Representing uncertain data: models, properties, and algorithms

Sarma, Anish Das; Benjelloun, Omar; Halevy, Alon; Nabar, Shubha U.; Widom, Jennifer

doi:10.1007/s00778-009-0147-0

Cited by 60 publications

(37 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In dealing with uncertainty in the databases domain, a lot of previous work has been done [1]- [6]. In probabilistic databases, the attribute-wise uncertainty is represented with a set of discrete values with separate probabilities or a random variable with a probabilistic density function (PDF) [7].…”

Section: Related Workmentioning

confidence: 99%

Uncertainty Handling in a Tabular Representation

Li¹,

Chen²,

Feng³

2015

IJIET

View full text Add to dashboard Cite

Abstract-Nowadays a lot of uncertainty appears due to the burst of data on the internet. This challenges the traditional data processing methods because of its volume and variety. Such uncertainty is hard to be represented in simply continuous distribution functions when it is too hard or complicated to be obtained. Considering the realistic situations that people may be interested in queries falling into a scope rather than a specific value, we present a new data model, called N-DB model, where the attribute value is represented with a tabular form in an increasing order, denoted N-table (i.e., a set of ordered pairs). This model can deal with queries in a scope efficiently, such as "movies with reputation level bigger than 5". We modify the relational algebra, including the aggregation query, and show the query processing in a running example. We also define an uncertain measurement (-precision) to measure the precision and information of the N-table, which can be used in the computation of precision requirements. Through experimental results, we find queries can be evaluated efficiently by searching in the N-tables, and are returned with confidence intervals.

show abstract

Section: Related Workmentioning

confidence: 99%

Uncertainty Handling in a Tabular Representation

Li¹,

Chen²,

Feng³

2015

IJIET

View full text Add to dashboard Cite

show abstract

“…Sarma et al [20] describes various models of uncertainty, varying from the simplest basic model to the (very expensive) complete model that can describe any probability distribution of data instances.…”

Section: Background and State Of The Artmentioning

confidence: 99%

“…Existing work on histograms on uncertain data [5][6][7] adopted two popular models that extend the basic model, i.e., the tuple model and the value model, and compared their properties and descriptive abilities. The tuple and value models are two common extensions of the basic model in terms of the tuple-and attribute-level uncertainty [20], that were extensively used in the literature (see discussion in [5][6][7]). …”

Section: Background and State Of The Artmentioning

confidence: 99%

Scalable histograms on large probabilistic data

Tang

2014

Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Histogram construction is a fundamental problem in data management, and a good histogram supports numerous mining operations. Recent work has extended histograms to probabilistic data [5][6][7]. However, constructing histograms for probabilistic data can be extremely expensive, and existing studies suffer from limited scalability [5][6][7]. This work designs novel approximation methods to construct scalable histograms on probabilistic data. We show that our methods provide constant approximations compared to the optimal histograms produced by the state-of-the-art in the worst case. We also extend our methods to parallel and distributed settings so that they can run gracefully in a cluster of commodity machines. We introduced novel synopses to reduce communication cost when running our methods in such settings. Extensive experiments on large real data sets have demonstrated the superb scalability and efficiency achieved by our methods, when compared to the state-ofthe-art methods. They also achieved excellent approximation quality in practice.

show abstract

“…Sarma et al [28] describe various models of uncertainty. We consider the attribute-level uncertain tuple that has been used frequently in the literature, and suits the applications for our problem well (e.g., data in SAMOS).…”

Section: Problem Formulationmentioning

confidence: 99%

Efficient Threshold Monitoring for Distributed Probabilistic Data

Tang

Phillips

et al. 2012

2012 IEEE 28th International Conference on Data Engineering

View full text Add to dashboard Cite

Abstract-In distributed data management, a primary concern is monitoring the distributed data and generating an alarm when a user specified constraint is violated. A particular useful instance is the threshold based constraint, which is commonly known as the distributed threshold monitoring problem . This work extends this useful and fundamental study to distributed probabilistic data that emerge in a lot of applications, where uncertainty naturally exists when massive amounts of data are produced at multiple sources in distributed, networked locations. Examples include distributed observing stations, large sensor fields, geographically separate scientific institutes/units and many more. When dealing with probabilistic data, there are two thresholds involved, the score and the probability thresholds. One must monitor both simultaneously, as such, techniques developed for deterministic data are no longer directly applicable. This work presents a comprehensive study to this problem. Our algorithms have significantly outperformed the baseline method in terms of both the communication cost (number of messages and bytes) and the running time, as shown by an extensive experimental evaluation using several, real large datasets.

show abstract

Representing uncertain data: models, properties, and algorithms

Cited by 60 publications

References 48 publications

Uncertainty Handling in a Tabular Representation

Uncertainty Handling in a Tabular Representation

Scalable histograms on large probabilistic data

Efficient Threshold Monitoring for Distributed Probabilistic Data

Contact Info

Product

Resources

About