2015
EMSS 2015 Proceeding
Searching the longest common subsequences in distorted data
Authors: Tomá? Kocyan, Jan Martinovi?, Kate?ina Slaninová, Daniela Szturcová
Abstract
Many models and artificial intelligence methods work with the inputs in the form of time series. Success of many of them strongly depends on ability to quickly and precisely compare two time series or search the mutual parts. Such ability is especially crucial while recognizing characteristic patterns, indexing, prediction or compression. There are many algorithms able to handle that, however, many of them fail while processing distorted data. Unfortunately, the distortion is natural for many types of data collections, e.g. for measurements of natural phenomena such as precipitations, river discharge volume etc. This paper discusses the possibilities of searching such common subsequences in time series and presents a new approach for searching the longest common subsequences in distorted data. This approach is based on modified the dynamic time warping algorithm, which allows the effective processing distorted time series data.
I3M Scientific Sponsors
I3M Industrial Sponsors
I3M Media Sponsors
