• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.1
• /
• pp.142-149
• /
• 2016

This paper proposes a method to detect LP(License Plate) of vehicles in indoor and outdoor parking lots. In restricted environment, there are many conventional methods for detecting LP. But, it is difficult to detect LP in natural and complex scenes with background clutters because several patterns similar with text or LP always exist in complicated backgrounds. To verify the performance of LP text detection in natural images, we apply MB-LGP feature by combining with ensemble machine learning algorithm in purpose of selecting optimal features of small number in huge pool. The feature selection is performed by adaptive boosting algorithm that shows great performance in minimum false positive detection ratio and in computing time when combined with cascade approach. MSER is used to provide initial text regions of vehicle LP. Throughout the experiment using real images, the proposed method functions robustly extracting LP in natural scene as well as the controlled environment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.6
• /
• pp.2377-2397
• /
• 2020

Human activity recognition is widely used in smart homes, health care and indoor monitor. Traditional approaches all need hardware installation or wearable sensors, which incurs additional costs and imposes many restrictions on usage. Therefore, this paper presents a novel device-free activities recognition system based on the advanced wireless technologies. The fine-grained information channel state information (CSI) in the wireless channel is employed as the indicator of human activities. To improve accuracy, both amplitude and phase information of CSI are extracted and shaped into feature vectors for activities recognition. In addition, we discuss the classification accuracy of different features and select the most stable features for feature matrix. Our experimental evaluation in two laboratories of different size demonstrates that the proposed scheme can achieve an average accuracy over 95% and 90% in different scenarios.

• Proceedings of the IEEK Conference
• /
• 2001.06d
• /
• pp.5-8
• /
• 2001

We propose a realtime numeric caption recognition algorithm that automatically recognizes the numeric caption generated by computer graphics (CG) and displays the modified caption using the recognized resource only when a valuable numeric caption appears in the aimed specific region of the live sportscast scene produced by other broadcasting stations. We extract the mesh feature from the enhanced binary image as a feature vector after acquiring the sports broadcast scenes using a frame grabber in realtime and then recover the valuable resource from just a numeric image by perceiving the character using the neural network. Finally, the result is verified by the knowledge-based rule set designed for more stable and reliable output and is displayed on a screen as the converted CC caption serving our purpose. At present, we have actually provided the realtime automatic mile-to-kilometer caption conversion system taking up our algorithm f3r the regular Major League Baseball (MLB) program being broadcasted live throughout Korea over our nationwide network. This caption conversion system is able to automatically convert the caption in mile universally used in the United States into that in kilometer in realtime, which is familiar to almost Koreans, and makes us get a favorable criticism from the TV audience.

• The Journal of the Korea Contents Association
• /
• v.20 no.12
• /
• pp.49-57
• /
• 2020

This study predicts the ratio of added value, which represents the competitiveness of export industries in South Korea, using various machine learning techniques. To enhance the accuracy and stability of prediction, forecast combination technique was applied to predicted values of machine learning techniques. In particular, this study improved the efficiency of the prediction process by selecting key variables out of many variables using recursive feature elimination method and applying them to machine learning techniques. As a result, it was found that the predicted value by the forecast combination method was closer to the actual value than the predicted values of the machine learning techniques. In addition, the forecast combination method showed stable prediction results unlike volatile predicted values by machine learning techniques.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.4
• /
• pp.1518-1526
• /
• 2015

For now, there are some low frequency oscillations in the power system which feature low frequency oscillation with positive damping and cannot be explained by traditional low frequency oscillation mechanisms. Concerning this issue, the dynamic damping effect is put forward on the basis of the power-angle curve and the study of damping torque in this article. That is, in the process of oscillation, damping will dynamically change and will be less than that of the stable operating point especially when the angle of the stable operating point and the oscillation amplitude are large. In a situation with weak damping, the damping may turn negative when the oscillation amplitude increases to a certain extent, which may result in an amplitude-increasing oscillation. Finally, the simulation of the two-machine two-area system verifies the arguments in this paper which may provide new ideas for the analysis and control of some unclear low frequency phenomena.

• Proceedings of the SCSK Conference
• /
• 2003.09a
• /
• pp.417-430
• /
• 2003

A new method was developed to prepare microcapsules involving hydrophobic components. A totally new "silicone-resin-polypeptide" was used as the wall materials. The polypeptide was made by hydrolysis of collagen and silk protein and so on, and that was combined with silicone. This microcapsule was easily prepared from silicone-resin-polypeptide in water solution. The ratio of encapsulation in the microcapsule was not only high level as 90％, which had never been reached, but also the particle size could be controlled to obtain very small size (average particle size: 2${\mu}{\textrm}{m}$). Moreover, these microcapsules were resistant to high shearing forces and were stable over a long time period. This stable microcapsule was not crushed in pressure with finger spreading, so the core materials hardly touch the skin directly. Application in cosmetics by using microcapsule involving UV absorbents (2-ethylhexy1-4-methoxycinnamate (OMC) and 4-tert-butyl-4' -methoxydibenzoyl-methane (BMDBM)) was examined. It was possible to apply organic UV absorbents in water-rich formulations without any surfactant by using this microcapsule. This formulation demonstrated a good moisturizing and soft skin feel. Therefore, the microcapsule was applied to hair care products. As a result, the sunscreen hair lotion with microcapsule was able to prevent from damaging and decoloring of hair color by UV rays. As just, it was suggested that this microcapsules were be widely applied in cosmetics.cosmetics.

• The Journal of Information Systems
• /
• v.14 no.1
• /
• pp.41-65
• /
• 2005

The credit ration is a significant area of financial management which is of major interest to practitioners, financial and credit analysts. The components of credit rating are identified decision models are developed to assess credit rating an the corresponding creditworthiness of firms an accurately ad possble. Although many early studies demonstrate a priori which of these techniques will be most effective to solve a specific classification problem. Recently, a number of studies have demonstrate that a hybrid model integration artificial intelligence approaches with other feature selection algorthms can be alternative methodologies for business classification problems. In this article, we propose a hybrid approach using rough set theory as an alternative methodology to select appropriate attributes for case-based reasoning. This model uses rough specific interest lies in lthe stable combining of both rough set theory to extract knowledge that can guide dffective retrevals of useful cases. Our specific interest lies in the stable combining of both rough set theory and case-based reasoning in the problem of corporate credit rating. In addition, we summarize backgrounds of applying integrated model in the field of corporate credit rating with a brief description of various credit rating methodologies.

• The Journal of Korea Robotics Society
• /
• v.8 no.2
• /
• pp.92-103
• /
• 2013

Humanoid robot is the most intimate robot platform suitable for human interaction and services. Biped walking is its basic locomotion method, which is performed with combination of joint actuator's rotations in the lower extremity. The present work employs humanoid robot simulator and numerical optimization method to generate optimal joint trajectories for biped walking. The simulator is developed with Matlab based on the robot structure constructed with the Denavit-Hartenberg (DH) convention. Particle swarm optimization method minimizes the cost function for biped walking associated with performance index such as altitude trajectory of clearance foot and stability index concerning zero moment point (ZMP) trajectory. In this paper, instead of checking whether ZMP's position is inside the stable region or not, reference ZMP trajectory is approximately configured with feature points by which piece-wise linear trajectory can be drawn, and difference of reference ZMP and actual one at each sampling time is added to the cost function. The optimized joint trajectories realize three phases of stable gait including initial, periodic, and final steps. For validation of the proposed approach, a small-sized humanoid robot named DARwIn-OP is commanded to walk with the optimized joint trajectories, and the walking result is successful.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.19 no.9
• /
• pp.2089-2104
• /
• 1995

A novel and efficient cutter path planning method for machining intricately shaped curved surfaces, called the steepest directed tree method, is presented. The curved surface is defined by triangular facets, the density and structure of which are determined by the intricacy and form accuracy of the surface. Geometrical form definition and recognition of the topological features are used to connect the nodes of the triangulated surface meshes for the successive and interconnected steepest pathways, which makes good use of end milling characteristics. The planetary cutter centers are determined to locate along smoothly changing paths and then the height values of the cutter are adjusted to avoid surface interference. Several machined examples of intersecting and intricate surfaces are presented to illustrate the benefits of the new approach. It is shown that due to more consistent geometry matching between cutter and surface(in comparison with the current CC Cartesian method) surface finish can be typically improved. Moreover, the material in concave fillets which is difficult to be removed by ball mills can be removed efficiently. The built-in positioning of cutter to avoid interference runs minutely in the sharp and discontinuous regions. The steepest upward movement of the cutter gives a stable dynamic cutting state and allows increase in the feedrate and spindle speed while remaining the stable cutting state.

• Elastomers and Composites
• /
• v.50 no.4
• /
• pp.265-273
• /
• 2015

In this work, the emulsified asphalt with high phase stability and storage stability was prepared by using phase inversion emulsification and the surfactant mixed with cationic and nonionic surfactants. It was found that the asphalt together with Span 20, nonionic surfactant and DDA (Dimethyl Dodecyl Amine), cationic surfactant showed the most stable phase. The phase stability of the emulsified asphalt, therefore, was investigated through the particle size with mixed surfactant content, rheology behavior and Zeta potential value; the particle size decreased with the increase of the mixed surfactant content but the viscosity increased. The shear thinning behaviors and the Zeta potential value with 50 mV~60 mV were shown, which was found to be considered stable. In addition, SBR latex(Styrene-butadiene-rubber) and water dispersed Epoxy (EPD) were used to enhance the physical properties of the emulsified asphalt. The swelling and adhesion features of the emulsified asphalt were also studied with $CaCO_3$, Silica, and Montmorillonite (MMT). It was shown that the addition of SBR latex and MMT can be another way to improve the physical properties of the emulsified asphalt in that the lowest swelling feature was found.