Enhancing the Distinguishability of Minor Fluctuations in Time Series Classification Using Graph Representation: The MFSI-TSC Framework

In industrial systems, sensors often classify collected time series data for incipient fault diagnosis. However, time series data from sensors during the initial stages of a fault often exhibits minor fluctuation characteristics. Existing time series classification (TSC) methods struggle to achieve...

Full description

Saved in:
Bibliographic Details
Main Authors: He Nai, Chunlei Zhang, Xianjun Hu
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/15/4672
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849770489605521408
author He Nai
Chunlei Zhang
Xianjun Hu
author_facet He Nai
Chunlei Zhang
Xianjun Hu
author_sort He Nai
collection DOAJ
description In industrial systems, sensors often classify collected time series data for incipient fault diagnosis. However, time series data from sensors during the initial stages of a fault often exhibits minor fluctuation characteristics. Existing time series classification (TSC) methods struggle to achieve high classification accuracy when these minor fluctuations serve as the primary distinguishing feature. This limitation arises because the low-amplitude variations of these fluctuations, compared with trends, lead the classifier to prioritize and learn trend features while ignoring the minor fluctuations crucial for accurate classification. To address this challenge, this paper proposes a novel graph-based time series classification framework, termed MFSI-TSC. MFSI-TSC first extracts the trend component of the raw time series. Subsequently, both the trend series and the raw series are represented as graphs by extracting the “visible relationship” of the series. By performing a subtraction operation between these graphs, the framework isolates the differential information arising from the minor fluctuations. The subtracted graph effectively captures minor fluctuations by highlighting topological variations, thereby making them more distinguishable. Furthermore, the framework incorporates optimizations to reduce computational complexity, facilitating its deployment in resource-constrained sensor systems. Finally, empirical evaluation of MFSI-TSC on both real-world and publicly available datasets demonstrates its effectiveness. Compared with ten benchmark methods, MFSI-TSC exhibits both high accuracy and computational efficiency, making it more suitable for deployment in sensor systems to complete incipient fault detection tasks.
format Article
id doaj-art-e44a3fff551541e09363263f0e1352b0
institution DOAJ
issn 1424-8220
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-e44a3fff551541e09363263f0e1352b02025-08-20T03:02:58ZengMDPI AGSensors1424-82202025-07-012515467210.3390/s25154672Enhancing the Distinguishability of Minor Fluctuations in Time Series Classification Using Graph Representation: The MFSI-TSC FrameworkHe Nai0Chunlei Zhang1Xianjun Hu2College of Electronic Engineering, Naval University of Engineering, 717 Jiefang Avenue, Wuhan 430030, ChinaCollege of Electronic Engineering, Naval University of Engineering, 717 Jiefang Avenue, Wuhan 430030, ChinaCollege of Electronic Engineering, Naval University of Engineering, 717 Jiefang Avenue, Wuhan 430030, ChinaIn industrial systems, sensors often classify collected time series data for incipient fault diagnosis. However, time series data from sensors during the initial stages of a fault often exhibits minor fluctuation characteristics. Existing time series classification (TSC) methods struggle to achieve high classification accuracy when these minor fluctuations serve as the primary distinguishing feature. This limitation arises because the low-amplitude variations of these fluctuations, compared with trends, lead the classifier to prioritize and learn trend features while ignoring the minor fluctuations crucial for accurate classification. To address this challenge, this paper proposes a novel graph-based time series classification framework, termed MFSI-TSC. MFSI-TSC first extracts the trend component of the raw time series. Subsequently, both the trend series and the raw series are represented as graphs by extracting the “visible relationship” of the series. By performing a subtraction operation between these graphs, the framework isolates the differential information arising from the minor fluctuations. The subtracted graph effectively captures minor fluctuations by highlighting topological variations, thereby making them more distinguishable. Furthermore, the framework incorporates optimizations to reduce computational complexity, facilitating its deployment in resource-constrained sensor systems. Finally, empirical evaluation of MFSI-TSC on both real-world and publicly available datasets demonstrates its effectiveness. Compared with ten benchmark methods, MFSI-TSC exhibits both high accuracy and computational efficiency, making it more suitable for deployment in sensor systems to complete incipient fault detection tasks.https://www.mdpi.com/1424-8220/25/15/4672time series classificationminor fluctuationsidentificationgraphclassification accuracycomputational efficiency
spellingShingle He Nai
Chunlei Zhang
Xianjun Hu
Enhancing the Distinguishability of Minor Fluctuations in Time Series Classification Using Graph Representation: The MFSI-TSC Framework
Sensors
time series classification
minor fluctuations
identification
graph
classification accuracy
computational efficiency
title Enhancing the Distinguishability of Minor Fluctuations in Time Series Classification Using Graph Representation: The MFSI-TSC Framework
title_full Enhancing the Distinguishability of Minor Fluctuations in Time Series Classification Using Graph Representation: The MFSI-TSC Framework
title_fullStr Enhancing the Distinguishability of Minor Fluctuations in Time Series Classification Using Graph Representation: The MFSI-TSC Framework
title_full_unstemmed Enhancing the Distinguishability of Minor Fluctuations in Time Series Classification Using Graph Representation: The MFSI-TSC Framework
title_short Enhancing the Distinguishability of Minor Fluctuations in Time Series Classification Using Graph Representation: The MFSI-TSC Framework
title_sort enhancing the distinguishability of minor fluctuations in time series classification using graph representation the mfsi tsc framework
topic time series classification
minor fluctuations
identification
graph
classification accuracy
computational efficiency
url https://www.mdpi.com/1424-8220/25/15/4672
work_keys_str_mv AT henai enhancingthedistinguishabilityofminorfluctuationsintimeseriesclassificationusinggraphrepresentationthemfsitscframework
AT chunleizhang enhancingthedistinguishabilityofminorfluctuationsintimeseriesclassificationusinggraphrepresentationthemfsitscframework
AT xianjunhu enhancingthedistinguishabilityofminorfluctuationsintimeseriesclassificationusinggraphrepresentationthemfsitscframework