Pub Date : 2007-10-01DOI: 10.1109/WISP.2007.4447509
M. Gómez, T. Martínez, S. Sánchez, D. Meziat
The goal of the work described in this paper is to develop a particular optimal control technique based on a Cell-Mapping technique in combination with the Q-learning reinforcement learning method to control wheeled mobile vehicles. This approach manages 4 state variables due to a dynamic model is performed instead of a kinematics model which can be done with less variables. This new solution can be applied to non-linear continuous systems where reinforcement learning methods have multiple constraints. Emphasis is given to the new combination of techniques, which applied to optimal control problems produce satisfactory results. The proposed algorithm is very robust to any change involved in the vehicle parameters because the vehicle model is estimated in real time from received experience.
{"title":"Optimal Control Applied to Wheeled Mobile Vehicles","authors":"M. Gómez, T. Martínez, S. Sánchez, D. Meziat","doi":"10.1109/WISP.2007.4447509","DOIUrl":"https://doi.org/10.1109/WISP.2007.4447509","url":null,"abstract":"The goal of the work described in this paper is to develop a particular optimal control technique based on a Cell-Mapping technique in combination with the Q-learning reinforcement learning method to control wheeled mobile vehicles. This approach manages 4 state variables due to a dynamic model is performed instead of a kinematics model which can be done with less variables. This new solution can be applied to non-linear continuous systems where reinforcement learning methods have multiple constraints. Emphasis is given to the new combination of techniques, which applied to optimal control problems produce satisfactory results. The proposed algorithm is very robust to any change involved in the vehicle parameters because the vehicle model is estimated in real time from received experience.","PeriodicalId":164902,"journal":{"name":"2007 IEEE International Symposium on Intelligent Signal Processing","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116109412","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 : 2007-10-01DOI: 10.1109/WISP.2007.4447560
I. Adam, C. Nafornita, Jean-Marc Boucher, A. Isar
The property of shift-invariance associated with a good directional selectivity is important for the application of a wavelet transform, (WT), in many fields of image processing. Generally, complex wavelet transforms, like for example the double tree complex wavelet transform, (DTCWT), have these good properties. In this paper we propose the use of a new implementation of such a WT, recently introduced, namely the hyperanalytic wavelet transform, (HWT), in denoising applications. The proposed denoising method is very simple, implying three steps: the computation of the forward WT, the filtering in the wavelets domain and the computation of the inverse WT, (IWT). The goal of this paper is the association of a new implementation of the HWT, recently proposed, with a maximum a posteriori (MAP) filter. Some simulation examples and comparisons prove the performances of the proposed denoising method.
{"title":"A Bayesian Approach of Hyperanalytic Wavelet Transform Based Denoising","authors":"I. Adam, C. Nafornita, Jean-Marc Boucher, A. Isar","doi":"10.1109/WISP.2007.4447560","DOIUrl":"https://doi.org/10.1109/WISP.2007.4447560","url":null,"abstract":"The property of shift-invariance associated with a good directional selectivity is important for the application of a wavelet transform, (WT), in many fields of image processing. Generally, complex wavelet transforms, like for example the double tree complex wavelet transform, (DTCWT), have these good properties. In this paper we propose the use of a new implementation of such a WT, recently introduced, namely the hyperanalytic wavelet transform, (HWT), in denoising applications. The proposed denoising method is very simple, implying three steps: the computation of the forward WT, the filtering in the wavelets domain and the computation of the inverse WT, (IWT). The goal of this paper is the association of a new implementation of the HWT, recently proposed, with a maximum a posteriori (MAP) filter. Some simulation examples and comparisons prove the performances of the proposed denoising method.","PeriodicalId":164902,"journal":{"name":"2007 IEEE International Symposium on Intelligent Signal Processing","volume":"174 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126118453","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 : 2007-10-01DOI: 10.1109/WISP.2007.4447586
E. L. Izquierdo, P. Urquhart, M. López-Amo
A novel optical fibre bus network for the multiplexing of sensors, which can recover from one or more point failures in the fibre, is presented. We describe how protection switching can be performed so that it satisfies three simultaneous criteria: 1. the network can survive at least one failure at any location, 2. the propagation losses are nominally equal for all channels, both before and after protection switching, and 3. it is possible to signal the presence of the failure and the required remedial actions without using external network resources. We explain how well known telecommunications protection categories can be applied in the context of sensor networks and we argue that "dedicated line" and "dedicated path" protection are preferable in most circumstances. The two categories of dedicated protection allow the failed fibre segment to be remotely determined merely by monitoring the presence or absence of the channels arriving at the network's receiver node.
{"title":"Optical Fibre Bus Protection Architecture for the Networking of Sensors","authors":"E. L. Izquierdo, P. Urquhart, M. López-Amo","doi":"10.1109/WISP.2007.4447586","DOIUrl":"https://doi.org/10.1109/WISP.2007.4447586","url":null,"abstract":"A novel optical fibre bus network for the multiplexing of sensors, which can recover from one or more point failures in the fibre, is presented. We describe how protection switching can be performed so that it satisfies three simultaneous criteria: 1. the network can survive at least one failure at any location, 2. the propagation losses are nominally equal for all channels, both before and after protection switching, and 3. it is possible to signal the presence of the failure and the required remedial actions without using external network resources. We explain how well known telecommunications protection categories can be applied in the context of sensor networks and we argue that \"dedicated line\" and \"dedicated path\" protection are preferable in most circumstances. The two categories of dedicated protection allow the failed fibre segment to be remotely determined merely by monitoring the presence or absence of the channels arriving at the network's receiver node.","PeriodicalId":164902,"journal":{"name":"2007 IEEE International Symposium on Intelligent Signal Processing","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128055471","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 : 2007-10-01DOI: 10.1109/WISP.2007.4447507
L. Ribeiro, A. Ruano, M. Ruano, P. Ferreira
Technological and computing evolution promoted new opportunities to improve the quality of life through new medical achievements, in particular, the quality of diagnostic evaluations. Computerised tomography (CT) is one of the imaging equipments for diagnosis which has most benefited from technological improvements. Because of that, and due to the quality of the diagnosis produced, it is one of the most employed equipments in clinical applications. As an example, the ischaemic cerebral vascular accident (ICVA) is a pathology confirming the frequent use of CT. The interest in this pathology, and in general for the encephalon image analysis as a preventive diagnosis, is mainly due to its frequent occurrence in development countries and its social- economic impact. In this paper we propose to evaluate the ability of artificial neural networks (ANNs) for automatic identification of ICVAs by means of tissue density images obtained by CT. Cranioencephalon CT exams and their respective medical reports were used to train ANN classifiers by means of features extracted from the images. Once the ANNs were trained, the classifiers were tested with data never seen by the network. At this stage we may conclude that the ANNs may significantly contribute as an ICVAs CT diagnostic aid, since among the test cases the automatic identification of ischaemic lesions has been performed with no false negatives and very few false positives.
{"title":"Neural networks assisted diagnosis of ischemic CVA's through CT scan","authors":"L. Ribeiro, A. Ruano, M. Ruano, P. Ferreira","doi":"10.1109/WISP.2007.4447507","DOIUrl":"https://doi.org/10.1109/WISP.2007.4447507","url":null,"abstract":"Technological and computing evolution promoted new opportunities to improve the quality of life through new medical achievements, in particular, the quality of diagnostic evaluations. Computerised tomography (CT) is one of the imaging equipments for diagnosis which has most benefited from technological improvements. Because of that, and due to the quality of the diagnosis produced, it is one of the most employed equipments in clinical applications. As an example, the ischaemic cerebral vascular accident (ICVA) is a pathology confirming the frequent use of CT. The interest in this pathology, and in general for the encephalon image analysis as a preventive diagnosis, is mainly due to its frequent occurrence in development countries and its social- economic impact. In this paper we propose to evaluate the ability of artificial neural networks (ANNs) for automatic identification of ICVAs by means of tissue density images obtained by CT. Cranioencephalon CT exams and their respective medical reports were used to train ANN classifiers by means of features extracted from the images. Once the ANNs were trained, the classifiers were tested with data never seen by the network. At this stage we may conclude that the ANNs may significantly contribute as an ICVAs CT diagnostic aid, since among the test cases the automatic identification of ischaemic lesions has been performed with no false negatives and very few false positives.","PeriodicalId":164902,"journal":{"name":"2007 IEEE International Symposium on Intelligent Signal Processing","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130567903","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 : 2007-10-01DOI: 10.1109/WISP.2007.4447644
R. García-Retegui, S. A. Gonzalez, M. Funes, S. Maestri
This work presents a synchronization method based on the implementation of a sliding-window digital-filter that uses the Goertzel algorithm. The proposed method filters the incoming power grid signal and specifies the input frequency by measuring the period of the output phase. The sampling frequency is adjusted to correct the phase errors introduced by the filter whenever variations in the frequency occur. Regardless of the magnitude of the input frequency variations, this method determines the input frequency with high accuracy.
{"title":"Implementation of a novel synchronization method using Sliding Goertzel DFT","authors":"R. García-Retegui, S. A. Gonzalez, M. Funes, S. Maestri","doi":"10.1109/WISP.2007.4447644","DOIUrl":"https://doi.org/10.1109/WISP.2007.4447644","url":null,"abstract":"This work presents a synchronization method based on the implementation of a sliding-window digital-filter that uses the Goertzel algorithm. The proposed method filters the incoming power grid signal and specifies the input frequency by measuring the period of the output phase. The sampling frequency is adjusted to correct the phase errors introduced by the filter whenever variations in the frequency occur. Regardless of the magnitude of the input frequency variations, this method determines the input frequency with high accuracy.","PeriodicalId":164902,"journal":{"name":"2007 IEEE International Symposium on Intelligent Signal Processing","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131952186","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 : 2007-10-01DOI: 10.1109/WISP.2007.4447569
Jesús Vega, G. Rattá, A. Murari, P. Castro, S. Dormido-Canto, R. Dormido, G. Farías, A. Pereira, A. Portas, E. L. Luna, I. Pastor, Jose Angel Sanchez, N. Duro, R. Castro, Matilde Santos, H. Vargas
Physics studies in fusion devices require statistical analyses of a large number of discharges. Given the complexity of the plasma and the non-linear interactions between the relevant parameters, connecting a physical phenomenon with the signal patterns that it generates can be quite demanding Up to now, data retrieval has been typically accomplished by means of signal name and shot number. The search of the temporal segment to analyze has been carried out in a manual way. Manual searches in databases must be replaced by intelligent techniques to look for data in an automated way. Structural pattern recognition techniques have proven to be very efficient methods to index and retrieve data in JET and TJ-II databases. Waveforms and images can be accessed through several structural pattern recognition applications.
{"title":"Recent results on structural pattern recognition for Fusion massive databases","authors":"Jesús Vega, G. Rattá, A. Murari, P. Castro, S. Dormido-Canto, R. Dormido, G. Farías, A. Pereira, A. Portas, E. L. Luna, I. Pastor, Jose Angel Sanchez, N. Duro, R. Castro, Matilde Santos, H. Vargas","doi":"10.1109/WISP.2007.4447569","DOIUrl":"https://doi.org/10.1109/WISP.2007.4447569","url":null,"abstract":"Physics studies in fusion devices require statistical analyses of a large number of discharges. Given the complexity of the plasma and the non-linear interactions between the relevant parameters, connecting a physical phenomenon with the signal patterns that it generates can be quite demanding Up to now, data retrieval has been typically accomplished by means of signal name and shot number. The search of the temporal segment to analyze has been carried out in a manual way. Manual searches in databases must be replaced by intelligent techniques to look for data in an automated way. Structural pattern recognition techniques have proven to be very efficient methods to index and retrieve data in JET and TJ-II databases. Waveforms and images can be accessed through several structural pattern recognition applications.","PeriodicalId":164902,"journal":{"name":"2007 IEEE International Symposium on Intelligent Signal Processing","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130959319","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 : 2007-10-01DOI: 10.1109/WISP.2007.4447587
M. Jiang, Yong Wang, F. Rubio, D. Yuan
A new estimation method by the swarm intelligent optimization algorithm is presented to recover the transmitted data bits and code of spread spectrum signal over additive white Gaussian noise channel, while the receiver has no knowledge of the transmitter spreading sequence, only knows the length of spreading sequence. The presented estimation method by Artificial Fish Swarm Algorithm (AFSA) is insensitive to initial values, has a strong robustness, and has the faster convergence speed and better estimation precision than the estimation method by Genetic Algorithm (GA) and the estimation method by Particle Swarm Optimization (PSO). The results show that the method can obtain the optimal or sub-optimal estimation of spreading code, even when the signal power is below the noise power.
{"title":"Spread Spectrum Code Estimation by Artificial Fish Swarm Algorithm","authors":"M. Jiang, Yong Wang, F. Rubio, D. Yuan","doi":"10.1109/WISP.2007.4447587","DOIUrl":"https://doi.org/10.1109/WISP.2007.4447587","url":null,"abstract":"A new estimation method by the swarm intelligent optimization algorithm is presented to recover the transmitted data bits and code of spread spectrum signal over additive white Gaussian noise channel, while the receiver has no knowledge of the transmitter spreading sequence, only knows the length of spreading sequence. The presented estimation method by Artificial Fish Swarm Algorithm (AFSA) is insensitive to initial values, has a strong robustness, and has the faster convergence speed and better estimation precision than the estimation method by Genetic Algorithm (GA) and the estimation method by Particle Swarm Optimization (PSO). The results show that the method can obtain the optimal or sub-optimal estimation of spreading code, even when the signal power is below the noise power.","PeriodicalId":164902,"journal":{"name":"2007 IEEE International Symposium on Intelligent Signal Processing","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132370545","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 : 2007-10-01DOI: 10.1109/WISP.2007.4447625
A. J. Cantos, M. Santos
In the analysis of signals from massive databases it is desirable to have automatic mechanisms for classification. The synergy of diverse artificial intelligence techniques with advanced signal representation models is becoming very efficient in developing this kind of task. In this paper, it is shown that genetic algorithms focused on rule discovery might be used for this purpose. In our approach, each individual represents a classifying rule, composed of an antecedent and a consequence. Using a technique based on niches in order to avoid the extinction of any of the species, we obtain several solutions that form an expert classification system. The results have been compared with those of other classifiers on the same signals and they show efficiency of our procedure.
{"title":"Knowledge extraction in signals classification with genetic algorithms","authors":"A. J. Cantos, M. Santos","doi":"10.1109/WISP.2007.4447625","DOIUrl":"https://doi.org/10.1109/WISP.2007.4447625","url":null,"abstract":"In the analysis of signals from massive databases it is desirable to have automatic mechanisms for classification. The synergy of diverse artificial intelligence techniques with advanced signal representation models is becoming very efficient in developing this kind of task. In this paper, it is shown that genetic algorithms focused on rule discovery might be used for this purpose. In our approach, each individual represents a classifying rule, composed of an antecedent and a consequence. Using a technique based on niches in order to avoid the extinction of any of the species, we obtain several solutions that form an expert classification system. The results have been compared with those of other classifiers on the same signals and they show efficiency of our procedure.","PeriodicalId":164902,"journal":{"name":"2007 IEEE International Symposium on Intelligent Signal Processing","volume":"183 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115068740","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 : 2007-10-01DOI: 10.1109/WISP.2007.4447521
A. Khosravi, A. Jalali
This paper develops a low-order l1 optimal controller design method for linear continuous time-invariant two-input, two-output systems. The new technique, which is proposed as an algorithm, combines the original concept of peak-to-peak gain of design system with optimal control theory and employs a free design parameter allowing for a flexible management of the tradeoff between robustness to disturbance signals and magnitude of the worst peak-to-peak gain of the design system. For solving this nonconvex problem, several linear construction and coprime factors so that based on strictly positive real function have been used.
{"title":"Low-Order L1 Optimal Control Design via LMI","authors":"A. Khosravi, A. Jalali","doi":"10.1109/WISP.2007.4447521","DOIUrl":"https://doi.org/10.1109/WISP.2007.4447521","url":null,"abstract":"This paper develops a low-order l1 optimal controller design method for linear continuous time-invariant two-input, two-output systems. The new technique, which is proposed as an algorithm, combines the original concept of peak-to-peak gain of design system with optimal control theory and employs a free design parameter allowing for a flexible management of the tradeoff between robustness to disturbance signals and magnitude of the worst peak-to-peak gain of the design system. For solving this nonconvex problem, several linear construction and coprime factors so that based on strictly positive real function have been used.","PeriodicalId":164902,"journal":{"name":"2007 IEEE International Symposium on Intelligent Signal Processing","volume":"34 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121187919","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 : 2007-10-01DOI: 10.1109/WISP.2007.4447551
M. J. Flores, Jose M. Armingol, A. D. L. Escalera
This paper presents a skin-color model and an automatic face detection system on color images. Three probability distribution functions are proposed to model the skin color: flexible generalized skew-normal distribution, skew generalized normal distribution and Gaussian mixture model, over three color spaces: CbCr, HS and H. The best model is chosen to build a system for detection and tracking face, using color information. The algorithm has been tested on several sequences of color images.
{"title":"New Probability Models for Face Detection and Tracking in Color Images","authors":"M. J. Flores, Jose M. Armingol, A. D. L. Escalera","doi":"10.1109/WISP.2007.4447551","DOIUrl":"https://doi.org/10.1109/WISP.2007.4447551","url":null,"abstract":"This paper presents a skin-color model and an automatic face detection system on color images. Three probability distribution functions are proposed to model the skin color: flexible generalized skew-normal distribution, skew generalized normal distribution and Gaussian mixture model, over three color spaces: CbCr, HS and H. The best model is chosen to build a system for detection and tracking face, using color information. The algorithm has been tested on several sequences of color images.","PeriodicalId":164902,"journal":{"name":"2007 IEEE International Symposium on Intelligent Signal Processing","volume":"2016 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121334165","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：