Abstract
The classification of Phonocardiogram (PCG) time series, which is often used to indicate the heart conditions through a high-fidelity sound recording, is an important aspect in diagnosing heart-related medical conditions, particularly on canines. Both the size of the PCG time series and the irregularities featured within them render this classification process very challenging. In classifying PCG time series, motif-based approaches are considered to be very viable approach. The central idea behind motif-based approaches is to identify reoccurring sub-sequences (which are referred to as motifs) to build a classification model. However, this approach becomes challenging with large time series where the resource requirements for adopting motif-based approaches are very intensive. This paper proposes a novel two-layer PCG segmentation technique, called as PCGseg, that reduces the overall size of the time series, thus reducing the required for generating motifs. The evaluation results are encouraging and shows that the proposed approach reduces the generation time by a factor of six, without adversely affecting classification accuracy.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Bezruchko, B., Smirnov, D.: Extracting Knowledge From Time Series: An Introduction to Nonlinear Empirical Modeling. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-12601-7
Chiu, B., Keogh, E., Lonardi, S.: Probabilistic discovery of time series motifs. In: Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 493–498. ACM (2003)
Gao, Y., Lin, J., Rangwala, H.: Iterative grammar-based framework for discovering variable-length time series motifs. In: Proceedings of the 15th IEEE International Conference on Machine Learning and Applications (ICMLA 2017), pp. 111–116. IEEE (2017)
Serra, J., Arcos, J.: Cparticle swarm optimization for time series motif discovery. Knowl.-Based Syst. 92, 127–137 (2016)
Torkamani, S., Lohweg, V.: Survey on time series motif discovery. Wiley Interdiscip. Rev. Data Mining Knowl. Discov. 7(2), 1–8 (2017)
Keogh, E., Chu, S., Hart, D., Pazzani, M.: Segmenting time series: a survey and novel approach. In: Kandel, A., Bunke, H., Last, M. (eds.) Data mining in Time Series Databases, pp. 1–22. World Scientific (2001)
Huang, G., Zhou, X.: A piecewise linear representation method of hydrological time series based on curve feature. In: Proceedings of the 8th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC 2016), pp. 203–207 (2016)
Anirudh, R., Turaga, P.: Geometry-based symbolic approximation for fast sequence matching on manifolds. Int. J. Comput. Vis. 116(2), 161–173 (2016)
Keogh, E., Chakrabarti, K., Pazzani, M.: Mehrotra: dimensionality reduction for fast similarity search in large time series databases. J. Knowl. Inf. Syst. 3(3), 263–286 (2001)
Patel, A., Bullmore, E.: A wavelet-based estimator of the degrees of freedom in denoised fmri time series for probabilistic testing of functional connectivity and brain graphs. NeuroImage 142, 14–26 (2016)
Zhao, H., Dong, Z., Li, T., Wang, X., Pang, C.: Segmenting time series with connected lines under maximum error bound. Inf. Sci. 345, 1–8 (2016)
Zhao, H., Li, G., Zhang, H., Xue, Y.: An improved algorithm for segmenting online time series with error bound guarantee. Int. J. Mach. Learn. Cybern. 7(3), 365–374 (2016)
Belevich, I., Joensuu, M., Kumar, D., Vihinen, H., Jokitalo, E.: Microscopy image browser: a platform for segmentation and analysis of multidimensional datasets. PLOS Biol. J. 14(1), 1–13 (2016)
Oliveira, J., Sousa, C., Coimbra, M.: Coupled hidden Markov model for automatic ECG and PCG segmentation. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017), pp. 1023–1027 (2017)
Quiceno, A., Delgado, E., Vallverd, M., Matijasevic, A., Castellanos-Domnguez, G.: Effective phonocardiogram segmentation using nonlinear dynamic analysis and high-frequency decomposition. In: Proceedings of the Computers in Cardiology, pp. 161–164. IEEE (2008)
Ahlstrom, C.: NonLinear Phonocardiographic Signal Processing. Ph.D. thesis, Linkoping University, Sweden (2008)
Dokur, Z., lmez, T.: Heart sound classification using wavelet transform and incremental self-organizing map. Digit. Sig. Process. 18(6), 951–959 (2008)
Gavrovska, A., Paskas, M., Dujkovic, D., Reljin, I.: Region-based phonocardiogram event segmentation in spectrogram image. In: Proceedings of the Neural Network Applications in Electrical Engineering (NEUREL 2010), pp. 69–62. IEEE (2010)
Moukadem, A., Dieterlen, A., Hueber, N., Brandt, C.: Comparative study of heart sounds localization. In: Proceedings of the Bioelectronics, Biomedical and Bio-inspired Systems, SPIE Proceedings, vol. 8068, 9 p. (2011)
Helton, W.: Canine Ergonomics: The Science of Working Dogs. CRC Press, Boca Raton (2009)
Lin, J., Keogh, E., Wei, L., Lonardi, S.: Experiencing sax: a novel symbolic representation of time series. Data Min. Knowl. Disc. 15(2), 107–144 (2007)
Sklansky, J., Gonzalez, V.: Fast polygonal approximation of digitized curves. Pattern Recogn. 12(5), 327–331 (2007)
Mueen, A., Keogh, E., Zhu, Q., Cash, S., Westover, B.: Exact discovery of time series motifs. In: Proceedings of the SIAM International Conference on Data Mining, pp. 473–484 (2009)
Nakamura, K., Kawamoto, S., Osuga, T., Morita, T., Sasaki, N., Morishita, K., Takiguchi, M.: Left atrial strain at different stages of myxomatous mitral valve disease in dogs. J. Vet. Intern. Med. 31(2), 316–325 (2017)
Chen, C., Pau, L., Wang, P.: Handbook of Pattern Recognition and Computer Vision. World Scientific, River Edge (1993)
Kuncheva, L.: Combining Pattern Classifiers: Methods and Algorithms, 2nd edn. Wiley, New York (2014)
Wang, X., Fang, Z., Wang, P., Zhu, R., Wang, W.: A distributed multi-level composite index for KNN processing on long time series. In: Candan, S., Chen, L., Pedersen, T.B., Chang, L., Hua, W. (eds.) DASFAA 2017. LNCS, vol. 10177, pp. 215–230. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-55753-3_14
Stojanovic, M., Bozic, M., Stankovic, M., Stajic, Z.: A methodology for training set instance selection using mutual information in time series prediction. Neurocomputing 141, 236–245 (2014)
Witten, I., Frank, E., Hall, M., Pal, C.: Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Alhijailan, H., Coenen, F., Dukes-McEwan, J., Thiyagalingam, J. (2018). Segmenting Sound Waves to Support Phonocardiogram Analysis: The PCGseg Approach. In: Geng, X., Kang, BH. (eds) PRICAI 2018: Trends in Artificial Intelligence. PRICAI 2018. Lecture Notes in Computer Science(), vol 11013. Springer, Cham. https://doi.org/10.1007/978-3-319-97310-4_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-97310-4_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-97309-8
Online ISBN: 978-3-319-97310-4
eBook Packages: Computer ScienceComputer Science (R0)