A New Force Myography-Based Approach for Continuous Estimation of Knee Joint Angle in Lower Limb Amputees and Able-Bodied Subjects

• Published in: IEEE journal of biomedical and health informatics Vol. 25; no. 3; pp. 701 - 710
• Main Authors: Kumar, Amit, Godiyal, Anoop Kant, Joshi, Pradeep, Joshi, Deepak
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.03.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Amputation; artificial neural network (ANN); Artificial neural networks; Data acquisition; Force; Force myography (FMG); Gait; Goniometers; Joints (anatomy); Knee; knee joint angle; Legged locomotion; Muscle contraction; Muscles; Neural networks; Root-mean-square errors; Sensors; Thigh; Trans-femoral amputees; Treadmills
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2020.2993697

In this paper, we present a new method for estimating knee joint angle using force myography. The technique utilized force myogram signals from thigh muscles while subjects walked on a treadmill at different speeds, i.e., slow, medium, fast, and run. An eight-channel in-house force myography (FMG) data acquisition system was developed to collect the data wirelessly from seven healthy subjects and a transfemoral amputee. An artificial neural network was employed to estimate the knee joint angle from force myogram signals. The root-mean-square error across the healthy subjects was 6.9±1.5° at slow (1.5 km/hr), 6.5±1.3° at medium (4 km/hr), 7.4±2.2° at fast (6 km/hr) speeds, and 8.1±2.2° while running (8 km/hr). The root-mean-square error, across the trials, for the transfemoral amputee was 4.0±1.2° at slow (1 km/hr), 3.2±0.6° at medium (2 km/hr) and 3.8±0.9° at fast (3 km/hr) speeds. The proposed approach is useful in real-time gait analysis. The system is easily wearable, convenient in out-door use, portable, and commercially viable.