Deep learning approach for prediction of impact peak appearance at ground reaction force signal of running activity. Issue 14 (25th October 2020)

• Record Type: Journal Article
• Authors: Girka, Anastasiia; Kulmala, Juha-Pekka; Äyrämö, Sami
• Is Part Of: Computer methods in biomechanics and biomedical engineering. Volume 23:Issue 14(2020)
• Page Start: 1052
• Page End: 1059
• Publication Date: 2020-10-25
• Subjects: CNN -- binary classification -- running gait analysis -- risk assessment -- force platform; Biomechanics -- Data processing -- Periodicals; Biomedical engineering -- Periodicals; Biomechanics -- Periodicals; Biomedical Engineering -- methods -- Periodicals; Computing Methodologies -- Periodicals; 612.7
• DOI: 10.1080/10255842.2020.1786072
• Languages: English
• ISSNs: 1025-5842

Abstract

Abstract: Protruding impact peak is one of the features of vertical ground reaction force (GRF) that is related to injury risk while running. The present research is dedicated to predicting GRF impact peak appearance by setting a binary classification problem. Kinematic data, namely a number of raw signals in the sagittal plane, collected by the Vicon motion capture system (Oxford Metrics Group, UK) were employed as predictors. Therefore, the input data for the predictive model are presented as a multi-channel time series. Deep learning techniques, namely five convolutional neural network (CNN) models were applied to the binary classification analysis, based on a Multi-Layer Perceptron (MLP) classifier, support vector machine (SVM), logistic regression, k -nearest neighbors (kNN), and random forest algorithms. SVM, logistic regression, and random forest classifiers demonstrated performances that do not statistically significantly differ. The best classification accuracy achieved is 81.09% ± 2.58%. Due to good performance of the models, this study serves as groundwork for further application of deep learning approaches to predicting kinetic information based on this kind of input data.