Pub Date : 2012-07-02DOI: 10.1109/ISSPA.2012.6310467
F. Ahmad, M. Amin
Strong front wall returns tend to obscure indoor targets and render through-the-wall target detection difficult and challenging. Among the various techniques proposed for wall clutter mitigation under monostatic radar operation is subspace projection. This technique uses the strength of the wall EM reflections relative to that of the target to separate the wall subspace from the target subspace. In this paper, we present analyses of the subspace projection approach for suppressing wall clutter and preserving indoor targets in multi-input multi-output (MIMO) through-the-wall radar imaging systems. We highlight the similarities and the differences in performance of the subspace technique under MIMO and monostatic configurations. Supporting results based on simulated and experimental data are provided.
{"title":"Wall clutter mitigation for MIMO radar configurations in urban sensing","authors":"F. Ahmad, M. Amin","doi":"10.1109/ISSPA.2012.6310467","DOIUrl":"https://doi.org/10.1109/ISSPA.2012.6310467","url":null,"abstract":"Strong front wall returns tend to obscure indoor targets and render through-the-wall target detection difficult and challenging. Among the various techniques proposed for wall clutter mitigation under monostatic radar operation is subspace projection. This technique uses the strength of the wall EM reflections relative to that of the target to separate the wall subspace from the target subspace. In this paper, we present analyses of the subspace projection approach for suppressing wall clutter and preserving indoor targets in multi-input multi-output (MIMO) through-the-wall radar imaging systems. We highlight the similarities and the differences in performance of the subspace technique under MIMO and monostatic configurations. Supporting results based on simulated and experimental data are provided.","PeriodicalId":248763,"journal":{"name":"2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130138835","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 : 2012-07-02DOI: 10.1109/ISSPA.2012.6310681
Feras AbuTalib, D. Giannacopoulos, A. Abran
This paper addresses the problem of applying the COSMIC ISO 19761 measurement method on a Magnetic Resonance Imaging (MRI) medical software application. The application in our case study uses 3D constrained Delaunay triangulated algorithms to generate volumetric meshes from the segmented 2D MRI images. The various steps of the measurement method are explored and discussed in details after analyzing the requirements and the system architecture of the application. Examples are presented to illustrate how the measurement results obtained can be beneficial to researchers evaluating and comparing such applications.
本文讨论了在磁共振成像(MRI)医学软件应用中应用COSMIC ISO 19761测量方法的问题。在我们的案例研究中，应用程序使用3D约束Delaunay三角化算法从分割的2D MRI图像中生成体积网格。在分析了应用的需求和系统架构后，对测量方法的各个步骤进行了详细的探索和讨论。举例说明如何测量结果获得可以有利于研究人员评估和比较这些应用。
{"title":"Case study: Applying the cosmic ISO 19761 measurement method on an MRI mesh generation medical application","authors":"Feras AbuTalib, D. Giannacopoulos, A. Abran","doi":"10.1109/ISSPA.2012.6310681","DOIUrl":"https://doi.org/10.1109/ISSPA.2012.6310681","url":null,"abstract":"This paper addresses the problem of applying the COSMIC ISO 19761 measurement method on a Magnetic Resonance Imaging (MRI) medical software application. The application in our case study uses 3D constrained Delaunay triangulated algorithms to generate volumetric meshes from the segmented 2D MRI images. The various steps of the measurement method are explored and discussed in details after analyzing the requirements and the system architecture of the application. Examples are presented to illustrate how the measurement results obtained can be beneficial to researchers evaluating and comparing such applications.","PeriodicalId":248763,"journal":{"name":"2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130169977","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 : 2012-07-02DOI: 10.1109/ISSPA.2012.6310464
Marc-Antoine Rondeau, R. Rose
This paper addresses the problem of open vocabulary automatic speech recognition (ASR) using hybrid statistical language models (LMs). Hybrid LMs differ from closed vocabulary LMs in that the word level lexicon is augmented with an inventory of sub-lexical units (SLUs). The procedures used for selecting these SLUs and expanding out-of-vocabulary (OOV) words according to the SLUs is presented in the paper. The open-vocabulary ASR performance obtained using these techniques is presented for a lecture speech task domain.
{"title":"Developing a hybrid language model for open vocabulary automatic speech recognition in a lecture speech task","authors":"Marc-Antoine Rondeau, R. Rose","doi":"10.1109/ISSPA.2012.6310464","DOIUrl":"https://doi.org/10.1109/ISSPA.2012.6310464","url":null,"abstract":"This paper addresses the problem of open vocabulary automatic speech recognition (ASR) using hybrid statistical language models (LMs). Hybrid LMs differ from closed vocabulary LMs in that the word level lexicon is augmented with an inventory of sub-lexical units (SLUs). The procedures used for selecting these SLUs and expanding out-of-vocabulary (OOV) words according to the SLUs is presented in the paper. The open-vocabulary ASR performance obtained using these techniques is presented for a lecture speech task domain.","PeriodicalId":248763,"journal":{"name":"2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122364027","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 : 2012-07-02DOI: 10.1109/ISSPA.2012.6310701
A. Serir, Youcef Bouhafsi
This paper deals with the micro-Doppler (m-D) phenomenon which is a frequency modulation induced on the returned radar signal due to micro-motion. Indeed, the micro-Doppler provides an additional information for target recognition that is complementary to existing recognition methods. In this paper we present a comparative study between feature extraction based on 2 types of analysis: time frequency (Instantaneous Frequency IF) analysis and time scale analysis (Wavelet Transform WT and Multiplicative Multiresolution Decomposition MMD), associated to SVM classifier to perform target identification. These approaches are tested on RadEch Database, containing radar echoes from various targets. The data has been collected in controlled test environments at the premises of Military Academy - Republic of Serbia. Thus, the results show that good performances are provided by the association of the instantaneous frequency with the MMD descriptor.
{"title":"Micro-doppler radar signature classification by time-frequency and time-scale analysis","authors":"A. Serir, Youcef Bouhafsi","doi":"10.1109/ISSPA.2012.6310701","DOIUrl":"https://doi.org/10.1109/ISSPA.2012.6310701","url":null,"abstract":"This paper deals with the micro-Doppler (m-D) phenomenon which is a frequency modulation induced on the returned radar signal due to micro-motion. Indeed, the micro-Doppler provides an additional information for target recognition that is complementary to existing recognition methods. In this paper we present a comparative study between feature extraction based on 2 types of analysis: time frequency (Instantaneous Frequency IF) analysis and time scale analysis (Wavelet Transform WT and Multiplicative Multiresolution Decomposition MMD), associated to SVM classifier to perform target identification. These approaches are tested on RadEch Database, containing radar echoes from various targets. The data has been collected in controlled test environments at the premises of Military Academy - Republic of Serbia. Thus, the results show that good performances are provided by the association of the instantaneous frequency with the MMD descriptor.","PeriodicalId":248763,"journal":{"name":"2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122389154","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 : 2012-07-02DOI: 10.1109/ISSPA.2012.6310513
Ming Li, J. Azaña
An approach for programmable single-shot chirped microwave pulse compression is proposed and experimentally demonstrated based on an optical fiber-based microwave dispersive line. The microwave dispersive line is implemented based on a time-spectrum convolution system. This proposed technique has three key features. The first feature is that non-periodic input chirped microwave pulses can be single-shot compressed. The second one is that the compression system is programmable by shaping the spectrum of a broadband multi-wavelength laser or by tuning the first-order dispersion of a dispersive element. The last one is that microwave dispersive line provides an ultrahigh microwave dispersion approaching several ns2 over GHz bandwidths. The microwave dispersive line used to implement single-shot microwave pulse compression is theoretically analyzed and verified by a proof-of-concept experiment.
{"title":"Programmable and single-shot chirped microwave pulse compression using an optical fiber-based microwave dispersive line","authors":"Ming Li, J. Azaña","doi":"10.1109/ISSPA.2012.6310513","DOIUrl":"https://doi.org/10.1109/ISSPA.2012.6310513","url":null,"abstract":"An approach for programmable single-shot chirped microwave pulse compression is proposed and experimentally demonstrated based on an optical fiber-based microwave dispersive line. The microwave dispersive line is implemented based on a time-spectrum convolution system. This proposed technique has three key features. The first feature is that non-periodic input chirped microwave pulses can be single-shot compressed. The second one is that the compression system is programmable by shaping the spectrum of a broadband multi-wavelength laser or by tuning the first-order dispersion of a dispersive element. The last one is that microwave dispersive line provides an ultrahigh microwave dispersion approaching several ns2 over GHz bandwidths. The microwave dispersive line used to implement single-shot microwave pulse compression is theoretically analyzed and verified by a proof-of-concept experiment.","PeriodicalId":248763,"journal":{"name":"2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127882137","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 : 2012-07-02DOI: 10.1109/ISSPA.2012.6310683
Reza Javanmard Alitappeh, Kossar Jeddi Saravi, F. Mahmoudi
The SIFT descriptor is one of the most widely used descriptors and is very stable in regard to changes in rotation, scale, affine, illumination, etc. This method is based on key points extracted from the image. If there are many such points, a lot of time will be needed in the matching and recognition phases. For this reason, we have tried in this article to use the clustering technique in order to reduce the number of key points by omitting similar points. In other words, subtractive clustering is used to select key points which are more distinct from and less similar to other points. In the section on conclusions, a successful implementation of this method is presented. The efficiencies of the proposed algorithm and of the base SIFT algorithm on the data set ALOI were investigated and it was observed that by adding this method to the base SIFT descriptor the rate of recognition increases by two percent and the time complexity decreases by 1.035728 seconds.
{"title":"Key point reduction in SIFT descriptor used by subtractive clustering","authors":"Reza Javanmard Alitappeh, Kossar Jeddi Saravi, F. Mahmoudi","doi":"10.1109/ISSPA.2012.6310683","DOIUrl":"https://doi.org/10.1109/ISSPA.2012.6310683","url":null,"abstract":"The SIFT descriptor is one of the most widely used descriptors and is very stable in regard to changes in rotation, scale, affine, illumination, etc. This method is based on key points extracted from the image. If there are many such points, a lot of time will be needed in the matching and recognition phases. For this reason, we have tried in this article to use the clustering technique in order to reduce the number of key points by omitting similar points. In other words, subtractive clustering is used to select key points which are more distinct from and less similar to other points. In the section on conclusions, a successful implementation of this method is presented. The efficiencies of the proposed algorithm and of the base SIFT algorithm on the data set ALOI were investigated and it was observed that by adding this method to the base SIFT descriptor the rate of recognition increases by two percent and the time complexity decreases by 1.035728 seconds.","PeriodicalId":248763,"journal":{"name":"2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129195448","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 : 2012-07-02DOI: 10.1109/ISSPA.2012.6310574
B. Boashash, T. B. Jabeur
Prior to birth, fetus health can be monitored by the variety and scale of its movements. In addition, at birth, EEG signals are recorded from at-risk newborns. Studies have shown that both fetal movements and newborn EEGs are non-stationary signals. This paper aims to represent both newborn EEG and fetal movement signals in a time-frequency domain using a specifically designed time-frequency distribution (TFD) that is well adapted to these types of data for the purpose of analysis, detection and classification. The approach to design the quadratic TFDS is based on relating separable-kernel TFDS to DSP spectral window and digital filter design. To reach this goal, we compared recently proposed TFDs such as the Modified B distribution, a separable Gaussian distribution and the B distribution. Then, an extension of the modified B distribution (MBD) is proposed, referred to as the extended separable-kernel MBD. This new TFD uses a separable kernel based on an extension of the modified B kernel in both time and frequency domain with different windows for each domain. Simulation results are provided to compare the proposed Method with different TFDs and to assess its performance. The new TFD is then first applied to real fetal movement data recorded using accelerometers.
{"title":"Design of a high-resolution separable-kernel quadratic TFD for improving newborn health outcomes using fetal movement detection","authors":"B. Boashash, T. B. Jabeur","doi":"10.1109/ISSPA.2012.6310574","DOIUrl":"https://doi.org/10.1109/ISSPA.2012.6310574","url":null,"abstract":"Prior to birth, fetus health can be monitored by the variety and scale of its movements. In addition, at birth, EEG signals are recorded from at-risk newborns. Studies have shown that both fetal movements and newborn EEGs are non-stationary signals. This paper aims to represent both newborn EEG and fetal movement signals in a time-frequency domain using a specifically designed time-frequency distribution (TFD) that is well adapted to these types of data for the purpose of analysis, detection and classification. The approach to design the quadratic TFDS is based on relating separable-kernel TFDS to DSP spectral window and digital filter design. To reach this goal, we compared recently proposed TFDs such as the Modified B distribution, a separable Gaussian distribution and the B distribution. Then, an extension of the modified B distribution (MBD) is proposed, referred to as the extended separable-kernel MBD. This new TFD uses a separable kernel based on an extension of the modified B kernel in both time and frequency domain with different windows for each domain. Simulation results are provided to compare the proposed Method with different TFDs and to assess its performance. The new TFD is then first applied to real fetal movement data recorded using accelerometers.","PeriodicalId":248763,"journal":{"name":"2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128480265","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 : 2012-07-02DOI: 10.1109/ISSPA.2012.6310622
Shou-Chun Yin, R. Rose, Yun Tang
This paper investigates a new approach for detecting phoneme level mispronunciations from utterances obtained from impaired children with neuromuscular disorders. This new pronunciation verification (PV) approach is obtained from the subspace based Gaussian mixture model (SGMM) based pronunciation model, where a set of state level projection vectors is applied for representing phonetic variability. SGMM models are trained from disabled speakers' utterances and PV scores are computed directly from distances between disabled and reference speaker projection vectors. An experimental study was performed to evaluate the performance of the SGMM based approach with respect to an approach based on the lattice posterior probabilities. A reduction in equal error rate (EER) of approximately 15% was obtained when the SGMM based scores were combined with lattice posterior probabilities.
{"title":"A study of applying subspace based pronunciation modeling in verifying pronunciation accuracy","authors":"Shou-Chun Yin, R. Rose, Yun Tang","doi":"10.1109/ISSPA.2012.6310622","DOIUrl":"https://doi.org/10.1109/ISSPA.2012.6310622","url":null,"abstract":"This paper investigates a new approach for detecting phoneme level mispronunciations from utterances obtained from impaired children with neuromuscular disorders. This new pronunciation verification (PV) approach is obtained from the subspace based Gaussian mixture model (SGMM) based pronunciation model, where a set of state level projection vectors is applied for representing phonetic variability. SGMM models are trained from disabled speakers' utterances and PV scores are computed directly from distances between disabled and reference speaker projection vectors. An experimental study was performed to evaluate the performance of the SGMM based approach with respect to an approach based on the lattice posterior probabilities. A reduction in equal error rate (EER) of approximately 15% was obtained when the SGMM based scores were combined with lattice posterior probabilities.","PeriodicalId":248763,"journal":{"name":"2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128699517","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 : 2012-07-02DOI: 10.1109/ISSPA.2012.6310456
Luca Didaci, F. Roli
The co-training algorithm can be applied if a dataset admits a representation into two different feature sets (two views). However, its optimality is proved only under the conditions a) sufficiency of each view, and b) conditional independence given the class. We address the case where condition a) doesn't hold, as often happens in concrete applications. In such cases the co-training is unable to converge to the optimal Bayesian classifier, because samples added in the training set are not distributed according to the class-conditional distributions, even if their assigned label is correct. These results help to better understand the behavior of the co-training algorithm when the classes are only `statistically' separable.
{"title":"A Bayesian analysis of co-training algorithm with insufficient views","authors":"Luca Didaci, F. Roli","doi":"10.1109/ISSPA.2012.6310456","DOIUrl":"https://doi.org/10.1109/ISSPA.2012.6310456","url":null,"abstract":"The co-training algorithm can be applied if a dataset admits a representation into two different feature sets (two views). However, its optimality is proved only under the conditions a) sufficiency of each view, and b) conditional independence given the class. We address the case where condition a) doesn't hold, as often happens in concrete applications. In such cases the co-training is unable to converge to the optimal Bayesian classifier, because samples added in the training set are not distributed according to the class-conditional distributions, even if their assigned label is correct. These results help to better understand the behavior of the co-training algorithm when the classes are only `statistically' separable.","PeriodicalId":248763,"journal":{"name":"2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115956866","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 : 2012-07-02DOI: 10.1109/ISSPA.2012.6310512
L. Potí
Digital processing role in the optical communications is analyzed together with its historical evolution and perspectives. If optical systems at their early stage included weak digital processing in the electrical domain, a fast evolution towards completely all-optical technologies arises due to the bottleneck caused by the electronics bandwidth limitation. With the return of coherent communications, digital processing migrated again back to the electronic domain. Nowadays, algorithm complexity capable of mitigating for linear and nonlinear fibre impairments is becoming unsustainable due to huge level of parallelization and power demand. For such a reason one possible evolution will include processing both in the electronic and optical domain.
{"title":"Digital processing in the optical communications","authors":"L. Potí","doi":"10.1109/ISSPA.2012.6310512","DOIUrl":"https://doi.org/10.1109/ISSPA.2012.6310512","url":null,"abstract":"Digital processing role in the optical communications is analyzed together with its historical evolution and perspectives. If optical systems at their early stage included weak digital processing in the electrical domain, a fast evolution towards completely all-optical technologies arises due to the bottleneck caused by the electronics bandwidth limitation. With the return of coherent communications, digital processing migrated again back to the electronic domain. Nowadays, algorithm complexity capable of mitigating for linear and nonlinear fibre impairments is becoming unsustainable due to huge level of parallelization and power demand. For such a reason one possible evolution will include processing both in the electronic and optical domain.","PeriodicalId":248763,"journal":{"name":"2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA)","volume":"532 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116707988","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：