<div>This paper reviews the position/force control approach for governs an efficient knee joint in an active lower limb prosthesis, and the inter facing current control algorithm with human gate parameter is inserted. Two techniques are used to collect gait cycle data of leg: first, the foot ground force is obtained by the force platform device based on its position (x, y), then data of knee joint angles is recorded by using a video-camera device.The collected information is sent and used in the proposed intelligent controller. This intelligent control system used an adaptive neuro-fuzzy inference system (ANFIS) circuit in addition to the proportional integral derivative (PID) controller. This hybrid ANFIS-PID control system simulates and provides the ground force values. The experimental results show anexcellent response and lower root mean square error (RMSE) compared with each of PID and ANFIS controller that implemented for a similar purpose. In summary, the results showed acceptably stable performance of the proposedposition/force controller based on hybrid ANFIS-PID system. It can be concluded that the finest performance of the controlled force, as quantified by the RMSE criteria, is perceived by the proposed hybrid scheme depending on the controller intelligent decision circuit.</div>

The number of Above Knee (AK) amputees has increased in recent years and this has led to a need for urgent work on the design of proper lower limb prostheses. Lower limb prosthetics can be divided into active and passive devices. However, passive prosthetics cannot fully provide the natural motion of a healthy leg, and the technologies used in active prosthetics with knee joints are often far too expensive for amputees in developing countries such as Iraq. In this paper, an active lower limb prosthesis with an efficient knee joint is thus designed. Two strategies were used to collect data for gait cycle analysis of the leg in the sagittal plane: the first was based on the use of a force platform device to obtain the foot ground force according to the foot position (x, y), while the second utilised a video-camera based system to examine knee joint angles. The obtained data were all sent to an intelligent controller that uses an Adaptive Neuro-based Fuzzy Inference System (ANFIS). The ANFIS controller determines the ground force, mimicking the moment of the active knee with a DC motor and flexion-extension angle values. The experimental data for the motion of the knee joint were collected in the Gait Laboratory, then transformed to joint angles using the ANFIS controller. The results show excellent response in the proposed ANFIS controllers in terms of determining angle and moment values of the knee joint with a very low RMS error of 0.006.

<p>Control strategies of smart hand prosthesis-based myoelectric signals in<br />recent years don't provide the patients with the sensation of biological<br />control of prostheses hand fingers. Therefore, in current work<br />hyperparameters optimization in machine learning algorithm and hand<br />gesture recognition techniques were applied to the myoelectric signal-based<br />on residual muscles contraction of the amputees corresponding to intact<br />forearm limb movement to improve their biological control. In this paper,<br />myoelectric signals are extracted using the MYO armband to recognize ten<br />gestures from ten volunteers (healthy and transradial amputation) on the<br />forearm, thereafter the noise of myoelectric signals using a notch filter (NF)<br />is removed. The proposed classification system involved two machine<br />learning algorithms: (1) the decision tree (DT), tri-layered neural network<br />(TLNN), k-nearest-neighbor (KNN), support vector machine (SVM) and<br />ensemble boosted tree (EBT) classifiers. (2) the optimized machine learning<br />classifiers, i.e., OKNN, OSVM, OEBT with optical diffraction tomography<br />(ODT) and ommatidia detecting algorithm (ODA). The experimental results<br />of classifiers comparison pointed out an algorithm that outperformed with<br />high accuracy is OEBT closely followed by OKNN achieves an accuracy of<br />97.8% and 97.1% for intact forearm limb, while for transradial amputation<br />with an accuracy of 91.9% and 91.4%, respectively.</p>

No abstract