Search

This paper presents work to support collaborative visualisation and data analysis in the microarray time-series explorer (MaTSE) software. We introduce a novel visualisation component called the `pattern browser΄ which is used to support the annotation and adjustment of user queries. This includes an explanation of why this component is required and how it can be used with our online pattern repository by biologists collaborating in the analysis of a microarray time-course data set. To conclude we suggest which other types of collaborative visualisation would benefit from the introduction of a component with comparable functionality. [ABSTRACT FROM AUTHOR]

Despite the success that Component-Based Development has achieved so far, component mismatch remains as a major hurdle for wider and smoother component reuse due to the lack of effective and automated approaches to component specification and retrieval. This paper presents a novel ontology-based approach to solve the above problem via holistic, semantic-based and adaptation-aware component specification and retrieval. The Multiple-Viewed and Interrelated Component Specification ontology model (MVICS) provides an ontology based architecture to specify components in a spectrum of perspectives. A semantic-based component retrieval method is then developed and the result of retrieval is presented to CBD engineers in a comprehensive component matching profile. Uniquely, the effect of possible component adaptation is included in the MVICS model and associated component specification and retrieval, which enables a more systematic and holistic view in component specification and selection. [ABSTRACT FROM AUTHOR]

All aspects of organismal biology rely on the accurate identification of specimens described and observed. This is particularly important for ecological surveys of biodiversity, where organisms must be identified and labelled, both for the purposes of the original research, but also to allow reinterpretation or reuse of collected data by subsequent research projects. Yet it is now clear that biological names in isolation are unsuitable as unique identifiers for organisms. Much modern research in ecology is based on the integration (and re-use) of multiple datasets which are inherently complex, reflecting any of the many spatial and temporal environmental factors and organismal interactions that contribute to a given ecosystem. We describe visualization tools that aid in the process of building concept relations between related classifications and then in understanding the effects of using these relations to match across sets of classifications. [ABSTRACT FROM AUTHOR]

Efficient evaluation of queries on XML data is a major research issue. Structural join based techniques are well known for XPath evaluation. For the long path expressions, join techniques are not efficient as they increase the number of joins and disk I/O cost. Path based techniques try to reduce the number of joins. In this paper, we propose a metadata guided query evaluation technique which uses path based storage. We use interval encoding for the nodes. In addition, we use Strong DataGuide to assign integer path labels to distinct root-to-node label paths in the data tree. An element list is maintained for each distinct path consisting of nodes that can be reached by that path. The Element-Map gives the one-to-many mapping between element names (or tag names) to element lists with nodes having that tag-name. The Path-Map gives the root-to-leaf path for a given path label. Using these structures, we can combine top-down path matching and bottom-up path selections to efficiently evaluate linear path expressions. For twig queries, we perform structural joins at branch points. Through experimental evaluation on standard datasets, we show that our approach outperforms the existing path-index based approaches which in turn outperform structural join methods. [ABSTRACT FROM AUTHOR]

We present a new approach for accelerating the execution of XPath expressions using parameterized materialized XPath views (PXV). While the approach is generic we show how it can be utilized in an XML extension for relational database systems. Furthermore we discuss an algorithm for automatically determining the best PXV candidates to materialize based on a given workload. We evaluate our approach and show the superiority of our cost based algorithm for determining PXV candidates over frequent pattern based algorithms. [ABSTRACT FROM AUTHOR]

Many distributed data mining DDM tasks such as distributed association rules and distributed classification have been proposed and developed in the last few years. However, only a few research concerns distributed clustering for analysing large, heterogeneous and distributed datasets. This is especially true with distributed density-based clustering although the centralised versions of the technique have been widely used fin different real-world applications. In this paper, we present a new approach for distributed density-based clustering. Our approach is based on two main concepts: the extension of local models created by DBSCAN at each node of the system and the aggregation of these local models by using tree based topologies to construct global models. The preliminary evaluation shows that our approach is efficient and flexible and it is appropriate with high density datasets and a moderate difference in dataset distributions among the sites. [ABSTRACT FROM AUTHOR]

Mining Fault-Tolerant (FT) Frequent Patterns in real world (dirty) databases is considered to be a fruitful direction for future data mining research. In last couple of years a number of different algorithms have been proposed on the basis of Apriori-FT frequent pattern mining concept. The main limitation of these existing FT frequent pattern mining algorithms is that, they try to find all FT frequent patterns without considering only useful long (maximal) patterns. This not only increases the processing time of mining process but also generates too many redundant short FT frequent patterns that are un-useful. In this paper we present a novel concept of mining only maximal (long) useful FT frequent patterns. For mining such patterns algorithm we introduce a novel depth first search algorithm Max-FTP (Maximal Fault-Tolerant Frequent Pattern Mining), with its various search space pruning and fast frequency counting techniques. Our different extensive experimental result on benchmark datasets show that Max-FTP is very efficient in filtering un-interesting FT patterns and execution as compared to Apriori-FT. [ABSTRACT FROM AUTHOR]

Information Extraction, the process of eliciting data from natural language documents, usually relies on the ability to parse the document and then to detect the meaning of the sentences by exploiting the syntactic structures encountered. In previous papers, we have discussed an application to extract information from short (e-mail and text) messages which takes an alternative approach. The application is lightweight and uses pattern matching rather than parsing, since parsing is not feasible for messages in which both the syntax and the spelling are unreliable. The application works in the context of a high level database schema and identifies sentences which make statements about data describable by this schema. The application matches sentences with templates to identify metadata terms and the data values associated with them. However, the initial prototype could only manage simple, time independent assertions about the data, such as "Jane Austen is the author." This paper describes an extension to the application which can extract temporal data, both time instants and time periods. It also manages time stamps - temporal information which partitions the values of time varying attributes, such as the monarch of a country. In order to achieve this, the original data model has had to be extended with a temporal component and a set of sentence templates has been constructed to recognise statements in this model. The paper describes the temporal model and the extensions to the application, concluding with a worked example. [ABSTRACT FROM AUTHOR]

A practical approach for developing fine-grained access control (FGAC) for database management systems is reported in this paper. We extend SQL language to support security policies. The concept of the policy type for databases is proposed. We implement the policy reuse through the use of policy types and policy instances to alleviate the administration workload of maintaining security policies. The policies for rows and columns can be expressed with policy types. Moreover, complicated database integrity constraints can also be expressed by policy types, and no further purpose-built programs are needed to create specific security control policies. We implement the fine-grained access control in a relational database management system DM5 [4]. The performance test results based on TPC-W are also presented. [ABSTRACT FROM AUTHOR]

K-anonymisation is a technique for protecting privacy contained within a dataset. Many k-anonymisation algorithms have been proposed, and one class of such algorithms are clustering-based. These algorithms can offer high quality solutions, but are rather inefficient to execute. In this paper, we propose a method that partitions a dataset into groups first and then clusters the data within each group for k-anonymisation. Our experiments show that combining partitioning with clustering can improve the performance of clustering-based k-anonymisation algorithms significantly while maintaining the quality of anonymisations they produce. [ABSTRACT FROM AUTHOR]

When distributed databases are developed independently, they may be semantically heterogeneous with respect to data granularity, scheme information and the embedded semantics. However, most traditional distributed knowledge discovery (DKD) methods assume that the distributed databases derive from a single virtual global table, where they share the same semantics and data structures. This data heterogeneity and the underlying semantics bring a considerable challenge for DKD. In this paper, we propose a model-based clustering method for aggregate databases, where the heterogeneous schema structure is due to the heterogeneous classification schema. The underlying semantics can be captured by different clusters. The clustering is carried out via a mixture model, where each component of the mixture corresponds to a different virtual global table. An advantage of our approach is that the algorithm resolves the heterogeneity as part of the clustering process without previously having to homogenise the heterogeneous local schema to a shared schema. Evaluation of the algorithm is carried out using both real and synthetic data. Scalability of the algorithm is tested against the number of databases to be clustered; the number of clusters; and the size of the databases. The relationship between performance and complexity is also evaluated. Our experiments show that this approach has good potential for scalable integration of semantically heterogeneous databases. [ABSTRACT FROM AUTHOR]

We investigate XML query processing in a portable/handheld client device with limited memory in ubiquitous computing environment. Because of memory limitation in the client, the source XML data possibly of large volume is fragmented in the server and streamed in fragments over which query processing is done in the client. The state-of-the-art techniques employ the hole-filler model in fragmenting XML data and processing queries over XML fragment stream. In this paper, we propose a new technique where an XML labeling scheme is employed instead of the hole-filler model. Through preliminary experiments, we show that our technique outperforms the state-of-the-art techniques both in memory usage and in query processing time. [ABSTRACT FROM AUTHOR]

One problem exists in current substructure mining algorithms is that when the sizes of molecular structure databases increase, the costs in terms of both time and space increase to a level that normal PCs are not powerful enough to perform substructure data mining tasks. After examining a number of well known molecular structure databases, we found that there exist a large number of common loop substructures within molecular structure databases, and repeatedly mining these same substructures costs the system resources significantly. In this paper, we introduce a new method: (1) to treat these common loop substructures as some kinds of "atom" structures; (2) to maintain the links of the new "atom" structures with the rest of the molecular structures, and to reorganize the original molecular structures. Therefore we avoid repeat many same operations during mining process and produce less redundant results. We tested the method using four real molecular structure databases: AID2DA'99/CA, AID2DA'99/CM, AID2DA'99 and NCI'99. The results indicated that (1) the speed of substructure mining has been improved due to the reorganization; (2) the number of patterns obtained by mining has been reduced with less redundant information. [ABSTRACT FROM AUTHOR]

Spreadsheets such as Microsoft Excel are OLAP(On-Line Analytical Processing) [2] applications to easily analyze complex multidimensional data. In general, spreadsheets provide grid-like graphical interfaces together with various chart tools [4,5]. However, previous work on OLAP spreadsheets adopts a naive approach that directly retrieves, transmits, and presents all the resulting data at once. Thus, it is difficult to use the previous work for very large relational tables with millions of rows or columns due to the communication and space overhead. [ABSTRACT FROM AUTHOR]

Whenever mobile ad-hoc networks are used as a large data storage, a huge number of queries requesting the same information again and again can slow down the network and drain battery power. In this paper, we introduce an example application, the query classes that are required to be supported, and show up two possible caching methods. The two caching methods are based on the concept of query shipping and data shipping, respectively. Since our caching strategies can be used simultaneously, the decision for doing data shipping depends among other aspects on the overhead of transferred data. We explain why an XML Query Result Size Estimator can assist the application in the question of which mechanism should be used for a certain query, and point to other related estimation techniques. [ABSTRACT FROM AUTHOR]