Pub Date : 2003-09-04DOI: 10.1109/ISP.2003.1275825
M. Moura, A. Leiria, M. Ruano
Adaptive estimation of blood flow signals is performed resorting to a framework developed to support research on Doppler blood flow signals' analysis. Real time spectral estimation methods, real time performance evaluation and run-time adjustment of the estimation methods parameters are bound together, allowing the system to adapt itself to varying signal characteristic that are caused by physiological reasons.
{"title":"Adaptive system for blood flow estimation","authors":"M. Moura, A. Leiria, M. Ruano","doi":"10.1109/ISP.2003.1275825","DOIUrl":"https://doi.org/10.1109/ISP.2003.1275825","url":null,"abstract":"Adaptive estimation of blood flow signals is performed resorting to a framework developed to support research on Doppler blood flow signals' analysis. Real time spectral estimation methods, real time performance evaluation and run-time adjustment of the estimation methods parameters are bound together, allowing the system to adapt itself to varying signal characteristic that are caused by physiological reasons.","PeriodicalId":285893,"journal":{"name":"IEEE International Symposium on Intelligent Signal Processing, 2003","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130764839","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 : 2003-09-04DOI: 10.1109/ISP.2003.1275832
P. Liatsis, C. Kammerer, G. Kouremetis
We propose a novel sensor fusion system for lane following in autonomous vehicle navigation. The redundant sensors are a camera positioned in front of the rear view mirror of the vehicle and a map matching system consisting of a DGPS and a digital map. A local estimate of the road curvature is obtained with the use of the extended Kalman filter, while the global estimate is obtained from the map matching system. A fuzzy logic "gating network" is used to partition the input space into clusters, each associated with a RBF expert network. Training of the complete system is carried out online. Simulation results demonstrate the superior performance of the fusion scheme.
{"title":"Parameter estimation using a committee of local expert RBF networks","authors":"P. Liatsis, C. Kammerer, G. Kouremetis","doi":"10.1109/ISP.2003.1275832","DOIUrl":"https://doi.org/10.1109/ISP.2003.1275832","url":null,"abstract":"We propose a novel sensor fusion system for lane following in autonomous vehicle navigation. The redundant sensors are a camera positioned in front of the rear view mirror of the vehicle and a map matching system consisting of a DGPS and a digital map. A local estimate of the road curvature is obtained with the use of the extended Kalman filter, while the global estimate is obtained from the map matching system. A fuzzy logic \"gating network\" is used to partition the input space into clusters, each associated with a RBF expert network. Training of the complete system is carried out online. Simulation results demonstrate the superior performance of the fusion scheme.","PeriodicalId":285893,"journal":{"name":"IEEE International Symposium on Intelligent Signal Processing, 2003","volume":"539 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116500834","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 : 2003-09-04DOI: 10.1109/ISP.2003.1275828
J. Arenas-García, M. Martínez‐Ramón, V. Gómez-Verdejo, A. Figueiras-Vidal
The least mean square (LMS) algorithm has become a very popular algorithm for adaptive filtering due to its robustness and simplicity. A difficulty concerning LMS filters is their inherent compromise between tracking capabilities and precision, that is imposed by the selection of a fixed value for the adaption step. An adaptive convex combination of one fast LMS filter (high adaption step) and one slow LMS filter (low adaption step) was proposed as a way to break this balance. We propose to generalize this idea, combining multiple LMS filters with different adaption steps. Additional speeding up procedures are necessary to improve the performance of the basic scheme. Some simulation work has been carried out to show the appropriateness of this approach when identifying plants that vary at different rates.
{"title":"Multiple plant identifier via adaptive LMS convex combination","authors":"J. Arenas-García, M. Martínez‐Ramón, V. Gómez-Verdejo, A. Figueiras-Vidal","doi":"10.1109/ISP.2003.1275828","DOIUrl":"https://doi.org/10.1109/ISP.2003.1275828","url":null,"abstract":"The least mean square (LMS) algorithm has become a very popular algorithm for adaptive filtering due to its robustness and simplicity. A difficulty concerning LMS filters is their inherent compromise between tracking capabilities and precision, that is imposed by the selection of a fixed value for the adaption step. An adaptive convex combination of one fast LMS filter (high adaption step) and one slow LMS filter (low adaption step) was proposed as a way to break this balance. We propose to generalize this idea, combining multiple LMS filters with different adaption steps. Additional speeding up procedures are necessary to improve the performance of the basic scheme. Some simulation work has been carried out to show the appropriateness of this approach when identifying plants that vary at different rates.","PeriodicalId":285893,"journal":{"name":"IEEE International Symposium on Intelligent Signal Processing, 2003","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127989930","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 : 2003-09-04DOI: 10.1109/ISP.2003.1275850
S. Bartha, Z. Gabriel, L. Mezofi, G. Péceli
Most embedded signal processing applications are developed in at least two separate stages: signal-processing design followed by its digital implementation. With such an approach computational tasks that implement the signal processing algorithms are usually scheduled by treating their execution times and periods as unchangeable parameters. Task schedulability therefore is independent of the actual state of the physical environment; it depends only on the amount of computing resources available. In embedded systems, typically due to power and energy constraints, the available computing resources are definitely limited. A better overall performance might be achieved if signal-processing design and task scheduling are linked, and an integrated approach is applied. An attempt is made to handle temporary resource insufficiency by introducing quality-of-service (QoS) adaptation into signal processing. The approach applied can be considered as a "never-give-up" strategy, where the signal processing is performed in any case at the price of lower quality. In the proposed solution different algorithms are available at task execution level, having different execution times and quality. The version to be executed is selected by the ongoing scheduling mechanism. In our experimental setup the earliest deadline first (EDF) algorithm is applied for this purpose, and different-order median-filters are utilized to illustrate the concept of QoS adaptation in signal processing.
{"title":"Signal processing in resource insufficient environment","authors":"S. Bartha, Z. Gabriel, L. Mezofi, G. Péceli","doi":"10.1109/ISP.2003.1275850","DOIUrl":"https://doi.org/10.1109/ISP.2003.1275850","url":null,"abstract":"Most embedded signal processing applications are developed in at least two separate stages: signal-processing design followed by its digital implementation. With such an approach computational tasks that implement the signal processing algorithms are usually scheduled by treating their execution times and periods as unchangeable parameters. Task schedulability therefore is independent of the actual state of the physical environment; it depends only on the amount of computing resources available. In embedded systems, typically due to power and energy constraints, the available computing resources are definitely limited. A better overall performance might be achieved if signal-processing design and task scheduling are linked, and an integrated approach is applied. An attempt is made to handle temporary resource insufficiency by introducing quality-of-service (QoS) adaptation into signal processing. The approach applied can be considered as a \"never-give-up\" strategy, where the signal processing is performed in any case at the price of lower quality. In the proposed solution different algorithms are available at task execution level, having different execution times and quality. The version to be executed is selected by the ongoing scheduling mechanism. In our experimental setup the earliest deadline first (EDF) algorithm is applied for this purpose, and different-order median-filters are utilized to illustrate the concept of QoS adaptation in signal processing.","PeriodicalId":285893,"journal":{"name":"IEEE International Symposium on Intelligent Signal Processing, 2003","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132352979","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 : 2003-09-04DOI: 10.1109/ISP.2003.1275815
R. Micheletti
The paper deals with the accurate slip measurement of induction motors. The proposed procedure uses a noninvasive slip measurement scheme based on digital filtering and dynamic parameter estimation. The slip measurement is carried out without speed sensor and is deduced analyzing the magnetic field harmonics spectrum in proximity of the induction motor. First the EMF induced waveform, taken from a searching coil, is filtered using algorithms based on the discrete Fourier transform. Then the stator frequency and rotor frequency are obtained by comparing the filtered voltage with a mathematical model using an optimization procedure. The model's parameters are varied until an adequate match is obtained with the filtered voltage. Experimental results are presented to validate this method.
{"title":"Sensorless speed measurement of induction motors","authors":"R. Micheletti","doi":"10.1109/ISP.2003.1275815","DOIUrl":"https://doi.org/10.1109/ISP.2003.1275815","url":null,"abstract":"The paper deals with the accurate slip measurement of induction motors. The proposed procedure uses a noninvasive slip measurement scheme based on digital filtering and dynamic parameter estimation. The slip measurement is carried out without speed sensor and is deduced analyzing the magnetic field harmonics spectrum in proximity of the induction motor. First the EMF induced waveform, taken from a searching coil, is filtered using algorithms based on the discrete Fourier transform. Then the stator frequency and rotor frequency are obtained by comparing the filtered voltage with a mathematical model using an optimization procedure. The model's parameters are varied until an adequate match is obtained with the filtered voltage. Experimental results are presented to validate this method.","PeriodicalId":285893,"journal":{"name":"IEEE International Symposium on Intelligent Signal Processing, 2003","volume":"80 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121012650","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 : 2003-09-04DOI: 10.1109/ISP.2003.1275830
A. Rovid, G. Melegh
Car body deformation modeling plays a very important role in crash accident analyses, as well as the determination of the energy absorbed by the deformation and the corresponding energy equivalent speed /EES/. These parameters are of key importance, but on the other hand their precise determination is a very difficult task. However, by utilizing the results of the crash tests and the method of digital image processing, it is possible to state the absorbed energy through the digital processing of the photos.
{"title":"Modelling of road vehicle body deformation using EES values detection","authors":"A. Rovid, G. Melegh","doi":"10.1109/ISP.2003.1275830","DOIUrl":"https://doi.org/10.1109/ISP.2003.1275830","url":null,"abstract":"Car body deformation modeling plays a very important role in crash accident analyses, as well as the determination of the energy absorbed by the deformation and the corresponding energy equivalent speed /EES/. These parameters are of key importance, but on the other hand their precise determination is a very difficult task. However, by utilizing the results of the crash tests and the method of digital image processing, it is possible to state the absorbed energy through the digital processing of the photos.","PeriodicalId":285893,"journal":{"name":"IEEE International Symposium on Intelligent Signal Processing, 2003","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121967696","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 : 2003-09-04DOI: 10.1109/ISP.2003.1275818
Meng Xiangwei, Guan Jian, He You
Since the OTHR background noise is too strong, the target echoes would be embedded in sea clutter and environment noise. In order to detect targets such as ships or aircrafts from radar returns, a range Doppler CFAR schemes is presented, the identical Doppler frequency resolution cells over adjacent range or azimuth resolution cells are used to form a sliding window for targets detection. Since the OTHR range resolution cells is very large and so do the azimuth resolution cells, the total number of range Doppler resolution cells that forms sliding window is limited in order to guarantee stationary. Some CFAR algorithms such as CA, CM, TM, BLU and QBW methods that are suitable for OTHR are compared and analyzed versus different total range or azimuth resolution cells number. If the total range Doppler resolution cells number is small (less than 12), CA-CFAR is preferred in order to get the good detection performance. In multiple targets situation, CM-CFAR or TM-CFAR are suggested which trims the largest samples that possibly be interfering targets.
{"title":"CFAR techniques for over-the-horizon radar","authors":"Meng Xiangwei, Guan Jian, He You","doi":"10.1109/ISP.2003.1275818","DOIUrl":"https://doi.org/10.1109/ISP.2003.1275818","url":null,"abstract":"Since the OTHR background noise is too strong, the target echoes would be embedded in sea clutter and environment noise. In order to detect targets such as ships or aircrafts from radar returns, a range Doppler CFAR schemes is presented, the identical Doppler frequency resolution cells over adjacent range or azimuth resolution cells are used to form a sliding window for targets detection. Since the OTHR range resolution cells is very large and so do the azimuth resolution cells, the total number of range Doppler resolution cells that forms sliding window is limited in order to guarantee stationary. Some CFAR algorithms such as CA, CM, TM, BLU and QBW methods that are suitable for OTHR are compared and analyzed versus different total range or azimuth resolution cells number. If the total range Doppler resolution cells number is small (less than 12), CA-CFAR is preferred in order to get the good detection performance. In multiple targets situation, CM-CFAR or TM-CFAR are suggested which trims the largest samples that possibly be interfering targets.","PeriodicalId":285893,"journal":{"name":"IEEE International Symposium on Intelligent Signal Processing, 2003","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130399984","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 : 2003-09-04DOI: 10.1109/ISP.2003.1275847
G. Beligiannis, L.V. Skarlas, S. D. Likothanassis, K. Perdikouri
In this contribution, a genetic programming based technique, which combines the ability of genetic programming to explore both automatically and effectively, the whole set of candidate model structures and the robustness of evolutionary multimodel partitioning filters, is presented. The method is applied to the nonlinear system identification problem of complex biomedical data. Simulation results show that the algorithm identifies the true model and the true values of the unknown parameters for each different model structure, thus assisting the genetic programming technique to converge more quickly to the (near) optimal model structure. The method has all the known advantages of the evolutionary multimodel partitioning filters, that is, it is not restricted to the Gaussian case, it is applicable to online/adaptive operation and is computationally efficient. Furthermore, it can be realized in a parallel processing fashion, a fact, which makes it amenable to VLSI implementation.
{"title":"Nonlinear model structure identification of complex biomedical data using a genetic programming based technique","authors":"G. Beligiannis, L.V. Skarlas, S. D. Likothanassis, K. Perdikouri","doi":"10.1109/ISP.2003.1275847","DOIUrl":"https://doi.org/10.1109/ISP.2003.1275847","url":null,"abstract":"In this contribution, a genetic programming based technique, which combines the ability of genetic programming to explore both automatically and effectively, the whole set of candidate model structures and the robustness of evolutionary multimodel partitioning filters, is presented. The method is applied to the nonlinear system identification problem of complex biomedical data. Simulation results show that the algorithm identifies the true model and the true values of the unknown parameters for each different model structure, thus assisting the genetic programming technique to converge more quickly to the (near) optimal model structure. The method has all the known advantages of the evolutionary multimodel partitioning filters, that is, it is not restricted to the Gaussian case, it is applicable to online/adaptive operation and is computationally efficient. Furthermore, it can be realized in a parallel processing fashion, a fact, which makes it amenable to VLSI implementation.","PeriodicalId":285893,"journal":{"name":"IEEE International Symposium on Intelligent Signal Processing, 2003","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122222641","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 : 2003-09-04DOI: 10.1109/ISP.2003.1275812
J.P. Lanslots, A. Vecchio
Users of industrial software applications suffer from fast development cycles, and cannot keep up with the increasing complexity. However, an intelligent agent system assist the user in managing these complex environments by interaction of service-offering and service-requesting agents. This paper proposes such a multiagent framework that applies to a distributed measurement task in the structural testing domain. We define such a task as a setting in which both the objects under measurement as well as the users are physically spread out over the entire globe. The complexity of performing such complicated measurements and its coordination can be controlled by a multiagent system. The proposed framework outlines how a society of agents manage the entire data acquisition system. It coordinates its use by auction scheduling, and it presents an ontology that publishes the framework to the outside world. It is shown that the use of such service-offering agents in a distributed measurement setting is a feasible solution to encapsulate the complexity of industrial applications. This is shown based on a practical real-life measurement scenario.
{"title":"Using intelligent agents for distributed measurements","authors":"J.P. Lanslots, A. Vecchio","doi":"10.1109/ISP.2003.1275812","DOIUrl":"https://doi.org/10.1109/ISP.2003.1275812","url":null,"abstract":"Users of industrial software applications suffer from fast development cycles, and cannot keep up with the increasing complexity. However, an intelligent agent system assist the user in managing these complex environments by interaction of service-offering and service-requesting agents. This paper proposes such a multiagent framework that applies to a distributed measurement task in the structural testing domain. We define such a task as a setting in which both the objects under measurement as well as the users are physically spread out over the entire globe. The complexity of performing such complicated measurements and its coordination can be controlled by a multiagent system. The proposed framework outlines how a society of agents manage the entire data acquisition system. It coordinates its use by auction scheduling, and it presents an ontology that publishes the framework to the outside world. It is shown that the use of such service-offering agents in a distributed measurement setting is a feasible solution to encapsulate the complexity of industrial applications. This is shown based on a practical real-life measurement scenario.","PeriodicalId":285893,"journal":{"name":"IEEE International Symposium on Intelligent Signal Processing, 2003","volume":"229 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122354638","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 : 2003-09-04DOI: 10.1109/ISP.2003.1275851
J. Orozco, C. Reyes-García
We present the development of an automatic recognition system of infant cry, with the objective to classify two types of cry: normal and pathological cry from deaf babies. We used acoustic characteristics obtained by the linear prediction technique and as a classifier a feedforward neural network that was trained with several learning methods, resulting better the scaled conjugate gradient algorithm. Current results are shown, which, up to the moment, are very encouraging with an accuracy up to 94.3%.
{"title":"Implementation and analysis of training algorithms for the classification of infant cry with feed-forward neural networks","authors":"J. Orozco, C. Reyes-García","doi":"10.1109/ISP.2003.1275851","DOIUrl":"https://doi.org/10.1109/ISP.2003.1275851","url":null,"abstract":"We present the development of an automatic recognition system of infant cry, with the objective to classify two types of cry: normal and pathological cry from deaf babies. We used acoustic characteristics obtained by the linear prediction technique and as a classifier a feedforward neural network that was trained with several learning methods, resulting better the scaled conjugate gradient algorithm. Current results are shown, which, up to the moment, are very encouraging with an accuracy up to 94.3%.","PeriodicalId":285893,"journal":{"name":"IEEE International Symposium on Intelligent Signal Processing, 2003","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124767447","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：