Machine learning-based classification of healthy and impaired gaits using 3D-GRF signals

• Published in: Biomedical signal processing and control Vol. 81; p. 104448
• Main Authors: Nazmul Islam Shuzan, Md, Chowdhury, Muhammad E.H., Bin Ibne Reaz, Mamun, Khandakar, Amith, Fuad Abir, Farhan, Ahasan Atick Faisal, Md, Hamid Md Ali, Sawal, Bakar, Ahmad Ashrif A., Hossain Chowdhury, Moajjem, Mahbub, Zaid B., Monir Uddin, M., Alhatou, Mohammed
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.03.2023
• Subjects: Feature extraction; Feature ranking; Gait classification; Ground reaction force; Feature extraction; Gait classification; Feature ranking; Ground reaction force
• ISSN: 1746-8094; 1746-8108
• DOI: 10.1016/j.bspc.2022.104448

•This study is conducted with a large benchmark database combining two datasets.•The trained models on this dataset will have better generalizability.•Large number of time, frequency, and time–frequency features were extracted.•3D-GRF performance was compared with 1D GRF signal.•Thorough experimentations in classifying healthy and gait disorder patients.•The machine learning model produces state of the art results. Gait analysis is helpful for rehabilitation, clinical diagnoses, and sporting activities. Among the gathered signals, ground reaction forces (GRF) may be used for assisting doctors in recognizing and categorizing gait patterns using Machine-Learning methods. In this study, GaitRec and Gutenberg databases were used, where GaitRec contains 2645 gait disorder (GD) patients and 211 Healthy Controls (HCs), and the Gutenberg database has 350 HCs. The combined database has HCs and four GD classes: hip, knee, ankle, and calcaneus. GD is an abnormality in the hip, knee, or ankle joints, whereas Calcaneus gait is calcaneus fractures or ankle fusions. We pre-processed the GRF signals, applied different feature extraction techniques, removed the highly correlated features, and ranked the features using three feature selection algorithms. K-nearest neighbour model (KNN) showed the top performance in terms of accuracy in all experiments. Four different experimental schemes were pursued: (i) 6 binary classifications; (ii) 1 three-class classification; (iii) 2 four-class classifications; (iv) one five-class classification. We also compared the performance of vertical GRF with three-dimensional GRF. We found that using three-dimensional GRF increased the overall performance. Furthermore, it is found that time-domain and Wavelet features are among the most useful in identifying gait patterns. The findings show promising performance in automated gait disorder classification.