Lune

ICDE2024Top-tier venue

TSec: An Efficient and Effective Framework for Time Series Classification

Yuanyuan Yao, Hailiang Jie, Lu Chen, Tianyi Li, Yunjun Gao, Shiting Wen

Abstract

Time series classification assigns predefined labels or classes to sequences of data points ordered chronologically, which is a fundamental task for time series analysis. Existing time series classification methods mainly focus on a specific type of time series (i.e., univariate time series or multivariate time series), while failing to support both of them efficiently and effectively. In addition, most of existing multivariate time series classification methods model all variables collectively, resulting in protracted computational times and suboptimal accuracy. In this paper, we introduce TSec, an innovative time series classification framework that exhibits high training efficiency and classification accuracy for both univariate time series and multivariate time series. During online classification, TSec first involves sequence segmentation and de-duplication, and then employs pre-trained models to perform classifications. To opti-mize the classification performance, TSec (i) utilizes correlation analysis to reveal closely interconnected groups of variables within multivariate time series data; (ii) incorporates time series alignment and different sliding windows to generate potential shapelets; (iii) applies PAA and SAX techniques to eliminate duplicates, thereby enhancing the quality of shapelets; (iv) adopts Bi-GRU and GCN-GRU models to effectively capture the characteristics of the two types of time series. Extensive experiments on 112 public univariate time series datasets and 26 public multivariate time series datasets show that TSec can achieve both high efficiency and accuracy compared with the state-of-the-art 19 toolkits.

Ask Lune

Know where this paper stands in minutes, not an afternoon.

Lune can read the top-tier papers that cite it and the ones closest to it, and tells you what it claims, what came after and where it falls short, each point cited to the paper it comes from. No skimming, no AI slop.

7 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

its abstract · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Arrow: Accelerator for Time Series Causal Discovery with Time Weaving cites DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting
  • AimTS: Augmented Series and Image Contrastive Learning for Time Series Classification cites DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting
  • Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective cites Arrow: Accelerator for Time Series Causal Discovery with Time Weaving
  • Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective cites DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting
  • Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective cites TAB: Unified Benchmarking of Time Series Anomaly Detection Methods
  • TAB: Unified Benchmarking of Time Series Anomaly Detection Methods cites AimTS: Augmented Series and Image Contrastive Learning for Time Series Classification
  • TAB: Unified Benchmarking of Time Series Anomaly Detection Methods cites DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers7

  1. Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch PerspectiveXingjian Wu, Xiangfei Qiu, Hanyin Cheng, Zhengyu Li et al.NeurIPS 2025 · 58 citations
  2. TAB: Unified Benchmarking of Time Series Anomaly Detection MethodsXiangfei Qiu, Zhe Li, Wanghui Qiu, Shiyan Hu et al.VLDB 2025 · 57 citations
  3. DUET: Dual Clustering Enhanced Multivariate Time Series ForecastingXiangfei Qiu, Xingjian Wu, Yan Lin, Chenjuan Guo et al.KDD 2025 · 37 citations
  4. AimTS: Augmented Series and Image Contrastive Learning for Time Series ClassificationYuxuan Chen, Shanshan Huang, Yunyao Cheng, Peng Chen et al.ICDE 2025 · 5 citations
  5. Arrow: Accelerator for Time Series Causal Discovery with Time WeavingYuanyuan Yao, Yuan Dong, Lu Chen, Kun Kuang et al.ICML 2025

Related papers

  1. ShapeFormer: Shapelet Transformer for Multivariate Time Series ClassificationXuan-May Le, Ling Luo, Uwe Aickelin, Minh-Tuan TranKDD 2024 · 27 citations
  2. ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification ModelsBosong Huang, Ming Jin, Yuxuan Liang, Johan Barthelemy et al.NeurIPS 2025 · 8 citations
  3. SVP-T: A Shape-Level Variable-Position Transformer for Multivariate Time Series ClassificationRundong Zuo, Guozhong Li, Byron Choi, Sourav S. Bhowmick et al.AAAI 2023 · 53 citations
  4. ShapeNet: A Shapelet-Neural Network Approach for Multivariate Time Series ClassificationGuozhong Li, Byron Choi, Jianliang Xu, Sourav S. Bhowmick et al.AAAI 2021 · 177 citations
  5. Con4m: Context-aware Consistency Learning Framework for Segmented Time Series ClassificationJunru Chen, Tianyu Cao, Jing Xu, Jiahe Li et al.NeurIPS 2024 · 4 citations
Dusk over the sea between two cliffs drawn in fine vertical lines