A new scheme for the development of IMU-based activity recognition systems for telerehabilitation. (October 2022)

• Record Type: Journal Article
• Authors: Nasrabadi, Amin M.; Eslaminia, Ahmad R.; Bakhshayesh, Parsa R.; Ejtehadi, Mehdi; Alibiglou, L.; Behzadipour, S.
• Is Part Of: Medical engineering & physics. Volume 108(2022)
• Publication Date: 2022-10
• Subjects: Human activity recognition -- Parkinson's disease -- Classification -- Tele-rehabilitation; Inertial Measurement Unit (IMU) -- Human Activity Recognition systems (HARs) -- Parkinson's disease (PD) -- National Institute of Neurological Disorders and Stroke (NINDS) -- Cost-Performance tradeoff Constraint (CPTc) -- Daubechies 7 (db7) -- User Datagram Protocol (UDP) -- Nearest Mean (NM) -- k-Nearest Neighbors (k-NN) -- Multi-Layer Perceptron (MLP) -- Radial Basis Function (RBP) -- Support Vectors Machine (SVM) -- Principal Component Analysis (PCA) -- Lee Silverman Voice Treatment (LSVT) -- Artificial Intelligence (AI) -- Timed Up & Go (TUG) -- Personal Computer (PC) -- power spectral density (PSD) -- Fast Fourier Transform (FFT) -- genetic algorithm (GA) -- Rock and Reach Forward and Backward (RRFB) -- Rock and Reach Side to Side (RRSS) -- Step Backward and Reach (SBR) -- Step Forward and Reach (SFR) -- Step to the Side and Reach (SSR) -- Floor to Ceiling (FC) -- Side to Side (SS) -- Pass the Obstacle (PO); Biomedical engineering -- Periodicals; Biomedical Engineering -- Periodicals; Physics -- Periodicals; Génie biomédical -- Périodiques; Biomedical engineering; Electronic journals; Periodicals; 610.28
• DOI: 10.1016/j.medengphy.2022.103876
• Languages: English
• ISSNs: 1350-4533

Abstract

Highlights: A tele-rehabilitation HAR system was developed using a minimal set of patient data. The HAR adapted to each patient through a single session of data collection. The proposed method resulted in a recall of higher than 80% with an NM classifier. Thigh is the best place for a single sensor in PD rehabilitation HAR. Abstract: Wearable human activity recognition systems (HAR) using inertial measurement units (IMU) play a key role in the development of smart rehabilitation systems. Training of a HAR system with patient data is costly, time-consuming, and difficult for the patients. This study proposes a new scheme for the optimal design of HARs with minimal involvement of the patients. It uses healthy subject data for optimal design for a set of activities used in the rehabilitation of PD 1 patients. It maintains its performance for individual PD subjects using a single session data collection and an adaptation procedure. In the optimal design, several classifiers (i.e. NM, k-NN, MLP with RBF as a hidden layer, and multistage RBF SVM) were investigated. Features were signal-based in the time, frequency, and time-frequency domains. Double-stage feature extraction by PCA and fisher technique was used. The optimal design reached a recall of 95% on healthy subjects using only two sensors on the left thigh and forearm. Implementing the adaptation procedure on two PD subjects, the performance was maintained above 80%. Post analysis on the performance of the adapted HAR showed a slight drop in precision (above 87% to above 81%) for activities that was performed in sitting condition.