• ETRI Journal
• /
• v.39 no.2
• /
• pp.181-190
• /
• 2017

The movements of the human body are difficult to capture owing to the complexity of the three-dimensional skeleton model and occlusion problems. In this paper, we propose a motion capture system that tracks dynamic human motions in real time. Without using external markers, the proposed system adopts multiple depth sensors (Microsoft Kinect) to overcome the occlusion and body rotation problems. To combine the joint data retrieved from the multiple sensors, our calibration process samples a point cloud from depth images and unifies the coordinate systems in point clouds into a single coordinate system via the iterative closest point method. Using noisy skeletal data from sensors, a posture reconstruction method is introduced to estimate the optimal joint positions for consistent motion generation. Based on the high tracking accuracy of the proposed system, we demonstrate that our system is applicable to various motion-based training programs in dance and Taekwondo.

• Advances in concrete construction
• /
• v.5 no.2
• /
• pp.87-99
• /
• 2017

After passing through a magnetic field, the physical quality of water improves, and magnetic water (MW) is produced. There are many investigations on the effects of magnetic field on water that shows MW properties like saturation and memory effect. This study investigates the fresh and hardened properties of concrete mixed with MW, which contains silica fume (SF) and superplasticizer (SP). The test variables included the magnetic field intensity for producing MW (three kinds of water), SF content replaced cement (0 and 10 percent), water-to-cementitious materials ratio (W/CM=0.25, 0.35 and 0.45) and curing time (7, 28 and 90 days). The results of this study show that MW had a positive impact on the workability and compressive strength of concrete. By rising the intensity of the magnetic field which was used for producing MW, its positive influence on both workability and compressive strength improved. MW had greater positive impacts on samples containing SP that did not have SF. Moreover, the best compressive strength improvements of concrete achieved as W/CM ratio decreased.

• Journal of Information Technology Services
• /
• v.15 no.1
• /
• pp.153-166
• /
• 2016

Ensemble classification is an approach that combines individually trained classifiers in order to improve prediction accuracy over individual classifiers. Ensemble techniques have been shown to be very effective in improving the generalization ability of the classifier. But base classifiers need to be as accurate and diverse as possible in order to enhance the generalization abilities of an ensemble model. Bagging is one of the most popular ensemble methods. In bagging, the different training data subsets are randomly drawn with replacement from the original training dataset. Base classifiers are trained on the different bootstrap samples. In this study we proposed a new bagging variant ensemble model, Randomized Bagging (RBagging) for improving the standard bagging ensemble model. The proposed model was applied to the bankruptcy prediction problem using a real data set and the results were compared with those of the other models. The experimental results showed that the proposed model outperformed the standard bagging model.

• Proceedings of the Korea Contents Association Conference
• /
• 2016.05a
• /
• pp.11-12
• /
• 2016

SVM (Support Vector machine) is powerful machine-learning method, and obtains better performance than traditional methods in the applications of muti-dimension nonlinear pattern classification. For the case of SVM model training and low efficiency in large samples, this paper proposes a combination of statistical parameters of the GMM-UBM (Universal Background Model) model. It is very effective to solve the problem of the large sample for the SVM training. The experiment is carried on four special dynamic hand gestures using the EPIC sensors. And the results show that the improved dynamic hand gesture recognition system has a high recognition rate up to 96.75%.

• Advances in materials Research
• /
• v.8 no.2
• /
• pp.137-154
• /
• 2019

In this study, thermal effects on the mechanical properties of cement mortars with some types of fibers is investigated. The replaced fibers were made of polypropylene (PP), aramid, glass and basalt. In other words, the main goal of this paper is to study the effects of different fibers on the mechanical properties of cement mortars after subjecting to normal and sub-elevated temperatures. The experimental tests used for investigating these effects were compressive, splitting tensile, and four-point bending tests at 20, 100 and $300^{\circ}C$, respectively. Moreover, the microstructures of the specimens in different temperatures were investigated using scanning electron microscope (SEM). Based on the experimental results, the negative effects of sub-elevated temperatures on four-point bending tests were much more than the others. Moreover, using the fibers with higher melting points could not improve the qualities of the samples in sub-elevated temperatures.

• Journal of Institute of Convergence Technology
• /
• v.11 no.1
• /
• pp.1-5
• /
• 2021

Deep learning based methods achieve state-of-the-art accuracy, however, they typically rely on supervised training with large labeled datasets. It is known in many medical applications that labeling medical images requires significant expertise and much time, and typical hand-tuned approaches for data augmentation fail to capture the complex variations in such images. This paper proposes a 3D image augmentation method to overcome these difficulties. It allows us to enrich diversity of training data samples that is essential in medical image segmentation tasks, thus reducing the data overfitting problem caused by the fact the scale of medical image dataset is typically smaller. Our numerical experiments demonstrate that the proposed approach provides significant improvements over state-of-the-art methods for 3D medical image segmentation.

• Knowledge Management Research
• /
• v.19 no.2
• /
• pp.187-203
• /
• 2018

The purpose of this study was to investigate the perception about AI assistants and the differences between two groups, workers(secretaries) and supervisors(bosses), using the Q-methodology which has an advantage in understanding the types of subjective perceptions. Through literature reviews and interviews, 34 Q-samples were extracted, and then Q-sorting was conducted by P-samples(20 workers and 15 supervisors). As a result of Q-sorting, the types and characteristics of AI assistants perceived by each P-sample were explained. The perception of the workers divided into five distinct types, and the perception of the supervisors was divided into three distinct types. The most crucial factors in distinguishing between workers and supervisors' perceptions depend on whether they are capable of performing certain tasks and whether they can replace existing secretarial jobs. This study, as the primary research on AI assistants, can help to redefine the work that can be replaced by AI and the work that only people can do, and thus to establish education, recruitment, and training plans.

• 제어로봇시스템학회:학술대회논문집
• /
• 1995.10a
• /
• pp.119-122
• /
• 1995

Neural network has found wide applications in the system identification, modeling, and realization based on its function approximation capability. THe system governe dby nonlinear dynamics is hard to be identified by the neural network because there exist following difficulties. FIrst, the training samples obtained by the stae trajectory are apt to be nonuniform over the region of interest. Second, the system may becomje unstable while attempting to obtain the samples. This paper deals with these problems in discrete-time system and suggest effective solutions which provide stability and uniform sampliing by the virtue of robust control theory and heuristic algorithms.

• Journal of Power Electronics
• /
• v.8 no.4
• /
• pp.345-353
• /
• 2008

In this paper, a novel loss minimization of an induction generator in wind energy generation systems is presented. The proposed algorithm is based on the flux level reduction, for which the generator d-axis current reference is estimated using support vector regression (SVR). Wind speed is employed as an input of the SVR and the samples of the generator d-axis current reference are used as output to train the SVR algorithm off-line. Data samples for wind speed and d-axis current are collected for the training process, which plots a relation of input and output. The predicted off-line function and the instantaneous wind speed are then used to determine the d-axis current reference. It is shown that the effect of loss minimization is more significant at low wind speed and the loss reduction is about to 40% at 4[m/s] wind speed. The validity of the proposed scheme has been verified by experimental results.

• Journal of Veterinary Clinics
• /
• v.38 no.5
• /
• pp.225-230
• /
• 2021

A 4-year-old gelding Thoroughbred racehorse, which had been undergoing antibiotic therapy at a local veterinary clinic, was referred to the KRA veterinary center with a 20-day history of continuous right nasal discharge. Patient's history, endoscopic examination, and radiographic examination revealed primary maxillary sinusitis. Under sedation, surgical intervention was performed to collect samples and remove the accumulated mucopurulent exudate in the sinus. Swab samples were collected from the sinus during surgery for cytology and antimicrobial susceptibility testing. Only one type of bacteria was cultured, and molecular analyses of 16S ribosomal RNA gene sequences identified it as Staphylococcus aureus (S. aureus). The isolate was resistant to multiple antibiotics, which are frequently used in equine practice. Trimethoprim-sulfamethoxazole was chosen based on antibiotic susceptibility test, trephination, and sinus lavage using saline were applied to treat bacterial sinusitis. The clinical signs improved after 1 month and the patient resumed training. This report describes S. aureus isolated from bacterial maxillary sinusitis in a horse and its antibiotic susceptibility.