Efficient index-based KNN join processing for high-dimensional data

Chen, Yu; Cui, Bin; Wang, Shuguang; Su, Jianwen

doi:10.1016/j.infsof.2006.05.006

Cited by 75 publications

(61 citation statements)

References 20 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However we leverage off related ideas in the literature [20][48] [116]. In particular, the iDistance method of Jagadish et al [48] introduces the idea of projecting data on to a single line, a core subroutine in our algorithm.…”

Section: Related Workmentioning

confidence: 99%

Exact Primitives for Time Series Data Mining

Mueen

2012

Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Exact Primitives for Time Series Data Mining

Mueen

2012

Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

“…The maximum of these distances is now used to extend the minimum bounding rectangle around the query set and thus, describes the current pruning area. In [11], a kNN join algorithm based on the similarity search method iDistance [12] is proposed. The paper describes a basic algorithm called iJoin extending iDistance to the kNN join problem.…”

Section: Related Workmentioning

confidence: 99%

Optimizing All-Nearest-Neighbor Queries with Trigonometric Pruning

Emrich

Graf

Kriegel

et al. 2010

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Many applications require to determine the k-nearest neighbors for multiple query points simultaneously. This task is known as all-(k)-nearest-neighbor (AkNN) query. In this paper, we suggest a new method for efficient AkNN query processing which is based on spherical approximations for indexing and query set representation. In this setting, we propose trigonometric pruning which enables a significant decrease of the remaining search space for a query. Employing this new pruning method, we considerably speed up AkNN queries.

show abstract

“…However we leverage off related ideas in the literature (Gonzalez et al 2008;Jagadish et al 2005;Yu and Wang 2007). In particular, the iDistance method of Jagadish et al (2005) introduces the idea of projecting data on to a single line, a core subroutine in our algorithm.…”

Section: Related Workmentioning

confidence: 99%

“…However they use this information to solve the approximate similarity search problem, whereas we use it to solve the exact closest-pair problem. In Jagadish et al (2005) and Yu and Wang (2007), Reference objects have been used for each partition of a B+ tree index which is adapted for different data distribution. However, we use only one reference object to do the data ordering.…”

Section: Related Workmentioning

confidence: 99%

“…While we exploit similar ideas, the design of the index is less useful for the closestpair problem because of data replication and parameter setting described previously. Both Jagadish et al (2005) and Yu and Wang (2007) use the idea of pivots to do K-nearest neighbor search, and report approximately one order of magnitude speedup over brute force. However we use the idea of pivots for motif discovery and report four to five orders or magnitude.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A disk-aware algorithm for time series motif discovery

Mueen

Keogh

Zhu

et al. 2010

Data Min Knowl Disc

View full text Add to dashboard Cite

Time series motifs are sets of very similar subsequences of a long time series. They are of interest in their own right, and are also used as inputs in several higher-level data mining algorithms including classification, clustering, rule-discovery and summarization. In spite of extensive research in recent years, finding time series motifs exactly in massive databases is an open problem. Previous efforts either found approximate motifs or considered relatively small datasets residing in main memory. In this work, we leverage off previous work on pivot-based indexing to introduce a disk-aware algorithm to find time series motifs exactly in multi-gigabyte databases which contain on the order of tens of millions of time series. We have evaluated our algorithm on datasets from diverse areas including medicine, anthropology, computer networking and image processing and show that we can find interesting and meaningful motifs in datasets that are many orders of magnitude larger than anything considered before.

show abstract

Efficient index-based KNN join processing for high-dimensional data

Cited by 75 publications

References 20 publications

Exact Primitives for Time Series Data Mining

Exact Primitives for Time Series Data Mining

Optimizing All-Nearest-Neighbor Queries with Trigonometric Pruning

A disk-aware algorithm for time series motif discovery

Contact Info

Product

Resources

About