Pub Date : 2011-06-23DOI: 10.1109/INES.2011.5954721
A. Rovid, L. Szeidl, P. Várlaki
The approximation methods of mathematics are widely used in theory and practice for several problems. In the framework of the paper a novel tensor-product based approach for representation of neural networks (NNs) is proposed. The NNs in this case stand for local models based on which a more complex parameter varying model can numerically be reconstructed and reduced using the higher order singular value decomposition (HOSVD). The HOSVD as well as the tensor-product based representation of NNs will be discussed in detail.
{"title":"On tensor-product model based representation of neural networks","authors":"A. Rovid, L. Szeidl, P. Várlaki","doi":"10.1109/INES.2011.5954721","DOIUrl":"https://doi.org/10.1109/INES.2011.5954721","url":null,"abstract":"The approximation methods of mathematics are widely used in theory and practice for several problems. In the framework of the paper a novel tensor-product based approach for representation of neural networks (NNs) is proposed. The NNs in this case stand for local models based on which a more complex parameter varying model can numerically be reconstructed and reduced using the higher order singular value decomposition (HOSVD). The HOSVD as well as the tensor-product based representation of NNs will be discussed in detail.","PeriodicalId":414812,"journal":{"name":"2011 15th IEEE International Conference on Intelligent Engineering Systems","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124533967","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 : 2011-06-23DOI: 10.1109/INES.2011.5954717
L. Horváth, I. Rudas
Definition of product in model space includes contextual decisions and relies upon background of those decisions. This background influences decisions on engineering objects in a very complex way. Appropriately selected combination of engineering object variants may be a compromise in a coordinated product definition. The authors of this paper recognized that conventional model space construction in recent product lifecycle management has not model representation capabilities for the above background. Paper starts with a discussion about influences on product definition in the course of product development in model space. Following this, the currently prevailing and the proposed process of human influence are explained and compared. As the main contribution in the paper, methods for coordinated control of product definition, extended engineering object space, and coordinated change requests for adaptive action generation are introduced. Finally, execution of enabled adaptive action and implementation in PLM system are explained as implementation issues.
{"title":"Control of product object definition by background of human influence","authors":"L. Horváth, I. Rudas","doi":"10.1109/INES.2011.5954717","DOIUrl":"https://doi.org/10.1109/INES.2011.5954717","url":null,"abstract":"Definition of product in model space includes contextual decisions and relies upon background of those decisions. This background influences decisions on engineering objects in a very complex way. Appropriately selected combination of engineering object variants may be a compromise in a coordinated product definition. The authors of this paper recognized that conventional model space construction in recent product lifecycle management has not model representation capabilities for the above background. Paper starts with a discussion about influences on product definition in the course of product development in model space. Following this, the currently prevailing and the proposed process of human influence are explained and compared. As the main contribution in the paper, methods for coordinated control of product definition, extended engineering object space, and coordinated change requests for adaptive action generation are introduced. Finally, execution of enabled adaptive action and implementation in PLM system are explained as implementation issues.","PeriodicalId":414812,"journal":{"name":"2011 15th IEEE International Conference on Intelligent Engineering Systems","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128737867","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 : 2011-06-23DOI: 10.1109/INES.2011.5954731
Jianjun Zhu, Shaohua Tan
Interpolative reasoning in sparse rule base has been an important research topic in the field of artificial intelligence. To solve effectively the problem of reasoning in multivariable sparse rule base whose resulting consequences are restricted in a finite set, this paper developed a new interpolative reasoning approach and offered its algorithm. The approach deduced consequent results by converting domains of antecedent and consequent variables into ternary qualitative spaces and building ternary qualitative function among such spaces as model of system for calculation. By applying this approach to an example, the paper illustrated that the new approach is more accurate and simple than the existing interpolative reasoning methods for such problem.
{"title":"An improvement to the qualitative interpolative reasoning in sparse rule base","authors":"Jianjun Zhu, Shaohua Tan","doi":"10.1109/INES.2011.5954731","DOIUrl":"https://doi.org/10.1109/INES.2011.5954731","url":null,"abstract":"Interpolative reasoning in sparse rule base has been an important research topic in the field of artificial intelligence. To solve effectively the problem of reasoning in multivariable sparse rule base whose resulting consequences are restricted in a finite set, this paper developed a new interpolative reasoning approach and offered its algorithm. The approach deduced consequent results by converting domains of antecedent and consequent variables into ternary qualitative spaces and building ternary qualitative function among such spaces as model of system for calculation. By applying this approach to an example, the paper illustrated that the new approach is more accurate and simple than the existing interpolative reasoning methods for such problem.","PeriodicalId":414812,"journal":{"name":"2011 15th IEEE International Conference on Intelligent Engineering Systems","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126317622","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 : 2011-06-23DOI: 10.1109/INES.2011.5954776
R. Szabó, A. Gontean, I. Lie
This paper presents a clock built around the MC9S12XDP512 microcontroller using an LCD display. This clock shows the time (hours, minutes, and seconds) and the date (year, month, day). The MC9S12XDP512 development board from Freescale has no integrated LCD module, so an external module had to be connected. The date is fully displayed (four digit years) and has an implemented algorithm to make the difference between the months with 30 or 31 days and to distinguish between February having 28 or 29 days. The clock has an adjustment option. All the programming is performed in assembly.
{"title":"Mobile LCD clock","authors":"R. Szabó, A. Gontean, I. Lie","doi":"10.1109/INES.2011.5954776","DOIUrl":"https://doi.org/10.1109/INES.2011.5954776","url":null,"abstract":"This paper presents a clock built around the MC9S12XDP512 microcontroller using an LCD display. This clock shows the time (hours, minutes, and seconds) and the date (year, month, day). The MC9S12XDP512 development board from Freescale has no integrated LCD module, so an external module had to be connected. The date is fully displayed (four digit years) and has an implemented algorithm to make the difference between the months with 30 or 31 days and to distinguish between February having 28 or 29 days. The clock has an adjustment option. All the programming is performed in assembly.","PeriodicalId":414812,"journal":{"name":"2011 15th IEEE International Conference on Intelligent Engineering Systems","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124950427","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 : 2011-06-23DOI: 10.1109/INES.2011.5954711
Hugo Guerreiro, R. Campos-Rebelo, L. Gomes
This paper describes a solution to decrease maintenance costs for the Éole Bridge expansion joints. The developed monitoring system is based on the analysis of the sound level and frequencies produced by the vehicles passing in these expansion joints, allowing an estimation of the joint overall structural damage. The system issue alerts to maintenance teams, improving their response time and preventing the increase of the damaged sections, leading to reduced maintenance costs and less road stopping time, and improving the quality delivered to the users of the bridge. The objective of the work presented was to make an adequate signal analysis in order to identify the progress of damaged sections in each inspected expansion joint.
{"title":"Bridge expansion joints monitoring system","authors":"Hugo Guerreiro, R. Campos-Rebelo, L. Gomes","doi":"10.1109/INES.2011.5954711","DOIUrl":"https://doi.org/10.1109/INES.2011.5954711","url":null,"abstract":"This paper describes a solution to decrease maintenance costs for the Éole Bridge expansion joints. The developed monitoring system is based on the analysis of the sound level and frequencies produced by the vehicles passing in these expansion joints, allowing an estimation of the joint overall structural damage. The system issue alerts to maintenance teams, improving their response time and preventing the increase of the damaged sections, leading to reduced maintenance costs and less road stopping time, and improving the quality delivered to the users of the bridge. The objective of the work presented was to make an adequate signal analysis in order to identify the progress of damaged sections in each inspected expansion joint.","PeriodicalId":414812,"journal":{"name":"2011 15th IEEE International Conference on Intelligent Engineering Systems","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121251555","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 : 2011-06-23DOI: 10.1109/INES.2011.5954763
P. Hauptle, P. Hubinský, G. Gruhler
In this contribution our interest focuses on applications with a mechatronic drive (MD) where electronics, a motor and a gear-box i.e. a harmonic drive(R) is merged to one module. Every mechatronic system (MS) has one or more resonances. Due to the modeling of such a system, two different challenges regarding oscillations has to be solved by control. Namely the ”transient”-effects as well as the ”semi-stead-state”-effects arise oscillations. We would like to introduce a new feedforward method where undesirable oscillations can be reduced. Beside simulation results also results from our experimental setup due to acceleration measurements are discussed in the following.
{"title":"Harmonic modulation in control to reduce oscillations in mechatronic systems","authors":"P. Hauptle, P. Hubinský, G. Gruhler","doi":"10.1109/INES.2011.5954763","DOIUrl":"https://doi.org/10.1109/INES.2011.5954763","url":null,"abstract":"In this contribution our interest focuses on applications with a mechatronic drive (MD) where electronics, a motor and a gear-box i.e. a harmonic drive(R) is merged to one module. Every mechatronic system (MS) has one or more resonances. Due to the modeling of such a system, two different challenges regarding oscillations has to be solved by control. Namely the ”transient”-effects as well as the ”semi-stead-state”-effects arise oscillations. We would like to introduce a new feedforward method where undesirable oscillations can be reduced. Beside simulation results also results from our experimental setup due to acceleration measurements are discussed in the following.","PeriodicalId":414812,"journal":{"name":"2011 15th IEEE International Conference on Intelligent Engineering Systems","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132752781","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 : 2011-06-23DOI: 10.1109/INES.2011.5954747
B. Simo, O. Habala, V. Tran, P. Krammer, L. Hluchý
This paper presents successful use of the data mining and integration (DMI) tools created by the EU ADMIRE project in the data mining based hydrological forecast use case. We present general architecture and tools of the ADMIRE framework, DISPEL language for description of distributed workflows, Eclipse based workbench for DMI workflow construction and execution and user portal. Then we describe the hydrological forecast use case, its implementation using the tools of ADMIRE project and share some thoughts on advantages of the framework described.
{"title":"Using ADMIRE data mining and integration tools in hydrological forecast use case","authors":"B. Simo, O. Habala, V. Tran, P. Krammer, L. Hluchý","doi":"10.1109/INES.2011.5954747","DOIUrl":"https://doi.org/10.1109/INES.2011.5954747","url":null,"abstract":"This paper presents successful use of the data mining and integration (DMI) tools created by the EU ADMIRE project in the data mining based hydrological forecast use case. We present general architecture and tools of the ADMIRE framework, DISPEL language for description of distributed workflows, Eclipse based workbench for DMI workflow construction and execution and user portal. Then we describe the hydrological forecast use case, its implementation using the tools of ADMIRE project and share some thoughts on advantages of the framework described.","PeriodicalId":414812,"journal":{"name":"2011 15th IEEE International Conference on Intelligent Engineering Systems","volume":"159 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134299109","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 : 2011-06-23DOI: 10.1109/INES.2011.5954736
C. K. Jung, C. S. Lee
Two online adaptation models tuning the flowrate of cooling water in plate mill are developed based on the feedback and feedforward control algorithm. In the feedback control based model, a multiplication factor is adopted which is composed of three adaptation coefficients. The calculations of the three coefficients are designed taking process variations into account. After tested on an offline simulator, the adaptation model is installed on the online process resulting in 10% increase of the accuracy rate of the final cooling temperature. And a neural network model is developed to factor in the variations of the prior processes. It uses 24 process variables as inputs and predicts the final cooling temperature. Comparing with the measured data, the predicted temperatures show an accuracy of ±15 °C.
{"title":"Online adaptation model for accelerated cooling process in plate mill","authors":"C. K. Jung, C. S. Lee","doi":"10.1109/INES.2011.5954736","DOIUrl":"https://doi.org/10.1109/INES.2011.5954736","url":null,"abstract":"Two online adaptation models tuning the flowrate of cooling water in plate mill are developed based on the feedback and feedforward control algorithm. In the feedback control based model, a multiplication factor is adopted which is composed of three adaptation coefficients. The calculations of the three coefficients are designed taking process variations into account. After tested on an offline simulator, the adaptation model is installed on the online process resulting in 10% increase of the accuracy rate of the final cooling temperature. And a neural network model is developed to factor in the variations of the prior processes. It uses 24 process variables as inputs and predicts the final cooling temperature. Comparing with the measured data, the predicted temperatures show an accuracy of ±15 °C.","PeriodicalId":414812,"journal":{"name":"2011 15th IEEE International Conference on Intelligent Engineering Systems","volume":"325 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115762550","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 : 2011-06-23DOI: 10.1109/INES.2011.5954735
Krisztián Búza, P. B. Kis, A. Buza
One of the most prominent challenges in data mining is the clustering of databases containing many categorical attributes. Representation of such data in continuous, Euclidean space usually does not reflect the true segments of data. As a crucial consequence, clustering algorithms working in continuous, Euclidean space may produce segmentations of poor quality. An alternative direction explores graph-based representation of data. In this paper, we show that graph-based data representation is well suitable for the case of categorical attributes. In particular, we offer the following contributions: i) we propose and analyze a flexible graph-based genetic clustering algorithm, where the ideal clusters can be characterized using external cluster quality functions, called kernels, ii) we study kernels, and define the crucial property of effective kernels, iii) we introduce a framework for distributed data-oriented graph clustering computations. In contrast of the complexity of our problem, which turns out to be NP-hard in our analysis, experiments show that in case of well clusterable data, our algorithm has attractive scalability properties. We also perform experiments on real medical data that provides us with further evidence about the practical applicability of our approach.
{"title":"Graph-based clustering based on cutting sets","authors":"Krisztián Búza, P. B. Kis, A. Buza","doi":"10.1109/INES.2011.5954735","DOIUrl":"https://doi.org/10.1109/INES.2011.5954735","url":null,"abstract":"One of the most prominent challenges in data mining is the clustering of databases containing many categorical attributes. Representation of such data in continuous, Euclidean space usually does not reflect the true segments of data. As a crucial consequence, clustering algorithms working in continuous, Euclidean space may produce segmentations of poor quality. An alternative direction explores graph-based representation of data. In this paper, we show that graph-based data representation is well suitable for the case of categorical attributes. In particular, we offer the following contributions: i) we propose and analyze a flexible graph-based genetic clustering algorithm, where the ideal clusters can be characterized using external cluster quality functions, called kernels, ii) we study kernels, and define the crucial property of effective kernels, iii) we introduce a framework for distributed data-oriented graph clustering computations. In contrast of the complexity of our problem, which turns out to be NP-hard in our analysis, experiments show that in case of well clusterable data, our algorithm has attractive scalability properties. We also perform experiments on real medical data that provides us with further evidence about the practical applicability of our approach.","PeriodicalId":414812,"journal":{"name":"2011 15th IEEE International Conference on Intelligent Engineering Systems","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125437960","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 : 2011-06-23DOI: 10.1109/INES.2011.5954722
K. Ambrus-Somogyi, A. Bakó
In the PhD dissertation [6] optimization models were developed for the pavement management system, which could help planning the optimal maintenance work. This model can be generalized for those engineering structures, where there are several types of structures and for each structure there are many components with many different types of deterioration options and duty uses. The condition of application is: the deterioration of certain components not only depends on time, but on the extent of use. In this paper we would like to present the development of Engineering Structures Management System, the different models, and furthermore a practical application — the deterioration model of car parts and the planning of their maintenance.
{"title":"Optimization model of maintenance of engineering structures","authors":"K. Ambrus-Somogyi, A. Bakó","doi":"10.1109/INES.2011.5954722","DOIUrl":"https://doi.org/10.1109/INES.2011.5954722","url":null,"abstract":"In the PhD dissertation [6] optimization models were developed for the pavement management system, which could help planning the optimal maintenance work. This model can be generalized for those engineering structures, where there are several types of structures and for each structure there are many components with many different types of deterioration options and duty uses. The condition of application is: the deterioration of certain components not only depends on time, but on the extent of use. In this paper we would like to present the development of Engineering Structures Management System, the different models, and furthermore a practical application — the deterioration model of car parts and the planning of their maintenance.","PeriodicalId":414812,"journal":{"name":"2011 15th IEEE International Conference on Intelligent Engineering Systems","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134301645","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：