Improving Classification of Microembolus and Artifact of HITS Event by Feature Selection

  • Najah GhazaliEmail author
  • Maz Jamilah MasnanEmail author
  • Dzati Athiar RamliEmail author
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 547)


In monitoring system using transcranial Doppler ultrasound for stroke detection, the occurrence of high intensity transient signal can happen at different branch of arteries, i.e. internal cerebral artery (ICA), middle cerebral artery (MCA) and posterior cerebral artery (PCA). The representations of features can sometimes be redundant and not useful, which can degrade the classification performance. Thus, feature selection is studied and presented in this paper. The applied selection criteria are based on the unbounded Mahalanobis distance (referred as A) and single-feature-accuracy measure (referred as B). The result indicates that kinematic descriptor (SMV) is the most significant feature to predict HITS with 85.8% correct. However, the classification accuracy further improved when SMV is combined with other features in different feature subsets.


Feature selection TCD ultrasound HITS classification 



The authors would like to thank the financial support provided by Research University Grant (1001.PELECT.8014057) for this research work.


  1. 1.
    Van der Zwan, A., Hillen, B., Tulleken, C.A., Dujovny, M.: A quantitative investigation of the variability of the major cerebral arterial territories. Stroke 24(12), 1951–1959 (1993)Google Scholar
  2. 2.
    Zuromskis, T., Wetterholm, R., Lindqvist, J.F., Svedlund, S., Sixt, C., Jatuzis, D., Obelieniene, D., Caidahl, K., Volkmann, R.: Prevalence of micro-emboli in symptomatic high grade carotid artery disease: a transcranial Doppler study. Eur. J. Vasc. Endovasc. Surg. 35(5), 534–540 (2008)CrossRefGoogle Scholar
  3. 3.
    Banahan, C., Patel, R., Jeyagopal, V., Mistri, A., Hague, J.P., Evans, D.H., Chung, E.M.L.: Microbubble signal properties from PFO tests using transcranial Doppler ultrasound. Perspect. Med. 1(1–12), 232–235 (2012)CrossRefGoogle Scholar
  4. 4.
    Ali, M., Magee, D., Dasgupta, U.: Signal processing overview of ultrasound systems for medical imaging (2008)Google Scholar
  5. 5.
    Rafiee, J., Rafiee, M.A., Prause, N., Schoen, M.P.: Wavelet basis functions in biomedical signal processing. Expert Syst. Appl. 38(5), 6190–6201 (2011)Google Scholar
  6. 6.
    Yang, W., Zhou, Y.: Effect of pulse repetition frequency of high-intensity focused ultrasound on in vitro thrombolysis. Ultrason. Sonochem. 35, 152–160 (2016)CrossRefGoogle Scholar
  7. 7.
    Masnan, M.J.: Discriminant Analysis of Multi Sensor Data Fusion Based on Percentile Forward Feature Selection (Doctoral dissertation), p. 64. UUM, Kedah, Malaysia (2017)Google Scholar
  8. 8.
    Ray, S., Turner, L.F.: Mahalanobis distance-based two new feature evaluation criteria. Inf. Sci. 60, 217–245 (1992)CrossRefGoogle Scholar
  9. 9.
    Masnan, M.J., Mahat, N.I., Shakaff, A.Y.M., Abdullah, A.H., Zakaria, N.Z.I., Yusuf, N., Subari, N., Zakaria, A., Aziz, A.H.A.: Understanding Mahalanobis distance criterion for feature selection. In: AIP Conference Proceedings, vol. 1660, p. 050075 (2015).

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Institute of Engineering MathematicsUniversiti Malaysia Perlis (UniMAP) Kampus Tetap Pauh PutraArauMalaysia
  2. 2.School of Electrical and Electronic EngineeringUniversiti Sains Malaysia, Engineering CampusNibong TebalMalaysia

Personalised recommendations