Pub Date : 2013-05-12DOI: 10.1109/WOSSPA.2013.6602366
M. Bahoura, H. Ezzaidi
In this paper, an acoustic feature extraction method based on mel frequency cepstral coefficients (MFCC) was implemented on FPGA for real-time respiratory sound analysis. The proposed technique was implemented using Xilinx System Generator (XSG) in MATLAB/SIMULINK environment. The feature vectors obtained with fixed-point XSG implementation is compared to those obtained with on the floating-point MATLAB one using normal and wheezing respiratory sounds.
本文在FPGA上实现了一种基于频谱倒谱系数(MFCC)的实时呼吸声特征提取方法。该技术在MATLAB/SIMULINK环境下使用Xilinx System Generator (XSG)实现。将定点XSG实现得到的特征向量与使用正常呼吸音和喘息呼吸音的浮点MATLAB实现得到的特征向量进行了比较。
{"title":"Hardware implementation of MFCC feature extraction for respiratory sounds analysis","authors":"M. Bahoura, H. Ezzaidi","doi":"10.1109/WOSSPA.2013.6602366","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602366","url":null,"abstract":"In this paper, an acoustic feature extraction method based on mel frequency cepstral coefficients (MFCC) was implemented on FPGA for real-time respiratory sound analysis. The proposed technique was implemented using Xilinx System Generator (XSG) in MATLAB/SIMULINK environment. The feature vectors obtained with fixed-point XSG implementation is compared to those obtained with on the floating-point MATLAB one using normal and wheezing respiratory sounds.","PeriodicalId":417940,"journal":{"name":"2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131902559","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 : 2013-05-12DOI: 10.1109/WOSSPA.2013.6602375
S. Maiz, M. El Badaoui, J. Leskow, C. Servière
In last decades, a well-studied characteristic of signals called Cyclostationarity (CS) has provided very important survey, highlighting the impact of CS models on signal analysis in telecommunication, mechanical, acoustic, biomechanical and econometric signals. It is a technique that offers diagnostic advantages for the analysis of failures, faults and disturbances which are related to a system being examined. The aim of this paper is to introduce the concept of CS for signals and to present possibilities of statistical resampling procedures available for such signals. The resampling method treated in this paper is referred to as Subsampling. A description of this method is presented and its applicability to CS simulated and real data is proved. This implies, in particular, that statistical CS analysis can be carried out without the assumption of Gaussianity on the CS process under consideration.
{"title":"Subsampling-based method for testing Cyclostationarity: Application to biomechanical signals","authors":"S. Maiz, M. El Badaoui, J. Leskow, C. Servière","doi":"10.1109/WOSSPA.2013.6602375","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602375","url":null,"abstract":"In last decades, a well-studied characteristic of signals called Cyclostationarity (CS) has provided very important survey, highlighting the impact of CS models on signal analysis in telecommunication, mechanical, acoustic, biomechanical and econometric signals. It is a technique that offers diagnostic advantages for the analysis of failures, faults and disturbances which are related to a system being examined. The aim of this paper is to introduce the concept of CS for signals and to present possibilities of statistical resampling procedures available for such signals. The resampling method treated in this paper is referred to as Subsampling. A description of this method is presented and its applicability to CS simulated and real data is proved. This implies, in particular, that statistical CS analysis can be carried out without the assumption of Gaussianity on the CS process under consideration.","PeriodicalId":417940,"journal":{"name":"2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129544609","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 : 2013-05-12DOI: 10.1109/WOSSPA.2013.6602348
Samira Ouddane, Sid Ahmed Fezza, K. Faraoun
3D imaging recently has attracted great attention from industries and research institutes, this is due to the novelty and the impression of depth generated by the exploitation of the stereovision phenomenon. Stereovision consists to exploit two images (left and right) of the same scene captured from different viewpoints, this pair of images is used to reconstruct the relief of the scene. Since, such a pair of images provides a large amount of data to be stored or transmitted, hence efficient compression techniques are essential for handling this type of images. This paper aims to make a complete review of all the most prevalent works in the literature for encoding stereoscopic images.
{"title":"Stereo image coding: State of the art","authors":"Samira Ouddane, Sid Ahmed Fezza, K. Faraoun","doi":"10.1109/WOSSPA.2013.6602348","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602348","url":null,"abstract":"3D imaging recently has attracted great attention from industries and research institutes, this is due to the novelty and the impression of depth generated by the exploitation of the stereovision phenomenon. Stereovision consists to exploit two images (left and right) of the same scene captured from different viewpoints, this pair of images is used to reconstruct the relief of the scene. Since, such a pair of images provides a large amount of data to be stored or transmitted, hence efficient compression techniques are essential for handling this type of images. This paper aims to make a complete review of all the most prevalent works in the literature for encoding stereoscopic images.","PeriodicalId":417940,"journal":{"name":"2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131082487","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 : 2013-05-12DOI: 10.1109/WOSSPA.2013.6602353
B. Alshaqaqi, Abdullah Salem Baquhaizel, Mohamed El Amine Ouis, M. Boumehed, A. Ouamri, M. Keche
Drowsiness and Fatigue of drivers are amongst the significant causes of road accidents. Every year, they increase the amounts of deaths and fatalities injuries globally. In this paper, a module for Advanced Driver Assistance System (ADAS) is presented to reduce the number of accidents due to drivers fatigue and hence increase the transportation safety; this system deals with automatic driver drowsiness detection based on visual information and Artificial Intelligence. We propose an algorithm to locate, track, and analyze both the drivers face and eyes to measure PERCLOS, a scientifically supported measure of drowsiness associated with slow eye closure.
{"title":"Driver drowsiness detection system","authors":"B. Alshaqaqi, Abdullah Salem Baquhaizel, Mohamed El Amine Ouis, M. Boumehed, A. Ouamri, M. Keche","doi":"10.1109/WOSSPA.2013.6602353","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602353","url":null,"abstract":"Drowsiness and Fatigue of drivers are amongst the significant causes of road accidents. Every year, they increase the amounts of deaths and fatalities injuries globally. In this paper, a module for Advanced Driver Assistance System (ADAS) is presented to reduce the number of accidents due to drivers fatigue and hence increase the transportation safety; this system deals with automatic driver drowsiness detection based on visual information and Artificial Intelligence. We propose an algorithm to locate, track, and analyze both the drivers face and eyes to measure PERCLOS, a scientifically supported measure of drowsiness associated with slow eye closure.","PeriodicalId":417940,"journal":{"name":"2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA)","volume":"92 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133007610","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 : 2013-05-12DOI: 10.1109/WOSSPA.2013.6602381
A. Mansoul, H. Kimouche
A reconfigurable microstrip antenna with switchable frequency is proposed. The proposed antenna has a simple structure, consisting of a square radiating patch and parasitic conductor of rectangular shape. PIN diodes switches are introduced to provide to operate antenna either 2.2 GHz or 2.45 GHz depending on the state of the diodes PIN switches. Very good matching is achieved for the two resonant frequencies. Simulated and measured parameters of the antenna are presented and it is demonstrated that the radiation patterns remain essentially unaffected by the frequency tuning.
{"title":"A simple frequency reconfigurable microstrip patch antenna for wireless communication","authors":"A. Mansoul, H. Kimouche","doi":"10.1109/WOSSPA.2013.6602381","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602381","url":null,"abstract":"A reconfigurable microstrip antenna with switchable frequency is proposed. The proposed antenna has a simple structure, consisting of a square radiating patch and parasitic conductor of rectangular shape. PIN diodes switches are introduced to provide to operate antenna either 2.2 GHz or 2.45 GHz depending on the state of the diodes PIN switches. Very good matching is achieved for the two resonant frequencies. Simulated and measured parameters of the antenna are presented and it is demonstrated that the radiation patterns remain essentially unaffected by the frequency tuning.","PeriodicalId":417940,"journal":{"name":"2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114822789","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}
Active contour model (ACM) approaches for image segmentation and feature extraction have emerged as very appealing and powerful tools in image processing. The basis of ACM approach is to evolve a curve, called level set, to extract the desired object (s) under some constraints. In this course, various extensions of earlier Osher's level set model have been suggested in the litareture. More recently, a new ACM model referred to selective binary and Gaussian filtering regularized level set (SBGFRIL) has been put forward as a fruitful combination of geodesic active contour model (GAC) and Chan-Vese (C-V) active contour models. This paper attempts to put forward some appealing performance indices to assess the performances of the suggested SBGFRIL compared with GAC and V-C models. The performance metrics involve the clustering based quality evaluations.
{"title":"Performance comparison of active contour level set methods in image segmentation","authors":"Messaoudi Zahir, Oussalah Mourad, Ouldali Abdelaziz","doi":"10.1109/WOSSPA.2013.6602338","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602338","url":null,"abstract":"Active contour model (ACM) approaches for image segmentation and feature extraction have emerged as very appealing and powerful tools in image processing. The basis of ACM approach is to evolve a curve, called level set, to extract the desired object (s) under some constraints. In this course, various extensions of earlier Osher's level set model have been suggested in the litareture. More recently, a new ACM model referred to selective binary and Gaussian filtering regularized level set (SBGFRIL) has been put forward as a fruitful combination of geodesic active contour model (GAC) and Chan-Vese (C-V) active contour models. This paper attempts to put forward some appealing performance indices to assess the performances of the suggested SBGFRIL compared with GAC and V-C models. The performance metrics involve the clustering based quality evaluations.","PeriodicalId":417940,"journal":{"name":"2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132006945","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 : 2013-05-12DOI: 10.1109/WOSSPA.2013.6602407
S. Azarian, M. Debbah
Advanced cognitive radio algorithms involve different technical fields like signal processing, wired network communication, computing, etc. Prototyping such systems raise new issues when one wants to find `off the shelf' bricks, ready for experiments: the integration step is time consuming, is not free of risks of non-compatibility and most of the time does not fall in the scope of a PhD work. For these reasons, many research groups have invested in building a testing platform for their cognitive radio activities. Because the Alcatel Lucent Chair on Flexible Radio is engaged in research covering a wide field of topics, the need for a fully customizable experimental test bed rose and was initiated with SDR4ALL on the radio side, and continued with the FlexiCells project for the infrastructure. This paper presents the platform we are designing at Supélec.
{"title":"Flexicells and SDR4ALL — A cognitive radio test bed","authors":"S. Azarian, M. Debbah","doi":"10.1109/WOSSPA.2013.6602407","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602407","url":null,"abstract":"Advanced cognitive radio algorithms involve different technical fields like signal processing, wired network communication, computing, etc. Prototyping such systems raise new issues when one wants to find `off the shelf' bricks, ready for experiments: the integration step is time consuming, is not free of risks of non-compatibility and most of the time does not fall in the scope of a PhD work. For these reasons, many research groups have invested in building a testing platform for their cognitive radio activities. Because the Alcatel Lucent Chair on Flexible Radio is engaged in research covering a wide field of topics, the need for a fully customizable experimental test bed rose and was initiated with SDR4ALL on the radio side, and continued with the FlexiCells project for the infrastructure. This paper presents the platform we are designing at Supélec.","PeriodicalId":417940,"journal":{"name":"2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132383119","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 : 2013-05-12DOI: 10.1109/WOSSPA.2013.6602373
M. T. Taba
The Fractional Fourier transform (FrFT) is the generalization of the classical Fourier Transform. It depends on a parameter α = aπ/2 and can be interpreted as a rotation by an angle a in the time-frequency plane. This paper describes the implementation of a watermark embedding technique for images using the discrete fractional Fourier transform. The idea is that a 2D discrete fractional Fourier transform of the image is computed. In this transform domain, a watermark logo is used to modify the transform coefficients of the real and imaginary component. Then the inverse transform is applied to give the watermarked image. The detection is based on performing the same transform operation. The watermark is recognized if there is a strong correlation with the embedded watermark.
{"title":"The fractional fourier transform and its application to digital watermarking","authors":"M. T. Taba","doi":"10.1109/WOSSPA.2013.6602373","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602373","url":null,"abstract":"The Fractional Fourier transform (FrFT) is the generalization of the classical Fourier Transform. It depends on a parameter α = aπ/2 and can be interpreted as a rotation by an angle a in the time-frequency plane. This paper describes the implementation of a watermark embedding technique for images using the discrete fractional Fourier transform. The idea is that a 2D discrete fractional Fourier transform of the image is computed. In this transform domain, a watermark logo is used to modify the transform coefficients of the real and imaginary component. Then the inverse transform is applied to give the watermarked image. The detection is based on performing the same transform operation. The watermark is recognized if there is a strong correlation with the embedded watermark.","PeriodicalId":417940,"journal":{"name":"2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129660103","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}
Different single biometric systems carry in their outputs redundant and complementary information. The concatenation of match scores from various systems in a single feature vector to feed the classifiers can provide an opportunity to develop more efficient system compared to other fusion schemes. In this work, we investigate the performance of classifier based biometric score fusion. For this purpose, the One-Class SVM (OC-SVM) classifier is employed since, in the general case of biometric systems, the data are highly unbalanced or available from only a single class. Experiments are conducted on the well known NIST-multimodal partition of the BSSRI database and results are reported using genuine acceptance and false acceptance criteria. The obtained results show the effectiveness of the OC-SVM compared to the standard two-class SVM classifier as well as to other score fusion schemes.
{"title":"Experimental investigation of OC-SVM for multibiometric score fusion","authors":"Nassim Abbas, Messaoud Bengherabi, Elhocine Boutellaa","doi":"10.1109/WOSSPA.2013.6602371","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602371","url":null,"abstract":"Different single biometric systems carry in their outputs redundant and complementary information. The concatenation of match scores from various systems in a single feature vector to feed the classifiers can provide an opportunity to develop more efficient system compared to other fusion schemes. In this work, we investigate the performance of classifier based biometric score fusion. For this purpose, the One-Class SVM (OC-SVM) classifier is employed since, in the general case of biometric systems, the data are highly unbalanced or available from only a single class. Experiments are conducted on the well known NIST-multimodal partition of the BSSRI database and results are reported using genuine acceptance and false acceptance criteria. The obtained results show the effectiveness of the OC-SVM compared to the standard two-class SVM classifier as well as to other score fusion schemes.","PeriodicalId":417940,"journal":{"name":"2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125938630","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 : 2013-05-12DOI: 10.1109/WOSSPA.2013.6602377
T. Al-Naffouri, M. Masood
We present an algorithm and its variants for sparse signal recovery from a small number of its measurements in a distribution agnostic manner. The proposed algorithm finds Bayesian estimate of a sparse signal to be recovered and at the same time is indifferent to the actual distribution of its non-zero elements. Termed Support Agnostic Bayesian Matching Pursuit (SABMP), the algorithm also has the capability of refining the estimates of signal and required parameters in the absence of the exact parameter values. The inherent feature of the algorithm of being agnostic to the distribution of the data grants it the flexibility to adapt itself to several related problems. Specifically, we present two important extensions to this algorithm. One extension handles the problem of recovering sparse signals having block structures while the other handles multiple measurement vectors to jointly estimate the related unknown signals. We conduct extensive experiments to show that SABMP and its variants have superior performance to most of the state-of-the-art algorithms and that too at low-computational expense.
{"title":"Distribution agnostic structured sparsity recovery algorithms","authors":"T. Al-Naffouri, M. Masood","doi":"10.1109/WOSSPA.2013.6602377","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602377","url":null,"abstract":"We present an algorithm and its variants for sparse signal recovery from a small number of its measurements in a distribution agnostic manner. The proposed algorithm finds Bayesian estimate of a sparse signal to be recovered and at the same time is indifferent to the actual distribution of its non-zero elements. Termed Support Agnostic Bayesian Matching Pursuit (SABMP), the algorithm also has the capability of refining the estimates of signal and required parameters in the absence of the exact parameter values. The inherent feature of the algorithm of being agnostic to the distribution of the data grants it the flexibility to adapt itself to several related problems. Specifically, we present two important extensions to this algorithm. One extension handles the problem of recovering sparse signals having block structures while the other handles multiple measurement vectors to jointly estimate the related unknown signals. We conduct extensive experiments to show that SABMP and its variants have superior performance to most of the state-of-the-art algorithms and that too at low-computational expense.","PeriodicalId":417940,"journal":{"name":"2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127046965","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：