• Journal of the Korean Society for Precision Engineering
• /
• v.25 no.8
• /
• pp.104-110
• /
• 2008

The aim of this study ultimately is verifying that PGO gait is more efficient than RGO fur paraplegics because the air muscle assists hip flexion power in heel off movement. The gait characteristics of the paraplegic wearing the PGO or RGO are compared with that of a normal person. PGO with air muscles was used to analyze the walking of patients with lower-limb paralysis, and the results showed that the hip joint flexion and pelvic tilt angle decreased in PGO. In comparison to RGO gait, which is propelled by the movements of the back, PGO uses air muscles, which decreases the movement in the upper limb from a stance phase rate of 79$\pm$4%(RGO) to 68$\pm$8%. The energy consumption rate was 8.65$\pm$3.3 (ml/min/Kg) for RGO, while it decreased to 7.21t2.5(ml/min/Kg) for PGO. The results from this study show that PGO decreases energy consumption while providing support for patients with lower-limb paralysis, and it is helpful in walking for extended times.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.6
• /
• pp.518-523
• /
• 2015

This paper proposes a gait phase classifier using a Recurrent Neural Network (RNN). Walking is a type of dynamic system, and as such it seems that the classifier made by using a general feed forward neural network structure is not appropriate. It is known that an RNN is suitable to model a dynamic system. Because the proposed RNN is simple, we use a back propagation algorithm to train the weights of the network. The input data of the RNN is the lower body's joint angles and angular velocities which are acquired by using the lower limb exoskeleton robot, ROBIN-H1. The classifier categorizes a gait cycle as two phases, swing and stance. In the experiment for performance verification, we compared the proposed method and general feed forward neural network based method and showed that the proposed method is superior.

• Journal of the Korean Society of Industry Convergence
• /
• v.21 no.1
• /
• pp.17-27
• /
• 2018

We propose a new approach to control a biped robot motion based on iterative learning of voice command for the implementation of smart factory. The real-time processing of speech signal is very important for high-speed and precise automatic voice recognition technology. Recently, voice recognition is being used for intelligent robot control, artificial life, wireless communication and IoT application. In order to extract valuable information from the speech signal, make decisions on the process, and obtain results, the data needs to be manipulated and analyzed. Basic method used for extracting the features of the voice signal is to find the Mel frequency cepstral coefficients. Mel-frequency cepstral coefficients are the coefficients that collectively represent the short-term power spectrum of a sound, based on a linear cosine transform of a log power spectrum on a nonlinear mel scale of frequency. The reliability of voice command to control of the biped robot's motion is illustrated by computer simulation and experiment for biped walking robot with 24 joint.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.6
• /
• pp.2470-2491
• /
• 2018

Web-scale open information extraction (Open IE) plays an important role in NLP tasks like acquiring common-sense knowledge, learning selectional preferences and automatic text understanding. A large number of Open IE approaches have been proposed in the last decade, and the majority of these approaches are based on supervised learning or dependency parsing. In this paper, we present a novel method for web scale open information extraction, which employs cosine distance based on Google word vector as the confidence score of the extraction. The proposed method is a purely unsupervised learning algorithm without requiring any hand-labeled training data or dependency parse features. We also present the mathematically rigorous proof for the new method with Bayes Inference and Artificial Neural Network theory. It turns out that the proposed algorithm is equivalent to Maximum Likelihood Estimation of the joint probability distribution over the elements of the candidate extraction. The proof itself also theoretically suggests a typical usage of word vector for other NLP tasks. Experiments show that the distance-based method leads to further improvements over the newly presented Open IE systems on three benchmark datasets, in terms of effectiveness and efficiency.

• ETRI Journal
• /
• v.40 no.4
• /
• pp.511-521
• /
• 2018

The ability to realize human-motion imitation using robots is closely related to developments in the field of artificial intelligence. However, it is not easy to imitate human motions entirely owing to the physical differences between the human body and robots. In this paper, we propose a work chain-based inverse kinematics to enable a robot to imitate the human motion of upper limbs in real time. Two work chains are built on each arm to ensure that there is motion similarity, such as the end effector trajectory and the joint-angle configuration. In addition, a two-phase filter is used to remove the interference and noise, together with a self-collision avoidance scheme to maintain the stability of the robot during the imitation. Experimental results verify the effectiveness of our solution on the humanoid robot Nao-H25 in terms of accuracy and real-time performance.

• Laser Solutions
• /
• v.12 no.3
• /
• pp.14-17
• /
• 2009

The laser welding was performed for the flange joint of two overlapped coaxial circular pipes which serve as the inlet and connector pipes of STS 316L. The laser welding test finally resulted in a good penetration depth of 1.8 to 2.0 mm. On the way to get the good welding quality, two important parameters were found to be optimized. One is the focal positioning which is the offset of the laser beam focus to the exact welding seam line, which is more critical in the inner flange laser welding. When the beam spot size was deviated more than $200\;{\mu}m$ from the seam line, welding of two pipes is failed. The other is a gap size since a certain amount of gap is inevitable due to fabrication tolerance, or artificial allowances for smooth insertion of a pipe. However, it is required to restrict the gap allowance within 0.2mm to avoid undesirable undercut on a welding bead.

• The Journal of the Korean bone and joint tumor society
• /
• v.1 no.1
• /
• pp.105-112
• /
• 1995

Soft tissue sarcomas are malignant tumors that arise in the extraskeletal connective tissues of the body. And the clinical behavior of soft tissue sarcomas is characterized by a tendency to extensively invade surrounding soft tissues as well as early metastatic dissemination. Difficulties were encounted when soft tissue sarcomas invade the major vessels. There are a few reprots about the reconstruction of the major vessels after resection of soft tissue sarcomas. We have treated 3 cases of the soft tissue sarcomas involving the major artery. After marginal excision of the tumor mass, the involved major artery was reconstructed with Gortex artificial vessel graft and we could salvage the patient's extremity.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10b
• /
• pp.124-129
• /
• 1992

The goal of the proposed Intelligent Assisting System - IAS is to assist human operators in an intelligent way, while leaving decision and goal planning instances for the human. To realize the IAS the very important issue of manipulation skill identification and analysis has to be solved, which then is stored in a Skill Data Base. Using this data base the IAS is able to perform complex manipulations on the motion control level and to assist the human operator flexibly. We propose a model for manipulation skill based on the dynamics of the grip transformation matrix, which describes the dynamic transformation between object space and finger joint space. Interaction with a virtual world simulator allows the calculation and feedback of appropriate forces through controlled actuators of the sensor glove with 10 degrees-of-freedom. To solve the sensor glove calibration problem, we learn the nonlinear calibration mapping by an artificial neural network(ANN). In this paper we also describe the experimental system setup of the skill acquisition and transfer system as a first approach to the IAS. Some simple manipulation examples and simulation results show the feasibility of the proposed manipulation skill model.

• Journal of the Speleological Society of Korea
• /
• no.66
• /
• pp.45-57
• /
• 2005

This Paper is a study on the duality of speleothem that appeared in 'Hyeob Jae Cave' which is designated as the natural monumen. No.236. It is located at Hyeob Jae Ri, Hanrim Eub, Bug Je-ju Gun, Je-judo. The findings are as follows. 1. The distribution range of the shelly sand which has maximum thickness of $10m{\pm}$ and average of $3m{\pm}$ was $3.2m^2$. 2. The desert hollow acted to promote the speleothem deposits in the lava tunnel with lava mound formed by lavapilz and artificial breaksand wall. 3. The main component of the pseudo limestone cavern was carbonate Calcium from shelly sand. And the deposition of speleothem in the Cave was accelerated after the volcanic erupsion of Biyang island in 1002. A.D. 4. The secondary depositions of Calcite recognized as speleothem up to now it can be used for the pseudo karst in general. 5. It seems that the variety of the cave deposits is decided depending upon the geology, land form, climate, vegetations and the structural environmental factors. 6. It seems that the wondering development of accretionary deposits caused by encrusting has a close relation with intermittent seepage of ground water. 7. Finally, we can acknowledge the coexistent duality of speleothem by shelly sand along with the joint and the lava stalactites formed at the same time with the lava tunnel on the ceiling where there was no seepage.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.21 no.3
• /
• pp.299-306
• /
• 2001

In this paper, artificial and real defects(delamination and debond) in composite structures were detected by using ESPI system. Three types of specimens, that is, composite laminates, honeycomb structures, and adhesive joints, were used to study the applicability of ESPI to composite structures. To detect defects in specimens, we selected thermal loading method that can easily induce the surface deformation of specimen. Experimental results show that defects in composite structures could be easily detected by ESPI. Moreover, it shows that ESPI could be usefully applied to the detection of defects in various composite structures.