Developing a method for quantifying hip joint angles and moments during walking using neural networks and wearables. Issue 1 (2nd January 2023)

• Record Type: Journal Article
• Authors: McCabe, Megan V.; Van Citters, Douglas W.; Chapman, Ryan M.
• Is Part Of: Computer methods in biomechanics and biomedical engineering. Volume 26:Issue 1(2023)
• Page Start: 1
• Page End: 11
• Publication Date: 2023-01-02
• Subjects: Hip joint -- wearable -- neural networks -- inertial measurement units -- instrumented insoles; Biomechanics -- Data processing -- Periodicals; Biomedical engineering -- Periodicals; Biomechanics -- Periodicals; Biomedical Engineering -- methods -- Periodicals; Computing Methodologies -- Periodicals; 612.7
• DOI: 10.1080/10255842.2022.2044028
• Languages: English
• ISSNs: 1025-5842

Abstract

Abstract: Quantifying hip angles/moments during gait is critical for improving hip pathology diagnostic and treatment methods. Recent work has validated approaches combining wearables with artificial neural networks (ANNs) for cheaper, portable hip joint angle/moment computation. This study developed a Wearable-ANN approach for calculating hip joint angles/moments during walking in the sagittal/frontal planes with data from 17 healthy subjects, leveraging one shin-mounted inertial measurement unit (IMU) and a force-measuring insole for data capture. Compared to the benchmark approach, a two hidden layer ANN (n = 5 nodes per layer) achieved an average rRMSE = 15% and R 2 =0.85 across outputs, subjects and training rounds.