Pub Date : 2009-05-11DOI: 10.1109/CIMSA.2009.5069953
Wei Li, D. Lin, Qing Li, M. Swain
Dental implantation to a certain extent changes the biomechanical environment, thereby leading to the surrounding supporting bone to remodel. Computational remodeling has been well established in lone bone community and a range of mathematical formulae have been available with acceptable accuracy and effectiveness. However, there has been limited information and remodeling data available for dental scenarios, despite its predominate importance and popularity in clinic. An in-vivo frequency test technique was developed to determine the extent of osseointegration and remodeling passively. It could not help predict on-going healing and consequence of implantation. This paper develops a predictive model to relate osseointegration and bone remodeling to a progressive change in natural frequencies, thereby better utilizing the data acquired from experiments. The results allow us to establish a more realistic remodeling formula, thereby making a patient-specific prediction possible.
{"title":"Monitoring natural frequency for osseointegration and bone remodeling induced by dental implants","authors":"Wei Li, D. Lin, Qing Li, M. Swain","doi":"10.1109/CIMSA.2009.5069953","DOIUrl":"https://doi.org/10.1109/CIMSA.2009.5069953","url":null,"abstract":"Dental implantation to a certain extent changes the biomechanical environment, thereby leading to the surrounding supporting bone to remodel. Computational remodeling has been well established in lone bone community and a range of mathematical formulae have been available with acceptable accuracy and effectiveness. However, there has been limited information and remodeling data available for dental scenarios, despite its predominate importance and popularity in clinic. An in-vivo frequency test technique was developed to determine the extent of osseointegration and remodeling passively. It could not help predict on-going healing and consequence of implantation. This paper develops a predictive model to relate osseointegration and bone remodeling to a progressive change in natural frequencies, thereby better utilizing the data acquired from experiments. The results allow us to establish a more realistic remodeling formula, thereby making a patient-specific prediction possible.","PeriodicalId":178669,"journal":{"name":"2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133948473","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 : 2009-05-11DOI: 10.1109/CIMSA.2009.5069961
D. Megherbi, M. Madera, L. Dang
In this paper, we study the stability (convergence time) of an interconnected dynamical system with respect to its connectivity in the presence of delayed feedbacks sensory inputs/outputs data. In particular, we show that under some conditions, that we introduce and present in this paper, related to the interconnected links time-delays, the less connected a given dynamical system is, the longer it will take for the overall system to stabilize. We address the conditions for obtaining an estimate of the convergence time of the system based on the system interconnections weights and time delays. In particular, we study the conditions under which such property is conserved when homogenous and/or heterogeneous time delays are introduced to the links of the interconnected system considered. Analysis of the affect of arbitrary heterogeneous time delays on the dynamical system links, system stability, and convergence time is also presented.
{"title":"Effect of heterogeneous time delays and link weights on the stability and convergence time of large interconnected dynamical systems: A case study","authors":"D. Megherbi, M. Madera, L. Dang","doi":"10.1109/CIMSA.2009.5069961","DOIUrl":"https://doi.org/10.1109/CIMSA.2009.5069961","url":null,"abstract":"In this paper, we study the stability (convergence time) of an interconnected dynamical system with respect to its connectivity in the presence of delayed feedbacks sensory inputs/outputs data. In particular, we show that under some conditions, that we introduce and present in this paper, related to the interconnected links time-delays, the less connected a given dynamical system is, the longer it will take for the overall system to stabilize. We address the conditions for obtaining an estimate of the convergence time of the system based on the system interconnections weights and time delays. In particular, we study the conditions under which such property is conserved when homogenous and/or heterogeneous time delays are introduced to the links of the interconnected system considered. Analysis of the affect of arbitrary heterogeneous time delays on the dynamical system links, system stability, and convergence time is also presented.","PeriodicalId":178669,"journal":{"name":"2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134445312","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 : 2009-05-11DOI: 10.1109/CIMSA.2009.5069907
K. Chen, Qing Li, Wei Li, H. Lau, A. Ruys, P. Carter
Cochlear implants have been one of most successful electronic devices implanted to human bodies to convert mechanical signals to electronic signals to stimulate auditory nerves to react. The current flow in the region of the cochlear is the key to determine the performance of Cochlear implants. One of the efforts could be made to reduce current leakage into the brain to increase the efficiency of the device. This paper aims to construct a three-dimensional finite element (FE) model to examine the current flow path in different surrounding tissues involved. The MRI data is processed to generate solid model and then FE model for the numerical analysis, which contains gray and white matters of the brain that was assembled and was analyzed in ABAQUS. The modeling results provide us with an effective means to improvement of Cochlear implant design in the future.
{"title":"Three-dimensional finite element modeling of Cochlear implant induced electrical current flows","authors":"K. Chen, Qing Li, Wei Li, H. Lau, A. Ruys, P. Carter","doi":"10.1109/CIMSA.2009.5069907","DOIUrl":"https://doi.org/10.1109/CIMSA.2009.5069907","url":null,"abstract":"Cochlear implants have been one of most successful electronic devices implanted to human bodies to convert mechanical signals to electronic signals to stimulate auditory nerves to react. The current flow in the region of the cochlear is the key to determine the performance of Cochlear implants. One of the efforts could be made to reduce current leakage into the brain to increase the efficiency of the device. This paper aims to construct a three-dimensional finite element (FE) model to examine the current flow path in different surrounding tissues involved. The MRI data is processed to generate solid model and then FE model for the numerical analysis, which contains gray and white matters of the brain that was assembled and was analyzed in ABAQUS. The modeling results provide us with an effective means to improvement of Cochlear implant design in the future.","PeriodicalId":178669,"journal":{"name":"2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130333278","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 : 2009-05-11DOI: 10.1109/CIMSA.2009.5069942
A. Esmaeili, N. Mozayani
Particle Swarm Optimization (PSO), a new promising evolutionary optimization technique, has a wide range of application in optimization problems including training of artificial neural networks. In this paper, an attempt is made to completely train a RBF neural network architecture including the centers, optimum spreads, and the number of hidden units. The proposed method has been evaluated on some benchmark problems: Iris, Wine, Glass, New-thyroid and its accuracy was compared with other algorithms. The results show its strong generalization ability.
{"title":"Adjusting the parameters of radial basis function networks using Particle Swarm Optimization","authors":"A. Esmaeili, N. Mozayani","doi":"10.1109/CIMSA.2009.5069942","DOIUrl":"https://doi.org/10.1109/CIMSA.2009.5069942","url":null,"abstract":"Particle Swarm Optimization (PSO), a new promising evolutionary optimization technique, has a wide range of application in optimization problems including training of artificial neural networks. In this paper, an attempt is made to completely train a RBF neural network architecture including the centers, optimum spreads, and the number of hidden units. The proposed method has been evaluated on some benchmark problems: Iris, Wine, Glass, New-thyroid and its accuracy was compared with other algorithms. The results show its strong generalization ability.","PeriodicalId":178669,"journal":{"name":"2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132928289","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 : 2009-05-11DOI: 10.1109/CIMSA.2009.5069958
V. Di Lecce, A. Amato, V. Piuri
Aim of this work is to present a new approach to the problem of user presence monitoring in working environments. Particularly, this work is focused on the evaluation of the presence or absence of a user in front of a terminal. This question is of paramount importance in applications requiring the user's presence e.g. video surveillance systems, control centrals, etc. The authors propose a technique of data fusion using signals from various low cost sensors.
{"title":"Data fusion for user presence identification","authors":"V. Di Lecce, A. Amato, V. Piuri","doi":"10.1109/CIMSA.2009.5069958","DOIUrl":"https://doi.org/10.1109/CIMSA.2009.5069958","url":null,"abstract":"Aim of this work is to present a new approach to the problem of user presence monitoring in working environments. Particularly, this work is focused on the evaluation of the presence or absence of a user in front of a terminal. This question is of paramount importance in applications requiring the user's presence e.g. video surveillance systems, control centrals, etc. The authors propose a technique of data fusion using signals from various low cost sensors.","PeriodicalId":178669,"journal":{"name":"2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123286051","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 : 2009-05-11DOI: 10.1109/CIMSA.2009.5069964
Yunfeng Wu, S. Ng
In order to provide function approximation solutions with high accuracy, we employ a multi-learner system that combines a group of component neural networks (CNNs) with an adaptive weighted fusion (AWF) method. In the AWF, the optimization of the normalized weights is obtained with the constrained quadratic programming. Depending on the prediction errors of the CNNs from one input sample to another, the AWF can adaptively adjust the weights which are assigned to the CNNs. The results of the function approximation experiments on six benchmark data sets demonstrate that the AWF method can effectively help the multi-learner system achieve higher accuracy (measured in terms of mean-squared error) of prediction, in comparison with the popular the Bagging algorithm.
{"title":"Adaptively fusing neural network predictors toward higher accuracy: A case study","authors":"Yunfeng Wu, S. Ng","doi":"10.1109/CIMSA.2009.5069964","DOIUrl":"https://doi.org/10.1109/CIMSA.2009.5069964","url":null,"abstract":"In order to provide function approximation solutions with high accuracy, we employ a multi-learner system that combines a group of component neural networks (CNNs) with an adaptive weighted fusion (AWF) method. In the AWF, the optimization of the normalized weights is obtained with the constrained quadratic programming. Depending on the prediction errors of the CNNs from one input sample to another, the AWF can adaptively adjust the weights which are assigned to the CNNs. The results of the function approximation experiments on six benchmark data sets demonstrate that the AWF method can effectively help the multi-learner system achieve higher accuracy (measured in terms of mean-squared error) of prediction, in comparison with the popular the Bagging algorithm.","PeriodicalId":178669,"journal":{"name":"2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127073953","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 : 2009-05-11DOI: 10.1109/CIMSA.2009.5069950
Gang Shi, Yuanwei Jing
Based on the clonal selection theory, this paper is put forward an improved immune clonal selection algorithm through the introduction of cloning operator, and used to solve the CVRP problem. The algorithm through the introduction of clonal proliferation, super mutation operators and clonal selection operators, improves the global convergence speed, and can effectively avoid prematurity. Through those operators, the variety ofantibody and afinity maturation was enhanced. Experimental results showed that the algorithm has a remarkable quality of the global convergence reliability and convergence velocity, thus solving effectively the CVRP problem.
{"title":"Research of improved immune clonal algorithms and its applications","authors":"Gang Shi, Yuanwei Jing","doi":"10.1109/CIMSA.2009.5069950","DOIUrl":"https://doi.org/10.1109/CIMSA.2009.5069950","url":null,"abstract":"Based on the clonal selection theory, this paper is put forward an improved immune clonal selection algorithm through the introduction of cloning operator, and used to solve the CVRP problem. The algorithm through the introduction of clonal proliferation, super mutation operators and clonal selection operators, improves the global convergence speed, and can effectively avoid prematurity. Through those operators, the variety ofantibody and afinity maturation was enhanced. Experimental results showed that the algorithm has a remarkable quality of the global convergence reliability and convergence velocity, thus solving effectively the CVRP problem.","PeriodicalId":178669,"journal":{"name":"2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114920831","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 : 2009-05-11DOI: 10.1109/CIMSA.2009.5069920
Lu Xin-jiang, L. Han-Xiong
In this paper, fuzzy control is proposed to control one kind of nonlinear curing process. The nonlinear curing process is firstly approximately modeled by the T-S fuzzy model, upon which fuzzy control is designed to guarantee the process stability and achieve the H∞ tracking performance. Finally, the proposed method is applied to control the temperature profile of a practical curing process.
{"title":"Fuzzy control for one kind of curing process","authors":"Lu Xin-jiang, L. Han-Xiong","doi":"10.1109/CIMSA.2009.5069920","DOIUrl":"https://doi.org/10.1109/CIMSA.2009.5069920","url":null,"abstract":"In this paper, fuzzy control is proposed to control one kind of nonlinear curing process. The nonlinear curing process is firstly approximately modeled by the T-S fuzzy model, upon which fuzzy control is designed to guarantee the process stability and achieve the H∞ tracking performance. Finally, the proposed method is applied to control the temperature profile of a practical curing process.","PeriodicalId":178669,"journal":{"name":"2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115201194","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 : 2009-05-11DOI: 10.1109/CIMSA.2009.5069960
J. Sloper, E. Hines
This paper describes how neural networks and support vector machines can be used to detect errors in a large scale distributed system, specifically the ATLAS Trigger and Data AcQuisition (TDAQ) system. By collecting, analysing and preprocessing some of the data available in the system it is possible to recognize and/or predict error situations arising in the system. This can be done without detailed knowledge of the system, nor of the data available. Hence the presented methods could be used in similar system without significant changes. The TDAQ system, and in particular the main components related to this work, is described together with the test setup used. We simulate a number of error situations in the system and simultaneously gather both performance measures and error messages from the system. The data are then preprocessed and neural networks and support vector machines are applied to try to detect the error situations, achieving classification accuracy ranging from 88% to 100% for the neural networks and 90.8% to a 100% for the support vector machines approach.
{"title":"Detecting errors in the ATLAS TDAQ system: A neural networks and support vector machines approach","authors":"J. Sloper, E. Hines","doi":"10.1109/CIMSA.2009.5069960","DOIUrl":"https://doi.org/10.1109/CIMSA.2009.5069960","url":null,"abstract":"This paper describes how neural networks and support vector machines can be used to detect errors in a large scale distributed system, specifically the ATLAS Trigger and Data AcQuisition (TDAQ) system. By collecting, analysing and preprocessing some of the data available in the system it is possible to recognize and/or predict error situations arising in the system. This can be done without detailed knowledge of the system, nor of the data available. Hence the presented methods could be used in similar system without significant changes. The TDAQ system, and in particular the main components related to this work, is described together with the test setup used. We simulate a number of error situations in the system and simultaneously gather both performance measures and error messages from the system. The data are then preprocessed and neural networks and support vector machines are applied to try to detect the error situations, achieving classification accuracy ranging from 88% to 100% for the neural networks and 90.8% to a 100% for the support vector machines approach.","PeriodicalId":178669,"journal":{"name":"2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications","volume":"21 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129577322","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 : 2009-05-11DOI: 10.1109/CIMSA.2009.5069952
M. Pourhassan, N. Mozayani
Incorporating expert knowledge in reinforcement learning is an important issue, especially when a large state space is concerned. In this paper, we present a novel method for accelerating the setting of Q-values in the well-known Q-learning algorithm. Fuzzy rules indicating the state values will be used, and the knowledge will be transformed to the Q-table or Q-function in some first training experiences. There have already been methods to initialize the Q-values using fuzzy rules, but the rules were the kind of state-action rules and needed the expert to know about environment transitions on actions. In the method introduced in this paper, the expert should only apply some rules to estimate the state value while no appreciations about state transitions are required. The introduced method has been examined in a multiagent system which has the shepherding scenario. The obtaining results show that Q-learning requires much less iterations for getting good results if using the fuzzy rules estimating the state value.
{"title":"Incorporating expert knowledge in Q-learning by means of fuzzy rules","authors":"M. Pourhassan, N. Mozayani","doi":"10.1109/CIMSA.2009.5069952","DOIUrl":"https://doi.org/10.1109/CIMSA.2009.5069952","url":null,"abstract":"Incorporating expert knowledge in reinforcement learning is an important issue, especially when a large state space is concerned. In this paper, we present a novel method for accelerating the setting of Q-values in the well-known Q-learning algorithm. Fuzzy rules indicating the state values will be used, and the knowledge will be transformed to the Q-table or Q-function in some first training experiences. There have already been methods to initialize the Q-values using fuzzy rules, but the rules were the kind of state-action rules and needed the expert to know about environment transitions on actions. In the method introduced in this paper, the expert should only apply some rules to estimate the state value while no appreciations about state transitions are required. The introduced method has been examined in a multiagent system which has the shepherding scenario. The obtaining results show that Q-learning requires much less iterations for getting good results if using the fuzzy rules estimating the state value.","PeriodicalId":178669,"journal":{"name":"2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129246653","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：