Pub Date : 2013-05-12DOI: 10.1109/WOSSPA.2013.6602347
Nabiha Azizi, Nawel Zemmal, Yamina Tlili Guiassa, N. Farah
This paper investigated a computer-aided diagnosis for breast mass classification by mammography examination using complementarity existing between features and classifiers. It is concerned with the design and development of an automatic mass classification of mammograms. The proposed method consists of three stages: segmentation, feature extraction and classification. In classification phase, kernel based classifiers combination is a current active paradigm in the field of machine learning. It takes benefit of classification fusion algorithms. The combination of Kernel-based classifiers was proposed as a research way allowing recognition reliability by using diversity which can be exist between classifiers. The proposed scheme is based on combination of support vector machine classifiers. Each one is associated with an homogenous family of features (Hu moments; central moments, Haralick moment. Diversity criteria between features are adopted in this study to ensure best performance. Our experiments demonstrated that developed system using (DDSM) database achieve very encouraging results.
{"title":"Kernel based classifiers fusion with features diversity for breast masses classification","authors":"Nabiha Azizi, Nawel Zemmal, Yamina Tlili Guiassa, N. Farah","doi":"10.1109/WOSSPA.2013.6602347","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602347","url":null,"abstract":"This paper investigated a computer-aided diagnosis for breast mass classification by mammography examination using complementarity existing between features and classifiers. It is concerned with the design and development of an automatic mass classification of mammograms. The proposed method consists of three stages: segmentation, feature extraction and classification. In classification phase, kernel based classifiers combination is a current active paradigm in the field of machine learning. It takes benefit of classification fusion algorithms. The combination of Kernel-based classifiers was proposed as a research way allowing recognition reliability by using diversity which can be exist between classifiers. The proposed scheme is based on combination of support vector machine classifiers. Each one is associated with an homogenous family of features (Hu moments; central moments, Haralick moment. Diversity criteria between features are adopted in this study to ensure best performance. Our experiments demonstrated that developed system using (DDSM) database achieve very encouraging results.","PeriodicalId":417940,"journal":{"name":"2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA)","volume":"20 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":"130920262","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.2013.6602337
D. Cherifi, A. Chellouche, Amazigh Ait Ouakli, Youcef Benamara, R. Deriche
Diffusion tensor imaging in a non-invasive in vivo image modality that allows us to measure molecular diffusion of water in tissues. We characterize diffusion transport of water by an effective diffusion tensor D. The practical importane of the effective diffusion tensor is that it contains new and useful structural and physiological informations about tissues that were previously unobtainable. In this article, we present a software implementation of the the estimation of these tensors and their visualization in order to extract these informations.
{"title":"Tensor estimation and visualization using dMRI","authors":"D. Cherifi, A. Chellouche, Amazigh Ait Ouakli, Youcef Benamara, R. Deriche","doi":"10.1109/WOSSPA.2013.6602337","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602337","url":null,"abstract":"Diffusion tensor imaging in a non-invasive in vivo image modality that allows us to measure molecular diffusion of water in tissues. We characterize diffusion transport of water by an effective diffusion tensor D. The practical importane of the effective diffusion tensor is that it contains new and useful structural and physiological informations about tissues that were previously unobtainable. In this article, we present a software implementation of the the estimation of these tensors and their visualization in order to extract these informations.","PeriodicalId":417940,"journal":{"name":"2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA)","volume":"35 52","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113941504","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.2013.6602414
Sabra Benkrinah, M. Benslama
In this work, we studied the effect of multi-user and multipath, on the performance of a serial acquisition search system, using adaptive threshold with constant false alarm rate, in Rayleigh fading channels. Since the received signal levels in mobile communications are unknown and location varying, the acquisition schemes for pseudo-noise (PN) sequences with fixed thresholds may cause too many false alarms and/or low probability of detection. Therefore, adaptively varying threshold schemes are proposed through the use of a constant false alarm rate (CFAR) algorithms. We propose the use of cell-averaging (CA), greatest-of (GO), smallest-of (SO) and order-statistics (OS) CFAR processors for PN code acquisition in DS/CDMA systems. From simulation results, we observe that the CA-CFAR detector gives good performances in this environment, followed by the SO-CFAR detector. The OS-CF AR outperforms the GO-CFAR which gives the worst results. All studied CFAR detectors are sensible to multi-user and multipath effect.
{"title":"Effect of multi-users and multipaths on the performance of an adaptive serial acquisition scheme for DS/CDMA systems","authors":"Sabra Benkrinah, M. Benslama","doi":"10.1109/WOSSPA.2013.6602414","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602414","url":null,"abstract":"In this work, we studied the effect of multi-user and multipath, on the performance of a serial acquisition search system, using adaptive threshold with constant false alarm rate, in Rayleigh fading channels. Since the received signal levels in mobile communications are unknown and location varying, the acquisition schemes for pseudo-noise (PN) sequences with fixed thresholds may cause too many false alarms and/or low probability of detection. Therefore, adaptively varying threshold schemes are proposed through the use of a constant false alarm rate (CFAR) algorithms. We propose the use of cell-averaging (CA), greatest-of (GO), smallest-of (SO) and order-statistics (OS) CFAR processors for PN code acquisition in DS/CDMA systems. From simulation results, we observe that the CA-CFAR detector gives good performances in this environment, followed by the SO-CFAR detector. The OS-CF AR outperforms the GO-CFAR which gives the worst results. All studied CFAR detectors are sensible to multi-user and multipath effect.","PeriodicalId":417940,"journal":{"name":"2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA)","volume":"200 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114090967","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.2013.6602399
I. Atoui, Hazem Meradi, R. Boulkroune, R. Saidi, A. Grid
Rotor unbalance is the most cause of machine vibration that reduces the life of the rotating machine. On the other hand, vibration monitoring is reported as an interesting technique for the rotating machinery condition diagnosis. This paper considers the Wavelet Transform (WT) and FFT of vibration signals for detect and diagnose of unbalance faults in rotating machinery. The fault condition and location of faults are success fully detected by WT-FFT for non-stationary vibration measurements obtained from accelerometer sensors. Experimental studies on the rotating machine include faulty rotor with different rotational speeds has been carried out in this paper. These experimental results confirm that WT-FFT serves as a good tool to online faults detection and diagnosis of rotating machines.
{"title":"Fault detection and diagnosis in rotating machinery by vibration monitoring using FFT and Wavelet techniques","authors":"I. Atoui, Hazem Meradi, R. Boulkroune, R. Saidi, A. Grid","doi":"10.1109/WOSSPA.2013.6602399","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602399","url":null,"abstract":"Rotor unbalance is the most cause of machine vibration that reduces the life of the rotating machine. On the other hand, vibration monitoring is reported as an interesting technique for the rotating machinery condition diagnosis. This paper considers the Wavelet Transform (WT) and FFT of vibration signals for detect and diagnose of unbalance faults in rotating machinery. The fault condition and location of faults are success fully detected by WT-FFT for non-stationary vibration measurements obtained from accelerometer sensors. Experimental studies on the rotating machine include faulty rotor with different rotational speeds has been carried out in this paper. These experimental results confirm that WT-FFT serves as a good tool to online faults detection and diagnosis of rotating machines.","PeriodicalId":417940,"journal":{"name":"2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA)","volume":"9 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":"125134726","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.2013.6602392
A. Senouci, Bensoukehal Ali, Senouci Houaria, A. Benyettou
In this article, we propose the use an algorithm of artificial ants inspired from chemical recognition system of ants in a biometric checking system by iris recognition, in order to make a success of the impostures tests and acceptances tests of the legitimate users. We presented our motivations which brought us to such a proposal, as we compared successfully our results with those obtained by the use of a decision threshold fixed relatively to a score of similarity calculated by using Hamming's distance. The approach appeared adequate.
{"title":"Use of artificial ants in a biometric checking system by iris recognition","authors":"A. Senouci, Bensoukehal Ali, Senouci Houaria, A. Benyettou","doi":"10.1109/WOSSPA.2013.6602392","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602392","url":null,"abstract":"In this article, we propose the use an algorithm of artificial ants inspired from chemical recognition system of ants in a biometric checking system by iris recognition, in order to make a success of the impostures tests and acceptances tests of the legitimate users. We presented our motivations which brought us to such a proposal, as we compared successfully our results with those obtained by the use of a decision threshold fixed relatively to a score of similarity calculated by using Hamming's distance. The approach appeared adequate.","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":"121261282","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.2013.6602341
K. Ferroudji, N. Benoudjit, Ayache Bouakaz
The classification of circulating microemboli, in the bloodstream, as gaseous or particulate matter is vital for selecting appropriate treatment for patients. Until now, Doppler techniques have shown some limitations to determine clearly the nature of circulating microemboli. The traditional techniques are largely based on the Fourier analysis. In this paper we present new emboli detection method based on Empirical mode decomposition and support vector machine using Radio Frequency (RF) signal instead of Doppler signals.
{"title":"Empirical mode decomposition based support vector machines for microemboli classification","authors":"K. Ferroudji, N. Benoudjit, Ayache Bouakaz","doi":"10.1109/WOSSPA.2013.6602341","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602341","url":null,"abstract":"The classification of circulating microemboli, in the bloodstream, as gaseous or particulate matter is vital for selecting appropriate treatment for patients. Until now, Doppler techniques have shown some limitations to determine clearly the nature of circulating microemboli. The traditional techniques are largely based on the Fourier analysis. In this paper we present new emboli detection method based on Empirical mode decomposition and support vector machine using Radio Frequency (RF) signal instead of Doppler signals.","PeriodicalId":417940,"journal":{"name":"2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA)","volume":"15 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":"114720923","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.2013.6602411
Ahmad Al-Rababa'a, Danny Dubé
The bit recycling compression technique has been introduced to minimize the redundancy caused by the multiplicity of encoding feature present in many compression techniques. It has achieved about 9% as a reduction in the size of the files compressed by Gzip. In this paper, we propose to adapt bit recycling to arithmetic code instead of Huffman code. This adaptation enables bit recycling to achieve better compression and a much wider applicability. A theoretical analysis that estimates the average amount of data compression that can be achieved by this adaptation is presented as well.
{"title":"Adaptation of bit recycling to arithmetic coding","authors":"Ahmad Al-Rababa'a, Danny Dubé","doi":"10.1109/WOSSPA.2013.6602411","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602411","url":null,"abstract":"The bit recycling compression technique has been introduced to minimize the redundancy caused by the multiplicity of encoding feature present in many compression techniques. It has achieved about 9% as a reduction in the size of the files compressed by Gzip. In this paper, we propose to adapt bit recycling to arithmetic code instead of Huffman code. This adaptation enables bit recycling to achieve better compression and a much wider applicability. A theoretical analysis that estimates the average amount of data compression that can be achieved by this adaptation is presented as well.","PeriodicalId":417940,"journal":{"name":"2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA)","volume":"6 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":"125890192","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.2013.6602364
Yan Zhang, Yi Tian, Zhaobin Wang, Yide Ma, Yurun Ma
This work presents a novel easy-to-use, portable, low-power, real-time, and autoalarm electrocardiogram (ECG) intelligent diagnosis system on MSP430 microcontroller. The real-time ECG signal is acquired at V1 lead and instantaneously amplified and filtered on front end circuit, and then, the signal is converted from analog ECG signal to digital value and filtered with Cohen Daubechies Feauveau 9/7 wavelet. Also, the ECG waveform is displayed on LCD and the real-time calculated heart rate is displayed on segment LCD, refreshed every 4 seconds. The buzzer alarms and the alarm message with the position information of the patient are sent to the doctors or relatives immediately, once an abnormal ECG is detected. A real-time R-wave detection algorithm based on integral projection function has been implemented, which is specially designed to be adaptive against the most common sources of noise and interference present and baseline wandering when acquiring the ECG. The system can identify premature ventricular contractions(PVC), which are very important for the subjects who are being monitored. Experimental results show the R-wave detection accuracy of the proposed system is 98.8% and the PVC detection and identification of the proposed system is 92.1%.
{"title":"An ECG intelligent monitoring system with MSP430 microcontroller","authors":"Yan Zhang, Yi Tian, Zhaobin Wang, Yide Ma, Yurun Ma","doi":"10.1109/WOSSPA.2013.6602364","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602364","url":null,"abstract":"This work presents a novel easy-to-use, portable, low-power, real-time, and autoalarm electrocardiogram (ECG) intelligent diagnosis system on MSP430 microcontroller. The real-time ECG signal is acquired at V1 lead and instantaneously amplified and filtered on front end circuit, and then, the signal is converted from analog ECG signal to digital value and filtered with Cohen Daubechies Feauveau 9/7 wavelet. Also, the ECG waveform is displayed on LCD and the real-time calculated heart rate is displayed on segment LCD, refreshed every 4 seconds. The buzzer alarms and the alarm message with the position information of the patient are sent to the doctors or relatives immediately, once an abnormal ECG is detected. A real-time R-wave detection algorithm based on integral projection function has been implemented, which is specially designed to be adaptive against the most common sources of noise and interference present and baseline wandering when acquiring the ECG. The system can identify premature ventricular contractions(PVC), which are very important for the subjects who are being monitored. Experimental results show the R-wave detection accuracy of the proposed system is 98.8% and the PVC detection and identification of the proposed system is 92.1%.","PeriodicalId":417940,"journal":{"name":"2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA)","volume":"13 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":"122150541","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.2013.6602340
Thomas Moranduzzo, F. Melgani, A. Daamouche
A problem of major interest for local governmental authorities is the monitoring of the number of cars invading the streets and the open parking lots. Different technologies have been used for such purpose. An emerging one is based on the use of remotely sensed images of very high spatial resolution, in particular those acquired from unmanned aerial vehicles. In this paper, we present a method to count objects in urban environments, with a focus on cars. It relies on an opportune sequence of processing and analysis steps so that to handle images of very few centimeters of resolution. Experimental results on real images are reported and discussed.
{"title":"An object detection technique for very high resolution remote sensing images","authors":"Thomas Moranduzzo, F. Melgani, A. Daamouche","doi":"10.1109/WOSSPA.2013.6602340","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602340","url":null,"abstract":"A problem of major interest for local governmental authorities is the monitoring of the number of cars invading the streets and the open parking lots. Different technologies have been used for such purpose. An emerging one is based on the use of remotely sensed images of very high spatial resolution, in particular those acquired from unmanned aerial vehicles. In this paper, we present a method to count objects in urban environments, with a focus on cars. It relies on an opportune sequence of processing and analysis steps so that to handle images of very few centimeters of resolution. Experimental results on real images are reported and discussed.","PeriodicalId":417940,"journal":{"name":"2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA)","volume":"45 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":"117090358","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.2013.6602328
A. Seghouane
When neural activity increases in a region of the brain, the local magnetic resonance signal produced in that part of the brain increases by a small amount owing to changes in blood oxygenation. This blood oxygenation level dependent (BOLD) effect is the basis for most functional magnetic resonance imaging (fMRI) studies done today to map patterns of activation in the working human brain. In this tutorial we will review the main techniques used to analyze fMRI data.
{"title":"FMRI: Principles and analysis","authors":"A. Seghouane","doi":"10.1109/WOSSPA.2013.6602328","DOIUrl":"https://doi.org/10.1109/WOSSPA.2013.6602328","url":null,"abstract":"When neural activity increases in a region of the brain, the local magnetic resonance signal produced in that part of the brain increases by a small amount owing to changes in blood oxygenation. This blood oxygenation level dependent (BOLD) effect is the basis for most functional magnetic resonance imaging (fMRI) studies done today to map patterns of activation in the working human brain. In this tutorial we will review the main techniques used to analyze fMRI data.","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":"123302005","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：