• Journal of the Korean Applied Science and Technology
• /
• v.37 no.4
• /
• pp.755-761
• /
• 2020

The purpose of this study was to investigate the effects of balance board and whole-body vibration stimulator application on body muscle activities during static squat motion. Twenty adult males(age, 21.90±0.36 years; height, 174.30±1.09 cm; body mass, 66.50±1.00 kg; and BMI, 21.90±0.31 kg/㎡) were participated in this study as subjects. Three types' static squat motions were performed(basic static squat motion, BSSM; static squat motion with balance board, SSBB; static squat motion with whole-body vibration stimulator, SSVS). We measured the right side's body muscle activities of the rectus abdominis(RA), internal oblique(IO), external oblique(EO), rectus femoris(RF), vastus lateralis(VL), and vastus medialis(VM). The research findings were as follows. There was a significant higher RA, IO, and EO muscle activity of SSBB and SSVS(p=.001, p=.004, p=.000). And RF, VL, and VM muscle activities were greatest during SSVS(p=.000). These findings are expected to serve as references for static squat motion applications in training programs for body muscle strengthening.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• Journal of the Korean Society for Precision Engineering
• /
• v.26 no.3
• /
• pp.81-87
• /
• 2009

Lightweight board has been used for manufacturing various fields of automotive interior trims for years. The GMPU board was constructed with glass fiber mat, honeycomb and polyurethane foamed using polyol and isocyanate materials which were sprayed by robot that is interlocked foaming machine. For more lightweight and cost reduction this paper shows how to optimize GMPU process parameters that related to foaming condition, robot position and robot velocity for polyurethane weight. The results show that flexural strength and modulus of board's specimens were evaluated by robot velocity and moving pattern. Based on that, a innovative process was developed for more lightweight and cost reduction.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10e
• /
• pp.385-387
• /
• 2002

인터넷 상에서 IP 주소의 부족 문제를 해결하기 위해 IPv6 프로토콜이 제안되었고 현재 실용화 단계에 접어들었다. IPv6에서는 보안기능의 강화를 위해 IPsec 프로토콜을 기본 요구사항으로 채택하였고, 본 논문에서는 이러한 IPsec 프로토콜을 하드웨어로 설계하고 구현하였다. 이를 위해 IPv6에서 보안기능을 담당하는 헤더와 IPsec의 기간 암호화 알고리즘을 설계하여 각각 VHDL로 구현하였고, 전용 FPGA 보드와 IPv6 테스트망에서 그 기능과 성능을 검증하였다. 구현된 IPsec 프로토콜 칩은 TCP／IPv6와 IPsec 프로토콜을 하나의 칩으로 구현함으로써 별도의 프로세서 없이 인터넷 접속 기능과 보안기능을 동시에 제공하며 소프트웨어 모듈보다 뛰어난 성능을 나타낸다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.288-291
• /
• 2022

본 논문은 4족 지능 로봇의 비평탄 지형 극복 기능을 구현하기 위해, 시뮬레이션 환경에서 제공하는 역기구학(Inverse Kinematic)과 개선된 강화 학습 방법(Partially Observable Markov Decision Process)을 분석하여 수립한 알고리즘을 동작 검증을 위한 임베디드 보드(Embedded Board)에 실제 적용하여 보았다. 이 연구를 통해 4족 보행 로봇의 효율적인 지형 극복형 보행 방식 설계 방법을 제안하며, 특히 IMU 센서의 지능적인 균형제어 방법을 평가하고 다양한 통신방식과 서보모터 제어 방식을 실험하고 구현하였다. 또한 모터 가감속 제어를 통해 보다 부드럽고 안정적인 보행을 구현한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.618-620
• /
• 2022

게임은 수많은 NPC 와 규칙에 의해 작동되는 가상 공간을 의미한다. 이런 가상 공간에서는 규칙을 엄격히 지키면서 수행되는 AI 를 필수로 요구하게 된다. 하지만 강화 학습 기반의 AI 는 복잡한 게임의 규칙을 온전히 지키지 못하고 예상 밖의 행동을 돌출하면서 이를 해결하기 위한 많은 연구도 수행되고 있다. 본 논문에서는 규칙 기반으로 획득한 오목판의 확률 맵과 학습을 통해 획득한 확률맵 데이터를 병합하여 가장 높은 Value 를 가지는 위치를 다음 수로 반환하는 방법을 사용하였다. 향후 연구에서는 ANN(Approximate Nearest Neighbor)알고리즘을 적극 활용하여, 커널의 State 와 보드의 State 비교를 확률적으로 개선할 예정이다. 본 논문에서 제안된 프레임 워크는 게임 AI 연구에 기여할 수 있길 바란다.

• Journal of Korea Multimedia Society
• /
• v.13 no.9
• /
• pp.1391-1398
• /
• 2010

Animation is breathing life into drawings through motion. Animation is formed by the afterimage phenomenon, that is, deviation of sequential pictures in every frame makes a person possibly perceive it as a live video. Consequently, animation is mostly produced using traditional frame-by-frame methods. The study of relations on timing has been a major concern of animation theory. Nevertheless, issues of timing on production outcomes and effectiveness are mostly ignored. Special focus, analysis and leadership studies on timing are addressed on animatics. Creating better timing through animatics, that is writing movies, directing, scheduling and amending storyboard in pre-production stage, eventually shorten time to animation production. This research is centered on animatics as a cutting edge educational courses. This course will introduce students to the animation production skill and instructors to in-depth teaching points. One of the concepts that we want to go for is keeping animatics apart from mere storyboard. In conjunction with the animation theory, this research conducted under the focus of production of animatics will lead to more efficient way of education on animatics.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.7
• /
• pp.1-8
• /
• 2020

In this paper, we present an implementation of high speed image data transfer using XDMA for a video signal generation / acquisition device developed as a military test equipment. The technology proposed in this study obtains efficiency by replacing the method of copying data using the system buffer in the kernel area with the transmission and reception through the DMA engine in the FPGA. For this study, the device was developed as a PXIe platform in consideration of life cycle, and performance was maximized by using a low-cost FPGA considering mass productivity. The video I/O board implemented in this paper was tested by changing the AXI interface clock frequency and link speed through the existing memory copy method. In addition, the board was constructed using the DMA engine of the FPGA, and as a result, it was confirmed that the transfer speed was increased from 5~8Hz to 140Hz. The proposed method will contribute to strengthening defense capability by reducing the cost of device development using the PXIe platform and increasing the technology level.

• Journal of Broadcast Engineering
• /
• v.21 no.4
• /
• pp.525-537
• /
• 2016

In this paper, we develop an online video mash-up system which use automatic scene elements composition scheme using a storyboard. There are two conventional online video production schemes. Video collage method is simple and easy, but it was difficult to reflect narrative or story. Another way is a template based method which usually select a template and it replaces resources such as photos or videos in the template. However, if the related templates do not exist, there are limitations that cannot create the desired output. In addition, the quality and atmosphere of the output is too dependent on the template. To solve these problems, we propose a video mash-up scheme using storyboard and we also implement a classification and recommendation scheme based on topic modeling.

• Journal of Korean Society of Forest Science
• /
• v.104 no.2
• /
• pp.254-260
• /
• 2015

This paper assesses the tariff reduction on imported wood products that will have impact on the demand for domestic wood products in South Korea, by estimating the Armington substitution elasticities based on the assumption that they are imperfect substitutes. Results indicate that domestic and foreign wood products are far from perfect substitutes to each other. The substitution elasticities in plywood and fiberboard appeared to be high, implying that tariff reduction may have negative effects on those industries. On the contrary, imported and domestic particleboard showed a low substitution elasticity. The decline of fiberboard industry may lead to the decline in forestry since fiberboard is produced mainly by thinned woods supplied from domestic forests. Therefore, effective countermeasures to enhance the competitiveness of wood products industry are needed to cope with the market opening.