• Journal of information and communication convergence engineering
• /
• 제21권4호
• /
• pp.337-345
• /
• 2023

In this study, we formulated a method that evaluates Taekwondo Poomsae performance using a series of choreographed training movements. Despite recent achievements in 3D human pose estimation (HPE) performance, the analysis of human actions remains challenging. In particular, Taekwondo Poomsae action analysis is challenging owing to the absence of time synchronization data and necessity to compare postures, rather than directly relying on joint locations owing to differences in human shapes. To address these challenges, we first decomposed human joint representation into joint rotation (posture) and limb length (body shape), then synchronized a comparison between test and reference pose sequences using DTW (dynamic time warping), and finally compared pose angles for each joint. Experimental results demonstrate that our method successfully synchronizes test action sequences with the reference sequence and reflects a considerable gap in performance between practitioners and professionals. Thus, our method can detect incorrect poses and help practitioners improve accuracy, balance, and speed of movement.

• 생약학회지
• /
• 제19권3호
• /
• pp.208-215
• /
• 1988

To investigate the experimental effects of Chunwangboshimdan which have been widely used for aterial or auricular flutter, neurosis, insomnia and disease caused by cardiac malfunction, we have done the effects on the central nervous and cardiovascular system. The result as follow; It inhibited the convulsion induced by caffeine, the writhing syndrome induced by acetic acid and the spontaneous movement. Furthermore it prolonged the sleeping time induced by thiopental-Na in mice. It also showed the negative inotropic action on the isolated heart of frog, the vasodilative action as to peripheral bloods of rabbit ear and the hypotensive action in the anesthetized rabbit.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.174-174
• /
• 2000

Q-learning, based on discrete state and action space, is a most widely used reinforcement Learning. However, this requires a lot of memory and much time for learning all actions of each state when it is applied to a real mobile robot navigation using continuous state and action space Region-based Q-learning is a reinforcement learning method that estimates action values of real state by using triangular-type action distribution model and relationship with its neighboring state which was defined and learned before. This paper proposes a new Region-based Q-learning which uses a reward assigned only when the agent reached the target, and get out of the Local optimal path with adjustment of random action rate. If this is applied to mobile robot navigation, less memory can be used and robot can move smoothly, and optimal solution can be learned fast. To show the validity of our method, computer simulations are illusrated.

• 약학회지
• /
• 제43권5호
• /
• pp.665-673
• /
• 1999

This study was performed in order to investigate the effect of ketanserin, a specific antagonist of 5-HT2 receptor, on renal function in dogs. Ketanserin (50.0 and $150.0{\;}\mu\textrm{g}/kg$), when given intravenously, produced antidiuretic action accompanied with the decreased amounts of sodium and potassium excreted in urine (ENa, EK) and the increased reabsorption rates of sodium and potassium in renal tubules (RNa, RK). Ketanserin (50.0 and $50.0{\;}\mu\textrm{g}/kg$), when administered into a renal artery, elicited antidiuretic action in both experimental and control kidney, this time changes of renal function showed the same aspect as when given intravenously. Ketanserin (15.0 and $50.0{\;}\mu\textrm{g}/kg$) injected into the carotid artery exhibited also antidiuretic action and this antidiuretic action was not affected by renal denervation. Above results suggest that ketanserin elicits antidiuretic through central function, this central antidiuretic action is not mediated by renal nerves.

• Journal of Information Processing Systems
• /
• 제19권4호
• /
• pp.554-562
• /
• 2023

This research offers a sports video action recognition approach based on the fish swarm algorithm in light of the low accuracy of existing sports video action recognition methods. A modified fish swarm algorithm is proposed to construct invariant features and decrease the dimension of features. Based on this algorithm, local features and global features can be classified. The experimental findings on the typical sports action data set demonstrate that the key details of sports action can be successfully retained by the dimensionality-reduced fusion invariant characteristics. According to this research, the average recognition time of the proposed method for walking, running, squatting, sitting, and bending is less than 326 seconds, and the average recognition rate is higher than 94%. This proves that this method can significantly improve the performance and efficiency of online sports video motion recognition.

• Journal of Pharmaceutical Investigation
• /
• 제16권1호
• /
• pp.18-23
• /
• 1986

Anemarrhenae Rhizoma has been clinically used as a sedative drug in oriental medicine. We observed the sedative action and effect on the movement of isolated-ileum with each water extract of Anemarrhenae Rhizoma (F-I), saline solution treated preparation (F-II) and 25% ethanol treated preparation (F-III). The results obtained were summerized as follows; 1) Sedative actions were recognized with F-I, F-II and F-III. 2) Prolonged effect of sleeping time was recognized significantly with F-I, F-II and F-III. 3) Each fraction of Anemarrhenae Rhizoma showed the released action on the isolated-ileum of the mouse, rat, rabbit and guinea pig, and antagonic action against contraction induced by acetylcholine, barium chloride and histamine. Thus the mechanism in the released action of the smooth muscle was partly considered as the direct dependence of the smooth muscle.

• 한국멀티미디어학회논문지
• /
• 제22권12호
• /
• pp.1457-1465
• /
• 2019

3D convolution is to stack multiple consecutive frames to form a cube, and then apply the 3D convolution kernel in the cube. In this structure, each feature map of the convolutional layer is connected to multiple adjacent sequential frames in the previous layer, thus capturing the motion information. However, due to the changes of pedestrian posture, motion and position, the convolution at the same place is inappropriate, and when the 3D convolution kernel is convoluted in the time domain, only time domain features of three consecutive frames can be extracted, which is not a good enough to get action information. This paper proposes an action recognition method based on feature fusion of 3D convolutional neural network. Based on the VGG16 network model, sending a pre-acquired optical flow image for learning, then get the time domain features, and then the feature of the time domain is extracted from the features extracted by the 3D convolutional neural network. Finally, the behavior classification is done by the SVM classifier.

• 로봇학회논문지
• /
• 제15권4호
• /
• pp.385-391
• /
• 2020

As deep learning technology has been developed and applied to various fields, it is gradually changing from an existing single image based application to a video based application having a time base in order to recognize human behavior. However, unlike 2D CNN in a single image, 3D CNN in a video has a very high amount of computation and parameter increase due to the addition of a time axis, so improving accuracy in action recognition technology is more difficult than in a single image. To solve this problem, we investigate and analyze various techniques to improve performance in 3D CNN-based image recognition without additional training time and parameter increase. We propose a time base ensemble using the time axis that exists only in the videos and an ensemble in the input frame. We have achieved an accuracy improvement of up to 7.1% compared to the existing performance with a combination of techniques. It also revealed the trade-off relationship between computational and accuracy.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2000년도 추계학술대회 논문집
• /
• pp.184-187
• /
• 2000

This paper describes action of synchronous error between z axis and spindle axis on rigid tapping. Because rigid tapping cuts the threads synchronizing the movement of z axis to spindle rotation, synchronous error between z axis and spindle is very important. Increase of synchronous error degrades the accuracy of thread and crushes the tap in worst case. So we developed the realtime measurement system of synchronous error in order to know the action of synchronous error on rigid tapping. In result, we have known that synchronous error was increased according to rise of spindle speed and z axis speed. And because the cutting torque(M3-30Ncm∼M10-300Ncm) on rigid tapping are less than maximum motor torque(3500Ncm), it specially doesn't affect the synchronous error. The most important parameter which has affected the increase of synchronous error was acceleration/deceleration time. On worst case, spindle motor was tripped because of the excess of synchronous error. Because the acceleration/deceleration time ocuupies the most of the total cutting time, in order to move on the high speed rigid tapping, the acceleration/deceleration time of spindle must be remarkably reduced.

• 약학회지
• /
• 제33권3호
• /
• pp.183-190
• /
• 1989

Angiotensin II, adminstered (infused or injected) intravenously, elicited the antidiuretic action with the decreased parameters of renal function at a small dose ($0.01\;{\mu}g/kg/min$), whereas, at a large dose (0.03, $0.1\;{\mu}g/kg/min$ and $5.0\;{\mu}g/kg$), it produced the diuretic action accompanied the increased amounts of sodium and potassium excreted in urine ($E_{Na}\;and\;R_K$). At this time, glomerular filtration rates (GFR) were weakened slightly and renal plasma flows (RPF) were reduced markedly, and then filtration fractions (FF) were increased. Angiotensin II, infused into a renal artery, exhibited antidiuretic action at a small dose ($0.003\;{\mu}g/kg/min$), and diuretic action at a large dose ($0.01\;{\mu}g/kg/min$), only in infused (experimental) kidney. The mechanism of the action was similar to the cases of the intravenous angiotensin II. The above results suggest that angiotensin II of a large dose produced diuretic action due to mechanism inhibiting reabsorption of electrolytes in renal tubules, mainly in proximal tubule in dog.