• Journal of the Korean Society of Industry Convergence
• /
• v.23 no.2_1
• /
• pp.149-161
• /
• 2020

We describe a new approach to implement of trajectory control and track record of articulated manipulator based on monitoring simulator for smart factory. The learning control algorithm was applied in implementation real-time control to provide enhanced motion control performance for robotic manipulators. The proposed control scheme is simple in structure, fast in computation, and suitable for real-time control. Moreover, this scheme does not require any accurate dynamic modeling, or values of manipulator parameters and payload. Performance of the proposed controller is illustrated by simulation and experimental results for robot manipulator consisting of six joints at the joint space and Cartesian space.by monitoring simulator.

• Journal of the Korean Society of Industry Convergence
• /
• v.22 no.2
• /
• pp.87-93
• /
• 2019

This research deals with posture optimization for humanoid robot against external forces using genetic algorithm and neural network. When the robot takes a motion to push an object, the torque of each joint is generated by reaction force at the palm. This study aims to optimize the posture of the humanoid robot that will change this torque. This study finds an optimized posture using a genetic algorithm such that torques are evenly distributed over the all joints. Then, a number of different optimized postures are generated from various the reaction forces at the palm. The data is to be used as training data of MLP(Multi-Layer Perceptron) neural network with BP(Back Propagation) learning algorithm. Humanoid robot can find the optimal posture at different reaction forces in real time using the trained neural network include non-training data.

• ETRI Journal
• /
• v.41 no.2
• /
• pp.207-223
• /
• 2019

Network function virtualization can significantly improve the flexibility and effectiveness of network appliances via a mapping process called service function chaining. However, the failure of any single virtualized network function causes the breakdown of the entire chain, which results in resource wastage, delays, and significant data loss. Redundancy can be used to protect network appliances; however, when failures occur, it may significantly degrade network efficiency. In addition, it is difficult to efficiently map the primary and backups to optimize the management cost and service reliability without violating the capacity, delay, and reliability constraints, which is referred to as the reliability-aware service chaining mapping problem. In this paper, a mixed integer linear programming formulation is provided to address this problem along with a novel online algorithm that adopts the joint protection redundancy model and novel backup selection scheme. The results show that the proposed algorithm can significantly improve the request acceptance ratio and reduce the consumption of physical resources compared to existing backup algorithms.

• Journal of Multimedia Information System
• /
• v.7 no.4
• /
• pp.257-262
• /
• 2020

In this paper, a method of detecting the emergency situations such as body fall is proposed by using color images. We detect body areas and key parts of a body through a pre-learned Mask R-CNN in the images captured by a camera. Then we find the centerline of the body through the joint points of both shoulders and feet. Also, we calculate an angle to the center line and then calculate the amount of change in the angle per hour. If the angle change is more than a certain value, then it is decided as a suspected fall. Also, if the suspected fall state persists for more than a certain frame, then it is determined as a fall situation. Simulation results show that the proposed method can detect body fall situation accurately.

• The Journal of Korea Robotics Society
• /
• v.17 no.1
• /
• pp.58-67
• /
• 2022

In this paper, we propose an approach resolving inaccuracy of the low-cost redundant manipulator workspace with low encoder and low stiffness. When the manipulators are manufactured with low-cost encoders and low-cost links, the robots can run into workspace inaccuracy issues. Furthermore, trajectory generation based on conventional forward/inverse kinematics without taking into account inaccuracy issues will introduce the risk of end-effector fluctuations. Hence, we propose an optimization for the trajectory generation method based on the DDPG (Deep Deterministic Policy Gradient) algorithm for the low-cost redundant manipulators reaching the target position in Euclidean space. We designed the DDPG algorithm minimizing the distance along with the jacobian condition number. The training environment is selected with an error rate of randomly generated joint spaces in a simulator that implemented real-world physics, the test environment is a real robotic experiment and demonstrated our approach.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.1048-1051
• /
• 2020

본 논문에서는 사람의 손에 관한 개별적으로 분리되어 진행되고 있는 손 위치 추정, 손 자세 추정, 손 동작 인식 작업을 통합하는 Faster-RCNN기반의 프레임워크를 제안하였다. 제안된 프레임워크에서는 RGB 동영상을 입력으로 하여, 먼저 손 위치에 대한 박스를 생성하고, 생성된 박스 정보를 기반으로 손 자세와 동작을 인식하도록 한다. 손 위치, 손 자세, 손 동작에 대한 정답을 동시에 모두 가지는 데이터셋이 존재하지 않기 때문에 Egohands, FPHA 데이터를 동시에 효과적으로 사용하는 방안을 제안하였으며 제안된 프레임워크를 FPHA데이터에 평가하였다., 손 위치 추정 정확도는 mAP 90.3을 기록했고, 손 동작 인식은 FPHA의 정답을 사용한 정확도에 근접한 70.6%를 기록하였다.

• ETRI Journal
• /
• v.45 no.5
• /
• pp.811-821
• /
• 2023

We propose an adaptive unmanned aerial vehicle (UAV)-assisted object recognition algorithm for urban surveillance scenarios. For UAV-assisted surveillance, UAVs are equipped with learning-based object recognition models and can collect surveillance image data. However, owing to the limitations of UAVs regarding power and computational resources, adaptive control must be performed accordingly. Therefore, we introduce a self-adaptive control strategy to maximize the time-averaged recognition performance subject to stability through a formulation based on Lyapunov optimization. Results from performance evaluations on real-world data demonstrate that the proposed algorithm achieves the desired performance improvements.

• Journal of Technology Innovation
• /
• v.30 no.2
• /
• pp.29-58
• /
• 2022

Startups lack resources and manpower to build internal capabilities to strengthen market competitiveness; external cooperation such as joint research and networking plays is important. In this study, we analyzed the effect of startups' industry-university cooperation on organizational learning capability and innovation performance. Empirical results demonstrate the mechanism by which government R&D investment strengthens organizational learning capability and creates innovative results by promoting cooperation between startups and universities. First, industry-university cooperation strengthened organizational learning capability. An empirical analysis shows that startups increase internal capabilities through external cooperation. Second, startups' organizational learning capability had a significant effect on innovation performance. We analyze how organizations with high learning capabilities positively develop corporate innovation performance by having a culture of discovery and sharing new ideas. Finally, industry-university cooperation had different effects on organizational learning capability and innovation performance according to the previous experiences of startup founders. In particular, small- and medium-sized (startup) businesses and individual-based experience groups positively affected the creation of organizational learning capabilities and innovation performance through industry-university cooperation. Small- and medium-sized businesses and individual founders have a relatively small cooperative network with the outside world compared to founders of large companies, universities, and research institutes; therefore, they strengthen organizational learning capabilities through cooperation with universities. This study demonstrates that government should create policy inducements for cooperation with universities to maximize the R&D performance of startups. Criticism exists that lending support to startups and universities will hinder innovation performance; nevertheless, government investment plays a role in expanding intangible resources such as accumulating technologies, fostering high-quality human resources, and strengthening innovation networks. Therefore, the government should appropriately utilize the its authority to strengthen investment strategies for startup growth.

• Journal of the Korean Academy of Clinical Electrophysiology
• /
• v.5 no.2
• /
• pp.35-45
• /
• 2007

The purpose of this study was to examine spiral way movement of a trunk exerts on the movement ability. The details established to achieve for this article. This examination confirmed the weight, weight/height2 index, ratio of lumbar to pelvic, musculoskeletal quantity, push up for 2 minute, pitch a ball and voluntary isometric contraction with flexion and extension of knee joint of the subjects with spiral direct movement. Healthy eighteen subjects who understand fully the significance of procedure, consented to a plan, without neuromuscular disease were participated in two groups of experiment. The group were a spiral movement(9), rectilinear movement(9). Trunk movement tested 2 sessions of a spiral movement and rectilinear movement with a push up for 2 minute, 5days per a week, for the 4 weeks. This experiment tested 3 times with a sufficient rest for fatigue limitation. An analysis of the results used a paired samples t-test for difference from before and after experiment. The following results were obtained; At an internal change of the body, the musculoskeletal quantity was increased significantly to spiral movement group, but the weight was increased significantly, the musculoskeletal quantity was not significant to rectilinear movement. The movement ability evaluation for a external change was increased significantly in a push up for 2 minute, pitch a ball, isometric contraction with extension of knee joint of a spiral movement group, but a push up for 2 minute was increased significantly in a push up for 2 minute on the abdominal muscle training of a rectilinear movement group. As compared with a rectilinear movement, a spiral movement was more effect by cooperation with nerve and musculoskeletal system and an increase in movement ability was caused by learning acknowledgment, muscular reeducation. These results lead us to the conclusion that a spiral movement of trunk was more effect than a rectilinear movement, the coordination of nerve and musculoskeletal system was of importance of Multi-direction movement. Therefore, A further studies concerning the therapeutic exercise intervention and active-dynamic analysis could enhance the development of the most effect on the trunk.

• Journal of Intelligence and Information Systems
• /
• v.5 no.1
• /
• pp.103-123
• /
• 1999

Input filtering as a preprocessing method is so much crucial to get good performance in time series forecasting. There are a few preprocessing methods (i.e. ARMA outputs as time domain filters, and Fourier transform or wavelet transform as time-frequency domain filters) for handling time series. Specially, the time-frequency domain filters describe the fractal structure of financial markets better than the time domain filters due to theoretically additional frequency information. Therefore, we, first of all, try to describe and analyze specially some issues on the effectiveness of different filtering methods from viewpoint of the performance of a neural network based forecasting. And then we discuss about neural network model architecture issues, for example, what type of neural network learning architecture is selected for our time series forecasting, and what input size should be applied to a model. In this study an input selection problem is limited to a size selection of the lagged input variables. To solve this problem, we simulate on analyzing and comparing a few neural networks having different model architecture and also use an embedding dimension measure as chaotic time series analysis or nonlinear dynamic analysis to reduce the dimensionality (i.e. the size of time delayed input variables) of the models. Throughout our study, experiments for integration methods of joint time-frequency analysis and neural network techniques are applied to a case study of daily Korean won / U. S dollar exchange returns and finally we suggest an integration framework for future research from our experimental results.