research-article

InceptionTime: Finding AlexNet for time series classification

Authors:

Hassan Ismail Fawaz,

Benjamin Lucas,

Germain Forestier,

Charlotte Pelletier,

Daniel F. Schmidt,

Jonathan Weber,

Geoffrey I. Webb,

Lhassane Idoumghar,

Pierre-Alain Muller,

François PetitjeanAuthors Info & Claims

Data Mining and Knowledge Discovery, Volume 34, Issue 6

Pages 1936 - 1962

https://doi.org/10.1007/s10618-020-00710-y

Published: 01 November 2020 Publication History

Abstract

This paper brings deep learning at the forefront of research into time series classification (TSC). TSC is the area of machine learning tasked with the categorization (or labelling) of time series. The last few decades of work in this area have led to significant progress in the accuracy of classifiers, with the state of the art now represented by the HIVE-COTE algorithm. While extremely accurate, HIVE-COTE cannot be applied to many real-world datasets because of its high training time complexity in

O (N^{2} \cdot T^{4})

for a dataset with N time series of length T. For example, it takes HIVE-COTE more than 8 days to learn from a small dataset with

N = 1500

time series of short length

T = 46

. Meanwhile deep learning has received enormous attention because of its high accuracy and scalability. Recent approaches to deep learning for TSC have been scalable, but less accurate than HIVE-COTE. We introduce InceptionTime—an ensemble of deep Convolutional Neural Network models, inspired by the Inception-v4 architecture. Our experiments show that InceptionTime is on par with HIVE-COTE in terms of accuracy while being much more scalable: not only can it learn from 1500 time series in one hour but it can also learn from 8M time series in 13 h, a quantity of data that is fully out of reach of HIVE-COTE.

References

[1]

Bagnall A, Lines J, Hills J, Bostrom A (2016) Time-series classification with COTE: the collective of transformation-based ensembles. In: International conference on data engineering, pp 1548–1549

[2]

Bagnall A, Lines J, Bostrom A, Large J, and Keogh EThe great time series classification bake off: a review and experimental evaluation of recent algorithmic advancesData Min Knowl Disc2017313606-6603640659

[3]

Benavoli A, Corani G, and Mangili FShould we really use post-hoc tests based on mean-ranks?Mach Learn Res2016171152-16134829251360.62208

[4]

Brunel A, Pasquet J, Pasquet J, Rodriguez N, Comby F, Fouchez D, Chaumont M (2019) A CNN adapted to time series for the classification of Supernovae. In: Electronic imaging

[5]

Cui Z, Chen W, Chen Y (2016) Multi-scale convolutional neural networks for time series classification. ArXiv:1603.06995

[6]

Cuturi M, Blondel M (2017) Soft-dtw: a differentiable loss function for time-series. In: International conference on machine learning, pp 894–903

[7]

Dau HA, Bagnall A, Kamgar K, Yeh CCM, Zhu Y, Gharghabi S, Ratanamahatana CA, Keogh E (2018) The ucr time series archive. ArXiv

[8]

Demšar JStatistical comparisons of classifiers over multiple data setsMach Learn Res200671-3022743601222.68184

[9]

Forestier G, Petitjean F, Senin P, Despinoy F, Huaulmé A, Ismail Fawaz H, Weber J, Idoumghar L, Muller PA, and Jannin P Surgical motion analysis using discriminative interpretable patterns Artif Intell Med 2018 91 3-11

[10]

Friedman MA comparison of alternative tests of significance for the problem of

m

rankingsAnn Math Stat194011186-922085

[11]

Garcia S and Herrera FAn extension on “statistical comparisons of classifiers over multiple data sets” for all pairwise comparisonsMach Learn Res200892677-26941225.68178

[12]

Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feed forward neural networks. In: International conference on artificial intelligence and statistics vol 9, pp 249–256

[13]

Guan C, Wang X, Zhang Q, Chen R, He D, Xie X (2019) Towards a deep and unified understanding of deep neural models in NLP. In: International conference on machine learning, pp 2454–2463

[14]

He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition, pp 770–778

[15]

Hills J, Lines J, Baranauskas E, Mapp J, and Bagnall AClassification of time series by shapelet transformationData Min Knowl Disc2014284851-8813176926

[16]

Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: IEEE conference on computer vision and pattern recognition, pp 4700–4708

[17]

Ismail Fawaz H, Forestier G, Weber J, Idoumghar L, Muller PA (2018) Transfer learning for time series classification. In: IEEE international conference on big data, pp 1367–1376

[18]

Ismail Fawaz H, Forestier G, Weber J, Idoumghar L, Muller PA (2019a) Adversarial attacks on deep neural networks for time series classification. In: IEEE international joint conference on neural networks

[19]

Ismail Fawaz H, Forestier G, Weber J, Idoumghar L, Muller PA (2019b) Deep learning for time series classification: a review. Data Min Knowl Discov

[20]

Ismail Fawaz H, Forestier G, Weber J, Idoumghar L, Muller PA (2019c) Deep neural network ensembles for time series classification. In: IEEE international joint conference on neural networks

[21]

Ismail Fawaz H, Forestier G, Weber J, Petitjean F, Idoumghar L, Muller PA (2019d) Automatic alignment of surgical videos using kinematic data. In: Artificial intelligence in medicine, pp 104–113

[22]

Karimi-Bidhendi S, Munshi F, Munshi A (2018) Scalable classification of univariate and multivariate time series. In: IEEE international conference on big data, pp 1598–1605

[23]

Kashiparekh K, Narwariya J, Malhotra P, Vig L, Shroff G (2019) Convtimenet: A pre-trained deep convolutional neural network for time series classification. In: IEEE international joint conference on neural networks

[24]

Keogh EJ, Pazzani MJ (2001) Derivative dynamic time warping. In: Proceedings of the 2001 SIAM international conference on data mining, SIAM, pp 1–11

[25]

Kingma DP, Ba J (2015) Adam: A method for stochastic optimization. In: International conference on learning representations

[26]

Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105

[27]

Le Guennec A, Malinowski S, Tavenard R (2016) Data augmentation for time series classification using convolution neural networks. In: ECML/PKDD workshop on advanced analytics and learning on temporal data

[28]

LeCun Y, Bottou L, Orr GB, Müller KR (1998) Efficient backprop. In: Neural networks: tricks of the trade, this book is an outgrowth of a 1996 NIPS workshop, pp 9–50

[29]

LeCun Y, Bengio Y, and Hinton G Deep learning Nature 2015 521 436-444

[30]

Lee W, Park S, Joo W, Moon IC (2018) Diagnosis prediction via medical context attention networks using deep generative modeling. In: IEEE international conference on data mining, pp 1104–1109

[31]

Lines J and Bagnall ATime series classification with ensembles of elastic distance measuresData Min Knowl Disc2015293565-5923334315

[32]

Lines J, Taylor S, Bagnall A (2016) HIVE-COTE: The hierarchical vote collective of transformation-based ensembles for time series classification. In: IEEE international conference on data mining, pp 1041–1046

[33]

Liu Y, Yu J, and Han Y Understanding the effective receptive field in semantic image segmentation Multimed Tools Appl 2018 77 17 22159-22171

[34]

Lucas B, Shifaz A, Pelletier C, O’Neill L, Zaidi N, Goethals B, Petitjean F, and Webb GI Proximity forest: an effective and scalable distance-based classifier for time series Data Min Knowl Disc 2019 33 3 607-635

[35]

Luo W, Li Y, Urtasun R, Zemel R (2016) Understanding the effective receptive field in deep convolutional neural networks. In: Advances in neural information processing systems, pp 4898–4906

[36]

Marteau P Time warp edit distance with stiffness adjustment for time series matching IEEE Trans Pattern Anal Mach Intell 2009 31 2 306-318

[37]

Pelletier C, Webb GI, and Petitjean F Temporal convolutional neural network for the classification of satellite image time series Remote Sens 2019 11 5 523

[38]

Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, and Fei-Fei LImageNet large scale visual recognition challengeInt J Comput Vision20151153211-2523422482

[39]

Sabour S, Frosst N, Hinton GE (2017) Dynamic routing between capsules. In: Advances in neural information processing systems, pp 3856–3866

[40]

Scardapane S and Wang D Randomness in neural networks: an overview Wiley Interdiscip Rev Data Min Knowl Discov 2017 7 2 e1200

[41]

Schäfer PThe boss is concerned with time series classification in the presence of noiseData Min Knowl Disc20152961505-15303401818

[42]

Schäfer P (2015b) Scalable time series classification. Data Min Knowl Discov, pp 1–26

[43]

Schäfer P, Leser U (2017) Fast and accurate time series classification with WEASEL. In: Proceedings of the 2017 ACM on conference on information and knowledge management, ACM, pp 637–646

[44]

Stefan A, Athitsos V, and Das G The move-split-merge metric for time series IEEE Trans Knowl Data Eng 2013 25 6 1425-1438

[45]

Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9

[46]

Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: AAAI conference on artificial intelligence

[47]

Tan CW, Webb GI, Petitjean F (2017) Indexing and classifying gigabytes of time series under time warping. In: Proceedings of the 2017 SIAM international conference on data mining, SIAM, pp 282–290

[48]

Vlachos M, Hadjieleftheriou M, Gunopulos D, and Keogh E Indexing multidimensional time-series VLDB J Int J Very Large Data Bases 2006 15 1 1-20

[49]

Wang Z, Yan W, Oates T (2017) Time series classification from scratch with deep neural networks: A strong baseline. In: International joint conference on neural networks, pp 1578–1585

[50]

Yi F, Yu Z, Zhuang F, Zhang X, Xiong H (2018) An integrated model for crime prediction using temporal and spatial factors. In: IEEE international conference on data mining, pp 1386–1391

[51]

Yuan Y, Xun G, Ma F, Wang Y, Du N, Jia K, Su L, Zhang A (2018) Muvan: A multi-view attention network for multivariate temporal data. In: IEEE international conference on data mining, pp 717–726

[52]

Zhang C, Tavanapong W, Kijkul G, Wong J, de Groen PC, Oh J (2018) Similarity-based active learning for image classification under class imbalance. In: IEEE international conference on data mining, pp 1422–1427

Cited By

Farahani MMcCormick MHarik RWuest T(2025)Time-series classification in smart manufacturing systemsRobotics and Computer-Integrated Manufacturing10.1016/j.rcim.2024.10283991:COnline publication date: 1-Feb-2025
https://dl.acm.org/doi/10.1016/j.rcim.2024.102839
Li YWang MGuan MLu CLi ZChen T(2025)SAPTSTA-AnoECG: a PatchTST-based ECG anomaly detection method with subtractive attention and data augmentationApplied Intelligence10.1007/s10489-024-05881-555:2Online publication date: 1-Jan-2025
https://dl.acm.org/doi/10.1007/s10489-024-05881-5
Chen XQiu PZhu WLi HWang HSotiras AWang YRazi ASalakhutdinov RKolter ZHeller KWeller AOliver NScarlett JBerkenkamp F(2024)TimeMILProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3692348(7190-7206)Online publication date: 21-Jul-2024
https://dl.acm.org/doi/10.5555/3692070.3692348
Show More Cited By

Recommendations

Time Series Classification with HIVE-COTE: The Hierarchical Vote Collective of Transformation-Based Ensembles

A recent experimental evaluation assessed 19 time series classification (TSC) algorithms and found that one was significantly more accurate than all others: the Flat Collective of Transformation-based Ensembles (Flat-COTE). Flat-COTE is an ensemble that ...
Exploiting multi-channels deep convolutional neural networks for multivariate time series classification

Time series classification is related to many different domains, such as health informatics, finance, and bioinformatics. Due to its broad applications, researchers have developed many algorithms for this kind of tasks, e.g., multivariate time series ...
Data Augmentation for Time Series Classification with Deep Learning Models
Advanced Analytics and Learning on Temporal Data
Abstract
Deep Learning models for time series classification are benchmarked on the UCR Archive. This archive contains 128 datasets. Unfortunately only 5 datasets contain more than 1000 training samples. For most deep learning models, this lead to over-...

Comments

Information & Contributors

Information

Published In

cover image Data Mining and Knowledge Discovery

Data Mining and Knowledge Discovery Volume 34, Issue 6

Nov 2020

365 pages

ISSN:1384-5810

Issue’s Table of Contents

© The Author(s), under exclusive licence to Springer Science+Business Media LLC, part of Springer Nature 2020.

Publisher

Kluwer Academic Publishers

United States

Publication History

Published: 01 November 2020

Accepted: 27 July 2020

Received: 11 September 2019

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

226
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 06 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Farahani MMcCormick MHarik RWuest T(2025)Time-series classification in smart manufacturing systemsRobotics and Computer-Integrated Manufacturing10.1016/j.rcim.2024.10283991:COnline publication date: 1-Feb-2025
https://dl.acm.org/doi/10.1016/j.rcim.2024.102839
Li YWang MGuan MLu CLi ZChen T(2025)SAPTSTA-AnoECG: a PatchTST-based ECG anomaly detection method with subtractive attention and data augmentationApplied Intelligence10.1007/s10489-024-05881-555:2Online publication date: 1-Jan-2025
https://dl.acm.org/doi/10.1007/s10489-024-05881-5
Chen XQiu PZhu WLi HWang HSotiras AWang YRazi ASalakhutdinov RKolter ZHeller KWeller AOliver NScarlett JBerkenkamp F(2024)TimeMILProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3692348(7190-7206)Online publication date: 21-Jul-2024
https://dl.acm.org/doi/10.5555/3692070.3692348
Seong JKim JChoi JWooldridge MDy JNatarajan S(2024)Towards diverse perspective learning with selection over multiple temporal poolingsProceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence10.1609/aaai.v38i8.28743(8948-8956)Online publication date: 20-Feb-2024
https://dl.acm.org/doi/10.1609/aaai.v38i8.28743
Gullapalli BCarreiro SChapman BGarland ERahman TWooldridge MDy JNatarajan S(2024)Pharmacokinetics-informed neural network for predicting opioid administration moments with wearable sensorsProceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence10.1609/aaai.v38i21.30326(22892-22898)Online publication date: 20-Feb-2024
https://dl.acm.org/doi/10.1609/aaai.v38i21.30326
Bian CLi XBi QZhu GLyu JZhang WLi YZeng ZWooldridge MDy JNatarajan S(2024)Constraint latent space mattersProceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence10.1609/aaai.v38i10.28985(11087-11095)Online publication date: 20-Feb-2024
https://dl.acm.org/doi/10.1609/aaai.v38i10.28985
Campos DYang BKieu TZhang MGuo CJensen C(2024)QCore: Data-Efficient, On-Device Continual Calibration for Quantized ModelsProceedings of the VLDB Endowment10.14778/3681954.368195717:11(2708-2721)Online publication date: 30-Aug-2024
https://doi.org/10.14778/3681954.3681957
Zhong SSong SZhuo WLi GLiu YChan S(2024)A Multi-Scale Decomposition MLP-Mixer for Time Series AnalysisProceedings of the VLDB Endowment10.14778/3654621.365463717:7(1723-1736)Online publication date: 1-Mar-2024
https://dl.acm.org/doi/10.14778/3654621.3654637
Ravikumar DYeo AZhu YLakra ANagulapalli HRavindran SSuh SDutta NFogarty APark YKhushalani STarafdar AParekh KKrishnan S(2024)Intelligent Pooling: Proactive Resource Provisioning in Large-scale Cloud ServiceProceedings of the VLDB Endowment10.14778/3654621.365462917:7(1618-1627)Online publication date: 1-Mar-2024
https://dl.acm.org/doi/10.14778/3654621.3654629
Sankosik PRatanamahatana C(2024)Data Augmentation Strategies for Improving Time Series Classification AccuracyProceedings of the 2024 7th International Conference on Robot Systems and Applications10.1145/3702468.3702479(51-58)Online publication date: 12-Sep-2024
https://dl.acm.org/doi/10.1145/3702468.3702479
Show More Cited By

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents