Original Article Proc IMechE Part H: J Engineering in Medicine 1–11 Ó IMechE 2020 Article reuse guidelines: sagepub.com/journals-permissions DOI: 10.1177/0954411920935741 journals.sagepub.com/home/pih Comparison study of classification methods of intramuscular electromyography data for non-human primate model of traumatic spinal cord injury Farah Masood 1,2 , Maisha Farzana 1 , Shanker Nesathurai 3,4,5 and Hussein A. Abdullah 1 Abstract Traumatic spinal cord injury is a serious neurological disorder. Patients experience a plethora of symptoms that can be attributed to the nerve fiber tracts that are compromised. This includes limb weakness, sensory impairment, and truncal instability, as well as a variety of autonomic abnormalities. This article will discuss how machine learning classification can be used to characterize the initial impairment and subsequent recovery of electromyography signals in an non-human pri- mate model of traumatic spinal cord injury. The ultimate objective is to identify potential treatments for traumatic spinal cord injury. This work focuses specifically on finding a suitable classifier that differentiates between two distinct experi- mental stages (pre-and post-lesion) using electromyography signals. Eight time-domain features were extracted from the collected electromyography data. To overcome the imbalanced dataset issue, synthetic minority oversampling technique was applied. Different ML classification techniques were applied including multilayer perceptron, support vector machine, K-nearest neighbors, and radial basis function network; then their performances were compared. A confusion matrix and five other statistical metrics (sensitivity, specificity, precision, accuracy, and F-measure) were used to evaluate the performance of the generated classifiers. The results showed that the best classifier for the left- and right-side data is the multilayer perceptron with a total F-measure of 79.5% and 86.0% for the left and right sides, respectively. This work will help to build a reliable classifier that can differentiate between these two phases by utilizing some extracted time- domain electromyography features. Keywords Electromyography, non-human primate model, traumatic spinal cord injury, classification, MLP, SVM, KNN, RBFN, SMOTE Date received: 26 March 2019; accepted: 28 May 2020 Introduction Traumatic spinal cord injury (TSCI) is a serious neuro- logical disorder. Patients experience a plethora of symp- toms that can be attributed to the nerve fiber tracts that are compromised. This includes limb weakness, sensory impairment, and truncal instability, as well as a variety of autonomic abnormalities, 1–3 Common causes of TSCI include motor vehicle crashes, sports-related inju- ries (i.e. driving and skiing), and interpersonal vio- lence. 1 Biomedical treatments have improved quality of life and long-term survival. However, current treat- ments have had only a limited impact on improving the clinical impairments associated with TSCI. 3 1 School of Engineering, University of Guelph, Guelph, ON, Canada 2 Department of Biomedical Engineering, Al-Khwarizmi College of Engineering, Baghdad University, Baghdad, Iraq 3 Wisconsin National Primate Research Center, University of Wisconsin– Madison, Madison, WI, USA 4 Division of Physical Medicine and Rehabilitation, Department of Medicine, McMaster University, Hamilton, ON, Canada 5 Department of Physical Medicine and Rehabilitation, Hamilton Health Sciences, St Joseph’s Hamilton Healthcare, Hamilton, ON, Canada Corresponding author: Farah Masood, School of Engineering, University of Guelph, 50 Stone Rd E, Guelph, ON N1G 2W1, Canada. Emails: fmasood@uoguelph.ca; farahmasood16@gmail.com