A Convolutional Neural Network Model to Classify the Effects of Vibrations on Biceps Muscles

Jen Yung Tsai, Yih Kuen Jan, Ben Yi Liau, Raden Bagus Reinaldy Subiakto, Chih Yang Lin, Rimuljo Hendradi, Yi Chuan Hsu, Quanxin Lin, Hsin Ting Chang, Chi Wen Lung

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Muscle fatigue occurs after sports activities, repeated actions in a routine job, or a heavy-duty job. It causes soreness and reduces performance in athletes and workers. Various therapies have been developed to reduce muscle fatigue. Vibration therapy has been used to reduce muscle fatigue and delay muscle soreness. However, its effectiveness remains unclear. Ultrasound images provide a non-invasive diagnosis and instant visual examinations. However, it requires extensive training to analyze ultrasound images. The purpose of this study was to develop an automated classification system of ultrasound images using deep learning to assist clinical diagnosis. The ultrasound images of the biceps muscle were measured from four healthy people. The primary objective of the study was to use the convolutional neural network (CNN) models to classify between the vibration control condition (0 Hz) and vibration test conditions (5, 35, and 50 Hz) with subjects in different time duration the pattern (2 and 10-min). These images were preprocessed to resize to 224 × 224 pixels and augmentation to feed into the dataset, including the augmentation training dataset (74%), validation dataset (15%), and non-augmentation test dataset (11%). This study used the AlexNet, VGG-16, and VGG-19 of CNN models for recognition and classification ultrasound images. These models compared the differences of ultrasound images of biceps after various vibration between two conditions. The results showed that AlexNet has the best performance with the accuracy 82.5%, sensitivity 67.3%, and specificity 99.5% when 10-min 35 Hz local vibration was applied. The deep learning method, AlexNet, shows the potential for automated classification of biceps ultrasound images for assessing treatment outcomes of vibration therapy.

Original languageEnglish (US)
Title of host publicationAdvances in Physical, Social and Occupational Ergonomics - Proceedings of the AHFE 2020 Virtual Conferences on Physical Ergonomics and Human Factors, Social and Occupational Ergonomics and Cross-Cultural Decision Making
EditorsWaldemar Karwowski, Ravindra S. Goonetilleke, Shuping Xiong, Richard H.M. Goossens, Atsuo Murata
PublisherSpringer
Pages56-62
Number of pages7
ISBN (Print)9783030515485
DOIs
StatePublished - 2020
EventAHFE Virtual Conference on Physical Ergonomics and Human Factors, the Virtual Conference on Social and Occupational Ergonomics, and the Virtual Conference on Cross-Cultural Decision Making, 2020 - San Diego, United States
Duration: Jul 16 2020Jul 20 2020

Publication series

NameAdvances in Intelligent Systems and Computing
Volume1215 AISC
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Conference

ConferenceAHFE Virtual Conference on Physical Ergonomics and Human Factors, the Virtual Conference on Social and Occupational Ergonomics, and the Virtual Conference on Cross-Cultural Decision Making, 2020
CountryUnited States
CitySan Diego
Period7/16/207/20/20

Keywords

  • Deep learning
  • Skeletal muscle fatigue
  • Ultrasound images

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Fingerprint Dive into the research topics of 'A Convolutional Neural Network Model to Classify the Effects of Vibrations on Biceps Muscles'. Together they form a unique fingerprint.

Cite this