Hybrid fusion of linear, non-linear and spectral models for the dynamic modeling of sEMG and skeletal muscle force: An application to upper extremity amputation

• Published in: Computers in biology and medicine Vol. 43; no. 11; pp. 1815 - 1826
• Main Authors: Potluri, Chandrasekhar, Anugolu, Madhavi, Schoen, Marco P, Subbaram Naidu, D, Urfer, Alex, Chiu, Steve
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.11.2013; Elsevier Limited
• Subjects: Adult; Algorithms; Amputation; Data fusion; Electromyography - methods; Female; Fingers - physiology; Forearm - physiology; Humans; Internal Medicine; Male; Models, Statistical; Muscle force estimation based on sEMG; Muscle, Skeletal - physiology; Muscular system; Musculoskeletal system; Neural networks; Noise; Other; Prostheses; Robotics; Spectral models; Wavelet Analysis; Wavelet transforms; Wavelets; Wiener–Hammerstein; ADC; Independent Component Analysis; PAFA; Daubechies; WH; Optimized Linear Model Fusion Algorithm; OE; Weiner Hammerstein; Spectral Analysis Frequency Dependent Resolution; AIC; BIC; Discrete Wavelet Transform; Db; DKF; Decentralized Kalman Filter; DWT; SPFDR; Bayesian Information Criterion; VWA; Wiener–Hammerstein; Spectral models; KIC; ICA; Output Error Model; Probability Analysis based Fusion Algorithm; PCA; Principle Component Analysis; Surface Electromyography; Wavelets; Analog to Digital Converter; Muscle force estimation based on sEMG; OLMFA; Akakie Information Criterion; sEMG; Data fusion; Kullback Information Criterion; Variance Weighted Average
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2013.08.023

Abstract Estimating skeletal muscle (finger) forces using surface Electromyography (sEMG) signals poses many challenges. In general, the sEMG measurements are based on single sensor data. In this paper, two novel hybrid fusion techniques for estimating the skeletal muscle force from the sEMG array sensors are proposed. The sEMG signals are pre-processed using five different filters: Butterworth, Chebychev Type II, Exponential, Half-Gaussian and Wavelet transforms. Dynamic models are extracted from the acquired data using Nonlinear Wiener Hammerstein (NLWH) models and Spectral Analysis Frequency Dependent Resolution (SPAFDR) models based system identification techniques. A detailed comparison is provided for the proposed filters and models using 18 healthy subjects. Wavelet transforms give higher mean correlation of 72.6±1.7 (mean±SD) and 70.4±1.5 (mean±SD) for NLWH and SPAFDR models, respectively, when compared to the other filters used in this work. Experimental verification of the fusion based hybrid models with wavelet transform shows a 96% mean correlation and 3.9% mean relative error with a standard deviation of ±1.3 and ±0.9 respectively between the overall hybrid fusion algorithm estimated and the actual force for 18 test subjects’ k-fold cross validation data.