Abstract
A process for generating a unifying motif-based homogeneous feature vector representation is described and evaluated. The motivation was to determine the viability of this representation as a unifying representation for heterogeneous data classification. The focus for the work was cardiovascular disease classification. The reported evaluation indicates that the proposed unifying representation is a viable one, producing better classification results than when a Recurrent Neural Network (RNNs) was applied to just ECG time series data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Dau, H.A., Keogh, E.: Matrix profile V: a generic technique to incorporate domain knowledge into motif discovery. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 125–134 (2017)
Lip, G., et al.: Atrial fibrillation. Nat. Rev. Dis. Primers 31, 16016 (2016)
Liu, F., et al.: An open access database for evaluating the algorithms of electrocardiogram rhythm and morphology abnormality detection. J. Med. Imaging Health Inform. 8(7), 1368–1373 (2018)
Mueen, A., Keogh, E., Zhu, Q., Sydney Cash, S., Westover, B.: Exact discovery of time series motifs. In: SIAM International Conference on Data Mining, pp. 473–484. SIAM (2009)
Oh, S.L., Ng, E.Y., San Tan, R., Acharya, U.R.: Automated diagnosis of arrhythmia using combination of CNN and LSTM techniques with variable length heart beats. Comput. Biol. Med. 102, 278–287 (2018)
Pourbabaee, B., Roshtkhari, M.J., Khorasani, K.: Deep convolutional neural networks and learning ECG features for screening paroxysmal atrial fibrillation patients. IEEE Tran. Syst. Man Cybern. Syst. 48(12), 2095–2104 (2018)
Wang, G., et al.: A global and updatable ECG beat classification system based on recurrent neural networks and active learning. Inf. Sci. 501, 523–542 (2019)
Yeh, C.C.M., et al.: Matrix profile I: all pairs similarity joins for time series: a unifying view that includes motifs, discords and shapelets. In: IEEE 16th International Conference on Data Mining (ICDM), pp. 1317–1322. IEEE (2016)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Aldosari, H., Coenen, F., Lip, G.Y.H., Zheng, Y. (2021). Motif Based Feature Vectors: Towards a Homogeneous Data Representation for Cardiovascular Diseases Classification. In: Golfarelli, M., Wrembel, R., Kotsis, G., Tjoa, A.M., Khalil, I. (eds) Big Data Analytics and Knowledge Discovery. DaWaK 2021. Lecture Notes in Computer Science(), vol 12925. Springer, Cham. https://doi.org/10.1007/978-3-030-86534-4_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-86534-4_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86533-7
Online ISBN: 978-3-030-86534-4
eBook Packages: Computer ScienceComputer Science (R0)