Time series classification and class imbalance problem are two common issues in a multitude of real-life scenarios. This paper simultaneously explores both issues with deep convolution neural networks (CNNs). Because standard networks treat the majority and minority classes with same class weights, most CNN-based networks fail to classify imbalanced time series. Until recently, there is very little work applying deep learning to imbalanced time series classification (ITSC). Thus, we propose an adaptive cost-sensitive learning strategy to address the ITSC problem. The standard CNN is modified to a cost-sensitive network (CS-CNN), which is able to punish the misclassified samples using a class-dependent cost matrix. Moreover, this cost matrix is automatically updated based on overall class distribution and the CS-CNN’s training performance. The proposed method is extended to FCN, LSTM-FCN and ResNet. It is experimentally tested on five public benchmark UCR datasets and a real-life large volume dataset. Four cost-sensitive CNN-based networks are compared with several data samplers and two traditional ITSC methods. The modified networks are superior in all metrics. Results show that cost-sensitive networks successfully complete the ITSC tasks.
AcharyaU.R.OhS.L.HagiwaraY.TanJ.H.AdamM.GertychA. and TanR.S., A deep convolutional neural network model to classify heartbeats, Computers in Biology and Medicine89 (2017), 389–396.
2.
BatistaG.E.BazzanA.L. and MonardM.C., Balancing Training Data for Automated Annotation of Keywords: a Case Study, in: Proceedings of the Second Brazilian Workshop on Bioinformatics, BSB, Macaé, RJ, 2003, pp. 35–43.
3.
BatistaG.E.PratiR.C. and MonardM.C., A study of the behavior of several methods for balancing machine learning training data, ACM SIGKDD Explorations Newsletter6 (2004), 20–29.
4.
BoulléM., Predicting Dangerous Seismic Events in Coal Mines under Distribution Drift, in: 2016 Federated Conference on Computer Science and Information Systems (FedCSIS), IEEE, Gdansk, Poland, 2016, pp. 221–224.
5.
BudaM.MakiA. and MazurowskiM.A., A Systematic Study of the Class Imbalance Problem in Convolutional Neural Networks, arXiv preprint arXiv:1710.05381, 2017.
6.
CaoH.LiX.L.WoonD.Y.K. and NgS.K., Integrated oversampling for imbalanced time series classification, IEEE Transactions on Knowledge and Data Engineering25 (2013), 2809–2822.
7.
CaoH.LiX.L.WoonY.K. and NgS.K., SPO: Structure Preserving Oversampling for Imbalanced Time Series Classification, in: 2011 IEEE 11th International Conference on Data Mining, IEEE, Vancouver, BC, Canada, 2011, pp. 1008–1013.
8.
ChambonS.GaltierM.ArnalP.WainribG. and GramfortA., A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series, IEEE Ttransactions on Neural Systems and Rehabilitation Engineering26 (2018), 758–769.
9.
ChawlaN.V.BowyerK.W.HallL.O. and KegelmeyerW.P., SMOTE: synthetic minority over-sampling technique, Journal of Artificial Intelligence Research16 (2002), 321–357.
10.
ChenY.KeoghE.HuB.BegumN.BagnallA.MueenA. and BatistaG., The UCR time series classification archive (2015), URL www. cs. ucr. edu/ eamonn/time_series_data (2016).
11.
CuiZ.ChenW. and ChenY., Multi-scale convolutional neural networks for time series classification, arXiv preprint arXiv:1603.06995, 2016.
12.
GünnemannN. and PfefferJ., Predicting Defective Engines using Convolutional Neural Networks on Temporal Vibration Signals, in: Proceedings of the First International Workshop on Learning with Imbalanced Domains: Theory and Applications, PMLR, Dublin, Ireland, 2017, pp. 92–102.
13.
GamboaJ.C.B., Deep Learning for Time-Series Analysis, arXiv preprint arXiv:1701.01887, 2017.
14.
GarcíaV.MollinedaR.A. and SánchezJ.S., Index of Balanced Accuracy: A Performance Measure for Skewed Class Distributions, in: Conference on Pattern Recognition and Image Analysis, Springer, Berlin, Heidelberg, 2009, pp. 441–448.
15.
GlorotX.BordesA. and BengioY., Deep Sparse Rectifier Neural Networks, in: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, PMLR, Fort Lauderdale, FL, USA, 2011, pp. 315–323.
16.
HaiboH.YangB.GarciaE.A. and ShutaoL., ADASYN: Adaptive synthetic sampling approach for imbalanced learning, in: IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), IEEE, Hong Kong, China, 2008, pp. 1322–1328.
17.
HaixiangG.YijingL.ShangJ.MingyunG.YuanyueH. and BingG., Learning from class-imbalanced data: review of methods and applications, Expert Systems with Applications73 (2017), 220–239.
18.
HanH.WangW.-Y. and MaoB.-H., Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning, in: International Conference on Intelligent Computing, Springer, Hefei, China, 2005, pp. 878–887.
19.
HeG.DuanY.PengR.JingX.QianT. and WangL., Early classification on multivariate time series, Neurocomputing149 (2015), 777–787.
20.
HeH. and GarciaE.A., Learning from imbalanced data, IEEE Transactions on Knowledge and Data Engineering21 (2009), 1263–1284.
21.
JanuszA.GrzegorowskiM.MichalakM.WróbelL.SikoraM. and SlezakD., Predicting seismic events in coal mines based on underground sensor measurements, Engineering Applications of Artifical Intelligence64 (2017), 83–94.
22.
Köknar-TezelS. and LateckiL.J., Improving SVM classification on imbalanced time series data sets with ghost points, Knowledge and Information Systems28 (2011), 1–23.
23.
KarimF.MajumdarS.DarabiH. and ChenS., LSTM fully convolutional networks for time series classification, IEEE Access6 (2018), 1662–1669.
24.
KasfiK.T.HellicarA. and RahmanA., Convolutional Neural Network for Time Series Cattle Behaviour Classification, in: Proceedings of the Workshop on Time Series Analytics and Applications, ACM, Hobart, TAS, Australia, 2016, pp. 8–12.
25.
KhanS.H.HayatM.BennamounM.SohelF.A. and TogneriR., Cost-sensitive learning of deep feature representations from imbalanced data, IEEE Transactions on Neural Networks and Learning Systems (2018), 1–15.
26.
KubatM. and MatwinS., Addressing the Curse of Imbalanced Training Sets: One-Sided Selection, in: Proceedings of the Fourteen International Conference on Machine Learning, ACM, Nashville, USA, 1997, pp. 179–186.
27.
KukarM. and KononenkoI., Cost-Sensitive Learning with Neural Networks, in: European Conferene on Artifiial Intelligence, John Wiley and Sons, Brighton, UK, 1998, pp. 445–449.
28.
LópezV.FernándezA.GarcícS.PaladeV. and HerreraF., An insight into classification with imbalanced data: empirical results and current trends on using data intrinsic characteristics, Information Sciences250 (2013), 113–141.
29.
LaurikkalaJ., Improving Identification of Difficult Small Classes by Balancing Class Distribution, in: Conference on Artificial Intelligence in Medicine in Europe, Springer, Cascais, Portugal, 2001, pp. 63–66.
30.
LemaîreG.NogueiraF. and AridasC.K., Imbalanced-learn: a python toolbox to tackle the curse of imbalanced datasets in machine learning, Journal of Machine Learning Research18 (2017), 1–5.
31.
LiangG., An Effective Method for Imbalanced Time Series Classification: Hybrid Sampling, in: Proceedings of the 26th Australasian Joint Conference on AI 2013, Springer, Dunedin, NewZealand, 2013, pp. 374–385.
32.
LiangG. and ZhangC., A Comparative Study of Sampling Methods and Algorithms for Imbalanced Time Series Classification, in: Autralasial Joint Conference on Artificial Intelligence, Springer, Melbourne, VIC, Australia, 2012, pp. 637–648.
33.
ManiI. and ZhangI., KNN Approach to Unbalanced Data Distributions: A Case Study Involving Information Extraction, in: Proceedings of the ICML’03 Workshop on Learning from Imbalanced Datasets, AAAI, Washington, DC, USA, 2003.
34.
MonizN.BrancoP. and TorgoL., Resampling Strategies for Imbalanced Time Series, in: 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA), IEEE, Montreal, QC, Canada, 2016, pp. 282–291.
35.
NguyenH.M.CooperE.W. and KameiK., Borderline over-sampling for imbalanced data classification, International Journal of Knowledge Engineering and Soft Data Paradigms3 (2011), 4–21.
36.
RajV.MaggS. and WermterS., Towards effective classification of imbalanced data with convolutional neural networks, in: IAPR Workshop on Artificial Neural Networks in Pattern Recognition, Springer, ULM, Germany, 2016, pp. 150–162.
37.
RoychoudhuryS.GhalwashM. and ObradovicZ., Cost Sensitive Time-Series Classification, in: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Springer, Skopje, Macedonia, 2017, pp. 495–511.
38.
SammutC. and WebbG.I., Encyclopedia of Machine Learning, Springer Publishing Company, Incorporated, 2011, pp. 209–210.
39.
SmithM.R.MartinezT. and Giraud-CarrierC., An instance level analysis of data complexity, Machine Learning95 (2014), 225–256.
40.
ThodoroffP.PineauJ. and LimA., Learning Robust Features using Deep Learning for Automatic Seizure Detection, in: Proceedings of the 1st Machine Learning for Healthcare Conference, PMLR, Los Angeles, CA, USA, 2016, pp. 178–190.
41.
TomekI., Two modifications of CNN, IEEE Trans. Systems, Man and Cybernetics6 (1976), 769–772.
42.
WangJ.FengJ. and HanZ., Fault detection for the class imbalance problem in semiconductor manufactoring provesses, Journal of Circuits, Systems and Computers23 (2014), 1450049: 1–20.
43.
WangS.LiuW.WuJ.CaoL.MengQ. and KennedyP.J., Training Deep Neural Networks on Imbalanced Data Sets, in: 2016 International Joint Conference on Neural Networks (IJCNN), IEEE, Vancouver, BC, Canada, 2016, pp. 4368–4374.
44.
WangW.ChenC.WangW.RaiP. and CarinL., Earliness-Aware Deep Convolutional Networks for Early Time Series Classification, arXiv preprint arXiv:1611.04578, 2016.
45.
WangZ.YanW. and OatesT., Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline, in: 2017 International Joint Conference on Neural Networks (IJCNN), IEEE, Anchorage, AK, USA, 2017, pp. 1578–1585.
46.
WilsonD.L., Asymptotic properties of nearest neighbor rules using edited data, IEEE Transactions on Systems, Man, and CyberneticsSMC-2 (1972), 408–421.
47.
XiX.KeoghE.SheltonC.WeiL. and RatanamahatanaC.A., Fast Time Series Classification Using Numerosity Reduction, in: Proceedings of the 23rd International Conference on Machine Learning, ACM, Pittsburgh, Pennsylvania, USA, 2006, pp. 1033–1040.
48.
YangQ. and WuX., 10 challenging problems in data mining research, International Journal of Information Technology & Decision Making5 (2006), 597–604.
49.
ZhengY.LiuQ.ChenE.GeY. and ZhaoJ.L., Time Series Classification Using Multi-Channels Deep Convolutional Neural Networks, in: International Conference on Web-Age Information Management, Springer, Nanchang, China, 2014, pp. 298–310.
50.
ZhengY.LiuQ.ChenE.GeY. and ZhaoJ.L., Exploiting multi-channels deep convolutional neural networks for multivariate time series classification, Frontiers of Computer Science10 (2016), 96–112.
51.
ZhouZ.-H. and LiuX.-Y., Training cost-sensitive neural networks with methods addressing the class imbalance problem, IEEE Transactions on Knowledge and Data Engineering18 (2006), 63–77.
