Search

Big Data is a generic term that involves the storing and processing of a large amount of data. This large amount of data has been promoted by technologies such as mobile applications, Internet of Things (IoT), and Geographic Information Systems (GIS). An example of GIS is a Spatio-Temporal Database (STDB). A complex problem to address in terms of processing time is pattern searching on STDB. Nowadays, high information processing capacity is available everywhere. Nevertheless, the pattern searching problem on STDB using traditional Data Mining techniques is complex because the data incorporate the temporal aspect. Traditional techniques of pattern searching, such as time series, do not incorporate the spatial aspect. For this reason, traditional algorithms based on association rules must be adapted to find these patterns. Most of the algorithms take exponential processing times. In this paper, a new efficient algorithm (named Minus-F1) to look for periodic patterns on STDB is presented. Our algorithm is compared with Apriori, Max-Subpattern, and PPA algorithms on synthetic and real STDB. Additionally, the computational complexities for each algorithm in the worst cases are presented. Empirical results show that Minus-F1 is not only more efficient than Apriori, Max-Subpattern, and PAA, but also it presents a polynomial behavior. [ABSTRACT FROM AUTHOR]

We present efficient algorithms to compute simple and complex map algebra operations over raster data stored in main memory, using the k2-acc compact data structure. Raster data correspond to numerical data that represent attributes of spatial objects, such as temperature or elevation measures. Compact data structures allow efficient data storage in main memory and query them in their compressed form. A k2-acc is a set of k2-trees, one for every distinct numeric value in the raster matrix. We demonstrate that map algebra operations can be computed efficiently using this compact data structure. In fact, some map algebra operations perform over five orders of magnitude faster compared with algorithms working over uncompressed datasets. [ABSTRACT FROM AUTHOR]