Abstract
Time series classification is an important branch of data analysis. Scholars have proposed a large number of time series classification methods in recent years. However, time series classification remains a challenging problem due to feature selection in time series classification. In order to further simplify the feature selection procedure and improve time series classification accuracy, an automatic feature selection of a time series classification method based on an image feature fusion strategy and a deep learning algorithm is proposed. First, a time series is transformed into images using different types of image transformation methods, i.e. the recurrence plot, Gramian angle difference field, Gramian angle summation field and Markov transition field. Second, the above four images are encoded into a new image type, that is the combined image, by a feature fusion strategy. Finally, a convolutional neural network is used for combined image classification and forecasting model selection. Time series from the M1 and M3 competition datasets are used to verify the effectiveness of the proposed method. The experimental results show that the algorithm has a higher classification accuracy and smaller prediction error compared to the benchmark models. Moreover, the forecasting error MAPE of combined image method is reduced by 0.2020 and 1.7454 compared with the traditional image method and single forecasting methdd respectively.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-022-10783-z/MediaObjects/11063_2022_10783_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-022-10783-z/MediaObjects/11063_2022_10783_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-022-10783-z/MediaObjects/11063_2022_10783_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-022-10783-z/MediaObjects/11063_2022_10783_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-022-10783-z/MediaObjects/11063_2022_10783_Fig5_HTML.jpg)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-022-10783-z/MediaObjects/11063_2022_10783_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-022-10783-z/MediaObjects/11063_2022_10783_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-022-10783-z/MediaObjects/11063_2022_10783_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-022-10783-z/MediaObjects/11063_2022_10783_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-022-10783-z/MediaObjects/11063_2022_10783_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-022-10783-z/MediaObjects/11063_2022_10783_Fig11_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-022-10783-z/MediaObjects/11063_2022_10783_Fig12_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-022-10783-z/MediaObjects/11063_2022_10783_Fig13_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-022-10783-z/MediaObjects/11063_2022_10783_Fig14_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-022-10783-z/MediaObjects/11063_2022_10783_Fig15_HTML.png)
Similar content being viewed by others
References
Yang S , Zheng X , Ji C , et al (2021) Multi-layer representation learning and its application to electronic health records. Neural Process Lett 1–17
Liu B , Zhang Z , Cui R (2020) Efficient time series augmentation methods. In: 2020 13th international congress on image and signal processing, BioMedical engineering and informatics (CISP-BMEI)
Auge D, Hille J, Mueller E et al (2021) A survey of encoding techniques for signal processing in spiking neural networks. Neural Process Lett 53:4693–4710
Ghanem W, Jantan A (2019) Training a neural network for cyberattack classification applications using hybridization of an artificial bee colony and monarch butterfly optimization. Neural Process Lett 51:905–946
Zg A, Vk B, Mi B et al (2020) Weighted kNN and constrained elastic distances for time-series classification - ScienceDirect. Expert Syst Appl 162:113829
Lines J, Bagnall A (2015) Time series classification with ensembles of elastic distance measures. Data Min Knowl Disc 29(3):565–592
Xiao X, Lu Y, Huang X et al (2021) Temporal series crop classification study in rural china based on sentinel-1 SAR data. IEEE J Sel Top Appl Earth Obs Remote Sens 99:1–1
Geler Z , Kurbalija V , Ivanovic M , et al. (2020) Time-series classification with constrained DTW distance and inverse-square weighted k-NN. In: 2020 international conference on innovations in intelligent systems and applications (INISTA)
Lines J, Bagnall A (2015) Time series classification with ensembles of elastic distance measures. Data Min Knowl Disc 29(3):565–592
Buza K, Nanopoulos A, Schmidt-Thieme L (2011) Time-series classification based on individualised error prediction. In: IEEE international conference on computational science engineering. IEEE
Morchen F, Ultsch A, Thies M et al (2006) Modeling timbre distance with temporal statistics from polyphonic music. IEEE Trans Audio Speech Lang Process 14(1):81–90
Wang X, Smith K, Hyndman R (2006) Characteristic-based clustering for time series data. Data Min knowl discov 13(3):335–364
Lin J, Keogh E, Wei L et al (2007) Experiencing SAX: a novel symbolic representation of time series. Data Min Knowl Discov 15(2):107–144
Baydogan MG, Runger G, Tuv E (2013) A bag-of-features framework to classify time series. IEEE Trans Pattern Anal Mach Intell 35(11):2796–2802
Bagnall A, Lines J, Bostrom A, Large J, Keogh E (2017) The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Min Knowl Disc 31(3):606–660
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444
Xu J-L et al (2021) Deep learning for classification of time series spectral images using combined multi-temporal and spectral features. Anal Chim Acta 1143:9–20. https://doi.org/10.1016/j.aca.2020.11.018
Yang C, Jiang W, Guo Z (2019) Time series data classification based on dual path cnn-rnn cascade network. IEEE Access 7:155304–155312
Gupta S, Kumar M, Garg A (2019) Improved object recognition results using SIFT and ORB feature detector. Multimed Tools Appl 78(23):34157–34171
Kumar M, Gupta S (2021) 2D-human face recognition using SIFT and SURF descriptors of face’s feature regions. Vis Comput 37(11)
Chhabra P, Garg NK, Kumar M (2020) Content-based image retrieval system using ORB and SIFT features. Neural Comput Appl 32(7):2725–2733
Kumar M , Kumar R , Saluja K K , et al. (2021) Gait recognition based on vision systems: a systematic survey. J Vis Commun Image Represent 75(6)
Goldberg Y (2016) A primer on neural network models for natural language processing. Artif Intell Res 57(1):345–420
Bansal M, Kumar M, Kumar M, et al. (2020) An efficient technique for object recognition using Shi-Tomasi corner detection algorithm. Soft Comput 1–10
Kumar M, Bansal M, Kumar M (2020) XGBoost: 2D-object recognition using shape descriptors and extreme gradient boosting classifier. In: International conference on computational methods and data engineering (ICMDE 2020)
Kumar Munish, Chhabra et al (2018) An efficient content based image retrieval system using BayesNet and K-NN. Multimed Tools Appl 77(16):21557–21570
Garg Diksha, Naresh et al (2018) Underwater image enhancement using blending of CLAHE and percentile methodologies[J]. Multimed Tools Appl 77(20):26545–26561
Lecun Y, Boser B, Denker J et al (2014) Backpropagation applied to handwritten zip code recognition. Neural Comput 1(4):541–551
Pereira S, Pinto A, Alves V, Silva CA (2016) Brain tumor segmentation using convolutional neural networks in mri images. IEEE Trans Med Imaging 35(5):1240–1251
Campanharo ASLO, Sirer MI, Malmgren RD, Ramos FM, Amaral LAN (2011) Duality between time series and networks. PLoS ONE 6(8):1–13
Wang Z, Oates T (2015) Encoding time series as images for visual inspection and classification using tiled convolutional neural networks. In: Workshops at the twenty-ninth aaai conference on artificial intelligence
Li X, Kang Y, Li F (2020) Forecasting with time series imaging. Expert Syst Appl 1(3):113–130
Akbar S, Ali F, Khan S et al (2020) Deep-AntiFP: prediction of antifungal peptides using distanct multi-information fusion incorporating with deep neural networks. Chemom Intell Lab Syst 208:104214
Zhang X, Zhao H (2021) Hyperspectral-cube-based mobile face recognition: a comprehensive review. Inf Fusion 74(24)
Ye TA, Xm A, Hc A et al (2021) Using Z-number to measure the reliability of new information fusion method and its application in pattern recognition. Appl Soft Comput 111:107658
Campanharo AS, Sirer MI, Malmgren RD, Ramos FM, Amaral LAN (2011) Duality between time series and networks. PLoS ONE 6(8):233–248
Eckmann JP, Kamphorst SO, Ruelle D (1987) Recurrence plots of dynamical systems. Europhys Lett 4(9):973–977
Thiel M, Romano MC, Jürgen Kurths (2004) How much information is contained in a recurrence plot? Phys Lett A 330(5):343–349
Xu JL, Hugelier S, Zhu H et al (2020) Deep learning for classification of time series spectral images using combined multi-temporal and spectral features. Anal Chim Acta 1143:9–20
He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. IEEE Comput Soc 33(5):243–249
Jaworek-Korjakowska J, Kleczek P, Gorgon M (2019) Melanoma thickness prediction based on convolutional neural network with VGG-19 model transfer learning. In: 2019 IEEE/CVF conference on computer vision and pattern recognition workshops (CVPRW). IEEE
Zhu Y, Newsam S (2017) DenseNet for dense flow. Comput Sci 6(2):790–794
Acknowledgements
This work was supported by the National Natural Science Foundation of China (71971089,72001083) and Natural Science Foundation of Guangdong Province (No. 2022A1515011612).
Funding
Natural Science Foundation of Guangdong Province (No.2022A1515011612). Thanks for your coorperation.
Author information
Authors and Affiliations
Contributions
WJ Software, Data curation, Writing, Methodology. DZ Writing-review, Supervision. LL Conceptualization, Methodology, Writing—review, Supervision. RL Software, Data curation.
Corresponding author
Ethics declarations
Conflict of interest
All Authors declar that they have no conflict of interest.
Ethical approval
This artical does not contain any studies with human participants or animals performed by any of the authors.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Jiang, W., Zhang, D., Ling, L. et al. Time Series Classification Based on Image Transformation Using Feature Fusion Strategy. Neural Process Lett 54, 3727–3748 (2022). https://doi.org/10.1007/s11063-022-10783-z
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-022-10783-z