A fuzzy clustering neural network architecture for multifunction upper-limb prosthesis

2003 ◽  
Vol 50 (11) ◽  
pp. 1255-1261 ◽  
Author(s):  
B. Karlik ◽  
M.O. Tokhi ◽  
M. Alci
Keyword(s):  
Neural Network ◽  
Fuzzy Clustering ◽  
Upper Limb ◽  
Network Architecture ◽  
Neural Network Architecture ◽  
Upper Limb Prosthesis ◽  
Limb Prosthesis

scholarly journals Smartphone supported upper limb prosthesis

2015 ◽  
Vol 1 (1) ◽  
pp. 484-487
Author(s):  
D. Hepp ◽  
J. Kirsch ◽  
F. Capanni
Keyword(s):  
Neural Network ◽  
Upper Limb ◽  
Design Development ◽  
Test Setup ◽  
Software Application ◽  
Patient Feedback ◽  
Emg Signal ◽  
Upper Limb Prosthesis ◽  
Upper Limb Prostheses ◽  
Limb Prosthesis

AbstractState of the art upper limb prostheses offer up to six active DoFs (degrees of freedom) and are controlled using different grip patterns. This low number of DoFs combined with a machine-human-interface which does not provide control over all DoFs separately result in a lack of usability for the patient. The aim of this novel upper limb prosthesis is both offering simplified control possibilities for changing grip patterns depending on the patients’ priorities and the improvement of grasp capability. Design development followed the design process requirements given by the European Medical Device Directive 93/42 ECC and was structured into the topics mechanics, software and drive technology. First user needs were identified by literature research and by patient feedback. Consequently, concepts were evaluated against technical and usability requirements. A first evaluation prototype with one active DoF per finger was manufactured. In a second step a test setup with two active DoF per finger was designed. The prototype is connected to an Android based smartphone application. Two main grip patterns can be preselected in the software application and afterwards changed and used by the EMG signal. Three different control algorithms can be selected: “all-day”, “fine” and “tired muscle”. Further parameters can be adjusted to customize the prosthesis to the patients’ needs. First patient feedback certified the prosthesis an improved level of handling compared to the existing devices. Using the two DoF test setup, the possibilities of finger control with a neural network are evaluated at the moment. In a first user feedback test, the smartphone based software application increased the device usability, e.g. the change within preselected grip patterns and the “tired muscle” algorithm. Although the overall software application was positively rated, the handling of the prosthesis itself needs to be proven within a patient study to be performed next. The capability of the neural network to control the hand has also to be proven in a next step.

scholarly journals Random Target Localization for an Upper Limb Prosthesis

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Xinglei Zhang ◽  
Binghui Fan ◽  
Chuanjiang Wang ◽  
Xiaolin Cheng ◽  
Hongguang Feng ◽  
...  
Keyword(s):  
Neural Network ◽  
Upper Limb ◽  
Target Position ◽  
Target Localization ◽  
General Regression Neural Network ◽  
Localization Algorithm ◽  
Upper Limb Prosthesis ◽  
Error Correction Algorithm ◽  
Limb Prosthesis ◽  
Random Target

To achieve the purpose of accurately grasping a random target with the upper limb prosthesis, the acquisition of target localization information is especially important. For this reason, a novel type of random target localization algorithm is proposed. Firstly, an initial localization algorithm (ILA) that uses two 3D attitude sensors and a laser range sensor to detect the target attitude and distance is presented. Secondly, an error correction algorithm where a multipopulation genetic algorithm (MPGA) optimizes backpropagation neural network (BPNN) is utilized to improve the accuracy of ILA. Thirdly, a general regression neural network (GRNN) algorithm is proposed to calculate the joint angles, which are used to control the upper limb prosthetic gripper to move to the target position. Finally, the proposed algorithm is applied to the 5-DOF upper limb prosthesis, and the simulations and experiments are proved to demonstrate the validity of the proposed localization algorithm and inverse kinematics (IK) algorithm.

SCORING MODELING BASED ON NEURAL NETWORKS FOR DETERMINING A BANK BORROWER'S RATING

2020 ◽  
Vol 2020 (10) ◽  
pp. 54-62
Author(s):  
Oleksii VASYLIEV ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Statistical Data ◽  
Activation Function ◽  
Decision Making Process ◽  
Neural Network Architecture ◽  
Acceptable Accuracy ◽  
The Neural Network ◽  
Sigmoid Activation Function

The problem of applying neural networks to calculate ratings used in banking in the decision-making process on granting or not granting loans to borrowers is considered. The task is to determine the rating function of the borrower based on a set of statistical data on the effectiveness of loans provided by the bank. When constructing a regression model to calculate the rating function, it is necessary to know its general form. If so, the task is to calculate the parameters that are included in the expression for the rating function. In contrast to this approach, in the case of using neural networks, there is no need to specify the general form for the rating function. Instead, certain neural network architecture is chosen and parameters are calculated for it on the basis of statistical data. Importantly, the same neural network architecture can be used to process different sets of statistical data. The disadvantages of using neural networks include the need to calculate a large number of parameters. There is also no universal algorithm that would determine the optimal neural network architecture. As an example of the use of neural networks to determine the borrower's rating, a model system is considered, in which the borrower's rating is determined by a known non-analytical rating function. A neural network with two inner layers, which contain, respectively, three and two neurons and have a sigmoid activation function, is used for modeling. It is shown that the use of the neural network allows restoring the borrower's rating function with quite acceptable accuracy.

Sign in / Sign up

Export Citation Format

Share Document