With the rapid advancements in industrial big data, the Internet of Things, and sensor acquisition technologies, the similarity measurement of multivariate time series has emerged as a pivotal research area in data mining and machine learning. To enhance the accuracy and efficacy of multivariate time series similarity measurement, this paper proposes a sliding window approach based on Transformer. Specifically, each dimension of the multivariate time series is processed through sliding windows and input into a Transformer for feature extraction. By using multiple window sizes, the method simultaneously captures localized temporal segment features and identifies local patterns within the time series. Encoded window features for each sample are combined to form a comprehensive feature sequence that represents the global characteristics of the entire time series. These global features are then used to compute the final similarity measure through Dynamic Time Warping (DTW). This approach effectively captures both local and global features of multivariate time series, significantly improving similarity measurement precision. The effectiveness of the proposed method is validated through 1-Nearest Neighbor (1NN) classification experiments, demonstrating superior accuracy and enhanced performance in similarity measurement. The experiments showed that ten of the sixteen datasets had the best performance in terms of classification accuracy.
RuizAPFlynnMLargeJ, et al.The great multivariate time series classification bake off: a review and experimental evaluation of recent algorithmic advances[J]. Data Min Knowl Discov2021; 35: 401–449.
2.
HamiltonJD. Time series analysis[M]. Princeton, NJ: Princeton University Press, 2020.
3.
ZhaoFGaoYLiX, et al.A similarity measurement for time series and its application to the stock market[J]. Expert Syst Appl2021; 182: 115217.
4.
GargY. Multi-variate time series similarity measures and their robustness against temporal asynchrony[M]. Tempe, AZ: Arizona State University, 2015.
5.
WeiWWS. Multivariate time series analysis and applications[M]. Hoboken, NJ: John Wiley & Sons, 2019.
6.
MalkauthekarMD. Analysis of Euclidean distance and manhattan distance measure in face recognition[C]. Third International Conference on Computational Intelligence and Information Technology (CIIT 2013). IET, 2013: 503–507.
7.
ZermiNKhaldiAKafiR, et al.A DWT-SVD based robust digital watermarking for medical image security[J]. Forensic Sci Int2021; 320: 110691.
8.
BootsBNGetlsA. Point pattern analysis[J]. Geogr Anal2020; 52: 543–561.
9.
RabinerLSchmidtC. Application of dynamic time warping to connected digit recognition[J]. IEEE Trans Acoust Speech Signal Process1980; 28: 377–388.
10.
SuHLiuSZhengB, et al.A survey of trajectory distance measures and performance evaluation[J]. VLDB J2020; 29: 3–32.
11.
BarandasMFolgadoDFernandesL, et al.TSFEL: time series feature extraction library[J]. SoftwareX2020; 11: 100456.
12.
FanRZhuMZhangX. Multivariate time series feature extraction and clustering framework for multi-function radar work mode recognition[J]. Electronics (Basel)2024; 13: 1412.
13.
MalekiMManshouriNKayikçioğluT.Fast and accurate classifier-based brain-computer interface system using single channel EEG data[C]. 2018 26th Signal Processing and Communications Applications Conference (SIU). IEEE, 2018: 1–4.
14.
ManshouriNKayıkçıoğluT. Classification of 2D and 3D videos based on EEG waves[C]. 2016 24th Signal Processing and Communication Application Conference (SIU). IEEE, 2016: 949–952.
15.
ManshouriNKayikciogluT. A comprehensive analysis of 2D&3D video watching of EEG signals by increasing PLSR and SVM classification results[J]. Comput J2020; 63: 425–434.
16.
ChiarotGSilvestriC. Time series compression survey[J]. ACM Comput Surv2023; 55: 1–32.
17.
IslamMRLimaAADasSC, et al.A comprehensive survey on the process, methods, evaluation, and challenges of feature selection[J]. IEEE Access2022; 10: 99595–99632.
18.
SchmidlSWenigPPapenbrockT. Anomaly detection in time series: a comprehensive evaluation[J]. Proceedings of the VLDB Endowment2022; 15: 1779–1797.
19.
KaurJParmarKSSinghS. Autoregressive models in environmental forecasting time series: a theoretical and application review[J]. Environmental Science and Pollution Research2023; 30: 19617–19641.
20.
DongHGuoXReichgeltH, et al.Predictive power of ARIMA models in forecasting equity returns: a sliding window method[J]. Journal of Asset Management2020; 21: 549–566.
21.
MorBGarhwalSKumarA. A systematic review of hidden Markov models and their applications[J]. Arch Comput Methods Eng2021; 28: 1429–1448.
22.
ChatfieldCXingH. The analysis of time series: an introduction with R[M]. Boca Raton, FL: Chapman and Hall/CRC, 2019.
23.
PradoRWestM. Time series: modeling, computation, and inference[M]. Boca Raton, FL: Chapman and Hall/CRC, 2010.
24.
ReddyGTReddyMPKLakshmannaK, et al.Analysis of dimensionality reduction techniques on big data[J]. Ieee Access2020; 8: 54776–54788.
25.
KuritaT. Principal component analysis (PCA)[M]. In: Computer vision: a reference guide. Cham: Springer International Publishing, 2021: 1013–1016.
26.
DaraSTummaP.Feature extraction by using deep learning: a survey[C]. 2018 Second international conference on electronics, communication and aerospace technology (ICECA). IEEE, 2018: 1795–1801.
27.
BankDKoenigsteinNGiryesR.Autoencoders[J]. In: Machine learning for data science handbook: data mining and knowledge discovery handbook. Cham, Switzerland: Springer, 2023: 353–374.
28.
LeaCFlynnM DVidalR, et al.Temporal convolutional networks for action segmentation and detection[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017: 156–165.
29.
SchmidtRM. Recurrent neural networks (rnns): A gentle introduction and overview[J]. arXiv preprint2019; arXiv:1912.05911: 1–18.
30.
YuYSiXHuC, et al.A review of recurrent neural networks: LSTM cells and network architectures[J]. Neural Comput2019; 31: 1235–1270.
31.
WenQZhouTZhangC, et al.Transformers in time series: a survey[J]. arXiv preprint2022; arXiv:2202.07125: 1–35.
32.
LinTWangYLiuX, et al.A survey of transformers[J]. AI open2022; 3: 111–132.
33.
ZerveasGJayaramanSPatelD, et al.A transformer-based framework for multivariate time series representation learning[C]. Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining. 2021: 2114–2124.
34.
ZhouHZhangSPengJ, et al.Informer: beyond efficient transformer for long sequence time-series forecasting[C]. Proceedings of the AAAI Conference on Artificial Intelligence2021; 35: 11106–11115.
35.
LiuMRenSMaS, et al.Gated transformer networks for multivariate time series classification[J]. arXiv preprint2021; arXiv:2103.14438.
36.
TuliSCasaleGJenningsNR. Tranad: Deep transformer networks for anomaly detection in multivariate time series data[J]. arXiv preprint 2022; arXiv:2201.07284: 1–10.
37.
LiXMetsisVWangH, et al.Tts-gan: a transformer-based time-series generative adversarial network[C]. International conference on artificial intelligence in medicine. Cham: Springer International Publishing, 2022: 133–143.
38.
ZengAChenMZhangL, et al.Are transformers effective for time series forecasting? [C]. Proceedings of the AAAI Conference on Artificial Intelligence2023; 37: 11121–11128.
39.
SakoeHChibaS. Dynamic programming algorithm optimization for spoken word recognition[J]. IEEE Trans Acoust Speech Signal Process1978; 26: 43–49.
40.
AshishV. Attention is all you need[J]. Adv Neural Inf Process Syst2017; 30: I.
41.
The UEA multivariate time series classification archive, 2018.
