A machine vision-based classification system to sort coffee fruits (cherries) according their ripeness stage is presented. Eight categories were defined and they include the entire coffee cherry ripeness process, from the initial stage (early green) to over-ripe and dry stages. A Bayesian classifier was implemented using a set of nine features which include color, shape and texture computed on an image of the fruit, with a 96.88% of performance using the cross-validation approach.
{"title":"Digital Image Processing for Classification of Coffee Cherries","authors":"Zulma L. Sandoval, F. Prieto, J. Betancur","doi":"10.1109/CERMA.2010.54","DOIUrl":"https://doi.org/10.1109/CERMA.2010.54","url":null,"abstract":"A machine vision-based classification system to sort coffee fruits (cherries) according their ripeness stage is presented. Eight categories were defined and they include the entire coffee cherry ripeness process, from the initial stage (early green) to over-ripe and dry stages. A Bayesian classifier was implemented using a set of nine features which include color, shape and texture computed on an image of the fruit, with a 96.88% of performance using the cross-validation approach.","PeriodicalId":119218,"journal":{"name":"2010 IEEE Electronics, Robotics and Automotive Mechanics Conference","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115466009","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}
J. Mendiola-Santibañez, Lidia G. Ortega-Bucio, I. Terol-Villalobos, I. Santillán
In this work, first is exposed the various definitions of connection by the mathematical morphology, then the application of several morphological connected openings for image segmentation is presented. Each one of the openings has a particular behavior because its definition under the concept of connection, so it could be exploited to separate some particular objects in the images or to filter different structures of interest. Finally, the performance of each operator is illustrated through several examples.
{"title":"Morphological Connected Openings to Image Segmentation","authors":"J. Mendiola-Santibañez, Lidia G. Ortega-Bucio, I. Terol-Villalobos, I. Santillán","doi":"10.1109/CERMA.2010.114","DOIUrl":"https://doi.org/10.1109/CERMA.2010.114","url":null,"abstract":"In this work, first is exposed the various definitions of connection by the mathematical morphology, then the application of several morphological connected openings for image segmentation is presented. Each one of the openings has a particular behavior because its definition under the concept of connection, so it could be exploited to separate some particular objects in the images or to filter different structures of interest. Finally, the performance of each operator is illustrated through several examples.","PeriodicalId":119218,"journal":{"name":"2010 IEEE Electronics, Robotics and Automotive Mechanics Conference","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116925890","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}
The proposed antenna is formed by a patch rectangular antenna with an inner pentagonal one, built on FR-4, due its low cost and availability. There were considered 2.4 and 5.8 GHz as the operation frequencies, considering linear polarization in order to apply them to Wi-Fi equipments. The pentagonal patches were designed considering them as equivalents with the corresponding circular resonators. The simulations are realized using CADFEKO, software based on the Moment Method (MoM). The proofs were realized considering the designed antennas as replacement ones on a router. Simulated input return loss show a good agreement with the operation frequencies design. It has been demonstrated that the dual antenna operate satisfactorily in the 2.4 and 5.8 GHz frequency ranges, showing its feasibility to use it for Wi-Fi applications. Experimental results are compared to predictions from a software package confirming monopolar radiation in two bands at 2.4 GHz and 5.8 GHz.
{"title":"Dual Band Pentagonal Microstrip Antenna for Wi-Fi Applications","authors":"M. Tecpoyotl-Torres, J. G. Vera-Dimas","doi":"10.1109/CERMA.2010.102","DOIUrl":"https://doi.org/10.1109/CERMA.2010.102","url":null,"abstract":"The proposed antenna is formed by a patch rectangular antenna with an inner pentagonal one, built on FR-4, due its low cost and availability. There were considered 2.4 and 5.8 GHz as the operation frequencies, considering linear polarization in order to apply them to Wi-Fi equipments. The pentagonal patches were designed considering them as equivalents with the corresponding circular resonators. The simulations are realized using CADFEKO, software based on the Moment Method (MoM). The proofs were realized considering the designed antennas as replacement ones on a router. Simulated input return loss show a good agreement with the operation frequencies design. It has been demonstrated that the dual antenna operate satisfactorily in the 2.4 and 5.8 GHz frequency ranges, showing its feasibility to use it for Wi-Fi applications. Experimental results are compared to predictions from a software package confirming monopolar radiation in two bands at 2.4 GHz and 5.8 GHz.","PeriodicalId":119218,"journal":{"name":"2010 IEEE Electronics, Robotics and Automotive Mechanics Conference","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127357387","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}
This paper presents a vision chip for laser spot detection. The sensor has an architecture that comprises a 64x64 pixel array with a pixel pitch of 38.6μm x 30.8μm and fill factor of 30% and two position processors that deliver coordinate position for both axes. Under maximum speed condition, power consumption was 103mW, where maximum frame rate was 870000 frames per second. The maximum mismatch between pixels was 3% and maximum position accuracy was 0.013(2 x).
介绍了一种用于激光光斑检测的视觉芯片。该传感器的架构包括一个64x64像素阵列，像素间距为38.6μm x 30.8μm，填充系数为30%，以及两个位置处理器，可为两个轴提供坐标位置。在最大速度条件下，功耗为103mW，最大帧率为870000帧/秒。像素之间的最大不匹配为3%，最大位置精度为0.013(2倍)。
{"title":"CMOS Vision Chip for Laser Spot Position Detection","authors":"J. Garcia-Lamont, M. Aleman-Arce","doi":"10.1109/CERMA.2010.90","DOIUrl":"https://doi.org/10.1109/CERMA.2010.90","url":null,"abstract":"This paper presents a vision chip for laser spot detection. The sensor has an architecture that comprises a 64x64 pixel array with a pixel pitch of 38.6μm x 30.8μm and fill factor of 30% and two position processors that deliver coordinate position for both axes. Under maximum speed condition, power consumption was 103mW, where maximum frame rate was 870000 frames per second. The maximum mismatch between pixels was 3% and maximum position accuracy was 0.013(2 x).","PeriodicalId":119218,"journal":{"name":"2010 IEEE Electronics, Robotics and Automotive Mechanics Conference","volume":"200 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123296145","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}
In this paper the problem of trajectory tracking is studied. Based on the V-stability and Lyapunov theory, a control law that achieves the global asymptotic stability of the tracking error between a delayed recurrent neural network and a complex dynamical network is obtained. To illustrate the analytic results we present a tracking simulation of a dynamical network with each node being a Chen’s dynamical system.
{"title":"Trajectory Tracking of Complex Dynamical Network for Delayed Recurrent Neural Network via Control V-Stability","authors":"J. Perez, Jorge A. Gonzalez, R. Soto, Joel Perez","doi":"10.1109/CERMA.2010.9","DOIUrl":"https://doi.org/10.1109/CERMA.2010.9","url":null,"abstract":"In this paper the problem of trajectory tracking is studied. Based on the V-stability and Lyapunov theory, a control law that achieves the global asymptotic stability of the tracking error between a delayed recurrent neural network and a complex dynamical network is obtained. To illustrate the analytic results we present a tracking simulation of a dynamical network with each node being a Chen’s dynamical system.","PeriodicalId":119218,"journal":{"name":"2010 IEEE Electronics, Robotics and Automotive Mechanics Conference","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126923396","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}
Surrogate modeling using a polynomial approximation of a coarse model of a Substrate Integrated Wave guide (SIW) with micro strip transitions is presented in this paper. The surrogate modeling process is realized considering different base points distributions, as well as different sizes for the region of interest in order to evaluate their impact on the corresponding surrogate modeling accuracy. The polynomial approximation is a low-order function of the design variables and it is used to approximate electromagnetic responses of the SIW interconnect in a region of interest around the selected central base point. The surrogate modeling process is implemented in Matlab, while the electromagnetic responses of the SIW are obtained using a low-resolution EM model implemented in CST Microwave Studio to speed up the modeling process.
{"title":"Impact of Base Points Distributions on the Polynomial Surrogate Modeling of a Substrate Integrated Waveguide with Microstrip Transitions","authors":"J. Rayas-Sánchez, Diego E. Cordero-Baltazar","doi":"10.1109/CERMA.2010.80","DOIUrl":"https://doi.org/10.1109/CERMA.2010.80","url":null,"abstract":"Surrogate modeling using a polynomial approximation of a coarse model of a Substrate Integrated Wave guide (SIW) with micro strip transitions is presented in this paper. The surrogate modeling process is realized considering different base points distributions, as well as different sizes for the region of interest in order to evaluate their impact on the corresponding surrogate modeling accuracy. The polynomial approximation is a low-order function of the design variables and it is used to approximate electromagnetic responses of the SIW interconnect in a region of interest around the selected central base point. The surrogate modeling process is implemented in Matlab, while the electromagnetic responses of the SIW are obtained using a low-resolution EM model implemented in CST Microwave Studio to speed up the modeling process.","PeriodicalId":119218,"journal":{"name":"2010 IEEE Electronics, Robotics and Automotive Mechanics Conference","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115046114","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}
This paper describes the implementation of advice weaving in Énfasis. Énfasis is a domain-specific framework designed to program fine-grained aspects and apply crosscutting on local variables. Applications of fine-grained aspects include data flow analysis, program comprehension, assertions, code coverage, among others. The Énfasis framework uses byte code instrumentation to weave statically pieces of advice. We describe how Énfasis join points are mapped to specific regions of byte code, how to implement advice, and how to expose the point cut context without using arguments between point cuts and pieces of advice, a novel capability in our framework not available in Aspect J-like languages.
{"title":"Advise Weaving in Énfasis","authors":"U. Juárez-Martínez, G. Alor-Hernández","doi":"10.1109/CERMA.2010.92","DOIUrl":"https://doi.org/10.1109/CERMA.2010.92","url":null,"abstract":"This paper describes the implementation of advice weaving in Énfasis. Énfasis is a domain-specific framework designed to program fine-grained aspects and apply crosscutting on local variables. Applications of fine-grained aspects include data flow analysis, program comprehension, assertions, code coverage, among others. The Énfasis framework uses byte code instrumentation to weave statically pieces of advice. We describe how Énfasis join points are mapped to specific regions of byte code, how to implement advice, and how to expose the point cut context without using arguments between point cuts and pieces of advice, a novel capability in our framework not available in Aspect J-like languages.","PeriodicalId":119218,"journal":{"name":"2010 IEEE Electronics, Robotics and Automotive Mechanics Conference","volume":"75 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114042829","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}
Adriana Cortes Godinez, Luis Ernesto Mancilla Espinosa, E. M. Montes
The optimization of multi objective problems is currently an area of important research and development. The importance of type of problems has allowed the development of multiple metaheuristics for their solution. To determine which multi objective metaheuristic has the best performance with respect to a problem, in this article an experimental comparison between two of them: Sorting Genetic Algorithm No dominated-II (NSGA-II) and Multi Objective Particle Swarm Optimization (MOPS) using ZDT test functions is made. The results obtained by both algorithms are compared and analyzed based on different performance metrics that evaluate both the dispersion of the solutions on the Pareto front, and its proximity to it.
多目标问题的优化是当前一个重要的研究和发展领域。问题类型的重要性允许开发多种元启发式解决方案。为了确定哪一种多目标元启发式算法在某一问题上的性能最好，本文利用ZDT测试函数对两种多目标元启发式算法进行了实验比较:排序遗传算法No dominant - ii (NSGA-II)和多目标粒子群优化(MOPS)。基于不同的性能指标，对两种算法得到的结果进行了比较和分析，这些性能指标评估了解在Pareto前沿的离散性及其接近性。
{"title":"An Experimental Comparison of Multiobjective Algorithms: NSGA-II and OMOPSO","authors":"Adriana Cortes Godinez, Luis Ernesto Mancilla Espinosa, E. M. Montes","doi":"10.1109/CERMA.2010.13","DOIUrl":"https://doi.org/10.1109/CERMA.2010.13","url":null,"abstract":"The optimization of multi objective problems is currently an area of important research and development. The importance of type of problems has allowed the development of multiple metaheuristics for their solution. To determine which multi objective metaheuristic has the best performance with respect to a problem, in this article an experimental comparison between two of them: Sorting Genetic Algorithm No dominated-II (NSGA-II) and Multi Objective Particle Swarm Optimization (MOPS) using ZDT test functions is made. The results obtained by both algorithms are compared and analyzed based on different performance metrics that evaluate both the dispersion of the solutions on the Pareto front, and its proximity to it.","PeriodicalId":119218,"journal":{"name":"2010 IEEE Electronics, Robotics and Automotive Mechanics Conference","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117076329","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}
This paper presents a parallel array of processors implemented in a Field Programmable Gate Array (FPGA) for the solution of linear equation systems. The solution is performed using the division-free Gaussian elimination method. This algorithm was implemented in integrated processors in a FPGA Spartan 3 of Xilinx. A top-down design was used. The architecture modules were designed in VHDL language and simulated using the Model Sim 6.3f software. The proposed architecture can handle IEEE 754 single and double precision floating-point data and the architecture is implemented in 240 identical processors. Also, an algorithmic complexity of O(n^2) was obtained using a n^2 processor scheme that performs the solution of the linear equations.
{"title":"Array Processors Designed with VHDL for Solution of Linear Equation Systems Implemented in a FPGA","authors":"R. Martinez-Alonso, K. Mino, D. Torres-Lucio","doi":"10.1109/CERMA.2010.85","DOIUrl":"https://doi.org/10.1109/CERMA.2010.85","url":null,"abstract":"This paper presents a parallel array of processors implemented in a Field Programmable Gate Array (FPGA) for the solution of linear equation systems. The solution is performed using the division-free Gaussian elimination method. This algorithm was implemented in integrated processors in a FPGA Spartan 3 of Xilinx. A top-down design was used. The architecture modules were designed in VHDL language and simulated using the Model Sim 6.3f software. The proposed architecture can handle IEEE 754 single and double precision floating-point data and the architecture is implemented in 240 identical processors. Also, an algorithmic complexity of O(n^2) was obtained using a n^2 processor scheme that performs the solution of the linear equations.","PeriodicalId":119218,"journal":{"name":"2010 IEEE Electronics, Robotics and Automotive Mechanics Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129220879","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}
Gerardo Rosas-Cholula, J. Ramírez-Cortés, V. Alarcón-Aquino, Jorge Martínez-Carballido, P. Gómez-Gil
This paper describes an experiment on the detection of a P-300 rhythm from electroencephalographic signals for brain computer interfaces applications. The P300 evoked potential is obtained from visual stimuli followed by a motor response from the subject. The EEG signals are obtained with a 14 electrodes Emotiv EPOC headset. Preprocessing of the signals includes denoising and blind source separation using an Independent Component Analysis algorithm. The P300 rhythm is detected through a time-scale analysis based on the discrete wavelet transform (DWT). Comparison using the Short Time Fourier Transform (STFT), and Wigner–Ville Distribution (WVD) indicates that the DWT outperforms the others as an analyzing tool for P300 rhythm detection.
{"title":"On Signal P-300 Detection for BCI Applications Based on Wavelet Analysis and ICA Preprocessing","authors":"Gerardo Rosas-Cholula, J. Ramírez-Cortés, V. Alarcón-Aquino, Jorge Martínez-Carballido, P. Gómez-Gil","doi":"10.1109/CERMA.2010.48","DOIUrl":"https://doi.org/10.1109/CERMA.2010.48","url":null,"abstract":"This paper describes an experiment on the detection of a P-300 rhythm from electroencephalographic signals for brain computer interfaces applications. The P300 evoked potential is obtained from visual stimuli followed by a motor response from the subject. The EEG signals are obtained with a 14 electrodes Emotiv EPOC headset. Preprocessing of the signals includes denoising and blind source separation using an Independent Component Analysis algorithm. The P300 rhythm is detected through a time-scale analysis based on the discrete wavelet transform (DWT). Comparison using the Short Time Fourier Transform (STFT), and Wigner–Ville Distribution (WVD) indicates that the DWT outperforms the others as an analyzing tool for P300 rhythm detection.","PeriodicalId":119218,"journal":{"name":"2010 IEEE Electronics, Robotics and Automotive Mechanics Conference","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124135921","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：