• Journal of Digital Convergence
• /
• v.18 no.6
• /
• pp.495-500
• /
• 2020

This study was intended to quantify the acceleration and deceleration information measured in the competition by using GPS device for the national women's field hockey players and to identify the difference in movement by classifying them by position. For this study, 308 acceleration and deceleration data were collected from 16 women's field hockey players measured at international competitions. According to research results, the frequency of acceleration was in the order of midfield > defender > striker, acceleration distance was midfield > striker > defender. The frequency of deceleration appeared in the order of midfield > defender > striker, deceleration distance was defender > striker > defender. Based on the results of this study, can be used as basic data when setting the strength and amount of training for field hockey players.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.18 no.5
• /
• pp.20-24
• /
• 2010

The position of the automobile's head restraint is very important for the neck injury in rear end collision. This study is about influence of the head restraint height and distance on neck injury during rear end collision. The effects of the position have been evaluated experimentally. The neck injuries are calculated by the relative acceleration between the upper and lower neck. As a result, It is found that the head restraint should be close enough to the back of the head and high enough to the top of the head.

• Journal of Korea Game Society
• /
• v.9 no.3
• /
• pp.121-128
• /
• 2009

In this paper, we have developed the balance board with electronic devices to use in various fields of remedial and physical balance exercise with interesting game and the functional game. Rehabilitation training using a funny game will be effective for patient's rehabilitation training. A Personal training system uses a balance board with an acceleration sensor and the game controlled by physical balance. To evaluate the operation of the developed system, we developed rehabilitation training game. The proposed game can be applicable to rehabilitation and balance training, and suggested game interface method could use a commercial game with various function through our emulator.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.45 no.1
• /
• pp.46-55
• /
• 2009

To compare and evaluate the suitability and comfort levels of the environment on board a stern trawl training ship, KAYA(GT: 1737 tons, Pukyong National University), with the international standardization guide ISO 6954:2000(E), measurements of the hull vibration on accommodation areas and working areas of the training ship from July 8 to July 10, 2008 were completed upon KAYA's linear sea route. The vibrations along the z-axis were measured with the use of a 3-axis vibration level meter, which included a marine vibration card. Results show accelerations of the vibrations on the passenger's accommodation area to be 42.0-115.8(average: 78.0, standard deviation(SD): 21.0) mm/$s^2$, which is largely below the permissible upper limit, but 75 % of the observation points exceeded the permissible lower limit of 71.5 mm/$s^2$, indicating a comfortable environment. The accelerations of the vibration in a frequency of 10-24Hz lowering the visual performance were measured at 2.5-12.0(average: 7.6, SD: 3.1) mm/$s^2$. The crew s accommodation area experienced vibration accelerations of 42.9-82.3(average: 93.1, SD: 53.1) mm/$s^2$, which is generally below the permissible upper limit of 214.0 mm/$s^2$, and 62.5% of the observation points did not exceed the permissible lower limit of 107.0 mm/$s^2$, denoting a level of comfort. The acceleration of the vibration in a frequency of 10-24Hz were 4.7-28.3(average: 12.4, SD: 8.8) mm/$s^2$. On the crew s working area the accelerations were measured at 86.9-153.9(average 119.3, SD 18.0) mm/$s^2$. These values were generally below the permissible upper limit of 286.0 mm/$s^2$ and only 12.5% of the observation points did not exceed the permissible lower limit of 143.0 mm/$s^2$, the level at which a high level of comfort is maintained. The accelerations in frequency of 10-24Hz and 30Hz were 9.1-29.8 (average 13.8, SD= 4.5) mm/$s^2$ and 8.9-13.7 (average 11.8, SD 2.1) mm/$s^2$, respectively. In conclusion the boarding environment of the training ship was good in general although an improvement of the vibration condition partially needed on the crew s accommodation area near the engine room.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.1
• /
• pp.220-224
• /
• 2010

In this study, we designed a device for consecutively observing position, utilizing 3-axises acceleration sensor. This method offer to check his or her wrong position and developed could to help derived a position appliance. And, we developed a Cobb's angle value in three dimensional using 3-axises acceleration sensor. A proposed device with integrated accelerometers, which can detect postural changes in terms of curvature variation of the spine in the sagittal and coronal planes, has been developed with intention to facilitate posture training. The proposed device was evaluated with 3 normal subjects daily activities. We evaluated the performance of our designed device as calculating the correlation coefficients and mean errors between the angle measured by an electro-goniometer and that estimated by a gravity accelerometer and verified the accuracy and sensitivity. The results showed that the angle obtained from the proposed device revealed a linear characteristic at the range of $\pm60^{\circ}$(correlation coefficient 0.99, error range $\pm2^{\circ}$). We demonstrated that our device could detect the changes of the motion in upper trunk accurately. Also, our device showed good potential for treatment of the patients with scoliosis and prevention of the unbalance position during a daily life.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.3
• /
• pp.216-220
• /
• 2009

In this paper we propose a motion recognition method for handheld controller 3-D acceleration signals, generated by 3 axis accelerometer in the controller, are transmitted to the computer by Bluetooth communication. We extract motion segments from continuous acceleration signals and apply to each motion model, which is trained in training phase. Hidden Markov Model was used to model each motion. We applied proposed method to three motion sets, the recognition result was good enough to practical use.

• Smart Structures and Systems
• /
• v.32 no.6
• /
• pp.359-369
• /
• 2023

Servo-motor driven uniaxial shake tables have been widely used for education and research purposes in earthquake engineering. These shake tables are mostly displacement-controlled by a digital proportional-integral-derivative (PID) controller; however, accurate reproduction of acceleration time histories is not guaranteed. In this study, a control strategy is proposed and verified for uniaxial shake tables driven by a servo-motor. This strategy incorporates a deep-learning algorithm named Long Short-Term Memory (LSTM) network into a displacement PID feedback controller. The LSTM controller is trained by using a large number of experimental data of a self-made servo-motor driven uniaxial shake table. After the training is completed, the LSTM controller is implemented for directly generating the command voltage for the servo motor to drive the shake table. Meanwhile, a displacement PID controller is tuned and implemented close to the LSTM controller to prevent the shake table from permanent drift. The control strategy is named the LSTM-PID control scheme. Experimental results demonstrate that the proposed LSTM-PID improves the acceleration tracking performance of the uniaxial shake table for both bare condition and loaded condition with a slender specimen.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2005.04a
• /
• pp.367-374
• /
• 2005

The use of system identification approaches for damage detection has been expanded in recent years. Soft computing techniques such as neural networks have been utilized increasingly. Damage assessment using neural networks is presented in this study. Data set for training neural networks are acceleration response of simple beam under the various damage states ,which are the inputs. The outputs are the damage locations and extents. Not only the trained damages but also untrained damages are. detected accuratelyintheassessmentstage.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.1022-1027
• /
• 1991

A new method to control a robot manipulator by neural networks is proposed. The controller is composed of both a PD controller and a neural network-based feedforward controller. MLP(multi-layer perceptron) neural network is used for the feedforward controller and trained by BP(back-propagation) learning rule. Error terms for BP learning rule are composed of the outputs of a PD controller and the acceleration errors of manipulator joints. We compare the proposed method with existing ones and contrast performances of them by simulation. Also, We discuss the real application of the proposed method in consideration of the learning time of the neural network and the time required for sensing the joint acceleration.

• Electronics and Telecommunications Trends
• /
• v.38 no.5
• /
• pp.12-22
• /
• 2023

The development of neural networks is evolving towards the adoption of transformer structures with attention modules. Hence, active research focused on extending the concept of lightweight neural network algorithms and hardware acceleration is being conducted for the transition from conventional convolutional neural networks to transformer-based networks. We present a survey of state-of-the-art research on lightweight neural network algorithms and hardware architectures to reduce memory usage and accelerate both inference and training. To describe the corresponding trends, we review recent studies on token pruning, quantization, and architecture tuning for the vision transformer. In addition, we present a hardware architecture that incorporates lightweight algorithms into artificial intelligence processors to accelerate processing.