Beyond Information Distortion: Imaging Variable-Length Time Series Data for Classification

Time series data are prevalent in diverse fields such as manufacturing and sensor-based human activity recognition. In real-world applications, these data are often collected with variable sample lengths, which can pose challenges for classification models that typically require fixed-length inputs....

Full description

Saved in:
Bibliographic Details
Main Authors: Hyeonsu Lee, Dongmin Shin
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/3/621
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850200003392307200
author Hyeonsu Lee
Dongmin Shin
author_facet Hyeonsu Lee
Dongmin Shin
author_sort Hyeonsu Lee
collection DOAJ
description Time series data are prevalent in diverse fields such as manufacturing and sensor-based human activity recognition. In real-world applications, these data are often collected with variable sample lengths, which can pose challenges for classification models that typically require fixed-length inputs. Existing approaches either employ models designed to handle variable input sizes or standardize sample lengths before applying models; however, we contend that these approaches may compromise data integrity and ultimately reduce model performance. To address this issue, we propose Time series Into Pixels (TIP), an intuitive yet strong method that maps each time series data point into a pixel in 2D representation, where the vertical axis represents time steps and the horizontal axis captures the value at each timestamp. To evaluate our representation without relying on a powerful vision model as a backbone, we employ a straightforward LeNet-like 2D CNN model. Through extensive evaluations against 10 baseline models across 11 real-world benchmarks, TIP achieves 2–5% higher accuracy and 10–25% higher macro average precision. We also demonstrate that TIP performs comparably on complex multivariate data, with ablation studies underscoring the potential hazard of length normalization techniques in variable-length scenarios. We believe this method provides a significant advancement for handling variable-length time series data in real-world applications. The code is publicly available.
format Article
id doaj-art-b67f0607ae6d424a841ec74aeeeb84c5
institution OA Journals
issn 1424-8220
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-b67f0607ae6d424a841ec74aeeeb84c52025-08-20T02:12:29ZengMDPI AGSensors1424-82202025-01-0125362110.3390/s25030621Beyond Information Distortion: Imaging Variable-Length Time Series Data for ClassificationHyeonsu Lee0Dongmin Shin1Department of Industrial and Management Engineering, Hanyang University, Ansan 15588, Republic of KoreaDepartment of Industrial and Management Engineering, Hanyang University, Ansan 15588, Republic of KoreaTime series data are prevalent in diverse fields such as manufacturing and sensor-based human activity recognition. In real-world applications, these data are often collected with variable sample lengths, which can pose challenges for classification models that typically require fixed-length inputs. Existing approaches either employ models designed to handle variable input sizes or standardize sample lengths before applying models; however, we contend that these approaches may compromise data integrity and ultimately reduce model performance. To address this issue, we propose Time series Into Pixels (TIP), an intuitive yet strong method that maps each time series data point into a pixel in 2D representation, where the vertical axis represents time steps and the horizontal axis captures the value at each timestamp. To evaluate our representation without relying on a powerful vision model as a backbone, we employ a straightforward LeNet-like 2D CNN model. Through extensive evaluations against 10 baseline models across 11 real-world benchmarks, TIP achieves 2–5% higher accuracy and 10–25% higher macro average precision. We also demonstrate that TIP performs comparably on complex multivariate data, with ablation studies underscoring the potential hazard of length normalization techniques in variable-length scenarios. We believe this method provides a significant advancement for handling variable-length time series data in real-world applications. The code is publicly available.https://www.mdpi.com/1424-8220/25/3/621time series classification (TSC)variable-length time series
spellingShingle Hyeonsu Lee
Dongmin Shin
Beyond Information Distortion: Imaging Variable-Length Time Series Data for Classification
Sensors
time series classification (TSC)
variable-length time series
title Beyond Information Distortion: Imaging Variable-Length Time Series Data for Classification
title_full Beyond Information Distortion: Imaging Variable-Length Time Series Data for Classification
title_fullStr Beyond Information Distortion: Imaging Variable-Length Time Series Data for Classification
title_full_unstemmed Beyond Information Distortion: Imaging Variable-Length Time Series Data for Classification
title_short Beyond Information Distortion: Imaging Variable-Length Time Series Data for Classification
title_sort beyond information distortion imaging variable length time series data for classification
topic time series classification (TSC)
variable-length time series
url https://www.mdpi.com/1424-8220/25/3/621
work_keys_str_mv AT hyeonsulee beyondinformationdistortionimagingvariablelengthtimeseriesdataforclassification
AT dongminshin beyondinformationdistortionimagingvariablelengthtimeseriesdataforclassification