Ankle torque forecasting using time-delayed neural networks.

Elbow joint angle estimation is essential in the field of biomechanical engineering especially for an apparatus based on myoelectric control. The purpose of this study is to develop a model of electromyography (EMG) signal to elbow joint angle estimation using time delay neural network (TDANN). The EMG signals were recorded only from biceps muscle from ten healthy male subjects. In order to obtain the features, the EMG signal is extracted for every 100 samples using sign slope change (SSC) features. The EMG features are used as the training data, in order the TDANN able to recognize the elbow joint angle. The results of this study reveal that the performance of the estimation is better if it is compared to the other studies. The RMSE values for the continuous and random motion are 14.97°±5.17° and 18.69°± 2.76°, respectively. The Pearson correlation coefficients are 0.87± 0.0087 and 0.78±0.11 for continuous and random motion, respectively. The results have confirmed the usefulness of the proposed method to estimate the elbow joint angle.

Ankle sprains are one of the most common sports injuries which are about 40% of total sports injuries and 20~40% of them would be progressed to chronic ankle instability (CAI) [1]. Rehabilitation and surgical therapy have been used to treat CAI, and the open modified Brostrm operation (MBO) is the gold standard surgical procedure. There are various evaluation methods in CAI treatments, such as the interview, visual analogue scale (VAS), and the measurement of range of motion (ROM) and the ankle torque. However, in reality, it is difficult to measure the maximum ROM and torque. Therefore, some studies measured ankle ROM and torque with cadaver specimens [2,3]. In this study, both open and arthroscopic MBO were performed on cadavers, and ankle torque and angle were measured during ankle inversion using the axial-torsion testing system. Ankle stiffness was calculated from measured data, and effects of both operations were compared quantitatively. For this study, matched pairs of fresh-frozen human cadaver lower leg specimens were obtained from seven males and four females (average age 71.5 (range 58–98) years). Each specimen consisted of the distal half of a leg. The soft tissues were removed from the calcaneus and distal tibiofibular part, except for the ankle joint and ligament. The anterior talofibular ligament (ATFL) and the calcaneofibular ligament (CFL) were transected. The specimens for the arthroscopic and open MBO were chosen from the left and right legs alternately. Then, each specimen was fixed in the specially-designed jig that was mounted on the axial-torsion fatigue testing system (Instron 8874, Norwood, MA, USA). The test consisted of a single ramp from 0° to 70° by inverting the ankle at 5°/s, while measuring the angular position and resultant torque. There was no statistical difference in torque to failure between open and arthroscopic MBO. The maximum torque was 16.3±7.2 N•m at 45° for open MBO and 19.9±10.8 N•m at 40° for arthroscopic MBO (Figure ​(Figure1).1). Ankle stiffness increased faster in arthroscopic MBO (0.31±0.22 N•m/deg) than in open MBO (0.18±0.15 N•m/deg) in initial inversion range (<5°), but no statistically significant differences were observed. The maximum stiffness was 0.41±0.18 N•m/deg at 35° in open MBO and 0.50±0.27 N•m/deg at 40° in arthroscopic MBO (Figure ​(Figure11). Figure 1 Ankle torque and stiffness during inversion test during open and arthroscopic MBO In this study, biomechanical analysis was performed for operations of CAI and there was no statistically significance in torque and stiffness. In comparison to open MBO, arthroscopic MBO is good alternative technique for CAI.

In recent decades, there has been an increasing interest in the use of robotic powered exoskeletons to assist patients with movement disorders in rehabilitation and daily life. Providing assistive torque that compensates for the user's remaining muscle contributions is a growing and challenging field within exoskeleton control. In this article, ankle joint torques were estimated using electromyography (EMG)-driven neuromusculoskeletal (NMS) model and an artificial neural network (ANN) model in seven movement tasks, including fast walking, slow walking, self-selected speed walking, and isokinetic dorsi/plantar flexion at 60 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">°</sup> /s and 90 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">°</sup> /s. In each method, EMG signals and ankle joint angles were used as input, the models were trained with data from 3-D motion analysis, and ankle joint torques were predicted. Six cases using different motion trials as calibration (for the NMS model)/training (for the ANN) were devised, and the agreement between the predicted and measured ankle joint torques was computed. We found that the NMS model could overall better predict ankle joint torques from EMG and angle data than the ANN model with some exceptions; the ANN predicted ankle joint torques with better agreement when trained with data from the same movement. The NMS model predicted ankle joint torque best when calibrated with trials during which EMG reached maximum levels, whereas the ANN predicted well when trained with many trials and types of movements. In addition, the ANN prediction may become less reliable when predicting unseen movements. Detailed comparative studies of methods to predict ankle joint torque are crucial for determining strategies for exoskeleton control.

The majority of existing normative torque generation capability (torque capability for short) databases are reported in the form of torque as a function of joint angle. although it is well recognized that torque capability is a function of both the joint angular position and angular velocity. The main objective of this study was to develop the methodology of 3-D dynamic representation of torque capability using the ankle joint as an example. The ankle torque capability of 20 males and females was assessed at 5 levels of ankle joint angular positions and velocities in each direction of plantar and dorsi flexion. The ANOVA results indicated significant main effects of joint angular position, angular velocity, direction, and gender, in addition to the interaction effect of angular position and velocity (p &lt; .003) on the torque capability of the ankle joint. The regression analysis indicated that an individualized quadratic surface response performed significantly belter than the models developed for each gender or the whole population using the coefficient of determination and standard error of the regression as criteria. Such 3-D representation of torque capability has a broad spectrum of applications ranging from rehabilitation and ergonomic to biomechanical applications.

The ankle joint biomechanical dynamics plays an important role in the balance of the human body, especially under the small disturbance. In this paper, ankle joint biomechanical dynamics and muscle reflex control are investigated. Soleus(SOL), gastrocnemius(GAS) and tibialis anterior(TA) are selected to record the surface electromyography for analysis. Ankle joint angle is recorded by an encoder. The pressure insole records the foot pressure and the ankle joint torque is calculated using the data. The disturbance is exerted by a sandbag released at different height to hit backs of subjects. The experimental condition is controlled so that subjects pay no attention to the disturbance for upright standing balance. Seven subjects participate in the experiment. The experimental results indicate that there is no significant differences among muscle activation levels for different level disturbances. The linearity between the SOL activation and ankle joint torque is high. The joint angle and the torque also have high linearity. Considering that muscle reflex has the function of regulating muscle stiffness, the ankle joint seems to maintain ‘stiffness’ within a small variation to resist limited range external disturbance.

A nonlinear behavior may exist intrinsically with a deterministic dynamic system which shows high sensitivity with initial condition. Such behavior is characterized as chaotic behavior. Strange attractor confines the dynamic behavior of chaotic system in a finite state space region, and the available state variables show the stochastic behavior with time. In this research work, time delay neural network has applied to predict the various chaotic time series. Adaptive social behavior optimization has applied to evolve the optimal set of weights of the time delay neural network. Comparison of learning performance has given with popularly gradient descent-based learning. Performance evaluation has defined in terms of coefficient of determination along with root-mean-square error in prediction under learning and test phase of chaotic time series. The three benchmarks of chaotic time series (logistic differential equation, Mackey–Glass, and Lorenz system) have taken for predicting purpose. We have shown with experimental results that the proposed new method of neural network learning is very efficient and has delivered the better prediction for various complex chaotic time series.

Powered ankle-foot prostheses for walking often have limitations in the range of motion and in push-off power, if compared to a lower limb of a healthy person. A new design of a powered ankle-foot prosthesis is proposed to obtain a wide range of motion and an adequate power for a push-off step. The design methodology for this prosthesis has three points. In the first one, a dimensionless kinematic model of the lower limb in the sagittal plane is built, through an experimental campaign with healthy subjects, to calculate the angles of lower limb during the gait. In the second point a multibody inverse dynamic model of the lower limb is constructed to calculate the foot-ground contact force, its point of application and the ankle torque too, entering as input data the calculated angles of the lower limb in the previous point. The third point requires, as input of the inverse dynamic model, the first dimensioning data of the ankle-foot prosthesis to obtain the load acting on the components of the prosthesis and the angle torque of the actuator during the gait cycle. Finally, an iteration cycle begins with the inverse dynamic model modifying the ankle torque and angle until these quantities during the gait are as close as possible to the physiological quantities. After the mechanical design and the construction of the prototype of the prosthesis, an experimental methodology was used for preliminary validation of the design. The preliminary tests in the laboratory on the prototype alone show that the range of motion of the ankle angle during the gait is close to a healthy person’s: 27.6° vs. 29°. The pushing force of the distal area of the prototype is 1.000 N, instead of 1.600 N, because a budget reduction forced us to choose components for the prototype with lower performance.

What triggers the continuous muscle activity during upright standing?

How far is arterial spin labeling MRI from a clinical reality? Insights from arterial spin labeling comparative studies in Alzheimer's disease and other neurological disorders.

BackgroundDuring a stretch- shortening cycle (SSC), muscle force attained during concentric contractions (shortening phase) is potentiated by the preceding eccentric contractions (lengthening phase). The purpose of this study was to examine the influence of joint angular velocity on force potentiation induced by SSC (SSC effect).FindingsTwelve healthy men (age, 24.2 ± 3.2 years; height, 1.73 ± 0.05 m; body mass, 68.1 ± 11.0 kg) participated in this study. Ankle joint angle was passively moved by a dynamometer, with range of motion from dorsiflexion (DF) 15° to plantarflexion (PF) 15°. Muscle contractions were evoked by tetanic electrical stimulation. Joint angular velocity of concentric contraction was set at 30°/s and 150°/s. Magnitude of SSC effect was calculated as the ratio of joint torque obtained by concentric contraction with preliminary eccentric contraction trial relative to that obtained by concentric contraction without preliminary eccentric contraction trial. As a result, magnitude of SSC effect calculated at three joint angles was significantly larger in the 150°/s condition than in the 30°/s condition (p < 0.05).ConclusionsThese results indicate that the magnitude of SSC effect is affected by joint angular velocity, which is larger when joint angular velocity is larger. This phenomenon would be caused by insufficient duration to increase activation level in the large joint angular velocity condition. When the duration to increase activation level is insufficient due to short contraction duration, preactivation (one of the factors of SSC effect) leads to a significant increase in joint torque.

In recent years, respiratory monitoring has gained attention due to the high prevalence and severe consequences of sleep apnea, post-anesthesia respiratory instability and respiratory diseases. Nevertheless, respiratory monitoring oftentimes relies on obtrusive masks and belts, which are unsuitable for wearable, long-term monitoring. Impedance pneumography (IP) is a bioimpedance method aiming to assess respiratory parameters unobtrusively. However, most IP configurations require far-spaced electrodes. Based on our recent work on wearable IP, we propose a dual-lead, wearable IP setup with 55 mm electrode spacing to estimate respiratory flow and rate (RR). Using our recently presented multimodal patch stethoscope as well as commercial systems, we conducted a study including 10 healthy subjects which were recorded in the supine, lateral and prone position. Using time-delay neural networks, we achieved RR estimation errors below 0.6 breaths per minute and flow correlations of 0.88 with relative errors of 25 % to a pneumotachometer reference. We conclude that dual-lead IP increases the performance of respiratory signal estimation compared to a single lead and recommend research in the area of subject position dependency and movement artefacts.

The study examines postural activity of a constrained subject in response to a disturbance in sagittal plane for three different initial standing postures. Linear relationship between the ankle joint torque and the ankle joint angle, resulting in constant stiffness in the ankles can be observed for the majority of experimental conditions.

The movement recovery of ankle is extremely important for patients with ankle injuries especially with the stroke hemiplegia. In this paper, a novel control method of ankle rehabilitation robot is proposed to provide continuous motion assistant. Ankle joint torque is estimated based on EMG signals to establish the relationship between joint torque and joint angle. In detail, we firstly apply a LDA algorithm for recognizing the motor patterns of ankle using two channels EMG signals collected from anterior tibial (TA) and gastrocnemius (GA). Then, the corresponding BP neural network model established in previous is selected according to identified motion pattern. The muscle activity related with identified motion pattern is used as the inputs of the BP neural network model to estimate the relevant joint torque. In order to meet the requirements of movement range for the subjects with different rehabilitation conditions, the subjects just need reset the angle range to achieve the control of continuous ankle motion with adjustable amplitude. Experimental results on nine subjects demonstrated that the ankle motion intention can be precisely predicted in advance, and the angle range of ankle motion were also adjustable based on the requirements of subjects. Key Words: sEMG, Ankle rehabilitation, Ankle joint angle.

Multi-environment evaluation of peanut lines by model simulation with the cultivar coefficients derived from a reduced set of observed field data

BackgroundAging degrades the balance and locomotion ability due to frailty and pathological conditions. This demands balance rehabilitation and assistive technologies that help the affected population to regain mobility, independence, and improve their quality of life. While many overground gait rehabilitation and assistive robots exist in the market, none are designed to be used at home or in community settings.MethodsA device named Mobile Robotic Balance Assistant (MRBA) is developed to address this problem. MRBA is a hybrid of a gait assistive robot and a powered wheelchair. When the user is walking around performing activities of daily living, the robot follows the person and provides support at the pelvic area in case of loss of balance. It can also be transformed into a wheelchair if the user wants to sit down or commute. To achieve instability detection, sensory data from the robot are compared with a predefined threshold; a fall is identified if the value exceeds the threshold. The experiments involve both healthy young subjects and an individual with spinal cord injury (SCI). Spatial Parametric Mapping is used to assess the effect of the robot on lower limb joint kinematics during walking. The instability detection algorithm is evaluated by calculating the sensitivity and specificity in identifying normal walking and simulated falls.ResultsWhen walking with MRBA, the healthy subjects have a lower speed, smaller step length and longer step time. The SCI subject experiences similar changes as well as a decrease in step width that indicates better stability. Both groups of subjects have reduced joint range of motion. By comparing the force sensor measurement with a calibrated threshold, the instability detection algorithm can identify more than 93% of self-induced falls with a false alarm rate of 0%.ConclusionsWhile there is still room for improvement in the robot compliance and the instability identification, the study demonstrates the first step in bringing gait assistive technologies into homes. We hope that the robot can encourage the balance-impaired population to engage in more activities of daily living to improve their quality of life. Future research includes recruiting more subjects with balance difficulty to further refine the device functionalities.