• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.22-25
• /
• 2020

본 논문에서는 큰 크기의 심층 신경망을 압축하기위해 네트워크 수준의 가중치 공유방법인 Global Weight 패러다임을 최초로 제시한다. 기존의 가중치 공유방법은 계층별로 가중치를 공유하는 것이 대부분이었다. Global Weight 는 기존 방법과 달리 전체 네트워크에서 가중치를 공유하는 효율적인 방법이다. 우리는 Global Weight 를 사용하여 학습되는 새로운 컨볼루션 연산인 Global Weight Convolution(GWConv)연산과 GWConv를 적용한 Global Weight Networks(GWNet)을 제안한다. CIFAR10 데이터셋에서 실험한 결과 2.18 배 압축에서 85.64%, 3.41 배 압축에서 85.46%의 정확도를 보였다. Global Weight 패러다임은 가중치 공유가 궁극적으로 풀고자 했던 중복되는 가중치를 최소화하는 획기적인 방법이며, 추후 심도 있는 연구가 수행될 수 있음을 시사한다.

• International Journal of Advanced Culture Technology
• /
• v.7 no.1
• /
• pp.209-215
• /
• 2019

In order to provide a safe free-weight-training environment to people without workout trainers, we suggest a smart bench press machine with an automatic weight control system sensitive to user tiredness. Physical weight plates on the machine are replaced with a hydraulic cylinder as a press load and the cylinder knob is coupled with a step motor to change its tensile force automatically in-between lifting exercises. Three subjects participated to verify the usability of the smart bench press machine. They were asked to lift a 6-RM press load 10 times with 3 different lifting conditions: 1) no assistance, 2) a human assistance, and 3) the automatic weight control. All subjects were not able to complete the 10 sets without assistance due to tiredness, but they finished the full sets under the two assistive conditions. Average lifting speeds under the automatic weight control condition showed the most consistent level. Normalized quasi-tension data based on surface electromyogram signals of both Pectoralis Majors revealed that the subjects maintained the target muscle activation level above 50% but not more than 80% throughout the 10 sets. Therefore, the smart bench press machine is expected to both keep pace with the lifting exercise and reduce risk of injuries due to excessive muscle tensions.

• Nutrition Research and Practice
• /
• v.5 no.1
• /
• pp.11-19
• /
• 2011

Eotaxin is an important inflammatory chemokine in eosinophil chemotaxis and activation and, thus, is implicated in asthma. Recently, obesity was associated with an increased prevalence of asthma, but the relationship between obesity and eotaxin expression has only been partially understood in obese mice and human studies. Therefore, we studied the expression patterns of eotaxin in 3T3-L1 preadipocytes/adipocytes to determine whether eotaxin levels are influenced by body weight gain and/or reduction in diet-induced obese mice. First, we investigated eotaxin expression during differentiation in 3T3-L1 adipocytes. Then, we treated 3T3-L1 preadipoeytes/adipoeytes with tumor necrosis factor-alpha (TNF-${\alpha}$), eotaxin, interleukin (IL)-4, IL-5, or leptin. To examine the effects of weight loss in high-fat diet induced obese mice, we fed C57BL/6 mice a high-fat diet or a normal diet for 26 weeks. Then, half of the high-fat diet group were fed a normal diet until 30 weeks to reduce weight. Epididymal adipose tissue, visceral adipose tissue, serum, and bronchoalveolar fluid of mice were examined for eotaxin expression. The results showed that eotaxin expression levels increased with adipocyte differentiation and that more eotaxin was expressed when the cells were stimulated with TNF-${\alpha}$, eotaxin, IL-4, IL-5, or leptin. An in vivo study showed that eotaxin levels were reduced in visceral adipose tissues when high-fat diet fed mice underwent weight loss. Taken together, these results indicate a close relationship between eotaxin expression and obesity as well as weight loss, thus, they indirectly show a relation to asthma.

• Proceedings of the KSME Conference
• /
• 2004.11a
• /
• pp.817-822
• /
• 2004

This paper provides a global path planning method using self-organizing feature map which is a method among a number of neural network. The self-organizing feature map uses a randomized small valued initial weight vectors, selects the neuron whose weight vector best matches input as the winning neuron, and trains the weight vectors such that neurons within the activity bubble are move toward the input vector. On the other hand, the modified method in this research uses a predetermined initial weight vectors, gives the systematic input vector whose position best matches obstacles, and trains the weight vectors such that neurons within the activity bubble are move toward the input vector. According to simulation results one can conclude that the modified neural network is useful tool for the global path planning problem of a mobile robot.

• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.3 s.180
• /
• pp.94-101
• /
• 2006

A global path planning method using self-organizing feature map which is a method among a number of neural network is presented. The self-organizing feature map uses a randomized small valued initial weight vectors, selects the neuron whose weight vector best matches input as the winning neuron, and trains the weight vectors such that neurons within the activity bubble are moved toward the input vector On the other hand, the modified method in this research uses a predetermined initial weight vectors of 1-dimensional string and 2-dimensional mesh, gives the systematic input vector whose position best matches obstacles, and trains the weight vectors such that neurons within the activity bubble are moved toward the input vector. According to simulation results one can conclude that the modified neural network is useful tool for the global path planning problem of a mobile robot.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.5
• /
• pp.473-479
• /
• 2006

A global path planning algorithm using modified self-organizing feature map(SOFM) which is a method among a number of neural network is presented. The SOFM uses a randomized small valued initial weight vectors, selects the neuron whose weight vector best matches input as the winning neuron, and trains the weight vectors such that neurons within the activity bubble are move toward the input vector. On the other hand, the modified method in this research uses a predetermined initial weight vectors of the 2-dimensional mesh, gives the systematic input vector whose position best matches obstacles, and trains the weight vectors such that neurons within the activity bubble are move toward the opposite direction of input vector. According to simulation results one can conclude that the modified neural network is useful tool for the global path planning problem of a mobile robot.

• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.2
• /
• pp.137-143
• /
• 2005

Autonomous mobile robot has an ability to navigate using both map in known environment and sensors for detecting obstacles in unknown environment. In general, autonomous mobile robot navigates by global path planning on the basis of already made map and local path planning on the basis of various kinds of sensors to avoid abrupt obstacles. This paper provides a global path planning method using self-organizing feature map which is a method among a number of neural network. The self-organizing feature map uses a randomized small valued initial weight vectors, selects the neuron whose weight vector best matches input as the winning neuron, and trains the weight vectors such that neurons within the activity bubble are move toward the input vector. On the other hand, the modified method in this research uses a predetermined initial weight vectors, gives the systematic input vector whose position best matches obstacles, and trains the weight vectors such that neurons within the activity bubble are move toward the input vector. According to simulation results one can conclude that the modified neural network is useful tool for the global path planning problem of a mobile robot.

• Journal of the Korean Society for Precision Engineering
• /
• v.25 no.4
• /
• pp.69-76
• /
• 2008

The self-organizing feature map(SOFM) among a number of neural network uses a randomized small valued initial weight vectors, selects the neuron whose weight vector best matches input as the winning neuron, and trains the weight vectors such that neurons within the activity bubble are moved toward the input vector. On the other hand, the modified method in this research uses a predetermined initial weight vectors of the 1-dimensional string, gives the systematic input vector whose position best matches obstacles, and trains the weight vectors such that neurons within the activity bubble are move toward the opposite direction of input vector. According to simulation results one can conclude that the method using string and the modified neural network is useful tool to mobile robot for the global path planning.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.4
• /
• pp.451-455
• /
• 2009

This paper provides a comparison of global path planning method in single string by using pulled and pushed SOFM (Self-Organizing Feature Map) which is a method among a number of neural network. The self-organizing feature map uses a randomized small valued initial-weight-vectors, selects the neuron whose weight vector best matches input as the winning neuron, and trains the weight vectors such that neurons within the activity bubble are move toward the input vector. On the other hand, the modified SOFM method in this research uses a predetermined initial weight vectors of the one dimensional string, gives the systematic input vector whose position best matches obstacles, and trains the weight vectors such that neurons within the activity bubble are move toward or reverse the input vector, by rising a pulled- or a pushed-SOFM. According to simulation results one can conclude that the modified neural networks in single string are useful tool for the global path planning problem of a mobile robot. In comparison of the number of iteration for converging to the solution the pushed-SOFM is more useful than the pulled-SOFM in global path planning for mobile robot.

• Journal of the Korean Society of Physical Medicine
• /
• v.16 no.2
• /
• pp.63-70
• /
• 2021

PURPOSE: This study aimed to analyze the factors influencing the improvement of global synkinesis (GS) and gait in stroke patients by the weight shift exercise. METHODS: Twenty stroke patients were randomly assigned to experimental group I (n = 10) and experimental group II (n = 10). In experimental group I, weight shift with upper extremity exercises in a standing position were mediated and in experimental group II, upper extremity exercises in a standing position were mediated. These interventions were conducted in both groups for three sessions per week, 30 minutes per session over four weeks. Before the interventions, leg GS was measured using surface electromyography and the 10m walk test (10MWT). The same parameters were measured four weeks later. RESULTS: The GS and 10MWT of the experimental group I showed that there was a statistically significant difference between dorsiflexion (p < .05) and plantarflexion (p < .01) and 10MWT (p < .01). In experimental group II, there was a statistically significant difference only in 10MWT (p < .01). The comparison between the changes in both groups showed that in the case of GS, there was a statistically significant difference in the dorsiflexion (p < .01) and plantarflexion (p < .05), and in the 10MWT too (p < .05). CONCLUSION: GS of the lower extremities was decreased by improving posture control and enlarging soft tissues due to the symmetrical weight shift in experimental group I, which turned out to be effective in improving the gait speed.