H-MRST: A Novel Framework for Support Uncertain Data Range Query Using ELM

Probabilistic distance based abnormal pattern detection in uncertain series data

Nowadays, high volumes of valuable uncertain data can be easily collected or generated at high velocity in many real-life applications. Mining these uncertain Big data is computationally intensive due to the presence of existential probability values associated with items in every transaction in the uncertain data. Each existential probability value expresses the likelihood of that item to be present in a particular transaction in the Big data. In some situations, users may be interested in mining all frequent patterns from these uncertain Big data; in other situations, users may be interested in only a tiny portion of these mined patterns. To reduce the computation and to focus the mining for the latter situations, we propose a tree-based algorithm that (i) allows users to express the patterns to be mined according to their intention via the use of constraints and (ii) uses MapReduce to mine uncertain Big data for only those frequent patterns that satisfy user-specified constraints. Experimental results show the effectiveness of our algorithm in mining probabilistic databases of uncertain Big data.

Query processing over uncertain data has gained growing attention, because it is necessary to deal with uncertain data in many real-life applications. In this paper, we investigate skyline queries over uncertain data in distributed environments (DSUD query) whose research is only in an early stage. The state-of-the-art algorithm, called e-DSUD algorithm, is designed for processing this query. It has the desirable characteristics of progressiveness and minimum bandwidth consumption. However, it still needs to be perfected in three aspects. (1) Progressiveness. Each time it only returns one query result at most. (2) Efficiency. There are a significant amount of redundant I/O cost and numerous iterations which causes a long total query time. (3) Universality. It is restricted to the case where local skyline tuples are incomparability. To address these concerns, we first present a detailed analysis of the e-DSUD algorithm and then develop an improved framework for the DSUD query, namely IDSUD. Based on the new framework, we propose an adaptive algorithm, called ADSUD, for the DSUD query. In the algorithm, we redefine the approximate global skyline probability and choose local representative tuples due to minimum probabilistic bounding rectangle adaptively. Furthermore, we design a progressive pruning method and apply the reuse mechanism to improve its efficiency. The results of extensive experiments verify the better overall performance of our algorithm than the e-DSUD algorithm.

Uncertainty-aware twin support vector machines

Uncertain data has emerged as a key data type in many applications. New and efficient query processing techniques need to be developed due to the inherent complexity of this new type of data. In this paper, we investigate a special type of query, range queries, on uncertain data. We propose a threshold interval indexing structure that aims to balance different time consuming factors to achieve an optimal overall query performance. We also present a more efficient version of our structure which loads its primary tree into memory for faster processing. Experimental results are presented to justify the efficiency of the proposed query processing technique.

The technique of outlier detection is useful in many real world applications such as detection of network intrusion. It has been studied intensively on deterministic data. However, it is still a novel research field on uncertain data. To our best knowledge, this paper is the firstone to focus on distance-based outlier detection on uncertain data, in which each data is affiliated with a certain confidence value. In this paper, we propose a new definition of outlier on uncertain data. Based on the properties we discovered, both dynamic programming approach (DPA) and grid-based pruning approach(GPA) are used for detecting outliers on uncertain dataefficiently. Detailed analysis and thorough experimental results demonstrate the efficiency and scalability of our method.

Data uncertainty is ubiquitous in real-world applications, and the number of variables such as imprecise estimation, network latency, obsolete sources, and sampling errors leads to data uncertainty. It is important to carefully deal with this kind of ambiguity, or else the mining results might be inaccurate or even incorrect. We have therefore used a new method called bagging and boosting algorithms for decision tree for the classification and prediction algorithm. As a model of sequential decision problems under uncertainty, a decision tree may be used. To manage data with uncertain information, classifiers are used. To deal with data confusion, we primarily use the PDF distribution method. It is the method in which the complete data are carried out by the distributions of probability to construct a decision tree. Supply these values to the decision tree by calculating the PDF and accordingly generate the decision tree, and on the other hand, supply the bagging and boosting algorithms with PDF and then compare both outcomes. Bagging is one of the well-known techniques of the ensemble, which constructs data bags with the same class mark and the same probability of the original data collection. More complex strategies, such as boosting the distribution of the sample, rely on how difficult it is to identify each sample. Instead of abstracting unknown data by statistical derivatives, if we use the probability density function (PDF) distribution, the accuracy of a decision tree can be much better. The dataset is initially provided to the PDF generation in our project, we provide it to the bagging and boosting algorithm in the next stage instead of giving it directly to the decision tree, then, the generated dataset is given to the decision tree, and then, the classification is carried out.KeywordsBaggingBoostingNumerical uncertain dataDecision treeClassifiersEnsemblesRandom forestANN

We study coresets for various types of range counting queries on uncertain data. In our model each uncertain point has a probability density describing its location, sometimes defined as k distinct locations. Our goal is to construct a subset of the uncertain points, including their locational uncertainty, so that range counting queries can be answered by just examining this subset. We study three distinct types of queries. RE queries return the expected number of points in a query range. RC queries return the number of points in the range with probability at least a threshold. RQ queries returns the probability that fewer than some threshold fraction of the points are in the range. In both RC and RQ coresets the threshold is provided as part of the query. And for each type of query we provide coreset constructions with approximation-size tradeoffs. We show that random sampling can be used to construct each type of coreset, and we also provide significantly improved bounds using discrepancy-based approaches on axis-aligned range queries.

Aiming at the problem of passive detection of broadband sources in underwater acoustic vector signal processing, a novel detection algorithm based on beam-space transformation is proposed. The principle of spatial spectrum detection with human eyes is employed for reflerence, and the generalized likelihood ratio test (GLRT) is applied to the beam-space. First, the design criterion of beam-space transformation matrix is studied for the compreflensive consideration of the environment of multiple targets and the characteristic of vector ambient noise field, so that the analytical solution is obtained. Second, assuming that the number of beams not containing the target signal is given, the probability density function (PDF) model of beam-space data is constructed, and the new GLR test is made by calculating the maximum likelihood estimate of the unknown variables in PDF. Finally, the information of theoretical criterion is adopted in order to estimate the number of beams not containing target signals. The processing gain and the threshold value of this test statistics are also discussed, and the specific implement is explained in detail. Theoretical analysis and simulation results show that under the complex conditions of strong target interference and ambient noise with undulated and time-variant power spectrum, the proposed algorithm can give the processing result with higher gain and detection threshold at constant false alarm rate (CFAR); the results of lake experiment further prove the favorable and robust detection performance.

With the increasing popularity of the peer-to-peer (P2P) computing paradigm, many general range query schemes for distributed hash table (DHT)-based P2P systems have been proposed in recent years. Although those schemes can provide range query capability without modifying the underlying DHTs, they have the query delay depending on both the scale of the system and the size of the query space or the specific query, and thus cannot guarantee to return the query results in a bounded delay. In this paper, we propose Armada, an efficient range query processing scheme to support delay-bounded single-attribute and multiple-attribute range queries. It is the first delay-bounded general range query scheme on constant-degree DHTs, and can return the results for any range query within 2logN hops in a P2P system with N peers. Results of analysis and simulations show that the average delay in Armada is less than logN, and the average message cost of single-attribute range queries is about logN+2n 2 (n is the number of peers that intersect with the query). These results are very close to the lower bounds on delay and message cost of range queries over constant-degree DHTs.

An important database primitive for commonly used feature databases is the similarity join. It combines two datasets based on some similarity predicate into one set such that the new set contains pairs of objects of the two original sets. In many different application areas, e.g. sensor databases, location based services or face recognition systems, distances between objects have to be computed based on vague and uncertain data. In this paper, we propose to express the similarity between two uncertain objects by probability density functions which assign a probability value to each possible distance value. By integrating these probabilistic distance functions directly into the join algorithms the full information provided by these functions is exploited. The resulting probabilistic similarity join assigns to each object pair a probability value indicating the likelihood that the object pair belongs to the result set. As the computation of these probability values is very expensive, we introduce an efficient join processing strategy exemplarily for the distance-range join. In a detailed experimental evaluation, we demonstrate the benefits of our probabilistic similarity join. The experiments show that we can achieve high quality join results with rather low computational cost.

Improving classification accuracy on uncertain data by considering multiple subclasses

As the low-power sensor nodes are limited in computing competency and storage space and wireless sensor network features in lower bandwidth and higher channel error ratio, energy-efficient range-querying methods to privately protect multidimensional data are proposed with two-layer wireless sensor network taken as the research object. Based on the pre-shared key mechanism and Diffie-Hellman key exchange protocol, the key management mechanism of symmetric encryption algorithm is designed, and the confidentiality of data transmission and storage is realized on the basis of lightweight data encryption algorithms, such as AES and RC6; The multidimensional data's time-property of two-dimensional characteristic defined by formalization divides the storage structure of the privacy data included in sensor network into many two-dimensional subspaces according to the attribute and the collection time period of data, so as to achieve the storage of multidimensional collected data; Based on the approach of order-preserving function as well as Cramer's Rule working out polynomial, the range query of the multidimensional data for two-layer sensor network, without revealing privacy information, is accurately finished with the improvement the of energy consumption efficiency; The methods, the encryption chain formed by the neighbor data items and the code set encoded by reconstructed order-preserving, are adopted to respond to the attack by part returning query results, in order to verify integrity of search results. Fine-grained access control and anonymous access of the query are realized with taking the k-threshold strategy in the Sahai scheme as reference, and employing the attribute base encryption algorithm, attribute certificate, digital signature as well as threshold mechanism. Both theoretical analysis and experimental results show that this method privately protects perception data, query results and target ranges, and boasts higher energy efficiency than the existing methods.

As an important data mining and knowledge discovery task, association rule mining searches for implicit, previously unknown, and potentially useful pieces of information—in the form of rules revealing associative relationships—that are embedded in the data. In general, the association rule mining process comprises two key steps. The first key step, which mines frequent patterns (i.e., frequently occurring sets of items) from data, is more computationally intensive than the second key step of using the mined frequent patterns to form association rules. In the early days, many developed algorithms mined frequent patterns from traditional transaction databases of precise data such as shopping market basket data, in which the contents of databases are known. However, we are living in an uncertain world, in which uncertain data can be found almost everywhere. Hence, in recent years, researchers have paid more attention to frequent pattern mining from probabilistic databases of uncertain data. In this paper, we review recent algorithmic development on mining uncertain data in these probabilistic databases for frequent patterns. © 2011 John Wiley & Sons, Inc. WIREs Data Mining Knowl Discov 2011 1 316–329 DOI: 10.1002/widm.31This article is categorized under: Algorithmic Development > Association Rules

Large databases with uncertainty became more common in many applications. Ranking queries are essential tools to process these databases and return only the most relevant answers of a query, based on a scoring function. Many approaches were proposed to study and analyze the problem of efficiently answering such ranking queries. Managing distributed uncertain database is also an important issue. In fact ranking queries in such systems are an open challenge. The main objective of this paper is to discuss ranking in distributed uncertain database along with its issued problems. Starting with uncertain data representation, query processing and query types in such systems are discussed along with their challenges and open research area. Top-k query is presented with its properties, as a ranking technique in uncertain data environment, mentioning distributed top-k and distributed ranking problems.