUrl":"https://doi.org/10.1109/SIU.2010.5653553","url":null,"abstract":"Named Entity Recognition is an important subject of Natural Language Processing and is used to classify proper nouns into different types such as person, location and organization names in addition to formula, date and money definitions. Rule Based Named Entity Recognition means defining rules to classify named entities in a text through using lexical resources and creating patterns. This study focuses on classification of proper nouns into three types including person, location and organization names regardless of the subject of text.","PeriodicalId":152297,"journal":{"name":"2010 IEEE 18th Signal Processing and Communications Applications Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131309465","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}
{"title":"Facial expression and head gesture recognition using temporal self-similarity and bag of words of facial landmarks","authors":"Ismail Ari, Hua Gao, H. K. Ekenel, L. Akarun","doi":"10.1109/SIU.2010.5653965","DOIUrl":"https://doi.org/10.1109/SIU.2010.5653965","url":null,"abstract":"Automatic recognition of facial expressions and head gestures plays an important role in a wide range of research area including sign language recognition and human-computer interaction. In this work, we adopt the well-performing self-similarity based action recognition method to classify facial expressions and head gestures. Additionally, we propose a novel approach for facial gesture recognition based on the histogram of tracked facial landmarks. We fuse the presented techniques with our previous Hidden Markov Model based approach [1] and get 15% increase in classification results.","PeriodicalId":152297,"journal":{"name":"2010 IEEE 18th Signal Processing and Communications Applications Conference","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122446214","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}
{"title":"Performance of Alamouti scheme with transmit antenna selection in non-identical Nakagami-m fading channels","authors":"A. Coşkun, O. Kucur, I. Altunbas","doi":"10.1109/SIU.2010.5651096","DOIUrl":"https://doi.org/10.1109/SIU.2010.5651096","url":null,"abstract":"In this work, bit/symbol error rate (BER/SER) performances of multiple-input multiple-output (MIMO) systems that employ Alamouti coded transmission with transmit antenna selection (TAS) are examined for independent but non-identical flat Nakagami-m fading channels. Exact BER/SER expressions are derived by using the moment generating function (MGF)-based analysis method for binary phase shift keying (BPSK), binary frequency shift keying (BFSK), M-ary phase shift keying (M-PSK) and M-ary quadrature amplitude modulation (M-QAM) signals. Also, upper bound expressions have been obtained in order to examine the asymptotic diversity order of TAS/Alamouti scheme. Monte Carlo simulations have validated the theoretical SER performance results derived for different numbers of transmit and receive antennas.","PeriodicalId":152297,"journal":{"name":"2010 IEEE 18th Signal Processing and Communications Applications Conference","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122365924","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}
{"title":"Complex wavelet transform and singular value decomposition based image contrast enhancement","authors":"H. Demirel, G. Anbarjafari","doi":"10.1109/SIU.2010.5652001","DOIUrl":"https://doi.org/10.1109/SIU.2010.5652001","url":null,"abstract":"In this work, we have proposed a new image contrast enhancement technique based on complex wavelet transform (CWT) and singular value decomposition (SVD). The technique decomposes the input image into the eight frequency subbands by using CWT and estimates the singular value matrix of the real and complex low-low subbands, and then it reconstructs the enhanced image by applying the inverse CWT (ICWT). The technique is compared with the conventional image equalization techniques such as standard general histogram equalization (GHE) and local histogram equalization (LHE), as well as state-of-art technique such as Brightness Preserving Dynamic Histogram Equalization (BPDHE) and singular value equalization (SVE). The experimental results are showing the superiority of the proposed method over the conventional and the state-of-art techniques.","PeriodicalId":152297,"journal":{"name":"2010 IEEE 18th Signal Processing and Communications Applications Conference","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125247339","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}
{"title":"Attentive vision, scene representation and bubble space","authors":"O. Erkent, H. I. Bozma","doi":"10.1109/SIU.2010.5654374","DOIUrl":"https://doi.org/10.1109/SIU.2010.5654374","url":null,"abstract":"Visual data based environmental representation is crucial for mobile robot applications requiring recognition. Previous work has shown that bubble memory — which is an egocentric approach based on hypothetically surrounding a spherical surface around the robot, to provide a compact representation of the scene from a single viewpoint. This paper proposes bubble space as an extension of bubble model to time-varying robot viewpoint. In a given scene, at each viewpoint, the robot saccades around and deforms a set of bubbles based on its responses to a set of relatively complex visual filters. As each bubble can be compactly represented using double Fourier series, the associated Fourier descriptors can either be stored in its memory or be used to recognize previously encountered scenes as verified by experimental results with an attentive robot.","PeriodicalId":152297,"journal":{"name":"2010 IEEE 18th Signal Processing and Communications Applications Conference","volume":"117 13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126402869","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}
{"title":"Unsupervised classification of remotely sensed images via independent component analysis","authors":"M. C. Sahingil, Y. Ozkazanc","doi":"10.1109/SIU.2010.5650952","DOIUrl":"https://doi.org/10.1109/SIU.2010.5650952","url":null,"abstract":"In this paper, some independent component analysis based unsupervised classification methods for remotely sensed imagery are proposed. In order to determine the validity of the proposed unsupervised classification methodology, some clustering quality metrics are used. According to the obtained results, the successes of proposed methods are compared.","PeriodicalId":152297,"journal":{"name":"2010 IEEE 18th Signal Processing and Communications Applications Conference","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121017530","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}
{"title":"Competitive nonlinear prediction under additive noise","authors":"Y. Yilmaz, S. Kozat","doi":"10.1109/SIU.2010.5651533","DOIUrl":"https://doi.org/10.1109/SIU.2010.5651533","url":null,"abstract":"We consider sequential nonlinear prediction of a bounded, real-valued and deterministic signal from its noise-corrupted past samples in a competitive algorithm framework. We introduce a randomized algorithm based on context-trees [1]. The introduced algorithm asymptotically achieves the performance of the best piecewise affine model that can both select the best partition of the past observations space (from a doubly exponential number of possible partitions) and the affine model parameters based on the desired clean signal in hindsight. Although the performance measure including the loss function is defined with respect to the noise-free clean signal, the clean signal, its past samples or prediction errors are not available for training or constructing predictions. We demonstrate the performance of the introduced algorithm when its applied to certain chaotic signals.","PeriodicalId":152297,"journal":{"name":"2010 IEEE 18th Signal Processing and Communications Applications Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127650465","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}
{"title":"Tracking of sea-surface targets in infrared videos using scale invariant feature transform","authors":"A. O. Karali, T. Aytaç","doi":"10.1109/SIU.2010.5652431","DOIUrl":"https://doi.org/10.1109/SIU.2010.5652431","url":null,"abstract":"In this study, sea-surface targets are tracked using scale invariant feature transform (SIFT) in real and synthetic infrared (IR) videos. The effects of the parameters such as number of features, contrast threshold value, corner coefficient, and the threshold used in matching features on the tracking accuracy are investigated in detail and target tracking success is evaluated with respect to the ground truth target positions. The results obtained show the possibility of developing effective target detection and tracking algorithms using SIFT in IR videos containing sea-surface targets.","PeriodicalId":152297,"journal":{"name":"2010 IEEE 18th Signal Processing and Communications Applications Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130646080","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}
O. Koroglu, F. Arıkan, N. Turel, Melih S. Aysezen, Muh. Onur Lenk, Doc. Muh. Bahadir Aktug
{"title":"Estimation of Probability Density Function for TUSAGA TEC","authors":"O. Koroglu, F. Arıkan, N. Turel, Melih S. Aysezen, Muh. Onur Lenk, Doc. Muh. Bahadir Aktug","doi":"10.1109/SIU.2010.5653362","DOIUrl":"https://doi.org/10.1109/SIU.2010.5653362","url":null,"abstract":"In this study, the statistical properties of the Ionosphere are investigated by using Total Electron Content (TEC) estimates obtained from TUSAGA GPS stations in Turkey. The hourly histograms of TEC are computed using the processed data from 14 GPS stations located mostly in western Anatolia. Optimum Probability Density Function (PDF) that fits the histograms is investigated in Maximum Likelihood sense. It is observed that for all the stations and all hours of the day, TEC is distributed as Lognormal. The parameters of the Lognormal distribution are also very similar to each other. Generally, the mean of the PDF increases when the sun is close to local zenith and it decreases right before the sun rise and sunset. It is observed that a representative TEC PDF that can be used in statistical modeling of ionosphere over Turkey using a GPS network that covers Turkey homogeneously.","PeriodicalId":152297,"journal":{"name":"2010 IEEE 18th Signal Processing and Communications Applications Conference","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117006409","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}