Performances of Hill-Type and Neural Network Muscle Models—Toward a Myosignal-Based Exoskeleton

Rosén, Jacob; Fuchs, Moshe B.; Arcan, M.

doi:10.1006/cbmr.1999.1524

Cited by 112 publications

(41 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the activity timeframes of the EMG bursts consistently, signal envelopes were calculated (Fig. 3) using a digital band, fourth-order Butterworth 7-11 Hz filter (GLITSCH and BAUMAN, 1997;DE LUCA, 1984;ROSEN et al, 1999). initiation of the burst was recognised when the burst envelope exceeded 5% its maximum value, and termination was recognised when the burst envelope value dropped beneath 5% of the maximum.…”

Section: Muscular Fatigue Experimental Modelmentioning

confidence: 99%

Biomechanical analysis of fatigue-related foot injury mechanisms in athletes and recruits during intensive marching

Gefen

2002

Med. Biol. Eng. Comput.

View full text Add to dashboard Cite

Section: Muscular Fatigue Experimental Modelmentioning

confidence: 99%

Biomechanical analysis of fatigue-related foot injury mechanisms in athletes and recruits during intensive marching

Gefen

2002

Med. Biol. Eng. Comput.

View full text Add to dashboard Cite

“…Studies have also shown that biceps brachii muscle activity is highly correlated with elbow flexor muscle activity when the forearm is kept supinated [14], and can be used to represent the muscle activity of the elbow flexor muscle group [8]. Given that other studies have shown the ability to EMG based muscle models to represent torque during dynamic contraction conditions [44,42], insight into SSC enhancement may be provided by combining EMG and muscle modelling to the elbow joint.…”

Section: Relating In Vivo Results and Isolated Muscle Performancementioning

confidence: 99%

In vivo assessment of elbow flexor work and activation during stretch-shortening cycle tasks

Benoît¹,

Dowling²

2006

Journal of Electromyography and Kinesiology

View full text Add to dashboard Cite

“…Rosen et aL compared the performances of Hill-type and neural network muscle models in terms of predicting the torques of the elbow joint complex based on joint kinematics and neuromuscular activity during single-joint movements (ROSEN et al, 1999). A time-delayed ANN (TDANN) was used by Au and Kirsch to predict the shoulder and elbow motions from EMG signals in able-bodied and spinal cord-injured subjects (Au and KIRSCH, 2000).…”

Section: Block Diagram Of Musculoskeletal Modelmentioning

confidence: 99%

“…5 shows the relationship between the number of iteration and the RMSE of the training and test data. Many investigators used a fixed number of iterations (ROSEN et al, 1999;LIU et al, 1999;KOIKE and KAWATO, 1995) for training, and their stopping criterion could cause the system to stay in a local minimum and could decrease the robustness with too many iterations. As shown in Fig.…”

Section: Comparison Of Predicted Joint Torque and Expected Torque Fromentioning

confidence: 99%

Using recurrent artificial neural network model to estimate voluntary elbow torque in dynamic situations

Song

Tong

2005

Med. Biol. Eng. Comput.

View full text Add to dashboard Cite

Muscle modelling is an important component of body segmental motion analysis. Although many studies had focused on static conditions, the relationship between electromyographic (EMG) signals and joint torque under voluntary dynamic situations has not been well investigated. The aim of this study was to investigate the performance of a recurrent artificial neural network (RANN) under voluntary dynamic situations for torque estimation of the elbow complex. EMG signals together with kinematic data, which included angle and angular velocity, were used as the inputs to estimate the expected torque during movement. Moreover, the roles of angle and angular velocity in the accuracy of prediction were investigated, and two models were compared. One model used EMG and joint kinematic inputs and the other model used only EMG inputs without kinematic data. Six healthy subjects were recruited, and two average angular velocities (60 degrees s(-1) and 90 degrees s(-1)) with three different loads (0 kg, 1 kg, 2 kg) in the hand position were selected to train and test the RANN between 90 degrees elbow flexion and full elbow extension (0 degrees). After training, the root mean squared error (RMSE) between expected torque and predicted torque of the model, with EMG and joint kinematic inputs in the training data set and the test data set, were 0.17 +/- 0.03 Nm and 0.35 +/- 0.06 Nm, respectively. The RMSE values between expected torque and predicted torque of the model, with only EMG inputs in the training data set and the test set, were 0.57 +/- 0.07 Nm and 0.73 +/- 0.11 Nm, respectively. The results showed that EMG signals together with kinematic data gave significantly better performance in the joint torque prediction; joint angle and angular velocity provided important information in the estimation of joint torque in voluntary dynamic movement.

show abstract

Performances of Hill-Type and Neural Network Muscle Models—Toward a Myosignal-Based Exoskeleton

Cited by 112 publications

References 16 publications

Biomechanical analysis of fatigue-related foot injury mechanisms in athletes and recruits during intensive marching

Biomechanical analysis of fatigue-related foot injury mechanisms in athletes and recruits during intensive marching

In vivo assessment of elbow flexor work and activation during stretch-shortening cycle tasks

Using recurrent artificial neural network model to estimate voluntary elbow torque in dynamic situations

Contact Info

Product

Resources

About