scholarly journals A 10-Gb/s trans-impedance amplifier with LC-ladder input configuration

2010 ◽  
Vol 7 (16) ◽  
pp. 1201-1206 ◽  
Author(s):  
Kang-Yeob Park ◽  
Won-Seok Oh ◽  
Woo-Young Choi
Keyword(s):  
Input Configuration

Mechanical Redesign of a Transtibial Prosthesis With Active and Passive Components and a Four-Bar Mechanism

2020 ◽  
Author(s):  
Devon K. Plata ◽  
Jessica B. Thayer ◽  
Philip A. Voglewede
Keyword(s):  
Energy Expenditure ◽  
Energy Input ◽  
Impedance Control ◽  
Energy Requirement ◽  
Neutral Position ◽  
Passive Components ◽  
Input Configuration ◽  
Transtibial Prosthesis ◽  
Spring Mechanism

Abstract This paper proposes a redesign of a four-bar mechanism for an active transtibial prosthesis created by Bergelin 2010 and modified by Klein 2009. Bergelin utilized a four-bar mechanism, motor, and spring to match the prosthesis ankle moments to the ankle moments of a healthy ankle. Bergelin’s prosthesis did succeed in matching ankle moments closely, but with excessive motor energy expenditure when the prosthesis was in a neutral position. Klein proposed a redesign of the mechanism to change the motor-spring connection from parallel to series to eliminate the energy requirement when the device is in neutral position, which allowed for the application of impedance control of mechanism. This paper proposes a reoptimization of the series motor-spring mechanism configuration proposed by Klein, which further reduces the energy input configuration of the active prosthesis.

Cerebellar Input Configuration Toward Object Model Abstraction in Manipulation Tasks

2011 ◽  
Vol 22 (8) ◽  
pp. 1321-1328 ◽  
Author(s):  
N. R. Luque ◽  
J. A. Garrido ◽  
R. R. Carrillo ◽  
O. J. D. Coenen ◽  
E. Ros
Keyword(s):  
Object Model ◽  
Model Abstraction ◽  
Input Configuration

scholarly journals TUHAD: Taekwondo Unit Technique Human Action Dataset with Key Frame-Based CNN Action Recognition

Sensors ◽  
2020 ◽  
Vol 20 (17) ◽  
pp. 4871
Author(s):  
Jinkue Lee ◽  
Hoeryong Jung
Keyword(s):  
Action Recognition ◽  
Network Architecture ◽  
Human Action ◽  
Image Sequences ◽  
Neural Network Architecture ◽  
Key Frame ◽  
Full Contact ◽  
Proposed Model ◽  
Input Configuration ◽  
Quantitative Scoring

In taekwondo, poomsae (i.e., form) competitions have no quantitative scoring standards, unlike gyeorugi (i.e., full-contact sparring) in the Olympics. Consequently, there are diverse fairness issues regarding poomsae evaluation, and the demand for quantitative evaluation tools is increasing. Action recognition is a promising approach, but the extreme and rapid actions of taekwondo complicate its application. This study established the Taekwondo Unit technique Human Action Dataset (TUHAD), which consists of multimodal image sequences of poomsae actions. TUHAD contains 1936 action samples of eight unit techniques performed by 10 experts and captured by two camera views. A key frame-based convolutional neural network architecture was developed for taekwondo action recognition, and its accuracy was validated for various input configurations. A correlation analysis of the input configuration and accuracy demonstrated that the proposed model achieved a recognition accuracy of up to 95.833% (lowest accuracy of 74.49%). This study contributes to the research and development of taekwondo action recognition.

Sign in / Sign up

Export Citation Format

Share Document