Pub Date : 2009-12-28DOI: 10.1109/CISE.2009.5362879
Lunbo Li, Jun Li, Jianhong Sun
This paper presents a novel approach to recognize traffic signs using Support Vector Machines and radial Tchebichef moments. More than 3000 real road images were captured by a digital camera under various weather conditions and at different times and locations. After traffic sign is detected from real road images, it is then normalized, and radial Tchebichef moments are computed as the features of traffic sign, with which SVM classifiers are trained for the fine recognition. Experimental results indicate that RBF and Sigmoid kernels combined with C -SVM or ν -SVM give the best classification results, and the proposed method shows good robustness and high classification rate.
{"title":"Traffic Sign Classification Based on Support Vector Machines and Tchebichef Moments","authors":"Lunbo Li, Jun Li, Jianhong Sun","doi":"10.1109/CISE.2009.5362879","DOIUrl":"https://doi.org/10.1109/CISE.2009.5362879","url":null,"abstract":"This paper presents a novel approach to recognize traffic signs using Support Vector Machines and radial Tchebichef moments. More than 3000 real road images were captured by a digital camera under various weather conditions and at different times and locations. After traffic sign is detected from real road images, it is then normalized, and radial Tchebichef moments are computed as the features of traffic sign, with which SVM classifiers are trained for the fine recognition. Experimental results indicate that RBF and Sigmoid kernels combined with C -SVM or ν -SVM give the best classification results, and the proposed method shows good robustness and high classification rate.","PeriodicalId":135441,"journal":{"name":"2009 International Conference on Computational Intelligence and Software Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129335921","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 : 2009-12-28DOI: 10.1109/CISE.2009.5366841
Nai Lei, Jiao Du, Qiuzhan Zhou, Dan’e Wu
In order to improve the accuracy and stability of conventional Least Square estimation for noise power spectrum, this paper presents a new method of quantitative calculation which is based on the Squared Distance Minimization (SDM). The amplitudes of each noise can be gained by using this method, and then the reliability estimation of the semiconductor can be realized. The experiment results show that the SDM method is more stable and need less computation than that of the Least Square Method (LSM).
{"title":"Fitting Noise Power Spectrum Parameters by Squared Distance Minimization","authors":"Nai Lei, Jiao Du, Qiuzhan Zhou, Dan’e Wu","doi":"10.1109/CISE.2009.5366841","DOIUrl":"https://doi.org/10.1109/CISE.2009.5366841","url":null,"abstract":"In order to improve the accuracy and stability of conventional Least Square estimation for noise power spectrum, this paper presents a new method of quantitative calculation which is based on the Squared Distance Minimization (SDM). The amplitudes of each noise can be gained by using this method, and then the reliability estimation of the semiconductor can be realized. The experiment results show that the SDM method is more stable and need less computation than that of the Least Square Method (LSM).","PeriodicalId":135441,"journal":{"name":"2009 International Conference on Computational Intelligence and Software Engineering","volume":"18 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124691500","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 : 2009-12-28DOI: 10.1109/CISE.2009.5366426
Yang Lin, ZhongJian Teng
A novel method based on mixed graph structure is proposed for image representation and matching. The mixed graph structure is constructed according to the spatial relation of the regions within an image. This structure does not require redundant information to describe images. An image matching process focuses on evaluating region attributes and relationships contained in the corresponding mixed graph structure. An association graph based on this mixed graph structure is then constructed. By searching the largest cliques in the association graph, we are able to obtain the optimal similarity among images under this structure. Experimental results are presented showing the effectiveness of our approach. Keywords-image representation; image matching; mixed graph structure; association graph;
{"title":"A Novel Approach for Image Representation and Matching Based on Mixed Graph Structure","authors":"Yang Lin, ZhongJian Teng","doi":"10.1109/CISE.2009.5366426","DOIUrl":"https://doi.org/10.1109/CISE.2009.5366426","url":null,"abstract":"A novel method based on mixed graph structure is proposed for image representation and matching. The mixed graph structure is constructed according to the spatial relation of the regions within an image. This structure does not require redundant information to describe images. An image matching process focuses on evaluating region attributes and relationships contained in the corresponding mixed graph structure. An association graph based on this mixed graph structure is then constructed. By searching the largest cliques in the association graph, we are able to obtain the optimal similarity among images under this structure. Experimental results are presented showing the effectiveness of our approach. Keywords-image representation; image matching; mixed graph structure; association graph;","PeriodicalId":135441,"journal":{"name":"2009 International Conference on Computational Intelligence and Software Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129882092","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 : 2009-12-28DOI: 10.1109/CISE.2009.5364700
Shaohua Du, Dong Yu
Reconfigurable CNC system, as an extension of open CNC system, can be rapid designed, easy to integrate new technologies and flexible to fulfill different application requirements. In order to implement the reconfigurable CNC system, Component Based Software Engineering appears to be an efficient approach. This paper presents a component model for reconfigurable CNC system, which addresses the special functional and non-functional requirements, such as data-flow oriented, algorithm implementation, reconfiguration, etc. In order to implement the component model and build a prototype of reconfigurable CNC system, the Communication Management Layer is designed which can provide the system services, rapidly integrate the components and change the topology of the CNC system as needed. At last, some experiments are carried out in the designed system. Keywords-reconfigurable CNC system; component technology; system architecture
{"title":"Research on Component Technology for Reconfigurable CNC System","authors":"Shaohua Du, Dong Yu","doi":"10.1109/CISE.2009.5364700","DOIUrl":"https://doi.org/10.1109/CISE.2009.5364700","url":null,"abstract":"Reconfigurable CNC system, as an extension of open CNC system, can be rapid designed, easy to integrate new technologies and flexible to fulfill different application requirements. In order to implement the reconfigurable CNC system, Component Based Software Engineering appears to be an efficient approach. This paper presents a component model for reconfigurable CNC system, which addresses the special functional and non-functional requirements, such as data-flow oriented, algorithm implementation, reconfiguration, etc. In order to implement the component model and build a prototype of reconfigurable CNC system, the Communication Management Layer is designed which can provide the system services, rapidly integrate the components and change the topology of the CNC system as needed. At last, some experiments are carried out in the designed system. Keywords-reconfigurable CNC system; component technology; system architecture","PeriodicalId":135441,"journal":{"name":"2009 International Conference on Computational Intelligence and Software Engineering","volume":"603 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130306832","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 : 2009-12-28DOI: 10.1109/CISE.2009.5363225
Li-Bo Liu, Guomin Zhou
Rice leaf diseases have occurred all over the world,including china.They have had a significant impact on rice quality and yield.Now,the control method rely mainly on artificial means.In this study,BP neural network classifiers were designed for classifying the healthy and diseased parts of rice leaves.This paper select rice brown spot as study object,the training and testing samples of the images are gathered from the northern part of Ningxia Hui Autonomous Region.The result shows that the scheme is feasible to identify rice brown spot using image analysis and BP neural network classifier. Keywords-rice brown spot;BP neuralnetwork;color feature;feature extraction
{"title":"Extraction of the Rice Leaf Disease Image Based on BP Neural Network","authors":"Li-Bo Liu, Guomin Zhou","doi":"10.1109/CISE.2009.5363225","DOIUrl":"https://doi.org/10.1109/CISE.2009.5363225","url":null,"abstract":"Rice leaf diseases have occurred all over the world,including china.They have had a significant impact on rice quality and yield.Now,the control method rely mainly on artificial means.In this study,BP neural network classifiers were designed for classifying the healthy and diseased parts of rice leaves.This paper select rice brown spot as study object,the training and testing samples of the images are gathered from the northern part of Ningxia Hui Autonomous Region.The result shows that the scheme is feasible to identify rice brown spot using image analysis and BP neural network classifier. Keywords-rice brown spot;BP neuralnetwork;color feature;feature extraction","PeriodicalId":135441,"journal":{"name":"2009 International Conference on Computational Intelligence and Software Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130366811","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 : 2009-12-28DOI: 10.1109/CISE.2009.5363999
Junlong Jia, Xue Jia, Cheng-fei Tian
There are a lot of factors that affect the cost of logistics services .And when we try to give a specific price for customers, we should take into account for various factors to make our service and our price have a best match. It can reflect the tailored of logistics services. In this paper we take the warehousing & distribution enterprise as an example, and apply BP neural net model, with it's excellent characteristics such as the Parallel distributed processing, self-organize, self-adjust, self-learning and fault tolerance to solve the prediction of the service cost of logistics enterprise, which is a kind of problem with various factors, uncertainty and nonlinear. Then we come to a support pricing model which is based on BP neural net technology, and this support pricing model can provide the basis for logistics enterprise in service pricing with preferable value.
{"title":"The Application of BP Neural Net Model in Logistics Costs Decision-Making","authors":"Junlong Jia, Xue Jia, Cheng-fei Tian","doi":"10.1109/CISE.2009.5363999","DOIUrl":"https://doi.org/10.1109/CISE.2009.5363999","url":null,"abstract":"There are a lot of factors that affect the cost of logistics services .And when we try to give a specific price for customers, we should take into account for various factors to make our service and our price have a best match. It can reflect the tailored of logistics services. In this paper we take the warehousing & distribution enterprise as an example, and apply BP neural net model, with it's excellent characteristics such as the Parallel distributed processing, self-organize, self-adjust, self-learning and fault tolerance to solve the prediction of the service cost of logistics enterprise, which is a kind of problem with various factors, uncertainty and nonlinear. Then we come to a support pricing model which is based on BP neural net technology, and this support pricing model can provide the basis for logistics enterprise in service pricing with preferable value.","PeriodicalId":135441,"journal":{"name":"2009 International Conference on Computational Intelligence and Software Engineering","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130495910","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 : 2009-12-28DOI: 10.1109/CISE.2009.5362972
Yuanyuan Li, Ming Zhang
resources efficiently. In this study, we propose a network traffic forecasting strategy based on BP neural network (BP-NTF). First, we analyse the characteristics of network traffic and establish traffic forecasting methods based on BP neural network, then modeling and forecasting the time series of network traffic data; Second, we construct three module, namely, data collection, data processing and traffic forecasting; Last, we use the strong memory and the learning ability of BP neural network to shortterm forecast the network traffic .This model can provide a basis for network monitoring and management and has high application value and very wide meaning.
{"title":"Research on Network Traffic Forecasting Strategy Based on BP Neural Network","authors":"Yuanyuan Li, Ming Zhang","doi":"10.1109/CISE.2009.5362972","DOIUrl":"https://doi.org/10.1109/CISE.2009.5362972","url":null,"abstract":"resources efficiently. In this study, we propose a network traffic forecasting strategy based on BP neural network (BP-NTF). First, we analyse the characteristics of network traffic and establish traffic forecasting methods based on BP neural network, then modeling and forecasting the time series of network traffic data; Second, we construct three module, namely, data collection, data processing and traffic forecasting; Last, we use the strong memory and the learning ability of BP neural network to shortterm forecast the network traffic .This model can provide a basis for network monitoring and management and has high application value and very wide meaning.","PeriodicalId":135441,"journal":{"name":"2009 International Conference on Computational Intelligence and Software Engineering","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126686966","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 : 2009-12-28DOI: 10.1109/CISE.2009.5366994
Ling Song, Debiao Chen
It has been a social issue for undergraduate to pursue their jobs in China. With occurrence of 2008 financial crisis, this problem becomes more serious. This article, with the principles of Desperation Ecology, Knowledge Ecology and Entire Life- Cycle management of human resource as theoretic basis, and with Service-Oriented Architecuture to flexibly integrate the technology of data mining (which could be achieved on data warehouse architecuture) and business score card as a technical solution, intends to guide undergraduates' internal migration in university and external transit from university to enterprise.
{"title":"Research on the Issue of Undergraduate Employment Based on Desperation Ecology","authors":"Ling Song, Debiao Chen","doi":"10.1109/CISE.2009.5366994","DOIUrl":"https://doi.org/10.1109/CISE.2009.5366994","url":null,"abstract":"It has been a social issue for undergraduate to pursue their jobs in China. With occurrence of 2008 financial crisis, this problem becomes more serious. This article, with the principles of Desperation Ecology, Knowledge Ecology and Entire Life- Cycle management of human resource as theoretic basis, and with Service-Oriented Architecuture to flexibly integrate the technology of data mining (which could be achieved on data warehouse architecuture) and business score card as a technical solution, intends to guide undergraduates' internal migration in university and external transit from university to enterprise.","PeriodicalId":135441,"journal":{"name":"2009 International Conference on Computational Intelligence and Software Engineering","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126905013","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 : 2009-12-28DOI: 10.1109/CISE.2009.5363573
Shengtao Sun
In natural language, it is very common that one word has several different meanings. The well solution of Word Sense Disambiguation (WSD) problem is the basis of Natural Language Processing. In this paper, based on the certainty of word sense in certain language context, a new method is put forward based on Ontology to solve the problem of WSD. And also, a prototype is developed to solve the WSD of "打" in Chinese. Ontology is used to describe the knowledge of word and sense, and Jena reasoning rules are used to reason the mean of one ambiguous word. This method can be of great help to solve WSD. Keywords-Natural Language Processing; Word Sense Disambiguation; Ontology; reasoning rules
{"title":"The Realization and Discussion of Word Sense Disambiguation Based on Ontology","authors":"Shengtao Sun","doi":"10.1109/CISE.2009.5363573","DOIUrl":"https://doi.org/10.1109/CISE.2009.5363573","url":null,"abstract":"In natural language, it is very common that one word has several different meanings. The well solution of Word Sense Disambiguation (WSD) problem is the basis of Natural Language Processing. In this paper, based on the certainty of word sense in certain language context, a new method is put forward based on Ontology to solve the problem of WSD. And also, a prototype is developed to solve the WSD of \"打\" in Chinese. Ontology is used to describe the knowledge of word and sense, and Jena reasoning rules are used to reason the mean of one ambiguous word. This method can be of great help to solve WSD. Keywords-Natural Language Processing; Word Sense Disambiguation; Ontology; reasoning rules","PeriodicalId":135441,"journal":{"name":"2009 International Conference on Computational Intelligence and Software Engineering","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127041377","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 : 2009-12-28DOI: 10.1109/CISE.2009.5362996
Yi Yang, Rui Li
The paper gives an overview of the security issue on WiMax, which is a new and hot research point for telecommunication and computer scientist. In the IEEE 802.11 technology, security was added later while IEEE 802.16 considered the security issues during the design of the protocol. However, security mechanism of the IEEE 802.16 still remains a question. WiMax is relatively a new technology and does not deployed widely to justify the evidence of threats, risk and vulnerability in real situations. This paper reflects to most recent work of the IEEE and WiMax forums and it can be used to prioritize future research directions in Wireless security. KeywordsWiMAX, IEEE 802.16, Security
{"title":"Toward Wimax Security","authors":"Yi Yang, Rui Li","doi":"10.1109/CISE.2009.5362996","DOIUrl":"https://doi.org/10.1109/CISE.2009.5362996","url":null,"abstract":"The paper gives an overview of the security issue on WiMax, which is a new and hot research point for telecommunication and computer scientist. In the IEEE 802.11 technology, security was added later while IEEE 802.16 considered the security issues during the design of the protocol. However, security mechanism of the IEEE 802.16 still remains a question. WiMax is relatively a new technology and does not deployed widely to justify the evidence of threats, risk and vulnerability in real situations. This paper reflects to most recent work of the IEEE and WiMax forums and it can be used to prioritize future research directions in Wireless security. KeywordsWiMAX, IEEE 802.16, Security","PeriodicalId":135441,"journal":{"name":"2009 International Conference on Computational Intelligence and Software Engineering","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129071929","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：