A Mobile Percussograph for Medical Examination of the Torso

Kayode P Ayodele, Femi J Olugbon, Oluwadare Ogunlade, Olawale B Akinwale, Oluwasegun T Akinniyi, Lawrence O Kehinde


Medical percussion is a free, low-risk procedure used by physicians during physical examination of patients. Although it is very useful procedure, a downside to manual percussion is that its results are subjective, with typically low inter-observer agreement. Not much work has been done, however, to create automated and reliable percussion devices or percussograph. This paper reports the development of a mobile percussograph. A spring-loaded solenoid was used as the plessor generating mechanical impact for application to a subject’s skin. Generated signals were amplified and digitized at a rate of 22.1 kHz. Thereafter, Frequency B-Spline (FBSP) base wavelet transform at 512 scales was used for feature extraction. Spectrographs generated from the wavelet coefficients were used for training a MobileNet network with 17 inverted layers for a 3-way classification.  Training employed a cross entropy loss function and the Adam optimization algorithm. Learning rate was 0.001, and first and second moment decay rates were 0.9 and 0.999 respectively. Subject-specific test accuracies of 92.9 %, 93.7 %, and 96.4 % were obtained for three subjects, while the cross-subject classification accuracy was 95.0 %. As this is the first reported general purpose mobile percussograph reported in the literature, these results are state-of-the-art. This study has established the viability of implementing mobile percussography in a standard, repeatable and accurate manner, which can lead to faster and more reliable medical percussion globally.

Keywords— MobileNet, Percussion, Percussograph, Percussography, Wavelets

Full Text:



Alam, U., Asghar, O., Khan, S. Q., Hayat, S., & Malik, R. A. (2010). Cardiac auscultation: an essential clinical skill in decline. British Journal of Cardiology, 17(1), 8.

Amjad Hashemi, Hossein Arabalibiek, and Khosrow Agin. 2011. ‘Classification of Wheeze Sounds Using Wavelets and Neural Networks’. Pp. 127–31 in Vol. 11. Singapore: IACSIT.

Ayodele, K.P., Ogunlade, O., Olugbon, O.J., Akinwale, O.B., and Kehinde, L.O. (2020). A Wavelet-based Method for Manual or Automatic Classification of Medical Percussion Sounds. Unpublished Technical Report, Obafemi Awolowo University, Ile-Ife, Nigeria

Bhuiyan, Moinuddin, Eugene V. Malyarenko, Mircea A. Pantea, Dante Capaldi, Alfred E. Baylor, and Roman Gr. Maev. 2015. ‘Time-Frequency Analysis of Clinical Percussion Signals Using Matrix Pencil Method’. Journal of Electrical and Computer Engineering 2015:1–10.

Bhuiyan, Moinuddin, Eugene V. Malyarenko, Mircea A. Pantea, Fedar M. Seviaryn, and Roman Gr. Maev. 2013. ‘Advantages and Limitations of Using Matrix Pencil Method for the Modal Analysis of Medical Percussion Signals’. IEEE Transactions on Biomedical Engineering 60(2):417–26.

Bhuiyan, Moinuddin, Eugene V. Malyarenko, Mircea A. Pantea, Roman Gr Maev, and Alfred E. Baylor. 2012. ‘Estimating the Parameters of Audible Clinical Percussion Signals by Fitting Exponentially Damped Harmonics’. The Journal of the Acoustical Society of America 131(6):4690–98.

Bohadana, A. B., F. T. Coimbra, and J. R. Santiago. 1986. ‘Detection of Lung Abnormalities by Auscultatory Percussion: A Comparative Study with Conventional Percussion’. Respiration; International Review of Thoracic Diseases 50(3):218–25.

Guarino, J. R., and J. C. Guarino. 1994. ‘Auscultatory Percussion: A Simple Method to Detect Pleural Effusion’. Journal of General Internal Medicine 9(2):71–74.

Heckerling, P. S., S. L. Wiener, C. J. Wolfkiel, M. S. Kushner, E. M. Dodin, V. Jelnin, B. Fusman, and E. V. Chomka. 1993. ‘Accuracy and Reproducibility of Precordial Percussion and Palpation for Detecting Increased Left Ventricular End-Diastolic Volume and Mass. A Comparison of Physical Findings and Ultrafast Computed Tomography of the Heart’. JAMA 270(16):1943–48.

Heckerling, Paul S., Stanley L. Wiener, Vijai K. Moses, Jose Claudio, Mark S. Kushner, and Roger Hand. 1991. ‘Accuracy of Precordial Percussion in Detecting Cardiomegaly’. The American Journal of Medicine 91(4):328–34.

Howard, Andrew G., Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. ‘MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications’. ArXiv:1704.04861 [Cs].

Howard, Andrew, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang, Yukun Zhu, Ruoming Pang, Vijay Vasudevan, Quoc V. Le, and Hartwig Adam. 2019. ‘Searching for MobileNetV3’. ArXiv:1905.02244 [Cs].

Kandaswamy, A., C. Sathish Kumar, Rm. Pl. Ramanathan, S. Jayaraman, and N. Malmurugan. 2004. ‘Neural Classification of Lung Sounds Using Wavelet Coefficients’. Computers in Biology and Medicine 34(6):523–37.

Kingma, D.P., Ba, J., 2014. Adam: A method for stochastic optimization. arXiv preprint. arXiv:1412.6980 .

Mansy, H. A., T. J. Royston, and R. H. Sandler. 2002. ‘Use of Abdominal Percussion for Pneumoperitoneum Detection’. Medical and Biological Engineering and Computing 40(4):439–46.

Murray, A., and J. M. M. Neilson. 1975. ‘Diagnostic Percussion Sounds: 1. A Qualitative Analysis’. Medical and Biological Engineering 13(1):19–28.

Pantea, M. A., R. Gr Maev, E. V. Malyarenko, and A. E. Baylor. 2012. ‘A Physical Approach to the Automated Classification of Clinical Percussion Sounds’. The Journal of the Acoustical Society of America 131(1):608–19.

Peng, Y., Dai, Z., Mansy, H. A., Sandler, R. H., Balk, R. A., & Royston, T. J. (2014). Sound transmission in the chest under surface excitation: an experimental and computational study with diagnostic applications. Medical & biological engineering & computing, 52(8), 695-706.

Rao, Adam, Jorge Ruiz, Chen Bao, and Shuvo Roy. 2018. ‘Tabla: A Proof-of-Concept Auscultatory Percussion Device for Low-Cost Pneumonia Detection’. Sensors (Basel, Switzerland) 18(8).

Rowan, P., Hill, M., Gresham, G. A., Goodall, E., & Moore, T. (2010). The use of infrared aided photography in identification of sites of bruises after evidence of the bruise is absent to the naked eye. Journal of forensic and legal medicine, 17(6), 293-297.

Sánchez Morillo, Daniel, Antonio León Jiménez, and Sonia Astorga Moreno. 2013. ‘Computer-Aided Diagnosis of Pneumonia in Patients with Chronic Obstructive Pulmonary Disease’. Journal of the American Medical Informatics Association: JAMIA 20(e1):e111–17.

Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4510-4520).

Thierman, Jonathan S. 2007. ‘Device for Medical Percussion’.

Yan, Ruqiang, and Robert X. Gao. 2009. ‘Base Wavelet Selection for Bearing Vibration Signal Analysis’. International Journal of Wavelets, Multiresolution and Information Processing 07(04):411–26.

DOI: http://dx.doi.org/10.46792/fuoyejet.v5i2.560


  • There are currently no refbacks.

Copyright (c) 2020 The Author(s)

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Powered by ICT and Faculty of Engineering, FUOYE

Copyright © 2020 The Author(s). Published by Faculty of Engineering, FUOYE

image The FUOYEJET website and her metadata are licensed under CC BY-NC