Pub Date : 2005-03-19DOI: 10.1109/ICNSC.2005.1461249
Xuezhou Xu, Qiufang Zhan, Jing Yao
In a collaborative colony, changing message migration occurs frequently. In this paper, we introduce a concept of collaborative transaction group (CTG). Intra-group transactions can share the intermediate results with one another, and this is transparent outside the group. It is required to sustain the group memberships and the consistent update of group members' view, and to ensure such update events have the same effect on each collaborative member. Furthermore, we use mobile agents to implement the changing message migration mechanism, analyze a pluggable mobile agent platform, and put forward a mobile agent migration policy and a control model of adaptive mobile agents. We also present the implementation methods of this mechanism, while a simulation test is performed on the different scenarios with a network simulator Ns-2.
{"title":"Implementation of changing message migration using mobile agents","authors":"Xuezhou Xu, Qiufang Zhan, Jing Yao","doi":"10.1109/ICNSC.2005.1461249","DOIUrl":"https://doi.org/10.1109/ICNSC.2005.1461249","url":null,"abstract":"In a collaborative colony, changing message migration occurs frequently. In this paper, we introduce a concept of collaborative transaction group (CTG). Intra-group transactions can share the intermediate results with one another, and this is transparent outside the group. It is required to sustain the group memberships and the consistent update of group members' view, and to ensure such update events have the same effect on each collaborative member. Furthermore, we use mobile agents to implement the changing message migration mechanism, analyze a pluggable mobile agent platform, and put forward a mobile agent migration policy and a control model of adaptive mobile agents. We also present the implementation methods of this mechanism, while a simulation test is performed on the different scenarios with a network simulator Ns-2.","PeriodicalId":313251,"journal":{"name":"Proceedings. 2005 IEEE Networking, Sensing and Control, 2005.","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126788044","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 : 2005-03-19DOI: 10.1109/ICNSC.2005.1461299
Shuo Wang, M. Tan
In this paper, novel architecture for underwater sensor networks is presented. The nodes in sensor networks are divided into fixed nodes, mobile nodes. And there are three layers defined in the architecture; surface, underwater, bottom. Nodes composed of several basic function modules in different layers communicate and collaborate each other. In this architecture, the sensor networks also can change their topology and configuration according to practical situation. An underwater mobile sensor network based on this infrastructure is under research and introduced, which involves robotics, bionics, wireless communication, etc.
{"title":"Research on architecture for reconfigurable underwater sensor networks","authors":"Shuo Wang, M. Tan","doi":"10.1109/ICNSC.2005.1461299","DOIUrl":"https://doi.org/10.1109/ICNSC.2005.1461299","url":null,"abstract":"In this paper, novel architecture for underwater sensor networks is presented. The nodes in sensor networks are divided into fixed nodes, mobile nodes. And there are three layers defined in the architecture; surface, underwater, bottom. Nodes composed of several basic function modules in different layers communicate and collaborate each other. In this architecture, the sensor networks also can change their topology and configuration according to practical situation. An underwater mobile sensor network based on this infrastructure is under research and introduced, which involves robotics, bionics, wireless communication, etc.","PeriodicalId":313251,"journal":{"name":"Proceedings. 2005 IEEE Networking, Sensing and Control, 2005.","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124286035","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 : 2005-03-19DOI: 10.1109/ICNSC.2005.1461344
Chan-Yu Chang, Si-Yan Lin, M. Jeng
The occurrence of defect on a wafer may result in losing the yield ratio. The defective regions are usually identified through visual judgment with the aid of a scanning electron microscope and many people visually check wafers and hand-mark their defective regions leading to a significant amount of personnel cost. In addition, potential misjudgment may be introduced due to human fatigue. In this paper, a two-layer Hopfield neural network called the competitive Hopfield wafer-defect detection neural network (CHWDNN) is proposed for detecting the defective regions of wafer image. The CHWDNN extends the one-layer 2-D Hopfield neural network at the original image plane to a two-layer 3-D Hopfield neural network with defect detection to be implemented on its third dimension. With the extended 3-D architecture, the network is capable of incorporating a pixel's spatial information into a pixel-classifying procedure. The experimental results show the CHWDNN successfully identifies the defective regions on wafers images with good performances.
{"title":"Two-layer competitive Hopfield neural network for wafer defect detection","authors":"Chan-Yu Chang, Si-Yan Lin, M. Jeng","doi":"10.1109/ICNSC.2005.1461344","DOIUrl":"https://doi.org/10.1109/ICNSC.2005.1461344","url":null,"abstract":"The occurrence of defect on a wafer may result in losing the yield ratio. The defective regions are usually identified through visual judgment with the aid of a scanning electron microscope and many people visually check wafers and hand-mark their defective regions leading to a significant amount of personnel cost. In addition, potential misjudgment may be introduced due to human fatigue. In this paper, a two-layer Hopfield neural network called the competitive Hopfield wafer-defect detection neural network (CHWDNN) is proposed for detecting the defective regions of wafer image. The CHWDNN extends the one-layer 2-D Hopfield neural network at the original image plane to a two-layer 3-D Hopfield neural network with defect detection to be implemented on its third dimension. With the extended 3-D architecture, the network is capable of incorporating a pixel's spatial information into a pixel-classifying procedure. The experimental results show the CHWDNN successfully identifies the defective regions on wafers images with good performances.","PeriodicalId":313251,"journal":{"name":"Proceedings. 2005 IEEE Networking, Sensing and Control, 2005.","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122165330","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 : 2005-03-19DOI: 10.1109/ICNSC.2005.1461275
Guimin Chen, J. Jia, Zhiwu Li
The paper introduces two hybrid flexure hinges: right-circular corner-filleted (RCCF) and right-circular elliptical (RCE) hinges. Closed-form compliance equations are formulated. Checked by the finite element analysis, the theoretical formulation data are within 8 percent error margins. The results indicate that the RCCF flexures have the best rotation-compliance over the RCE flexures and right-circular (RC) flexures. RCCF and RCE flexures are both more rotation-compliant than the right-circular ones. Whereas, the three types of flexure hinges mentioned above perform equally in terms of preserving the center of the rotation center.
{"title":"On hybrid flexure hinges","authors":"Guimin Chen, J. Jia, Zhiwu Li","doi":"10.1109/ICNSC.2005.1461275","DOIUrl":"https://doi.org/10.1109/ICNSC.2005.1461275","url":null,"abstract":"The paper introduces two hybrid flexure hinges: right-circular corner-filleted (RCCF) and right-circular elliptical (RCE) hinges. Closed-form compliance equations are formulated. Checked by the finite element analysis, the theoretical formulation data are within 8 percent error margins. The results indicate that the RCCF flexures have the best rotation-compliance over the RCE flexures and right-circular (RC) flexures. RCCF and RCE flexures are both more rotation-compliant than the right-circular ones. Whereas, the three types of flexure hinges mentioned above perform equally in terms of preserving the center of the rotation center.","PeriodicalId":313251,"journal":{"name":"Proceedings. 2005 IEEE Networking, Sensing and Control, 2005.","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122224411","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 : 2005-03-19DOI: 10.1109/ICNSC.2005.1461261
E. Cooper, K. Kamei
The World Wide Web and modern desktop computers give novice designers an unprecedented ability to publish but provide little support for the designers' color selection, which is a major portion of the factors determining viewer experience. Effective color decision support systems help novices and professionals reach selected, quantifiable goals without hindering undefined goals. This paper describes a method of studying how individual decisions in the color selection process influence the outcome. Results are given for color placement experiments in which novice designers were asked to describe goals for individual selections. Also described is the application of this model to the design process for implementation in dynamic color palette support for Web-page designs.
{"title":"Kansei modeling of the color design decision process in Web designs","authors":"E. Cooper, K. Kamei","doi":"10.1109/ICNSC.2005.1461261","DOIUrl":"https://doi.org/10.1109/ICNSC.2005.1461261","url":null,"abstract":"The World Wide Web and modern desktop computers give novice designers an unprecedented ability to publish but provide little support for the designers' color selection, which is a major portion of the factors determining viewer experience. Effective color decision support systems help novices and professionals reach selected, quantifiable goals without hindering undefined goals. This paper describes a method of studying how individual decisions in the color selection process influence the outcome. Results are given for color placement experiments in which novice designers were asked to describe goals for individual selections. Also described is the application of this model to the design process for implementation in dynamic color palette support for Web-page designs.","PeriodicalId":313251,"journal":{"name":"Proceedings. 2005 IEEE Networking, Sensing and Control, 2005.","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131454644","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 : 2005-03-19DOI: 10.1109/ICNSC.2005.1461304
A. Agrawal, A. Agarwal
Landmines are significant barriers to financial, economic and social development in various parts of this world. Metal detectors currently used by teams engaged in the decontamination of mines cannot differentiate a mine from metallic debris where the soil contains large quantities of metal scraps and cartridge cases. So what is required is a sensor that will reliably confirm that the ground being tested does not contain an explosive device with almost perfect reliability. The various sensors provide different attributes about the nature of the soil. Even human experts are unable to give belief and plausibility to their rules. Thus the conventional Dempster-Shafer theory cannot be applied to build an expert system. Thus rough sets are applied to classify the landmine data because here, any prior knowledge of rules is not needed; these rules are automatically discovered from the database. For the application of rough set theory, first, approximation space is to be identified. This can be done by a human expert, otherwise, principal component analysis can be used. In fact the problem of identifying application space is similar to that of identifying redundant attributes (which carry no useful information for the purpose of classification) and throwing them away. It is observed that aspect ratio, blob size, and grayscale are important features for landmine classification. Now, all data tuples which agree on all task relevant attributes, form one elementary set. Thus the whole of the database is divided into mutually exclusive elementary sets. As no crisp rules exist for classification, this essentially implies the decision sets (the sets formed by the presence or absence of landmines) are not definable (cannot be expressed as union or intersection of elementary sets). Thus lower and upper approximations of the decision sets are taken and the boundary set is found.
{"title":"Rough logic for building a landmine classifier","authors":"A. Agrawal, A. Agarwal","doi":"10.1109/ICNSC.2005.1461304","DOIUrl":"https://doi.org/10.1109/ICNSC.2005.1461304","url":null,"abstract":"Landmines are significant barriers to financial, economic and social development in various parts of this world. Metal detectors currently used by teams engaged in the decontamination of mines cannot differentiate a mine from metallic debris where the soil contains large quantities of metal scraps and cartridge cases. So what is required is a sensor that will reliably confirm that the ground being tested does not contain an explosive device with almost perfect reliability. The various sensors provide different attributes about the nature of the soil. Even human experts are unable to give belief and plausibility to their rules. Thus the conventional Dempster-Shafer theory cannot be applied to build an expert system. Thus rough sets are applied to classify the landmine data because here, any prior knowledge of rules is not needed; these rules are automatically discovered from the database. For the application of rough set theory, first, approximation space is to be identified. This can be done by a human expert, otherwise, principal component analysis can be used. In fact the problem of identifying application space is similar to that of identifying redundant attributes (which carry no useful information for the purpose of classification) and throwing them away. It is observed that aspect ratio, blob size, and grayscale are important features for landmine classification. Now, all data tuples which agree on all task relevant attributes, form one elementary set. Thus the whole of the database is divided into mutually exclusive elementary sets. As no crisp rules exist for classification, this essentially implies the decision sets (the sets formed by the presence or absence of landmines) are not definable (cannot be expressed as union or intersection of elementary sets). Thus lower and upper approximations of the decision sets are taken and the boundary set is found.","PeriodicalId":313251,"journal":{"name":"Proceedings. 2005 IEEE Networking, Sensing and Control, 2005.","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126255837","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 : 2005-03-19DOI: 10.1109/ICNSC.2005.1461193
M. Toshniwal
Satellite image processing is one of the key research areas in the area of remote sensing. Remote sensing derives immense applications from this field like terrain analysis and generation, topographic mapping. Traditional statistical approaches provide reasonable success in this field, but the efficiency is limited with respect to the robustness of results. The statistical approaches are parametric, based on an assumed statistical distribution and hence the efficiency and correctness of results closely correlates to the proximity of data to the assumed distribution. Feed-forward neural networks can be trained to learn pixel classes and hence can be applied to the area of satellite image segmentation. This paper describes a technique developed to select training parameters and collection of training sets. An algorithm to accelerate the training process and reduce the time for classification is also explored. This paper provides a suitably developed neural network architecture with high accuracy. We obtained accuracy and efficiency in terms of standard parameters, and were able to achieve accurate image segmentation with kappa coefficient of 0.97. The time for classification was reduced by more than 70%.
{"title":"An optimized approach to application of neural networks to classification of multispectral, remote sensing data","authors":"M. Toshniwal","doi":"10.1109/ICNSC.2005.1461193","DOIUrl":"https://doi.org/10.1109/ICNSC.2005.1461193","url":null,"abstract":"Satellite image processing is one of the key research areas in the area of remote sensing. Remote sensing derives immense applications from this field like terrain analysis and generation, topographic mapping. Traditional statistical approaches provide reasonable success in this field, but the efficiency is limited with respect to the robustness of results. The statistical approaches are parametric, based on an assumed statistical distribution and hence the efficiency and correctness of results closely correlates to the proximity of data to the assumed distribution. Feed-forward neural networks can be trained to learn pixel classes and hence can be applied to the area of satellite image segmentation. This paper describes a technique developed to select training parameters and collection of training sets. An algorithm to accelerate the training process and reduce the time for classification is also explored. This paper provides a suitably developed neural network architecture with high accuracy. We obtained accuracy and efficiency in terms of standard parameters, and were able to achieve accurate image segmentation with kappa coefficient of 0.97. The time for classification was reduced by more than 70%.","PeriodicalId":313251,"journal":{"name":"Proceedings. 2005 IEEE Networking, Sensing and Control, 2005.","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116437350","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 : 2005-03-19DOI: 10.1109/ICNSC.2005.1461164
Shuang Gang, Hongnian Yu
The efficiency and accuracy of training neural-net classifiers is typically improved by eliminating of features that are redundant and irrelevant. The objective is to reduce the size of the input feature set and at the same time retain as much as possible of the class discriminatory information. Such an input features set after reducing features from the original input features, which is called best feature space, would offer a reduction of both cost and complexity of feature collection as well as improve the efficiency and accuracy of the resultant classifier. In this paper, we develop and evaluate two composite feature selection algorithms: mutual information feature space forward selection (MIFSFS) and mutual information feature space backward selection (MTFSBS). These two algorithms use mutual information (MI), for both continuous-valued and discrete-valued features, between the feature space and the class in order to find the best feature space from the original input features. The most important output from the new algorithms is that we not only can identity the irrelevant features, but also identify the redundant features, which cannot be identified by the common feature selection algorithms (for example artificial neural networks, ANN). Empirical studies of both realistic new and previously published classification problems indicate that the proposed algorithms are robust, stable and efficient. One of real application is drug discovery. Knowledge discovery from gene expression data is a highly research topical area for the drug discovery. Finding a number of genes out of the thousands caused a certain types of diseases is a significant contribution for the preventing and fighting diseases. Here we use the myeloma disease as an example to demonstrate how to identify the genes caused the myeloma disease.
{"title":"A new approach for detecting the best feature set","authors":"Shuang Gang, Hongnian Yu","doi":"10.1109/ICNSC.2005.1461164","DOIUrl":"https://doi.org/10.1109/ICNSC.2005.1461164","url":null,"abstract":"The efficiency and accuracy of training neural-net classifiers is typically improved by eliminating of features that are redundant and irrelevant. The objective is to reduce the size of the input feature set and at the same time retain as much as possible of the class discriminatory information. Such an input features set after reducing features from the original input features, which is called best feature space, would offer a reduction of both cost and complexity of feature collection as well as improve the efficiency and accuracy of the resultant classifier. In this paper, we develop and evaluate two composite feature selection algorithms: mutual information feature space forward selection (MIFSFS) and mutual information feature space backward selection (MTFSBS). These two algorithms use mutual information (MI), for both continuous-valued and discrete-valued features, between the feature space and the class in order to find the best feature space from the original input features. The most important output from the new algorithms is that we not only can identity the irrelevant features, but also identify the redundant features, which cannot be identified by the common feature selection algorithms (for example artificial neural networks, ANN). Empirical studies of both realistic new and previously published classification problems indicate that the proposed algorithms are robust, stable and efficient. One of real application is drug discovery. Knowledge discovery from gene expression data is a highly research topical area for the drug discovery. Finding a number of genes out of the thousands caused a certain types of diseases is a significant contribution for the preventing and fighting diseases. Here we use the myeloma disease as an example to demonstrate how to identify the genes caused the myeloma disease.","PeriodicalId":313251,"journal":{"name":"Proceedings. 2005 IEEE Networking, Sensing and Control, 2005.","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114997259","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 : 2005-03-19DOI: 10.1109/ICNSC.2005.1461180
Li Li, F. Qiao, Qidi Wu
Semiconductor wafer fab is considered as the third kind of production system, differentiated with job shop and flow shop. It has its own scheduling and control characteristics, such as re-entrance, large-scale, mix processing model and unbalanced production facilities. To solve scheduling problem of semiconductor wafer fab, an agent-based scheduling approach for semiconductor wafer fab is proposed. Firstly, an agent-based scheduling model, which integrates release control, dispatching and machine maintenance scheduling, is presented. Secondly, negotiation protocol between agents, extended contract net protocol (ECNP), is given. Thirdly, scheduling algorithms for decision making of agents are offered. Finally, a simple model, but with essential characters of semiconductor wafer fabrication, is used to demonstrate how to use the proposed agent-based scheduling approach.
{"title":"Agent-based dynamic scheduling for semiconductor wafer fab","authors":"Li Li, F. Qiao, Qidi Wu","doi":"10.1109/ICNSC.2005.1461180","DOIUrl":"https://doi.org/10.1109/ICNSC.2005.1461180","url":null,"abstract":"Semiconductor wafer fab is considered as the third kind of production system, differentiated with job shop and flow shop. It has its own scheduling and control characteristics, such as re-entrance, large-scale, mix processing model and unbalanced production facilities. To solve scheduling problem of semiconductor wafer fab, an agent-based scheduling approach for semiconductor wafer fab is proposed. Firstly, an agent-based scheduling model, which integrates release control, dispatching and machine maintenance scheduling, is presented. Secondly, negotiation protocol between agents, extended contract net protocol (ECNP), is given. Thirdly, scheduling algorithms for decision making of agents are offered. Finally, a simple model, but with essential characters of semiconductor wafer fabrication, is used to demonstrate how to use the proposed agent-based scheduling approach.","PeriodicalId":313251,"journal":{"name":"Proceedings. 2005 IEEE Networking, Sensing and Control, 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131035395","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 : 2005-03-19DOI: 10.1109/ICNSC.2005.1461198
Yongjae Lee, Yong-hwa Park, F. Niu, D. Filipović
In this paper, we propose an efficient approach for analysis, design, and optimization of two-port radio frequency microelectromechanical systems (RF MEMS) resonating structures. Methodology utilizes finite element method (FEM) for the prediction of electromechanical responses and fast/accurate mapping with an artificial neural networks (ANNs) technique, toward a final goal - a generic macromodel compatible with modern circuit computer aided design (CAD) tools. Thus, instead of using memory and time demanding full-wave analysis or more extensive and expensive design process using multiple fabrication cycles, a simple yet accurate circuit simulator compatible modeling and optimization procedure is developed.
{"title":"Artificial neural network based macromodeling approach for two-port RF MEMS resonating structures","authors":"Yongjae Lee, Yong-hwa Park, F. Niu, D. Filipović","doi":"10.1109/ICNSC.2005.1461198","DOIUrl":"https://doi.org/10.1109/ICNSC.2005.1461198","url":null,"abstract":"In this paper, we propose an efficient approach for analysis, design, and optimization of two-port radio frequency microelectromechanical systems (RF MEMS) resonating structures. Methodology utilizes finite element method (FEM) for the prediction of electromechanical responses and fast/accurate mapping with an artificial neural networks (ANNs) technique, toward a final goal - a generic macromodel compatible with modern circuit computer aided design (CAD) tools. Thus, instead of using memory and time demanding full-wave analysis or more extensive and expensive design process using multiple fabrication cycles, a simple yet accurate circuit simulator compatible modeling and optimization procedure is developed.","PeriodicalId":313251,"journal":{"name":"Proceedings. 2005 IEEE Networking, Sensing and Control, 2005.","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134253846","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：