Pub Date : 2008-07-20DOI: 10.1109/SSD.2008.4632860
A. Al-Haj
Artificial neural networks are highly parallel structures inspired by the human brain. They have been used successfully in many human-like applications, such as pattern recognition. Performance of these networks can be enhanced if used properly in conjunction with equally powerful mathematical tools. In this paper, we used the discrete wavelet transform as a pre-processing tool for two well-known neural classifiers; competitive layer networks and learning vector networks. The wavelets transform was used successfully to approximate the input patterns of the two classifiers and thus reduced their input-layer requirements considerably. Such reduction facilitates cost-effective hardware implementations of artificial neural networks.
{"title":"Wavelets pre-processing of Artificial Neural Networks classifiers","authors":"A. Al-Haj","doi":"10.1109/SSD.2008.4632860","DOIUrl":"https://doi.org/10.1109/SSD.2008.4632860","url":null,"abstract":"Artificial neural networks are highly parallel structures inspired by the human brain. They have been used successfully in many human-like applications, such as pattern recognition. Performance of these networks can be enhanced if used properly in conjunction with equally powerful mathematical tools. In this paper, we used the discrete wavelet transform as a pre-processing tool for two well-known neural classifiers; competitive layer networks and learning vector networks. The wavelets transform was used successfully to approximate the input patterns of the two classifiers and thus reduced their input-layer requirements considerably. Such reduction facilitates cost-effective hardware implementations of artificial neural networks.","PeriodicalId":267264,"journal":{"name":"2008 5th International Multi-Conference on Systems, Signals and Devices","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114408601","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 : 2008-07-20DOI: 10.1109/SSD.2008.4632882
S. Dachasilaruk
The paper presents the wavelet shrinkage and the image compression for SAR images, based on discrete wavelet transform (DWT). It is very efficient to integrate these two procedures in a single process. First, a speckled SAR image is transformed by using multiple level wavelet decomposition. The variance of noise is estimated from wavelet coefficients to determine the threshold, which is used for soft thresholding in all high frequency subbands. The well-known threshold estimation includes SimpleShrink, NormalShrink, VisuShrink, SureShrink, and BayesShrink. The obtained wavelet coefficients are then encoded by using embedded zero-tree wavelet (EZW) to produce the output bit stream of the despeckled image. By means of an evaluating technique include S/MSE, MSE, and PSNR. Experimental results on JERS-1/SAR images are also given.
{"title":"Wavelet shrinkage and compression for SAR images","authors":"S. Dachasilaruk","doi":"10.1109/SSD.2008.4632882","DOIUrl":"https://doi.org/10.1109/SSD.2008.4632882","url":null,"abstract":"The paper presents the wavelet shrinkage and the image compression for SAR images, based on discrete wavelet transform (DWT). It is very efficient to integrate these two procedures in a single process. First, a speckled SAR image is transformed by using multiple level wavelet decomposition. The variance of noise is estimated from wavelet coefficients to determine the threshold, which is used for soft thresholding in all high frequency subbands. The well-known threshold estimation includes SimpleShrink, NormalShrink, VisuShrink, SureShrink, and BayesShrink. The obtained wavelet coefficients are then encoded by using embedded zero-tree wavelet (EZW) to produce the output bit stream of the despeckled image. By means of an evaluating technique include S/MSE, MSE, and PSNR. Experimental results on JERS-1/SAR images are also given.","PeriodicalId":267264,"journal":{"name":"2008 5th International Multi-Conference on Systems, Signals and Devices","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117051613","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 : 2008-07-20DOI: 10.1109/SSD.2008.4632837
H. Kidwai, F. Sibai, T. Rabie
The IBM Cell Broadband Engine (BE) is a multi-core processor with a PowerPC host processor (PPE) and 8 synergic processor engines (SPEs). The Cell BE architecture is designed to improve upon conventional processors in terms of memory latency, bandwidth and compute power. In this paper, we describe a 2D graphics algorithm for image resizing which we parallelized and developed on the Cell BE. We report the performance measured on one Cell blade with varying numbers of synergic processor engines enabled. These results were compared to those obtained on the Cellpsilas single PPE and with all 8 SPEs disabled. The results indicate that the Cell processor can outperform modern RISC processors by 20x on SIMD compute intensive applications such as image resizing.
IBM Cell宽带引擎(BE)是一个多核处理器，具有一个PowerPC主机处理器(PPE)和8个协同处理器引擎(spe)。Cell BE架构旨在改进传统处理器在内存延迟、带宽和计算能力方面的性能。在本文中，我们描述了一个二维图形的图像调整算法，我们并行化和开发在Cell BE上。我们报告了在启用了不同数量的协同处理器引擎的Cell刀片上测量的性能。这些结果与Cellpsilas单个PPE和所有8个spe禁用时获得的结果进行了比较。结果表明，Cell处理器在SIMD计算密集型应用(如图像调整大小)上的性能比现代RISC处理器高出20倍。
{"title":"Image magnification and reduction using high order filtering on the cell broadband engine","authors":"H. Kidwai, F. Sibai, T. Rabie","doi":"10.1109/SSD.2008.4632837","DOIUrl":"https://doi.org/10.1109/SSD.2008.4632837","url":null,"abstract":"The IBM Cell Broadband Engine (BE) is a multi-core processor with a PowerPC host processor (PPE) and 8 synergic processor engines (SPEs). The Cell BE architecture is designed to improve upon conventional processors in terms of memory latency, bandwidth and compute power. In this paper, we describe a 2D graphics algorithm for image resizing which we parallelized and developed on the Cell BE. We report the performance measured on one Cell blade with varying numbers of synergic processor engines enabled. These results were compared to those obtained on the Cellpsilas single PPE and with all 8 SPEs disabled. The results indicate that the Cell processor can outperform modern RISC processors by 20x on SIMD compute intensive applications such as image resizing.","PeriodicalId":267264,"journal":{"name":"2008 5th International Multi-Conference on Systems, Signals and Devices","volume":"279 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116276320","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 : 2008-07-20DOI: 10.1109/SSD.2008.4632867
M. Chettouh, R. Toumi, M. Hamerlain
Pneumatic artificial rubber muscles (Parms) show similarity to biological muscles. A 2-sliding control technique is applied to the first two degrees of freedom of a robot actuated by such muscles. The Parms are arranged in opposite pair or antagonistic configuration. The objective is to show that without the use of the equivalent control, it is still possible to control the robot and at the same time reduce the chatter. Experimental results are presented.
{"title":"A 2-sliding control for pneumatic artificial muscles","authors":"M. Chettouh, R. Toumi, M. Hamerlain","doi":"10.1109/SSD.2008.4632867","DOIUrl":"https://doi.org/10.1109/SSD.2008.4632867","url":null,"abstract":"Pneumatic artificial rubber muscles (Parms) show similarity to biological muscles. A 2-sliding control technique is applied to the first two degrees of freedom of a robot actuated by such muscles. The Parms are arranged in opposite pair or antagonistic configuration. The objective is to show that without the use of the equivalent control, it is still possible to control the robot and at the same time reduce the chatter. Experimental results are presented.","PeriodicalId":267264,"journal":{"name":"2008 5th International Multi-Conference on Systems, Signals and Devices","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130018980","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 : 2008-07-20DOI: 10.1109/SSD.2008.4632891
C. Maaoui, A. Pruski
This paper investigates the performance of support vector machines with linear, cubic and radial basis function (RBF) kernels in the problem of emotion recognition from physiological signals. Five physiological signals: blood volume pulse (BVP), electromyography (EMG), skin conductance (SC), skin temperature (SKT) and respiration (RESP) were selected to extract 30 features for recognition. Support vector machine(SVM) is a new technique for pattern classification, and is used in many applications. Kernel type in the SVM training process, along with feature selection, will significantly impact classification accuracy. Experiments are designed and carried out to find the best SVM kernel among linear, cubic, and RBF for emotions recognition. The experimental results indicate that the proposed method provides very stable and successful emotional classification performance over six emotional states.
{"title":"A comparative study of SVM kernel applied to emotion recognition from physiological signals","authors":"C. Maaoui, A. Pruski","doi":"10.1109/SSD.2008.4632891","DOIUrl":"https://doi.org/10.1109/SSD.2008.4632891","url":null,"abstract":"This paper investigates the performance of support vector machines with linear, cubic and radial basis function (RBF) kernels in the problem of emotion recognition from physiological signals. Five physiological signals: blood volume pulse (BVP), electromyography (EMG), skin conductance (SC), skin temperature (SKT) and respiration (RESP) were selected to extract 30 features for recognition. Support vector machine(SVM) is a new technique for pattern classification, and is used in many applications. Kernel type in the SVM training process, along with feature selection, will significantly impact classification accuracy. Experiments are designed and carried out to find the best SVM kernel among linear, cubic, and RBF for emotions recognition. The experimental results indicate that the proposed method provides very stable and successful emotional classification performance over six emotional states.","PeriodicalId":267264,"journal":{"name":"2008 5th International Multi-Conference on Systems, Signals and Devices","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129129297","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 : 2008-07-20DOI: 10.1109/SSD.2008.4632838
O. Badran, E. Abdulhadi
Due to the economic growth, increasing population, high fossil fuel cost, and the growing energy demand in Jordan, the provision of reliable energy supply at reasonable cost is considered a crucial element of economic reform. The present study utilizes fuzzy logic methodology to assess wind sites in Jordan and to decide which sites should be given the highest priority respect to their benefits and costs. The criterion of evaluation using fuzzy logic is based on different parameters, i.e., wind resources, prevailing wind direction, above ground level (AGL), site capacity, soil conditions, site elevation, land cost, land roughness, temperature, cultural and environmental concerns, aviation/telecommunications conflicts, nearby residentpsilas concerns, site environmental issues (corrosion, humidity), and distance to transmission line. The results show that Al Harir site in Al Tafila city is found to be the best choice and should be given the highest priority. It is followed by Al-Fujeij in Al-Shawbak then Al-Kamsha in Jerash.
{"title":"Promotion of wind energy in Jordan","authors":"O. Badran, E. Abdulhadi","doi":"10.1109/SSD.2008.4632838","DOIUrl":"https://doi.org/10.1109/SSD.2008.4632838","url":null,"abstract":"Due to the economic growth, increasing population, high fossil fuel cost, and the growing energy demand in Jordan, the provision of reliable energy supply at reasonable cost is considered a crucial element of economic reform. The present study utilizes fuzzy logic methodology to assess wind sites in Jordan and to decide which sites should be given the highest priority respect to their benefits and costs. The criterion of evaluation using fuzzy logic is based on different parameters, i.e., wind resources, prevailing wind direction, above ground level (AGL), site capacity, soil conditions, site elevation, land cost, land roughness, temperature, cultural and environmental concerns, aviation/telecommunications conflicts, nearby residentpsilas concerns, site environmental issues (corrosion, humidity), and distance to transmission line. The results show that Al Harir site in Al Tafila city is found to be the best choice and should be given the highest priority. It is followed by Al-Fujeij in Al-Shawbak then Al-Kamsha in Jerash.","PeriodicalId":267264,"journal":{"name":"2008 5th International Multi-Conference on Systems, Signals and Devices","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126221050","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 : 2008-07-20DOI: 10.1109/SSD.2008.4632846
L. Amouri, M. Jallouli, N. Derbel
Localization is one of the most important functions for the mobile robot navigation. Most of previous position estimation methods calculate current position and orientation of mobile robot by applying various localization schemes with the information obtained from internal sensors which are set on the mobile robot, or by recognizing an artificial landmark attached on the environment. Several drawbacks about them have been brought up. To avoid these inconvenient, a new localization method that calculate in real time the absolute position of the mobile robot by using external camera fixed on the ceiling in the indoor environment is proposed. Besides, this approach provide a low expensive solution using a Webcam. The effectiveness of the proposed localization algorithm is demonstrated through the experiments.
{"title":"Real time localisation of a mobile robot using Webcam data","authors":"L. Amouri, M. Jallouli, N. Derbel","doi":"10.1109/SSD.2008.4632846","DOIUrl":"https://doi.org/10.1109/SSD.2008.4632846","url":null,"abstract":"Localization is one of the most important functions for the mobile robot navigation. Most of previous position estimation methods calculate current position and orientation of mobile robot by applying various localization schemes with the information obtained from internal sensors which are set on the mobile robot, or by recognizing an artificial landmark attached on the environment. Several drawbacks about them have been brought up. To avoid these inconvenient, a new localization method that calculate in real time the absolute position of the mobile robot by using external camera fixed on the ceiling in the indoor environment is proposed. Besides, this approach provide a low expensive solution using a Webcam. The effectiveness of the proposed localization algorithm is demonstrated through the experiments.","PeriodicalId":267264,"journal":{"name":"2008 5th International Multi-Conference on Systems, Signals and Devices","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122580650","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 : 2008-07-20DOI: 10.1109/SSD.2008.4632832
M. Younis, N. Rahim, S. Mekhilef
This paper presents the design and analysis of a new configuration of parallel connected inverter suitable for fuel cell system application. The configuration consists of DC/DC converter and parallel three-phase DC/AC inverter. Series resistors added to the inverter output to maintain same current in each inverter of the two parallel inverters, and to reduce the circulating current in the parallel inverters to minimum. Third harmonic injection PWM (THIPWM) reduces the total harmonic distortion and to make maximum use of the voltage source. DSP was used to create the THIPWM and the control algorithm for the converter. PID controller is applied on the full-bridge DC/DC converter side to maintain the ac voltage to the required level. Experimental results have been shown to validate the proposed system.
{"title":"Parallel connected inverter for fuel cell system","authors":"M. Younis, N. Rahim, S. Mekhilef","doi":"10.1109/SSD.2008.4632832","DOIUrl":"https://doi.org/10.1109/SSD.2008.4632832","url":null,"abstract":"This paper presents the design and analysis of a new configuration of parallel connected inverter suitable for fuel cell system application. The configuration consists of DC/DC converter and parallel three-phase DC/AC inverter. Series resistors added to the inverter output to maintain same current in each inverter of the two parallel inverters, and to reduce the circulating current in the parallel inverters to minimum. Third harmonic injection PWM (THIPWM) reduces the total harmonic distortion and to make maximum use of the voltage source. DSP was used to create the THIPWM and the control algorithm for the converter. PID controller is applied on the full-bridge DC/DC converter side to maintain the ac voltage to the required level. Experimental results have been shown to validate the proposed system.","PeriodicalId":267264,"journal":{"name":"2008 5th International Multi-Conference on Systems, Signals and Devices","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121125558","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 : 2008-07-20DOI: 10.1109/SSD.2008.4632859
N. Bedioui, S. Salhi, M. Ksouri
This paper deals with the problem of robust stability for a class of nonlinear systems. The systems are composed of a linear constant part perturbated by an additive nonlinear function which satisfies a quadratic constraint. A new sufficient condition, formulated in terms of linear matrix inequality LMI, is presented for static output feedback stabilization. Numerical examples are given to illustrate the effectiveness of the proposed design methods.
{"title":"An improved LMI approach for robust static output feedback stabilization of nonlinear system","authors":"N. Bedioui, S. Salhi, M. Ksouri","doi":"10.1109/SSD.2008.4632859","DOIUrl":"https://doi.org/10.1109/SSD.2008.4632859","url":null,"abstract":"This paper deals with the problem of robust stability for a class of nonlinear systems. The systems are composed of a linear constant part perturbated by an additive nonlinear function which satisfies a quadratic constraint. A new sufficient condition, formulated in terms of linear matrix inequality LMI, is presented for static output feedback stabilization. Numerical examples are given to illustrate the effectiveness of the proposed design methods.","PeriodicalId":267264,"journal":{"name":"2008 5th International Multi-Conference on Systems, Signals and Devices","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121048455","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 : 2008-07-20DOI: 10.1109/SSD.2008.4632781
Huang Letian, Li Guang-jun
Commonality of various algorithms is analyzed based on the research of algorithms commonly used digital signal processing and a reconfigurable cell is proposed. A reconfigurable system with the cells is designed, which is widely used in a variety of digital signal processing. The principle and method of using this system are discussed with the basic algorithms of digital signal processing - multiplication and adder - as example. By means of simulation and implementation, it is found that this system has much higher processing speed and efficiency, compared with other kinds of GM multipliers.
{"title":"A reconfigurable system for digital signal processing","authors":"Huang Letian, Li Guang-jun","doi":"10.1109/SSD.2008.4632781","DOIUrl":"https://doi.org/10.1109/SSD.2008.4632781","url":null,"abstract":"Commonality of various algorithms is analyzed based on the research of algorithms commonly used digital signal processing and a reconfigurable cell is proposed. A reconfigurable system with the cells is designed, which is widely used in a variety of digital signal processing. The principle and method of using this system are discussed with the basic algorithms of digital signal processing - multiplication and adder - as example. By means of simulation and implementation, it is found that this system has much higher processing speed and efficiency, compared with other kinds of GM multipliers.","PeriodicalId":267264,"journal":{"name":"2008 5th International Multi-Conference on Systems, Signals and Devices","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133880268","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：