In the paper, four kinds of pair of operators are discussed. Based on the discussed kinds of pair of operators, we introduced two type of formal concepts. The introduced formal concepts associate with a parameter delta, and we have different level formal concepts with different level delta.
{"title":"Multi-level Formal Concepts in Fuzzy Formal Contexts","authors":"Mingwen Shao, Chang-Xuan Wan","doi":"10.1109/GrC.2007.79","DOIUrl":"https://doi.org/10.1109/GrC.2007.79","url":null,"abstract":"In the paper, four kinds of pair of operators are discussed. Based on the discussed kinds of pair of operators, we introduced two type of formal concepts. The introduced formal concepts associate with a parameter delta, and we have different level formal concepts with different level delta.","PeriodicalId":259430,"journal":{"name":"2007 IEEE International Conference on Granular Computing (GRC 2007)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127827040","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}
Ontology learning technology has become a research hotspot in computer science nowadays. The main objective of this paper is to describe domain ontologies at different granularities and hierarchies based on granular computing. A granular space model for ontology learning was explored, and some definitions such as concept granules, granular worlds and the structure of granular space were described formally. Accordingly, the composition and decomposition of concept granules and operation properties were introduced. The proposed model is available for research on ontology learning and data mining at different levels of granularity based on granular computing.
{"title":"A Granular Space Model for Ontology Learning","authors":"Taorong Qiu, Xiaoqing Chen, Qing Liu, Houkuan Huang","doi":"10.1109/GrC.2007.59","DOIUrl":"https://doi.org/10.1109/GrC.2007.59","url":null,"abstract":"Ontology learning technology has become a research hotspot in computer science nowadays. The main objective of this paper is to describe domain ontologies at different granularities and hierarchies based on granular computing. A granular space model for ontology learning was explored, and some definitions such as concept granules, granular worlds and the structure of granular space were described formally. Accordingly, the composition and decomposition of concept granules and operation properties were introduced. The proposed model is available for research on ontology learning and data mining at different levels of granularity based on granular computing.","PeriodicalId":259430,"journal":{"name":"2007 IEEE International Conference on Granular Computing (GRC 2007)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129973391","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}
In this paper, we propose a method of remote sensing classification based on run-length features combined with neural network. According to the criterion of variances between & within classes, we choose efficient features and exclude redundant ones successfully with the method of rough set. In experiment, we use run-length features, co-occurrence features, gray-level gradient co-occurrence features and gray-level smoothed co-occurrence features respectively as inputs of three types of classifiers: BP net, RBF net and a nearest neighbor classifier: K-NN method when applying remote sensing classification for large scale panchromatic SPOT images with high spatial resolution. The result demonstrates the efficiency of the method proposed in this paper.
{"title":"The Application of Run-Length Features in Remote Sensing Classification Combined with Neural Network and Rough Set","authors":"Z. Cao, Yang Xiao, Lamei Zou","doi":"10.1109/GrC.2007.38","DOIUrl":"https://doi.org/10.1109/GrC.2007.38","url":null,"abstract":"In this paper, we propose a method of remote sensing classification based on run-length features combined with neural network. According to the criterion of variances between & within classes, we choose efficient features and exclude redundant ones successfully with the method of rough set. In experiment, we use run-length features, co-occurrence features, gray-level gradient co-occurrence features and gray-level smoothed co-occurrence features respectively as inputs of three types of classifiers: BP net, RBF net and a nearest neighbor classifier: K-NN method when applying remote sensing classification for large scale panchromatic SPOT images with high spatial resolution. The result demonstrates the efficiency of the method proposed in this paper.","PeriodicalId":259430,"journal":{"name":"2007 IEEE International Conference on Granular Computing (GRC 2007)","volume":"7 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120973463","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}
A delayed differential equation modeling a single neuron with time delay and external exciting is considered in this paper. The method to study Hopf bifurcation and periodic solution is researched by using the closed form with the aid of the center manifold and averaging theorem.
{"title":"The Research for Hopf Bifurcation in a Single Inertial Neuron Model with External Forcing","authors":"Qun Liu, X. Liao, Degang Yang, Songtao Guo","doi":"10.1109/GrC.2007.85","DOIUrl":"https://doi.org/10.1109/GrC.2007.85","url":null,"abstract":"A delayed differential equation modeling a single neuron with time delay and external exciting is considered in this paper. The method to study Hopf bifurcation and periodic solution is researched by using the closed form with the aid of the center manifold and averaging theorem.","PeriodicalId":259430,"journal":{"name":"2007 IEEE International Conference on Granular Computing (GRC 2007)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121042542","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 the affordable advanced computerized equipments and tools, systems engineering and software systems engineering become closely related. Software engineering to the low level computer software and systems is not sufficient enough for systems engineers' needs to build complex computerized systems. Every engineering system has its own systems engineering's theory and technology. Are there general principles, theories, and technology for two or a collection of systems? In this article a new integrated field called systems software engineering (SSE) is proposed. SSE research is to study the common paradigms, theories, technology of the systems among all or simply a collection of engineering fields, applied science fields, computer science, software engineering, and mathematical sciences. According to the author's opinion, none except few like Lofti Zadeh's soft computing and granular computing are towards this trend that they have integrated fuzzy set theory and granular computing as an example. An integrated "systems software engineering" theory based on Boolean logic, Hilbert logic and set theory is introduced. Based on Boolean logic and Hilbert logic as the foundation for the decision systems and control systems for information systems, we can develop integrated foundations, theories, principles, and tools for information science. We adopt bioinformatics, bioengineering and medical information systems as a special case to describe our integrated "software systems engineering". As a matter of fact, we can choose any other integrated modern related fields as our special case to study in this paper.
{"title":"On Systems Software Engineering with Application to Bioinformatics","authors":"James Kuodo Huang","doi":"10.1109/GrC.2007.84","DOIUrl":"https://doi.org/10.1109/GrC.2007.84","url":null,"abstract":"With the affordable advanced computerized equipments and tools, systems engineering and software systems engineering become closely related. Software engineering to the low level computer software and systems is not sufficient enough for systems engineers' needs to build complex computerized systems. Every engineering system has its own systems engineering's theory and technology. Are there general principles, theories, and technology for two or a collection of systems? In this article a new integrated field called systems software engineering (SSE) is proposed. SSE research is to study the common paradigms, theories, technology of the systems among all or simply a collection of engineering fields, applied science fields, computer science, software engineering, and mathematical sciences. According to the author's opinion, none except few like Lofti Zadeh's soft computing and granular computing are towards this trend that they have integrated fuzzy set theory and granular computing as an example. An integrated \"systems software engineering\" theory based on Boolean logic, Hilbert logic and set theory is introduced. Based on Boolean logic and Hilbert logic as the foundation for the decision systems and control systems for information systems, we can develop integrated foundations, theories, principles, and tools for information science. We adopt bioinformatics, bioengineering and medical information systems as a special case to describe our integrated \"software systems engineering\". As a matter of fact, we can choose any other integrated modern related fields as our special case to study in this paper.","PeriodicalId":259430,"journal":{"name":"2007 IEEE International Conference on Granular Computing (GRC 2007)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121297851","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}
Edges detection in digital images is a problem that has been solved by means of the application of different techniques from digital signal processing. Also the combination of some of these techniques with fuzzy inference system (FIS) has been applied. In this work a new FIS type-2 method is implemented for the detection of edges and the results of three different techniques for the same goal are compared.
{"title":"A New Method for Edge Detection in Image Processing Using Interval Type-2 Fuzzy Logic","authors":"O. Mendoza, P. Melin, G. Sandoval","doi":"10.1109/GrC.2007.115","DOIUrl":"https://doi.org/10.1109/GrC.2007.115","url":null,"abstract":"Edges detection in digital images is a problem that has been solved by means of the application of different techniques from digital signal processing. Also the combination of some of these techniques with fuzzy inference system (FIS) has been applied. In this work a new FIS type-2 method is implemented for the detection of edges and the results of three different techniques for the same goal are compared.","PeriodicalId":259430,"journal":{"name":"2007 IEEE International Conference on Granular Computing (GRC 2007)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122408954","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}
Enterprises have become increasingly dependent on information technology capabilities (e.g. secure remote access for mobile users) to support their business objectives. Consequently, determining which users are affected by component failures remains a very important and challenging problem. Analyzing operational impact requires an understanding of how the system components are inter-dependent, and when the components are actually employed by the system users. Our approach collects monitoring data from the end systems. Data mining and analysis are used to infer system dependency topologies and usage patterns. We compare centralized, partially distributed, and fully distributed implementation approaches using computers connected to a campus-wide system. The results show that distributed approaches can be used to minimize the amount of data transmitted between systems, without significantly reducing the overall quality of the impact analysis. These distributed approaches will support efficient and scalable impact assessment in modern enterprise systems.
{"title":"Comparing Centralized and Distributed Approaches for Operational Impact Analysis in Enterprise Systems","authors":"Mark Moss","doi":"10.1109/GrC.2007.130","DOIUrl":"https://doi.org/10.1109/GrC.2007.130","url":null,"abstract":"Enterprises have become increasingly dependent on information technology capabilities (e.g. secure remote access for mobile users) to support their business objectives. Consequently, determining which users are affected by component failures remains a very important and challenging problem. Analyzing operational impact requires an understanding of how the system components are inter-dependent, and when the components are actually employed by the system users. Our approach collects monitoring data from the end systems. Data mining and analysis are used to infer system dependency topologies and usage patterns. We compare centralized, partially distributed, and fully distributed implementation approaches using computers connected to a campus-wide system. The results show that distributed approaches can be used to minimize the amount of data transmitted between systems, without significantly reducing the overall quality of the impact analysis. These distributed approaches will support efficient and scalable impact assessment in modern enterprise systems.","PeriodicalId":259430,"journal":{"name":"2007 IEEE International Conference on Granular Computing (GRC 2007)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123390542","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}
Traditional algorithm of BP neural network has been mended and an improved predictive model using L-M method has been carried out to calculate the K/S values in dyeing with reactive dyes in this article. The results showed L-M method is superior in the prediction by comparing traditional and improved algorithm. Shorter predictive time and higher predictive veracity were obtained in the later.
{"title":"Improved Algorithm of BP Neural Network and its Application to Prediction of K/S Value in Dyeing with Reactive Dyes","authors":"HuiYu Jiang, Min Dong, Xiangpeng Li, Feng Yang","doi":"10.1109/GrC.2007.25","DOIUrl":"https://doi.org/10.1109/GrC.2007.25","url":null,"abstract":"Traditional algorithm of BP neural network has been mended and an improved predictive model using L-M method has been carried out to calculate the K/S values in dyeing with reactive dyes in this article. The results showed L-M method is superior in the prediction by comparing traditional and improved algorithm. Shorter predictive time and higher predictive veracity were obtained in the later.","PeriodicalId":259430,"journal":{"name":"2007 IEEE International Conference on Granular Computing (GRC 2007)","volume":"199 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115369747","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}
Most of classifiers implicitly assume that data samples belong to at least one class among predefined classes. However, all data patterns may not be known at the time of data collection or a new pattern can be emerging over time. Hence ideal classifiers need to be able to recognize an emerging pattern. In this paper, we explore the performances and limitations of the existing classification systems in detecting a new class. Also a new method is proposed that can monitor the change in class distribution and detect an emerging class. It works under the supervised learning model where along with classification an emerging class with new characteristic is detected so that classification model can be adapted systematically. For detection of an emerging class, we design statistical significance testing for signaling change of class distribution. When the alarm for new class generation is set on, candidates for new class members are retrieved for close examination by experts. Our experimental results demonstrate competent performances of the proposed method.
{"title":"On Detecting an Emerging Class","authors":"C. Park, Hongsuk Shim","doi":"10.1109/GrC.2007.12","DOIUrl":"https://doi.org/10.1109/GrC.2007.12","url":null,"abstract":"Most of classifiers implicitly assume that data samples belong to at least one class among predefined classes. However, all data patterns may not be known at the time of data collection or a new pattern can be emerging over time. Hence ideal classifiers need to be able to recognize an emerging pattern. In this paper, we explore the performances and limitations of the existing classification systems in detecting a new class. Also a new method is proposed that can monitor the change in class distribution and detect an emerging class. It works under the supervised learning model where along with classification an emerging class with new characteristic is detected so that classification model can be adapted systematically. For detection of an emerging class, we design statistical significance testing for signaling change of class distribution. When the alarm for new class generation is set on, candidates for new class members are retrieved for close examination by experts. Our experimental results demonstrate competent performances of the proposed method.","PeriodicalId":259430,"journal":{"name":"2007 IEEE International Conference on Granular Computing (GRC 2007)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131584028","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}
In this paper, we present an improved method for predicting missing attribute values in data sets. We make use of frequent itemsets, generated from the association rules algorithm, displaying the correlations between different items in a set of transactions. In particular, we consider a database as a set of transactions and each data instance as an itemset. Then frequent itemsets can be used as a knowledge base to predict missing attribute values. Our approach integrates the RSFit method based on rough sets theory that produces faster predictions by considering similarities of attribute value pairs, but only for those attributes contained in the core or reduct of the data set. Using empirical studies on UCI and other real world data sets, we demonstrate a significant increase in prediction accuracy obtained from our new integrated approach, referred to as ItemRSFit.
{"title":"Addressing Missing Attributes during Data Mining Using Frequent Itemsets and Rough Set Based Predictions","authors":"Jiye Li, N. Cercone, R. Cohen","doi":"10.1109/GrC.2007.144","DOIUrl":"https://doi.org/10.1109/GrC.2007.144","url":null,"abstract":"In this paper, we present an improved method for predicting missing attribute values in data sets. We make use of frequent itemsets, generated from the association rules algorithm, displaying the correlations between different items in a set of transactions. In particular, we consider a database as a set of transactions and each data instance as an itemset. Then frequent itemsets can be used as a knowledge base to predict missing attribute values. Our approach integrates the RSFit method based on rough sets theory that produces faster predictions by considering similarities of attribute value pairs, but only for those attributes contained in the core or reduct of the data set. Using empirical studies on UCI and other real world data sets, we demonstrate a significant increase in prediction accuracy obtained from our new integrated approach, referred to as ItemRSFit.","PeriodicalId":259430,"journal":{"name":"2007 IEEE International Conference on Granular Computing (GRC 2007)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125256629","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：