{"title":"Blind source separation based on moments matching","authors":"F. Ghassemi, H. Amindavar","doi":"10.1109/ISSPA.2005.1580973","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1580973","url":null,"abstract":"The Blind Source Separation (BSS) is a fundamental and challenging problem in signal processing. A new method based on the fractional moments and simulated annealing is presented in this paper. Fractional moments are used as a new measure of separation criterion contrary to the traditional integer moments. This is inspired by the fact that fractional moments lead to an enhanced estimation of the probability density function (PDF). Simulated Annealing (SA) is selected as the optimization algorithm to avoid being trapped into local minima. Simulation results validate the applicability of the new strategy for BSS .","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130287218","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":"An investigation on the step-size bound of the partitioned frequency-domain block LMS (PFBLMS) algorithm","authors":"Junghsi Lee, Yao-Hua Chen","doi":"10.1109/ISSPA.2005.1581052","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1581052","url":null,"abstract":"In this paper, we present an analysis on the step-size bound that guarantees the stability of the partitioned frequency-domain block LMS (PFBLMS). Frequency domain adaptive filters are attractive in applications requiring a large number of coefficients such as acoustic echo cancellation (AEC). However, the very restrictive convergence bound for BLMS has limited its usefulness. Since PFBLMS belongs to the BLMS family, it may suffer the very restrictive step-size bound too. Derivations on step-size bounds for the PFBLMS have been reported recently, but are not consistent with each other. In this paper, we analyse the step-size bound of PFBLMS, and derive a bound which is N times larger than that of the BLMS. This finding makes PFBLMS much more practical in the application of AEC. Extensive simulation results are provided to support our analysis.","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129672463","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":"Blind unique identification of Alamouti space-time coded channel via signal design and transmission technique","authors":"Lin Zhou, Jian-Kang Zhang, K. M. Wong","doi":"10.1109/ISSPA.2005.1581032","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1581032","url":null,"abstract":"In this paper, we present a simple signal design and transmission technique to uniquely and blindly identify Alamouti space-time coded channels under both noise-free and complex Gaussian noise environments in which pth-order and qth-order statistics (p and q are co-prime) of the received signals are available. A closed-form solution to determine the channel coefficients is obtained by exploiting specific properties of the Alamouti space-time code and the linear Diophantine equation theory. When only finite received data are given, we propose using the semi-definite relaxation algorithm to approximate maximum likelihood (ML) detection so that the joint estimation of the channel and symbols can be efficiently implemented. Simulation results show that our signal design and transmission method yields lower mean-square error in the estimation of the channel when compared to other existing methods and that the average symbol error rate approaches that of the coherent detector which needs perfect channel information at the receiver.","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127595995","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":"Angle QIM: on document to watermark ratio analysis","authors":"F. Ourique, V. Licks, R. Jordan","doi":"10.1109/ISSPA.2005.1580208","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1580208","url":null,"abstract":"Max Costa original results on dirty paper codes have given the foundation for Quantizatin Index Modulation (QIM) based for digital image watermarking. However, the standard QIM methods can be greatly degraded by simple amplitude scaling attacks. In order to overcome this limitation, Angle Quantization Index Modulation (AQIM) schemes have been recently introduced. By quantizing the angle of the watermark vector according to a symbol dependent lattice, AQIM’s construction leads to an inherent invariance against amplitude scaling distortions. In this paper, we present a theoretical analysis of the watermark distortion introduced by AQIM during the embedding process based on the angle quantization step parameter, ¢µ. Such theoretical analysis is validated by comparison with experimental results, which are also included in this paper.","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124570570","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":"Signal coordination in marine mammals: cues from the time domain of vocal interactions","authors":"D. Todt, F. Veit","doi":"10.1109/ISSPA.2005.1581066","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1581066","url":null,"abstract":"Marine mammals are renowned for a precise coordination of social behaviors. To further elucidate these accomplishments, we investigated the time domain of vocal interactions and also relationships between the quality and the coordination mode of signals. Subjects (n=10) were bottlenose dolphins (Tursiops truncatus) which produce several structurally diverse vocalizations: e.g. burst-pulse sounds (bursts) and whistles. Our study revealed that bursts were responded to by bursts only, which occurred statusrelated within a small time window after stimulus end (latency: ~ 0.2 s). Responses to whistles were statusrelated too, but occurred with a different timing and more flexible and as either other whistles or directed locomotion. These findings document that the coordination mode of dolphin signals is related to both social and signal class-specific properties. As the time of signal transmission is strikingly short in an aquatic medium, we conclude that marine mammals perform a highly sophisticated form of signal processing.","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123001446","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":"Micro-doppler signal estimation for vibrating and rotating targets","authors":"P. Setlur, M. Amin, T. Thayaparan","doi":"10.1109/ISSPA.2005.1581019","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1581019","url":null,"abstract":"Vibrations or rotations of a target or structures on a target give rise to the micro-Doppler effect of the reflected waveforms. In this paper, we analyze micro- Doppler signals in the joint time-frequency plane using commonly applied distributions and time-frequency transforms. Performance is evaluated based on achieved resolution and reduced artifacts. The latter is significant in microDoppler analysis, as the signals have sinusoidal timefrequency (TF) signatures. This presents a challenge for the already established distributions, as they have to suppress the cross as well as the auto artifacts. We propose a new decomposition of basis functions, given the apriori knowledge of the time varying nature of the radar returns. This approach can be cast as an application of waveform diversity. The new decomposition is free from any artifacts and provides improved estimates of the target micro-Doppler signature.","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131040986","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":"On a general sensor fusion method by state space modeling approach using particle filters","authors":"M. Kawanishi, N. Ikoma, H. Maeda","doi":"10.1109/ISSPA.2005.1581000","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1581000","url":null,"abstract":"Sensor fusion aims at obtaining information, which cannot be obtained by single sensor, by combining signals from multiple sensors. The main problem of sensor fusion is that computational cost increases exponentially with the number of sensors because the combination number of association between signals and sensors is large. We propose a general method to solve this problem in nonlinear state space model to deal with the unknown associations. We adapt the model to a specific situation of a sensor fusion. The target states and the associations are simultaneously estimated through the state estimation. In the estimation of the association, we apply particle filters with clever proposal. The associations are estimated in probabilistic way, not deterministic way, to avoid falling into a bad solution. As an example of the sensor fusion, we deal with tracking problem of sound target using camera and two microphones. Keyword: Sensor fusion, unknown association, particle filters, clever proposal, target tracking.","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127173089","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":"Modeling of time varying AR process using nonlinear energy operator","authors":"R. B. Pachori, P. Sircar","doi":"10.1109/ISSPA.2005.1581020","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1581020","url":null,"abstract":"In this paper, we present a time varying autoregressive (TVAR) representation for the amplitude frequency modulated (AM-FM) signal. In the proposed method the TVAR coefficients are estimated by the nonlinear energy (NLE) operator. It is demonstrated that the proposed technique based on NLE has certain distinct advantages over the conventional method employing basis functions (BF).","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125677360","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":"Gene and exon prediction using time domain algorithms","authors":"E. Ambikairajah, J. Epps, M. Akhtar","doi":"10.1109/ISSPA.2005.1580230","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1580230","url":null,"abstract":"The protein-coding regions of DNA sequences normally exhibit a period-3 behaviour that can be used to identify gene locations. Various methods have been used to automatically identify the coding regions, however these have been predominantly ‘frequency’ domain techniques. Numerous ‘time’ domain techniques are available from the signal processing literature, and this work examines their applicability to gene and exon prediction in DNA sequences. Two techniques new to this application are introduced: the Time Domain Periodogram (TDP) and the Average Magnitude Difference Function (AMDF). We also present an indicative comparison of time domain and existing frequency domain techniques, from which the AMDF appears to be the most promising technique. Autoregressive modelling methods are further investigated in this work.","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126590092","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":"Using overlapping arrays for an improved spatial mean quantization watermarking","authors":"Dima Pröfrock, M. Schlauweg, E. Müller","doi":"10.1109/ISSPA.2005.1580209","DOIUrl":"https://doi.org/10.1109/ISSPA.2005.1580209","url":null,"abstract":"This paper presents a new method for watermarking digital images. To achieve a high robustness to noise, lossy compression, blurring and sharpening attacks, spatial domain array mean values are quantized. To recover the embedded data, the original image is not required. Based on this approach, low image quality degradations with a high robustness can be achieved. To reduce the image degradations, our method uses overlapping arrays to embed the information. The method bases on the uniform distribution of quantization errors and uses the intersections of overlapping arrays to optimize the PSNR value. Theoretical analyses and practical results show the advantage over the non- overlapping-array method. Experimental results confirm the theoretical assumptions.","PeriodicalId":385337,"journal":{"name":"Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005.","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123144500","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}