lzz19980125/awesome-time-series-segmentation-papers lzz19980125/awesome-time-series-segmentation-papers

  • Stars
    star
    374
  • Rank 114,346 (Top 3 %)
  • Language
    MATLAB
  • License
    GNU General Publi...
  • Created 10 months ago
  • Updated 6 months ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
lzz19980125/awesome-time-series-segmentation-papers
github

lzz19980125

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

This repository contains a reading list of papers on Time Series Segmentation. This repository is still being continuously improved.

Awesome Time Series Segmentation Papers

Awesome PRs WelcomeStars

Star History

Star History Chart

Description

This repository contains a reading list of papers on Time Series Segmentation. This repository is still being continuously improved.

As a crucial time series preprocessing technique, semantic segmentation divides poorly understood time series into several discrete and homogeneous segments. This approach aims to uncover latent temporal evolution patterns, detect unexpected regularities and regimes, thereby rendering the analysis of massive time series data more manageable.

Time series segmentation often intertwines with research in many domains. Firstly, the relationship between time series segmentation, time series change point detection, and some aspects of time series anomaly/outlier detection is somewhat ambiguous. Therefore, this repository includes a selection of papers from these areas. Secondly, time series segmentation can be regarded as a process of information compression in time series, hence papers in this field often incorporate concepts from information theory (e.g., using minimum description length to guide the design of unsupervised time series segmentation models). Additionally, the task of decomposing human actions into a series of plausible motion primitives can be addressed through methods for segmenting sensor time series. Consequently, papers related to motion capture from the fields of computer vision and ubiquitous computing are also included in this collection.

Generally, the subjects of unsupervised semantic segmentation can be categorized into:

  • univariate time series forecasting univariate time series: , where is the length of the time series.
  • multivariate time series forecasting multivariate time series: , where is the number of variables (channels).
  • spatio-temporal forecasting tensor: , where denotes the dimensions other than time and variables.

In the field of time series research, unlike time series forecasting, anomaly detection, and classification/clustering, the number of papers on time series segmentation has been somewhat lukewarm in recent years (this observation may carry a degree of subjectivity from the author). Additionally, deep learning methods do not seem to dominate this area as they do in others. Some classic but solid algorithms remain highly competitive even today, with quite a few originating from the same research group. Therefore, in the following paper list, I will introduce them indexed by well-known researchers and research groups in this field.

Some Additional Information

🚩 2024/1/27: I have marked some recommended papers / datasets / implementations with 🌟 (Just my personal preference πŸ˜‰).

Survey & Evaluation

NOTE: the ranking has no particular order.

TYPE Venue Paper Title and Paper Interpretation Code
Dataset DARLI-AP@EDBT/ICDT '23 Time Series Segmentation Applied to a New Data Set for Mobile Sensing of Human Activities 🌟 MOSADStars
Dataset ECML-PKDD Workshop '23 Human Activity Segmentation Challenge@ECML/PKDD’23 🌟 Challenge Link
Visualization IEEE TVCG '21 MultiSegVA Using Visual Analytics to Segment Biologging Time Series on Multiple Scales None
Survey IEEE J. Sel. Areas Commun. '21 Sequential (Quickest) Change Detection Classical Results and New Directions None
Survey Signal Process. '20 Selective review of offline change point detection methods 🌟 RupturesStars
Evaluation Arxiv '20 An Evaluation of Change Point Detection Algorithms 🌟 TCPDBenchStars
Survey Knowl. Inf. Syst. '17 A survey of methods for time series change point detection 🌟 None
Evaluation Inf. Syst. '17 An evaluation of combinations of lossy compression and change-detection approaches for time-series data None
Survey IEEE Trans Hum. Mach. Syst. '16 Movement Primitive Segmentation for Human Motion Modeling A Framework for Analysis 🌟 None
Survey EAAI '11 A review on time series data mining None
Survey CSUR '11 Time-series data mining None
Dataset GI '04 Segmenting Motion Capture Data into Distinct Behaviors 🌟 Website

David Hallac (Stanford)

TYPE Venue Paper Title and Paper Interpretation Code
multivariate time series forecasting KDD Workshop MiLeTS '20 Driver2vec Driver Identification from Automotive Data Driver2vecStars
multivariate time series forecasting Adv. Data Anal. Classif. '19 Greedy Gaussian segmentation of multivariate time series 🌟 GGSStars
multivariate time series forecasting Arxiv '18 MASA: Motif-Aware State Assignment in Noisy Time Series Data MASAStars
Ph.D. Thesis ProQuest '18 Inferring Structure from Multivariate Time Series Sensor Data None
multivariate time series forecasting KDD '17 Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Data 🌟 TICCStars
multivariate time series forecasting KDD '17 Network Inference via the Time-Varying Graphical Lasso 🌟 TVGLStars

Shaghayegh Gharghabi (from Eamonn Keogh's Lab, UC Riverside)

TYPE Venue Paper Title and Paper Interpretation Code
multivariate time series forecasting DMKD '19 Domain agnostic online semantic segmentation for multi-dimensional time series 🌟 Floss & datasets)
univariate time series forecasting ICDM '17 Matrix Profile VIII Domain Agnostic Online Semantic Segmentation at Superhuman Performance Levels 🌟 Floss

Yasuko Matsubara & Yasushi Sakurai (from Sakurai & Matsubara Lab)

TYPE Venue Paper Title and Paper Interpretation Code
spatio-temporal forecasting WWW '24 Dynamic Multi-Network Mining of Tensor Time Series 🌟 DMMStars
spatio-temporal forecasting WWW '23 Fast and Multi-aspect Mining of Complex Time-stamped Event Streams 🌟 CubeScopeStars
spatio-temporal forecasting KDD '22 Fast Mining and Forecasting of Co-evolving Epidemiological Data Streams 🌟 None
spatio-temporal forecasting CIKM '22 Modeling Dynamic Interactions over Tensor Streams DismoStars
multivariate time series forecasting CIKM '22 Mining Reaction and Diffusion Dynamics in Social Activities 🌟 None
spatio-temporal forecasting NeurIPS '21 SSMF Shifting Seasonal Matrix Factorization ssmfStars
spatio-temporal forecasting KDD '20 Non-Linear Mining of Social Activities in Tensor Streams 🌟 None
spatio-temporal forecasting ICDM '19 Multi-aspect mining of complex sensor sequences 🌟 CubeMarkerStars
multivariate time series forecasting KDD '19 Dynamic Modeling and Forecasting of Time-evolving Data Streams OrbitMapStars
multivariate time series forecasting CIKM '19 Automatic Sequential Pattern Mining in Data Streams None
multivariate time series forecasting KDD '16 Regime Shifts in Streams: Real-time Forecasting of Co-evolving Time Sequences RegimeCast
spatio-temporal forecasting WWW '16 Non-linear mining of competing local activities CompCube
spatio-temporal forecasting WWW '15 The web as a jungle: Non-linear dynamical systems for co-evolving online activities 🌟 Ecoweb & dataset
multivariate time series forecasting SIGMOD '14 AutoPlait Automatic Mining of Co-evolving Time Sequences 🌟 AutoPlait
multivariate time series forecasting ICDM '14 Fast and Exact Monitoring of Co-evolving Data Streams None
spatio-temporal forecasting KDD '14 FUNNEL Automatic Mining of Spatially Coevolving Epidemics Funnel

Bryan Hooi (NUS)

TYPE Venue Paper Title and Paper Interpretation Code
multivariate time series forecasting TKDE '22 Time Series Anomaly Detection with Adversarial Reconstruction Networks 🌟 BeatGANStars
multivariate time series forecasting IJCAI '19 BeatGAN Anomalous Rhythm Detection using Adversarially Generated Time Series 🌟 BeatGANStars
Ph.D. Thesis ProQuest '19 Anomaly Detection in Graphs and Time Series Algorithms and Applications None
multivariate time series forecasting SDM '19 Branch and Border Partition Based Change Detection in Multivariate Time Series 🌟 Bnb
spatio-temporal forecasting SDM '19 SMF Drift-Aware Matrix Factorization with Seasonal Patterns smf & dataset
spatio-temporal forecasting WWW '17 AutoCyclone Automatic Mining of Cyclic Online Activities with Robust Tensor Factorization AutoCyclone

Liangzhe Chen & Anika Tabassum (Virginia Tech, supervised by B. Aditya Prakash)

TYPE Venue Paper Title and Paper Interpretation Code
Ph.D. Thesis ProQuest '21 Explainable and Network-Based Approaches for Decision-making in Emergency Management None
multivariate time series forecasting CIKM '21 Actionable Insights in Urban Multivariate Time-series RaTSSStars
multivariate time series forecasting TIST '20 Cut-n-Reveal: Time-Series Segmentations with Explanations 🌟 Cut-n-RevealStars
multivariate time series forecasting AAAI '18 Automatic Segmentation of Data Sequences DASSA
Ph.D. Thesis ProQuest '18 Segmenting, Summarizing and Predicting Data Sequences None
multivariate time series forecasting vt.edu '18 Segmentations with Explanations for Outage Analysis 🌟 None

Shohreh Deldari (from Cruise research group, RMIT ) & Flora D. Salim (UNSW)

TYPE Venue Paper Title and Paper Interpretation Code
multivariate time series forecasting JAIR '24 Detecting Change Intervals with Isolation Distributional Kernel 🌟 ICDStars
multivariate time series forecasting IMWUT '22 COCOA Cross Modality Contrastive Learning for Sensor Data 🌟 COCOAStars
multivariate time series forecasting WWW '21 Time Series Change Point Detection with Self-Supervised Contrastive Predictive Coding 🌟 TSCP2Stars
multivariate time series forecasting IMWUT '20 ESPRESSO Entropy and ShaPe awaRe timE-Series SegmentatiOn for Processing Heterogeneous Sensor Data ESPRESSOStars
multivariate time series forecasting Knowl. Inf. Syst. '20 Unsupervised online change point detection in high-dimensional time series None
multivariate time series forecasting WSDM Workshop '19 Inferring Work Routines and Behavior Deviations with Life-logging Sensor Data None
multivariate time series forecasting Pervasive Mob. Comput. '17 Information gain-based metric for recognizing transitions in human activities 🌟 IGTsStars

Peng Wang (fudan University)

TYPE Venue Paper Title and Paper Interpretation Code
univariate time series forecasting ICDE '21 GRAB: Finding Time Series Natural Structures via A Novel Graph-based Scheme GRAB
multivariate time series forecasting SIGMOD '11 Finding Semantics in Time Series 🌟 None

Arik Ermshaus (Humboldt-UniversitΓ€t zu Berlin)

TYPE Venue Paper Title and Paper Interpretation Code
univariate time series forecasting Arxiv '23 Raising the ClaSS of Streaming Time Series Segmentation 🌟 ClaspStars
Dataset ECML-PKDD Workshop '23 Human Activity Segmentation Challenge@ECML/PKDD’23 🌟 Challenge Link
univariate time series forecasting DMKD '23 ClaSP: parameter-free time series segmentation 🌟 Clasp
univariate time series forecasting CIKM '21 ClaSP - Time Series Segmentation 🌟 Clasp

Lei Li (CMU)

TYPE Venue Paper Title and Paper Interpretation Code
spatio-temporal forecasting Neurips '13 MLDS Multilinear Dynamical Systems for Tensor Time Series mldsStars
Ph.D. Thesis ProQuest '11 Fast Algorithms for Mining Co-evolving Time Series None
multivariate time series forecasting KDD '09 DynaMMo: Mining and Summarization of Coevolving Sequences with Missing Values 🌟 dynammoStars
multivariate time series forecasting VLDB '10 Parsimonious Linear Fingerprinting for Time Series pliF

Feng Zhou (CMU)

TYPE Venue Paper Title and Paper Interpretation Code
multivariate time series forecasting TPAMI '12 Hierarchical Aligned Cluster Analysis for Temporal Clustering of Human Motion 🌟 HACA

Chun-Tung Li (CUHK)

TYPE Venue Paper Title and Paper Interpretation Code
univariate time series forecasting ACM Trans. Comput. Healthcare '20 mSIMPAD: Efficient and Robust Mining of Successive Similar Patterns of Multiple Lengths in Time Series 🌟 mSIMPADStars
Ph.D. Thesis ProQuest '21 Mobile sensing based human stress monitoring for smart health applications None
univariate time series forecasting IEEE MASS '21 Repetitive Activity Monitoring from Multivariate Time Series A Generic and Efficient Approach None

Tong Hanghang (UIUC)

TYPE Venue Paper Title and Paper Interpretation Code
spatio-temporal forecasting Arxiv'24 Tensor time-series forecasting and anomaly detection with augmented causality None
spatio-temporal forecasting WWW'21 Network of Tensor Time Series NET3Stars
spatio-temporal forecasting SDM '15 Fast Mining of a Network of Coevolving Time Series dcmf (Unofficial) Stars
spatio-temporal forecasting KDD '15 Facets: Fast comprehensive mining of coevolving high-order time facets (Unofficial) Stars

Others

TYPE Venue Paper Title and Paper Interpretation Code
spatio-temporal forecasting TKDE'24 Discovering Dynamic Patterns From Spatiotemporal Data With Time-Varying Low-Rank Autoregression VarsStars
multivariate time series forecasting WWW '24 E2Usd: Efficient-yet-effective Unsupervised State Detection for Multivariate Time Series 🌟 E2UsdStars
multivariate time series forecasting Information Fusion '24 MultiBEATS Blocks of eigenvalues algorithm for multivariate time series dimensionality reduction 🌟 MultiBEATSStars
multivariate time series forecasting Information Sciences '24 Memetic segmentation based on variable lag aware for multivariate time series 🌟 None
multivariate time series forecasting TKDE '23 Change Point Detection in Multi-channel Time Series via a Time-invariant Representation 🌟 MC-TIREStars
multivariate time series forecasting TII '23 A Boundary Consistency-Aware Multitask Learning Framework for Joint Activity Segmentation and Recognition With Wearable Sensors Coming soom πŸ™ƒ
multivariate time series forecasting SIGMOD '23 Time2State: An Unsupervised Framework for Inferring the Latent States in Time Series Data 🌟 Time2StateStars
univariate time series forecasting TKDD '23 Modeling Regime Shifts in Multiple Time Series None
univariate time series forecasting World Wide Web '23 Anomaly and change point detection for time series with concept drift None
univariate time series forecasting EAAI '23 PrecTime A deep learning architecture for precise time series segmentation in industrial manufacturing operations None
spatio-temporal forecasting JASA'22 Factor Models for High-Dimensional Tensor Time Series None
spatio-temporal forecasting JSS'22 Analysis of Tensor Time Series: tensorTS tensorTSStars
multivariate time series forecasting IMWUT '22 ColloSSL Collaborative Self-Supervised Learning for Human Activity Recognition 🌟 collosslStars
multivariate time series forecasting MSSP '22 A multivariate time series segmentation algorithm for analyzing the operating statuses of tunnel boring machines None
multivariate time series forecasting Technometrics '22 Bayesian Hierarchical Model for Change Point Detection in Multivariate Sequences Supplementary Materials
multivariate time series forecasting Neurips Workshop '22 Are uGLAD? Time will tell! 🌟 tGLADStars
multivariate time series forecasting Applied Intelligence '22 Change point detection for compositional multivariate data None
univariate time series forecasting ICDM '22 Change Detection with Probabilistic Models on Persistence Diagrams None
univariate time series forecasting EAAI '22 Graft : A graph based time series data mining framework None
multivariate time series forecasting GLOBECOM '22 Multi-level Contrast Network for Wearables-based Joint Activity Segmentation and Recognition None
multivariate time series forecasting ESWA '22 Real-time Change-Point Detection A deep neural network-based adaptive approach for detecting changes in multivariate time series data None
univariate time series forecasting npj digital medicine '21 U-Sleep: resilient high-frequency sleep staging 🌟 website
univariate time series forecasting IEEE TSP '21 Change Point Detection in Time Series Data Using Autoencoders With a Time-Invariant Representation 🌟 TIREStars
univariate time series forecasting IJCNN '21 A Transferable Technique for Detecting and Localising Segments of Repeating Patterns in Time series None
univariate time series forecasting IOTJ '21 DeepSeg Deep-Learning-Based Activity Segmentation Framework for Activity Recognition Using WiFi DeepSegStars
univariate time series forecasting Information Sciences '21 Change-point detection based on adjusted shape context method cost None
multivariate time series forecasting KDD '21 Statistical Models Coupling Allows for Complex Local Multivariate Time Series Analysis None
univariate time series forecasting IEEE TCYB '20 An Online Unsupervised Dynamic Window Method to Track Repeating Patterns From Sensor Data 🌟 FingdingIOR
univariate time series forecasting Pattern Recognit. Lett. '20 A new approach for optimal time-series segmentation None
multivariate time series forecasting SDM '20 Lag-aware multivariate time-series segmentation 🌟 None
multivariate time series forecasting Pattern Recognit. Lett. '20 Memetic algorithm for multivariate time-series segmentation 🌟 ma_mtsStars
univariate time series forecasting ICASSP '20 Modeling Piece-Wise Stationary Time Series None
univariate time series forecasting Neurips '19 U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging 🌟 U-TimeStars
univariate time series forecasting Neurocomputing '19 A hybrid dynamic exploitation barebones particle swarm optimisation algorithm for time series segmentation tssaStars
univariate time series forecasting TKDE '18 BEATS Blocks of Eigenvalues Algorithm for Time series Segmentation 🌟 BEATSStars
univariate time series forecasting Arxiv '18 Time Series Segmentation through Automatic Feature Learning 🌟 None
univariate time series forecasting Applied Soft Computing '16 Change points detection in crime-related time series An on-line fuzzy approach based on a shape space representation None
multivariate time series forecasting WACV '16 Decomposing Time Series with application to Temporal Segmentation 🌟 Hog1D (Unofficial) Stars
multivariate time series forecasting J. Am. Stat. Assoc. '14 A Nonparametric Approach for Multiple Change Point Analysis of Multivariate Data None
univariate time series forecasting Neural Networks '13 Change-point detection in time-series data by relative density-ratio estimation 🌟 RuLSIF Stars

More Repositories

1

awesome-multivariate-time-series-clustering-algorithms

This repo collects effective multivariate time series clustering codes.
20
star
2

MIT_6.824

Go
3
star
3

lzz19980125.github.io

HTML
1
star
4

decomposed-transformer

Python re-implementation of decomposed transformer for multivariate time series anomaly detection (IEEE BigData '22)
Python
1
star
5

awesome-multivariate-time-series-anomaly-detection-algorithms

1
star