To solve the unbalanced data problems of learning models for semantic concepts, an optimized modeling method based on the posterior probability support vector machine （PPSVM） is presented. A neighborbased posterior ...To solve the unbalanced data problems of learning models for semantic concepts, an optimized modeling method based on the posterior probability support vector machine （PPSVM） is presented. A neighborbased posterior probability estimator for visual concepts is provided. The proposed method has been applied in a high-level visual semantic concept classification system and the experiment results show that it results in enhanced performance over the baseline SVM models, as well as in improved robustness with respect to high-level visual semantic concept classification.展开更多
To meet the increasing demand of national spatial database infrastructure construction and application, a concept model of China's coastal zone scientific data platform is established based on the information feat...To meet the increasing demand of national spatial database infrastructure construction and application, a concept model of China's coastal zone scientific data platform is established based on the information feature analysis of a compound dataset, consisting of remote sensing data and conventional data. Based on this concept model, the detailed logical database structure and the storage strategy of remote sensing data and their metadata using ArcSDE are designed. The complicated technology of multisources data combination in this research is crucial to the future coastal zone and offshore database construction and practical running, which will provide intelligent information analysis and technological service for coastal zone and offshore investigation, research, development and management.展开更多
The rapid developments in the fields of telecommunication, sensor data, financial applications, analyzing of data streams, and so on, increase the rate of data arrival, among which the data mining technique is conside...The rapid developments in the fields of telecommunication, sensor data, financial applications, analyzing of data streams, and so on, increase the rate of data arrival, among which the data mining technique is considered a vital process. The data analysis process consists of different tasks, among which the data stream classification approaches face more challenges than the other commonly used techniques. Even though the classification is a continuous process, it requires a design that can adapt the classification model so as to adjust the concept change or the boundary change between the classes. Hence, we design a novel fuzzy classifier known as THRFuzzy to classify new incoming data streams. Rough set theory along with tangential holoentropy function helps in the designing the dynamic classification model. The classification approach uses kernel fuzzy c-means(FCM) clustering for the generation of the rules and tangential holoentropy function to update the membership function. The performance of the proposed THRFuzzy method is verified using three datasets, namely skin segmentation, localization, and breast cancer datasets, and the evaluated metrics, accuracy and time, comparing its performance with HRFuzzy and adaptive k-NN classifiers. The experimental results conclude that THRFuzzy classifier shows better classification results providing a maximum accuracy consuming a minimal time than the existing classifiers.展开更多
We applied the decision tree algorithm to learn association rules between webpage’s category(pornographic or normal) and the critical features.Based on these rules, we proposed an efficient method of filtering pornog...We applied the decision tree algorithm to learn association rules between webpage’s category(pornographic or normal) and the critical features.Based on these rules, we proposed an efficient method of filtering pornographic webpages with the following major advantages: 1) a weighted window-based technique was proposed to estimate for the condition of concept drift for the keywords found recently in pornographic webpages; 2) checking only contexts of webpages without scanning pictures; 3) an incremental learning mechanism was designed to incrementally update the pornographic keyword database.展开更多
The purpose of this paper is to study the construction of concept lattice from variable formal contexts.Composition and decomposition theories are proposed for the unraveling of concept lattice from contexts with vari...The purpose of this paper is to study the construction of concept lattice from variable formal contexts.Composition and decomposition theories are proposed for the unraveling of concept lattice from contexts with variable attribute set in the process of information updating.The relationship between the extension sets of the original context and that of its sub-context is analyzed.The composition and decomposition theories are then generalized to the situation involving more than two sub-contexts and the situation with variable attribute set and object set.展开更多
Ontologies have been used for several years in life sciences to formally represent concepts and reason about knowledge bases in domains such as the semantic web, information retrieval and artificial intelligence. The ...Ontologies have been used for several years in life sciences to formally represent concepts and reason about knowledge bases in domains such as the semantic web, information retrieval and artificial intelligence. The exploration of these domains for the correspondence of semantic content requires calculation of the measure of semantic similarity between concepts. Semantic similarity is a measure on a set of documents, based on the similarity of their meanings, which refers to the similarity between two concepts belonging to one or more ontologies. The similarity between concepts is also a quantitative measure of information, calculated based on the properties of concepts and their relationships. This study proposes a method for finding similarity between concepts in two different ontologies based on feature, information content and structure. More specifically, this means proposing a hybrid method using two existing measures to find the similarity between two concepts from different ontologies based on information content and the set of common superconcepts, which represents the set of common parent concepts. We simulated our method on datasets. The results show that our measure provides similarity values that are better than those reported in the literature.展开更多
数据流分类方法研究在开放环境下的模型动态更新,以期从实时到达且不断变化的数据流中检测并适应概念演化,目前多数数据流分类方法通常假设数据流中样本的类别数是固定的,并且样本的标签可以不受限制地获取,这在真实场景下是不现实的。...数据流分类方法研究在开放环境下的模型动态更新,以期从实时到达且不断变化的数据流中检测并适应概念演化,目前多数数据流分类方法通常假设数据流中样本的类别数是固定的,并且样本的标签可以不受限制地获取,这在真实场景下是不现实的。为此,该文提出了一种概念演化数据流主动学习方法(Active Learning Method for Concept Evolution Data Stream,ALM-CEDS)。定义基于样本标准差的基分类器重要性度量,提出基于加权预测概率的样本预测方法,提升分类器的分类性能;提出基于混合标签查询策略的分类器更新方法,使用难区分和代表当前数据分布的样本更新分类器;提出基于微簇q-近邻轮廓系数的新类检测方法,在数据流中快速识别新类。在4个真实数据流与5个合成数据流上的对比实验表明,该概念演化数据流主动学习方法在分类性能上优于已有的6种数据流学习方法。展开更多
基金Sponsored by the Beijing Municipal Natural Science Foundation(4082027)
文摘To solve the unbalanced data problems of learning models for semantic concepts, an optimized modeling method based on the posterior probability support vector machine （PPSVM） is presented. A neighborbased posterior probability estimator for visual concepts is provided. The proposed method has been applied in a high-level visual semantic concept classification system and the experiment results show that it results in enhanced performance over the baseline SVM models, as well as in improved robustness with respect to high-level visual semantic concept classification.
基金the“863”Marine Monitor of Hitech Research and Development Program of China under contract No.,5 2003AA604040 a, 2002AA639640.
文摘To meet the increasing demand of national spatial database infrastructure construction and application, a concept model of China's coastal zone scientific data platform is established based on the information feature analysis of a compound dataset, consisting of remote sensing data and conventional data. Based on this concept model, the detailed logical database structure and the storage strategy of remote sensing data and their metadata using ArcSDE are designed. The complicated technology of multisources data combination in this research is crucial to the future coastal zone and offshore database construction and practical running, which will provide intelligent information analysis and technological service for coastal zone and offshore investigation, research, development and management.
基金supported by proposal No.OSD/BCUD/392/197 Board of Colleges and University Development,Savitribai Phule Pune University,Pune
文摘The rapid developments in the fields of telecommunication, sensor data, financial applications, analyzing of data streams, and so on, increase the rate of data arrival, among which the data mining technique is considered a vital process. The data analysis process consists of different tasks, among which the data stream classification approaches face more challenges than the other commonly used techniques. Even though the classification is a continuous process, it requires a design that can adapt the classification model so as to adjust the concept change or the boundary change between the classes. Hence, we design a novel fuzzy classifier known as THRFuzzy to classify new incoming data streams. Rough set theory along with tangential holoentropy function helps in the designing the dynamic classification model. The classification approach uses kernel fuzzy c-means(FCM) clustering for the generation of the rules and tangential holoentropy function to update the membership function. The performance of the proposed THRFuzzy method is verified using three datasets, namely skin segmentation, localization, and breast cancer datasets, and the evaluated metrics, accuracy and time, comparing its performance with HRFuzzy and adaptive k-NN classifiers. The experimental results conclude that THRFuzzy classifier shows better classification results providing a maximum accuracy consuming a minimal time than the existing classifiers.
基金supported by MOST under Grant No.MOST 103-2410-H-004-112
文摘We applied the decision tree algorithm to learn association rules between webpage’s category(pornographic or normal) and the critical features.Based on these rules, we proposed an efficient method of filtering pornographic webpages with the following major advantages: 1) a weighted window-based technique was proposed to estimate for the condition of concept drift for the keywords found recently in pornographic webpages; 2) checking only contexts of webpages without scanning pictures; 3) an incremental learning mechanism was designed to incrementally update the pornographic keyword database.
基金supported by grants from the National Natural Science Foundation of China(No.60703117 and No.11071281)the Fundamental Research Funds for the Central Universities(No.JY 10000903010 and No.JY 10000903014).
文摘The purpose of this paper is to study the construction of concept lattice from variable formal contexts.Composition and decomposition theories are proposed for the unraveling of concept lattice from contexts with variable attribute set in the process of information updating.The relationship between the extension sets of the original context and that of its sub-context is analyzed.The composition and decomposition theories are then generalized to the situation involving more than two sub-contexts and the situation with variable attribute set and object set.
文摘Ontologies have been used for several years in life sciences to formally represent concepts and reason about knowledge bases in domains such as the semantic web, information retrieval and artificial intelligence. The exploration of these domains for the correspondence of semantic content requires calculation of the measure of semantic similarity between concepts. Semantic similarity is a measure on a set of documents, based on the similarity of their meanings, which refers to the similarity between two concepts belonging to one or more ontologies. The similarity between concepts is also a quantitative measure of information, calculated based on the properties of concepts and their relationships. This study proposes a method for finding similarity between concepts in two different ontologies based on feature, information content and structure. More specifically, this means proposing a hybrid method using two existing measures to find the similarity between two concepts from different ontologies based on information content and the set of common superconcepts, which represents the set of common parent concepts. We simulated our method on datasets. The results show that our measure provides similarity values that are better than those reported in the literature.
文摘数据流分类方法研究在开放环境下的模型动态更新,以期从实时到达且不断变化的数据流中检测并适应概念演化,目前多数数据流分类方法通常假设数据流中样本的类别数是固定的,并且样本的标签可以不受限制地获取,这在真实场景下是不现实的。为此,该文提出了一种概念演化数据流主动学习方法(Active Learning Method for Concept Evolution Data Stream,ALM-CEDS)。定义基于样本标准差的基分类器重要性度量,提出基于加权预测概率的样本预测方法,提升分类器的分类性能;提出基于混合标签查询策略的分类器更新方法,使用难区分和代表当前数据分布的样本更新分类器;提出基于微簇q-近邻轮廓系数的新类检测方法,在数据流中快速识别新类。在4个真实数据流与5个合成数据流上的对比实验表明,该概念演化数据流主动学习方法在分类性能上优于已有的6种数据流学习方法。
