Hyper spectral unmixing (HU) is important for ground objects identification. Due to the mass data hyper spectral sensors bring, band selection plays an important role in boosting efficiency of HU. This paper proposes a high-efficiency approach of HU that carries out two modified algorithms of band selection followed by nonnegative matrix factorization (NMF), which are linear prediction (LP) combined with K-L divergence and mutual information (MI). Experiment results based on simulated data and real hyper spectral imagery demonstrate that the proposed scheme is more efficient than initial NMF in HU.
{"title":"High-Efficiency Hyperspectral Unmixing Based on Band Selection","authors":"Yang Zhou, Xiaorun Li, Jiantao Cui","doi":"10.1109/GCIS.2012.39","DOIUrl":"https://doi.org/10.1109/GCIS.2012.39","url":null,"abstract":"Hyper spectral unmixing (HU) is important for ground objects identification. Due to the mass data hyper spectral sensors bring, band selection plays an important role in boosting efficiency of HU. This paper proposes a high-efficiency approach of HU that carries out two modified algorithms of band selection followed by nonnegative matrix factorization (NMF), which are linear prediction (LP) combined with K-L divergence and mutual information (MI). Experiment results based on simulated data and real hyper spectral imagery demonstrate that the proposed scheme is more efficient than initial NMF in HU.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131110619","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}
Y. Tian, Qinghong Zhang, Guojian Cheng, Xuanchao Liu
The parameter calculation relating to petroleum reservoir characterization and lithologic identification based on RBF neural networks is studied in this paper. Two models for reservoir permeability prediction and litho logic identification have been constructed and are applied to predict the unknown samples. The prediction result of reservoir permeability has a higher consistency with the practical cases. The parameter prediction and litho logic identification precision have been greatly improved compared to the traditional BP neural networks. The results show that the RBF neural network is very promising for the application of petroleum reservoir characterization.
{"title":"An Application of RBF Neural Networks for Petroleum Reservoir Characterization","authors":"Y. Tian, Qinghong Zhang, Guojian Cheng, Xuanchao Liu","doi":"10.1109/GCIS.2012.75","DOIUrl":"https://doi.org/10.1109/GCIS.2012.75","url":null,"abstract":"The parameter calculation relating to petroleum reservoir characterization and lithologic identification based on RBF neural networks is studied in this paper. Two models for reservoir permeability prediction and litho logic identification have been constructed and are applied to predict the unknown samples. The prediction result of reservoir permeability has a higher consistency with the practical cases. The parameter prediction and litho logic identification precision have been greatly improved compared to the traditional BP neural networks. The results show that the RBF neural network is very promising for the application of petroleum reservoir characterization.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125382350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The pattern of blood veins is unique, even in identical twins. The human palms have a broad and complicated vascular pattern and thus contain many kinds of features. The Vein Based Biometric (VBB) depends on measurement of the vascular pattern made by the blood vessels on the back of the hand. The VBB technology is the world's leading and most promising biometric technology and can bring security and convenience to people in many areas. This paper firstly reviews the concepts and types of biometrics, then discusses VBB and vein image processing. According to the study of existing algorithms and techniques, a hand vein image segmentation and refinement algorithm is introduced in this section, a normalized image of the hand veins is processed by the Gaussian filtering and median filtering, in order to remove certain amount of speckle noise. By using local dynamic threshold segmentation NiBlack algorithm, a coarse vein image is produced. An image of veins lines with smaller distortion is obtained by refinement algorithm. It is also show some experimental results of VBB. The last section of this paper is about some new developments of biometrics.
{"title":"A Vein Based Biometric Experiment and Some New Developments","authors":"Wenhai Wu, Feiyuan Lu, Guojian Cheng, C. shi","doi":"10.1109/GCIS.2012.74","DOIUrl":"https://doi.org/10.1109/GCIS.2012.74","url":null,"abstract":"The pattern of blood veins is unique, even in identical twins. The human palms have a broad and complicated vascular pattern and thus contain many kinds of features. The Vein Based Biometric (VBB) depends on measurement of the vascular pattern made by the blood vessels on the back of the hand. The VBB technology is the world's leading and most promising biometric technology and can bring security and convenience to people in many areas. This paper firstly reviews the concepts and types of biometrics, then discusses VBB and vein image processing. According to the study of existing algorithms and techniques, a hand vein image segmentation and refinement algorithm is introduced in this section, a normalized image of the hand veins is processed by the Gaussian filtering and median filtering, in order to remove certain amount of speckle noise. By using local dynamic threshold segmentation NiBlack algorithm, a coarse vein image is produced. An image of veins lines with smaller distortion is obtained by refinement algorithm. It is also show some experimental results of VBB. The last section of this paper is about some new developments of biometrics.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122213675","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}
With analysis and research for of the serial formation of swarms robots movement, the strategy of keeping swarms robots formation in the process of schlepping and turning was proposed based on the discussion of the robot kinematic model. In the condition of the wireless communication the master-slave robots can control their speed based on environmental information in order to keep the spacing between robots as well as the configuration of the serial formation in the process of turning. Finally, the simulation of Matlab for the serial formation verifies that the formation configuration keep unchanged, which also verifies the validity of the method.
{"title":"Research on Formation Handling of Serial Swarm Robots","authors":"Jianhua Wu, M. Qi","doi":"10.1109/GCIS.2012.37","DOIUrl":"https://doi.org/10.1109/GCIS.2012.37","url":null,"abstract":"With analysis and research for of the serial formation of swarms robots movement, the strategy of keeping swarms robots formation in the process of schlepping and turning was proposed based on the discussion of the robot kinematic model. In the condition of the wireless communication the master-slave robots can control their speed based on environmental information in order to keep the spacing between robots as well as the configuration of the serial formation in the process of turning. Finally, the simulation of Matlab for the serial formation verifies that the formation configuration keep unchanged, which also verifies the validity of the method.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121457505","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}
Matthew effect or cumulative advantage (CA) is widely studied in all sorts of fields. It is considered as an important factor that causes inequality in labor wages, education and careers. This even greatly impacts the scientific activities including journal publication, grant application, peer recognition, promotion, etc. Numerous models are developed to analyze the CA process. However, we are not aware of any work on the analysis of CA issue encountered by young scientists at their early stage of careers in the form of tenure track. The CA process for this group has its unique characteristics and requires special treatment. Therefore, a modified CA model is constructed and its implications are also analyzed.
{"title":"A Cumulative Advantage Model for Tenure Tracking Young Scientists","authors":"M. Taypanhyavong, Hao Zhang","doi":"10.1109/GCIS.2012.59","DOIUrl":"https://doi.org/10.1109/GCIS.2012.59","url":null,"abstract":"Matthew effect or cumulative advantage (CA) is widely studied in all sorts of fields. It is considered as an important factor that causes inequality in labor wages, education and careers. This even greatly impacts the scientific activities including journal publication, grant application, peer recognition, promotion, etc. Numerous models are developed to analyze the CA process. However, we are not aware of any work on the analysis of CA issue encountered by young scientists at their early stage of careers in the form of tenure track. The CA process for this group has its unique characteristics and requires special treatment. Therefore, a modified CA model is constructed and its implications are also analyzed.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133786614","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}
Aiming at the safety problems in the vector data sharing process, a method of accuracy reducing for vector data based on random function is proposed. The characteristics of vector data are analyzed, and then the modifying strength is chosen based on the map scale. Finally the data accuracy is reduced by modifying the coordinate values based on the random function. The experiments show that this method maintains the availability of the vector data when reducing the data accuracy. It achieves the goal of protecting the data while maximizing the data sharing.
{"title":"A Method of Accuracy Reducing for Vector Data Based on Random Function","authors":"Cui Hanchuan, Xu Hui, Zhu Changqing","doi":"10.1109/GCIS.2012.88","DOIUrl":"https://doi.org/10.1109/GCIS.2012.88","url":null,"abstract":"Aiming at the safety problems in the vector data sharing process, a method of accuracy reducing for vector data based on random function is proposed. The characteristics of vector data are analyzed, and then the modifying strength is chosen based on the map scale. Finally the data accuracy is reduced by modifying the coordinate values based on the random function. The experiments show that this method maintains the availability of the vector data when reducing the data accuracy. It achieves the goal of protecting the data while maximizing the data sharing.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"207 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134380605","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}
Speaker classification is an important component for audio indexing technology for many applications such as multimedia conferencing. The primary input device of NIST speaker classification evaluation is Multiple Distant Microphones (MDM). MDM is composed of multiple microphones and has the merit of low price and easy-to-use. The spatial time-delay vector of MDM can be extracted as the speaker's discriminant feature. However the feature dimension will be expanded quickly with the increasing number of sensors. Locality Preserving Projections (LPP) and Discriminant locality preserving projection (DLPP) are the principal manifold dimension-reduction algorithms being proposed recently. In this paper, we proposed a novel method to overcome the drawbacks of traditional manifold algorithms such as the lack of class information or spatial identification information. Some basic concepts of spatial time-delay feature and merging feature for MDM speaker classification are first introduced. A review of known DLPP algorithm followed by Fisher criterion is given. Then the Multi-component Discriminant Locality Preserving Projections (MDLPP) method for speaker classification with MDM is described. Comparative experiment results on real meeting data showed the effectiveness of the proposed method.
{"title":"A Novel Discriminant Locality Preserving Projections for MDM-based Speaker Classification","authors":"Yi Yang, C. Bao","doi":"10.1109/GCIS.2012.55","DOIUrl":"https://doi.org/10.1109/GCIS.2012.55","url":null,"abstract":"Speaker classification is an important component for audio indexing technology for many applications such as multimedia conferencing. The primary input device of NIST speaker classification evaluation is Multiple Distant Microphones (MDM). MDM is composed of multiple microphones and has the merit of low price and easy-to-use. The spatial time-delay vector of MDM can be extracted as the speaker's discriminant feature. However the feature dimension will be expanded quickly with the increasing number of sensors. Locality Preserving Projections (LPP) and Discriminant locality preserving projection (DLPP) are the principal manifold dimension-reduction algorithms being proposed recently. In this paper, we proposed a novel method to overcome the drawbacks of traditional manifold algorithms such as the lack of class information or spatial identification information. Some basic concepts of spatial time-delay feature and merging feature for MDM speaker classification are first introduced. A review of known DLPP algorithm followed by Fisher criterion is given. Then the Multi-component Discriminant Locality Preserving Projections (MDLPP) method for speaker classification with MDM is described. Comparative experiment results on real meeting data showed the effectiveness of the proposed method.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"221 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133251275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The paper analyses the function of knowledge management platform for library, exploring the technology of knowledge management, such as knowledge excavation, knowledge store, knowledge share and spread. It puts forward using resource ontology theory and J2EE to construct a knowledge management platform for a library.
{"title":"Research on a Reconfigurable-Oriented Knowledge Management Platform for a Library Based on Ontology","authors":"J. Ye","doi":"10.1109/GCIS.2012.64","DOIUrl":"https://doi.org/10.1109/GCIS.2012.64","url":null,"abstract":"The paper analyses the function of knowledge management platform for library, exploring the technology of knowledge management, such as knowledge excavation, knowledge store, knowledge share and spread. It puts forward using resource ontology theory and J2EE to construct a knowledge management platform for a library.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131475510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents a new approach for petroleum pipeline data prediction. In order to obtain correlation coefficient matrix of variables of petroleum pipeline monitoring data monthly, a novel method of matrix rotation-generalized regression neural network for petroleum pipeline data prediction is proposed. The simulation analysis demonstrates that the model is not only more precise, but also more effective and feasible.
{"title":"The Prediction of Petroleum Pipeline Data Based on Matrix Rotation-Generalized Regression Neural Network","authors":"Shengyang Yan, Zhang Jing, Sun Shuangshuang","doi":"10.1109/GCIS.2012.17","DOIUrl":"https://doi.org/10.1109/GCIS.2012.17","url":null,"abstract":"This paper presents a new approach for petroleum pipeline data prediction. In order to obtain correlation coefficient matrix of variables of petroleum pipeline monitoring data monthly, a novel method of matrix rotation-generalized regression neural network for petroleum pipeline data prediction is proposed. The simulation analysis demonstrates that the model is not only more precise, but also more effective and feasible.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125353584","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}
At first the relationship between the volume of the data transmitted and the transmission time is tested and the analysis of the data shows that there is a significant linear relationship between the two in MATLAB Distributed Computing Engine. Then we give an implementation solution of the parallel ant colony optimization algorithm, and we also carried on the computation of a TSP example which shows a higher speedup and a better performance. All these show that the it is efficient and effective to use MATLAB to develop distributed computing application program.
{"title":"The Implementation of Parallel Ant Colony Optimization Algorithm Based on MATLAB","authors":"Wang Baocheng, Wang Tiane, Wang Zenghui","doi":"10.1109/GCIS.2012.62","DOIUrl":"https://doi.org/10.1109/GCIS.2012.62","url":null,"abstract":"At first the relationship between the volume of the data transmitted and the transmission time is tested and the analysis of the data shows that there is a significant linear relationship between the two in MATLAB Distributed Computing Engine. Then we give an implementation solution of the parallel ant colony optimization algorithm, and we also carried on the computation of a TSP example which shows a higher speedup and a better performance. All these show that the it is efficient and effective to use MATLAB to develop distributed computing application program.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115031530","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：