Capturing Temporal Components for Time Series Classification

arXiv:2406.14456v1 Announce Type: new
Abstract: Analyzing sequential data is crucial in many domains, particularly due to the abundance of data collected from the Internet of Things paradigm. Time series classification, the task of categorizing sequential data, has gained prominence, with machine learning approaches demonstrating remarkable performance on public benchmark datasets. However, progress has primarily been in designing architectures for learning representations from raw data at fixed (or ideal) time scales, which can fail to generalize to longer sequences. This work …

abstract arxiv benchmark classification components cs.cv cs.lg data datasets domains however internet internet of things machine machine learning paradigm performance progress public series temporal things time series type