Spatial objects have two types of attributes： geometrical attributes and non-geometrical attributes, which belong to two different attribute domains （geometrical and non-geometrical domains）. Although geometrically...Spatial objects have two types of attributes： geometrical attributes and non-geometrical attributes, which belong to two different attribute domains （geometrical and non-geometrical domains）. Although geometrically scattered in a geometrical domain, spatial objects may be similar to each other in a non-geometrical domain. Most existing clustering algorithms group spatial datasets into different compact regions in a geometrical domain without considering the aspect of a non-geometrical domain. However, many application scenarios require clustering results in which a cluster has not only high proximity in a geometrical domain, but also high similarity in a non-geometrical domain. This means constraints are imposed on the clustering goal from both geometrical and non-geometrical domains simultaneously. Such a clustering problem is called dual clustering. As distributed clustering applications become more and more popular, it is necessary to tackle the dual clustering problem in distributed databases. The DCAD algorithm is proposed to solve this problem. DCAD consists of two levels of clustering： local clustering and global clustering. First, clustering is conducted at each local site with a local clustering algorithm, and the features of local clusters are extracted clustering is obtained based on those features fective and efficient. Second, local features from each site are sent to a central site where global Experiments on both artificial and real spatial datasets show that DCAD is effective and efficient.展开更多
Privacy protection for big data linking is discussed here in relation to the Central Statistics Office （CSO）, Ireland＇s, big data linking project titled the ＇Structure of Earnings Survey - Administrative Data Proj...Privacy protection for big data linking is discussed here in relation to the Central Statistics Office （CSO）, Ireland＇s, big data linking project titled the ＇Structure of Earnings Survey - Administrative Data Project＇ （SESADP）. The result of the project was the creation of datasets and statistical outputs for the years 2011 to 2014 to meet Eurostat＇s annual earnings statistics requirements and the Structure of Earnings Survey （SES） Regulation. Record linking across the Census and various public sector datasets enabled the necessary information to be acquired to meet the Eurostat earnings requirements. However, the risk of statistical disclosure （i.e. identifying an individual on the dataset） is high unless privacy and confidentiality safe-guards are built into the data matching process. This paper looks at the three methods of linking records on big datasets employed on the SESADP, and how to anonymise the data to protect the identity of the individuals, where potentially disclosive variables exist.展开更多
The data used in the process of knowledge discovery often includes noise and incomplete information. The boundaries of different classes of these data are blur and unobvious. When these data are clustered or classifie...The data used in the process of knowledge discovery often includes noise and incomplete information. The boundaries of different classes of these data are blur and unobvious. When these data are clustered or classified, we often get the coverings instead of the partitions, and it usually makes our information system insecure. In this paper, optimal partitioning of incomplete data is researched. Firstly, the relationship of set cover and set partition is discussed, and the distance between set cover and set partition is defined. Secondly, the optimal partitioning of given cover is researched by the combing and parting method, acquiring the optimal partition from three different partitions set family is discussed. Finally, the corresponding optimal algorithm is given. The real wireless signals offten contain a lot of noise, and there are many errors in boundaries when these data is clustered based on the tradional method. In our experimant, the proposed method improves correct rate greatly, and the experimental results demonstrate the method's validity.展开更多
Recently, approaches utilizing spatial-temporal features to form Bag-of-Words （BoWs） models have achieved great success due to their simplicity and effectiveness. But they still have difficulties when distinguishing...Recently, approaches utilizing spatial-temporal features to form Bag-of-Words （BoWs） models have achieved great success due to their simplicity and effectiveness. But they still have difficulties when distinguishing between actions with high inter-ambiguity. The main reason is that they describe actions by orderless bag of features, and ignore the spatial and temporal structure information of visual words. In order to improve classification performance, we present a novel approach called sequential Bag-of-Words. It captures temporal sequential structure by segmenting the entire action into sub-actions. Meanwhile, we pay more attention to the distinguishing parts of an action by classifying sub- actions separately, which is then employed to vote for the final result. Extensive experiments are conducted on challenging datasets and real scenes to evaluate our method. Concretely, we compare our results to some state-of-the-art classification approaches and confirm the advantages of our approach to distinguish similar actions. Results show that our approach is robust and outperforms most existing BoWs based classification approaches, especially on complex datasets with interactive activities, cluttered backgrounds and inter-class action ambiguities.展开更多
Pattern discovery from time series is of fundamental importance. Most of the algorithms of pattern discovery in time series capture the values of time series based on some kinds of similarity measures. Affected by the...Pattern discovery from time series is of fundamental importance. Most of the algorithms of pattern discovery in time series capture the values of time series based on some kinds of similarity measures. Affected by the scale and baseline, value-based methods bring about problem when the objective is to capture the shape. Thus, a similarity measure based on shape, Sh measure, is originally proposed, andthe properties of this similarity and corresponding proofs are given. Then a time series shape pattern discovery algorithm based on Sh measure is put forward. The proposed algorithm is terminated in finite iteration with given computational and storage complexity. Finally the experiments on synthetic datasets and sunspot datasets demonstrate that the time series shape pattern algorithm is valid.展开更多
Since the early 1990, significant progress in database technology has provided new platform for emerging new dimensions of data engineering. New models were introduced to utilize the data sets stored in the new genera...Since the early 1990, significant progress in database technology has provided new platform for emerging new dimensions of data engineering. New models were introduced to utilize the data sets stored in the new generations of databases. These models have a deep impact on evolving decision-support systems. But they suffer a variety of practical problems while accessing real-world data sources. Specifically a type of data storage model based on data distribution theory has been increasingly used in recent years by large-scale enterprises, while it is not compatible with existing decision-support models. This data storage model stores the data in different geographical sites where they are more regularly accessed. This leads to considerably less inter-site data transfer that can reduce data security issues in some circumstances and also significantly improve data manipulation transactions speed. The aim of this paper is to propose a new approach for supporting proactive decision-making that utilizes a workable data source management methodology. The new model can effectively organize and use complex data sources, even when they are distributed in different sites in a fragmented form. At the same time, the new model provides a very high level of intellectual management decision-support by intelligent use of the data collections through utilizing new smart methods in synthesizing useful knowledge. The results of an empirical study to evaluate the model are provided.展开更多
基金Funded by the National 973 Program of China (No.2003CB415205)the National Natural Science Foundation of China (No.40523005, No.60573183, No.60373019)the Open Research Fund Program of LIESMARS (No.WKL(04)0303).
文摘Spatial objects have two types of attributes： geometrical attributes and non-geometrical attributes, which belong to two different attribute domains （geometrical and non-geometrical domains）. Although geometrically scattered in a geometrical domain, spatial objects may be similar to each other in a non-geometrical domain. Most existing clustering algorithms group spatial datasets into different compact regions in a geometrical domain without considering the aspect of a non-geometrical domain. However, many application scenarios require clustering results in which a cluster has not only high proximity in a geometrical domain, but also high similarity in a non-geometrical domain. This means constraints are imposed on the clustering goal from both geometrical and non-geometrical domains simultaneously. Such a clustering problem is called dual clustering. As distributed clustering applications become more and more popular, it is necessary to tackle the dual clustering problem in distributed databases. The DCAD algorithm is proposed to solve this problem. DCAD consists of two levels of clustering： local clustering and global clustering. First, clustering is conducted at each local site with a local clustering algorithm, and the features of local clusters are extracted clustering is obtained based on those features fective and efficient. Second, local features from each site are sent to a central site where global Experiments on both artificial and real spatial datasets show that DCAD is effective and efficient.
文摘Privacy protection for big data linking is discussed here in relation to the Central Statistics Office （CSO）, Ireland＇s, big data linking project titled the ＇Structure of Earnings Survey - Administrative Data Project＇ （SESADP）. The result of the project was the creation of datasets and statistical outputs for the years 2011 to 2014 to meet Eurostat＇s annual earnings statistics requirements and the Structure of Earnings Survey （SES） Regulation. Record linking across the Census and various public sector datasets enabled the necessary information to be acquired to meet the Eurostat earnings requirements. However, the risk of statistical disclosure （i.e. identifying an individual on the dataset） is high unless privacy and confidentiality safe-guards are built into the data matching process. This paper looks at the three methods of linking records on big datasets employed on the SESADP, and how to anonymise the data to protect the identity of the individuals, where potentially disclosive variables exist.
基金Supported by the National Natural Science Foundation of China (No. 61273302)partially by the Natural Science Foundation of Anhui Province (No. 1208085MF98, 1208085MF94)
文摘The data used in the process of knowledge discovery often includes noise and incomplete information. The boundaries of different classes of these data are blur and unobvious. When these data are clustered or classified, we often get the coverings instead of the partitions, and it usually makes our information system insecure. In this paper, optimal partitioning of incomplete data is researched. Firstly, the relationship of set cover and set partition is discussed, and the distance between set cover and set partition is defined. Secondly, the optimal partitioning of given cover is researched by the combing and parting method, acquiring the optimal partition from three different partitions set family is discussed. Finally, the corresponding optimal algorithm is given. The real wireless signals offten contain a lot of noise, and there are many errors in boundaries when these data is clustered based on the tradional method. In our experimant, the proposed method improves correct rate greatly, and the experimental results demonstrate the method's validity.
文摘Recently, approaches utilizing spatial-temporal features to form Bag-of-Words （BoWs） models have achieved great success due to their simplicity and effectiveness. But they still have difficulties when distinguishing between actions with high inter-ambiguity. The main reason is that they describe actions by orderless bag of features, and ignore the spatial and temporal structure information of visual words. In order to improve classification performance, we present a novel approach called sequential Bag-of-Words. It captures temporal sequential structure by segmenting the entire action into sub-actions. Meanwhile, we pay more attention to the distinguishing parts of an action by classifying sub- actions separately, which is then employed to vote for the final result. Extensive experiments are conducted on challenging datasets and real scenes to evaluate our method. Concretely, we compare our results to some state-of-the-art classification approaches and confirm the advantages of our approach to distinguish similar actions. Results show that our approach is robust and outperforms most existing BoWs based classification approaches, especially on complex datasets with interactive activities, cluttered backgrounds and inter-class action ambiguities.
文摘Pattern discovery from time series is of fundamental importance. Most of the algorithms of pattern discovery in time series capture the values of time series based on some kinds of similarity measures. Affected by the scale and baseline, value-based methods bring about problem when the objective is to capture the shape. Thus, a similarity measure based on shape, Sh measure, is originally proposed, andthe properties of this similarity and corresponding proofs are given. Then a time series shape pattern discovery algorithm based on Sh measure is put forward. The proposed algorithm is terminated in finite iteration with given computational and storage complexity. Finally the experiments on synthetic datasets and sunspot datasets demonstrate that the time series shape pattern algorithm is valid.
文摘Since the early 1990, significant progress in database technology has provided new platform for emerging new dimensions of data engineering. New models were introduced to utilize the data sets stored in the new generations of databases. These models have a deep impact on evolving decision-support systems. But they suffer a variety of practical problems while accessing real-world data sources. Specifically a type of data storage model based on data distribution theory has been increasingly used in recent years by large-scale enterprises, while it is not compatible with existing decision-support models. This data storage model stores the data in different geographical sites where they are more regularly accessed. This leads to considerably less inter-site data transfer that can reduce data security issues in some circumstances and also significantly improve data manipulation transactions speed. The aim of this paper is to propose a new approach for supporting proactive decision-making that utilizes a workable data source management methodology. The new model can effectively organize and use complex data sources, even when they are distributed in different sites in a fragmented form. At the same time, the new model provides a very high level of intellectual management decision-support by intelligent use of the data collections through utilizing new smart methods in synthesizing useful knowledge. The results of an empirical study to evaluate the model are provided.
