Problem
Research questions and friction points this paper is trying to address.
Representative Subsequences
Time Series Summarization
Waveform Discovery
Long Time Series
QSMP: finding representative time series subsequences through Quick Shift+Matrix Profile
🤖 AI Summary
This study addresses the challenges of discovering representative waveforms and generating summary visualizations for long time-series data by proposing QSMP, a novel method that innovatively integrates Quick Shift mode seeking with Matrix Profile similarity structures. By leveraging density-guided clustering, QSMP efficiently mines representative subsequences while significantly reducing spatial complexity compared to existing approaches. Extensive evaluations on both synthetic and real-world datasets demonstrate its superior performance in time-series summarization and visualization tasks. Consequently, this work provides an efficient and scalable solution for downstream analysis of long temporal sequences, effectively overcoming computational bottlenecks associated with traditional motif discovery techniques in large-scale time-series analytics.
📝 Abstract
Finding representative waveforms in long time series has scientific and practical value in many domains, as it enables summarization and visualization of large time series datasets, and downstream tasks like classification and forecasting. We present here QSMP, a method to find representative waveforms in long time series through a density-guided clustering of time series subsequences. Our method makes a novel connection between Quick Shift, a mode-seeking algorithm, and the Matrix Profile, a time series similarity-search data structure, to adapt Quick Shift to the clustering of subsequences in long time series, with a space complexity that is superior to the state-of-the-art method. Our experiments on synthetic and real datasets show that QSMP can be a valuable tool to summarize and visualize long time series by finding representative waveforms.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Quick Shift
Matrix Profile
density-guided clustering
representative subsequences
space complexity
🔎 Similar Papers
No similar papers found.
