Parallel indexing technique for spatio-temporal data

He, Zhenwen; Kraak, M.J.; Huisman, Otto; Ma, Xiaogang; Xiao, Jing

doi:10.1016/j.isprsjprs.2013.01.014

Cited by 18 publications

(19 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Generally, it can be represented by two attributes: start value and end value. Interval is a fundamental data type for temporal, spatial, and scientific databases that are essential to solve the problem of representing temporal knowledge and reasoning arising in a wide range of disciplines [6][7][8][9], especially in computer science and geoinformatics [10,11]. Since the 1990s, research on interval data management has made significant progress in various aspects and many remarkable results have been reported, however, many challenges in this filed still remain [8,9,12,13].…”

Section: Introductionmentioning

confidence: 99%

“…Interval is a fundamental data type for temporal, spatial, and scientific databases that are essential to solve the problem of representing temporal knowledge and reasoning arising in a wide range of disciplines [6][7][8][9], especially in computer science and geoinformatics [10,11]. Since the 1990s, research on interval data management has made significant progress in various aspects and many remarkable results have been reported, however, many challenges in this filed still remain [8,9,12,13]. According to the reference [8], the existing interval indexes, including the Time Index [14], Segment R-tree [15], PR-tree [16], Interval B-Tree [17], Snapshot index [18], Fully Persistent B + -tree [19,20], RI-tree [21,22], TD-Tree [8], TB-Tree [9], and the SHB + -tree [23], etc.…”

Section: Introductionmentioning

confidence: 99%

“…Since the 1990s, research on interval data management has made significant progress in various aspects and many remarkable results have been reported, however, many challenges in this filed still remain [8,9,12,13]. According to the reference [8], the existing interval indexes, including the Time Index [14], Segment R-tree [15], PR-tree [16], Interval B-Tree [17], Snapshot index [18], Fully Persistent B + -tree [19,20], RI-tree [21,22], TD-Tree [8], TB-Tree [9], and the SHB + -tree [23], etc. can be categorized into four groups [8].…”

Section: Introductionmentioning

confidence: 99%

“…In general, the tree-like index structures are a kind of centralized data structure. They are hierarchical and are not efficient for parallel implementations due to high concurrency control cost [9,27,28]. How to transform the tree-like structure into linear structure effectively and efficiently is one of the key solutions to this problem.…”

Section: Introductionmentioning

confidence: 99%

“…We present the "Distributed Triangle Increment Tree" (DTI-Tree) access method that is based on Apache Spark to index timeline datasets in this paper. In contrast to the above-mentioned tree-like index structures for interval data, this method is scalable and can efficiently answer all of the 15 interval relationships queries proposed in our previous work [9]. In addition, it also has the ability to index timeline datasets based on the interval-based representation of timelines.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Distributed Indexing Method for Timeline Similarity Query

2018

Algorithms

Self Cite

View full text Add to dashboard Cite

Timelines have been used for centuries and have become more and more widely used with the development of social media in recent years. Every day, various smart phones and other instruments on the internet of things generate massive data related to time. Most of these data can be managed in the way of timelines. However, it is still a challenge to effectively and efficiently store, query, and process big timeline data, especially the instant recommendation based on timeline similarities. Most existing studies have focused on indexing spatial and interval datasets rather than the timeline dataset. In addition, many of them are designed for a centralized system. A timeline index structure adapting to parallel and distributed computation framework is in urgent need. In this research, we have defined the timeline similarity query and developed a novel timeline index in the distributed system, called the Distributed Triangle Increment Tree (DTI-Tree), to support the similarity query. The DTI-Tree consists of one T-Tree and one or more TI-Trees based on a triangle increment partition strategy with the Apache Spark. Furthermore, we have provided an open source timeline benchmark data generator, named TimelineGenerator, to generate various timeline test datasets for different conditions. The experiments for DTI-Tree's construction, insertion, deletion, and similarity queries have been executed on a cluster with two benchmark datasets that are generated by TimelineGenerator. The experimental results show that the DTI-tree provides an effective and efficient distributed index solution to big timeline data.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Distributed Indexing Method for Timeline Similarity Query

2018

Algorithms

Self Cite

View full text Add to dashboard Cite

show abstract

Adaptable parallel strategy to extract polygons from massive classified images on multi‐core clusters

Chen

Zhou

et al. 2016

Concurrency and Computation

View full text Add to dashboard Cite

Summary It is always computing intensive and time consuming to extract polygons from massive classified images. Although parallel computing can improve the efficiency of geographical data processing, the performance of the conversion suffers from the trade‐off between data decomposition and result stitching. In this paper, we present an adaptable parallel strategy that accelerates the conversion process on a multi‐core cluster. The strategy improves the method of data decomposition and optimizes task scheduling. In our strategy, an adaptable decomposition method is used to partition raster data according to the data complexity of the raster dataset and computing capability of the computing nodes. Moreover, the hierarchical task scheduling optimizes task allocation and load balance among computing nodes for the procedure of parallel conversion and stitching. We implemented parallel algorithms based on a boundary linking algorithm using the adaptable parallel strategy and compared the performance with the performances of conventional parallel strategies. The results show that the processing time of experimental raster data was reduced from 1362.36 to 165.78 s and that a desirable speedup with the maximal value of 8.23 was achieved. Copyright © 2016 John Wiley & Sons, Ltd.

show abstract