Particle Swarm Optimization of Information-Content Weighting of Symbolic Aggregate Approximation
This work addresses the issue of information loss in time series representation for data analysis applications, but it is incremental as it builds on the existing SAX method with a novel weighting approach.
The authors tackled the information loss problem in Symbolic Aggregate Approximation (SAX) for time series representation by proposing a new weighted minimum distance (WMD) using Particle Swarm Optimization (PSO) to assign different weights to segments based on information content, resulting in enhanced performance as demonstrated through experiments on various datasets.
Bio-inspired optimization algorithms have been gaining more popularity recently. One of the most important of these algorithms is particle swarm optimization (PSO). PSO is based on the collective intelligence of a swam of particles. Each particle explores a part of the search space looking for the optimal position and adjusts its position according to two factors; the first is its own experience and the second is the collective experience of the whole swarm. PSO has been successfully used to solve many optimization problems. In this work we use PSO to improve the performance of a well-known representation method of time series data which is the symbolic aggregate approximation (SAX). As with other time series representation methods, SAX results in loss of information when applied to represent time series. In this paper we use PSO to propose a new minimum distance WMD for SAX to remedy this problem. Unlike the original minimum distance, the new distance sets different weights to different segments of the time series according to their information content. This weighted minimum distance enhances the performance of SAX as we show through experiments using different time series datasets.