• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.2 no.1
• /
• pp.141-146
• /
• 1998

Recently, the computer vision such as part measurement, and product inspection is very popular to achieve the factory automation since the labor cost is dramatically increasing. In this paper, the diameter and the length of rope are measured by CCD camera which is orthogonally mounted on the ceiling. Two parameters which are the diameter and the length of rope are used to measure the weight of rope. If the weight of rope is reached to predetermined weight, the information is transmitted to PLC(programmable logic control) to cut the rope on the wheel. The cutting machine cuts the rope according to the information obtained from the CCD camera. To measure the diameter and length of rope on real time, the searching space for image segmentation is restricted the predetermined area according to the camera calibration position. Finally, to estimate the weight of rope, the knowledge base system which depends on the diameter, the length of rope, and weight relation between these information are constructed according to diameters of rope. This method contributes to achieve the factory automation, and reduce the production cost since the operators are unnecessary to measure the weight of rope by try-and-error method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.11
• /
• pp.7508-7512
• /
• 2015

We propose a brain-machine interface(BMI) based human-robot interaction(HRI) platform which operates machines by interfacing intentions by capturing brain waves. Platform consists of capture, processing/mapping, and action parts. A noninvasive brain wave sensor, PC, and robot-avatar/LED/motor are selected as capture, processing/mapping, and action part(s), respectively. Various investigations to ensure the relations between intentions and brainwave sensing have been explored. Case studies-an interactive game, on-off controls of LED(s), and motor control(s) are presented to show the design and implementation process of new BMI based HRI platform.

• Journal of Information Processing Systems
• /
• v.14 no.4
• /
• pp.892-903
• /
• 2018

The paper proposes a novel gait recognition algorithm based on feature fusion of gait energy image (GEI) dynamic region and Gabor, which consists of four steps. First, the gait contour images are extracted through the object detection, binarization and morphological process. Secondly, features of GEI at different angles and Gabor features with multiple orientations are extracted from the dynamic part of GEI, respectively. Then averaging method is adopted to fuse features of GEI dynamic region with features of Gabor wavelets on feature layer and the feature space dimension is reduced by an improved Kernel Principal Component Analysis (KPCA). Finally, the vectors of feature fusion are input into the support vector machine (SVM) based on multi classification to realize the classification and recognition of gait. The primary contributions of the paper are: a novel gait recognition algorithm based on based on feature fusion of GEI and Gabor is proposed; an improved KPCA method is used to reduce the feature matrix dimension; a SVM is employed to identify the gait sequences. The experimental results suggest that the proposed algorithm yields over 90% of correct classification rate, which testify that the method can identify better different human gait and get better recognized effect than other existing algorithms.

• The KIPS Transactions:PartD
• /
• v.13D no.3 s.106
• /
• pp.369-376
• /
• 2006

This paper presents a new method of significantly improving conventional Bayesian statistical text classifier by incorporating accelerated EM(Expectation Maximization) algorithm. EM algorithm experiences a slow convergence and performance degrade in its iterative process, especially when real online-textual documents do not follow EM's assumptions. In this study, we propose a new accelerated EM algorithm with uncertainty-based selective sampling, which is simple yet has a fast convergence speed and allow to estimate a more accurate classification model on Naive Bayesian text classifier. Experiments using the popular Reuters-21578 document collection showed that the proposed algorithm effectively improves classification accuracy.

• Design & Manufacturing
• /
• v.11 no.2
• /
• pp.20-24
• /
• 2017

Recent industrial developments are constantly advancing, and rapid technological development is demanding high technology level in related fields. The need for polishing is increasing even more to improve quality. In order to improve the surface quality, the final finishing process or polishing process is a very important part. Research on super precise polishing method using MR fluid is actively being carried out in domestic and foreign countries. Fine magnetic abrasive grains are aligned in the direction of a magnetic force line formed by a magnetic field and serve as a brush to polish a metal surface. This method has the advantage that the shape of the tool is not fixed and is not affected by the shape of the workpiece or the machining area. We will design the electromagnets for the MR polish polishing system and apply the magnetic field analysis using the magnetic field analysis program (ANSYS). The data obtained through this process suggests an efficient method to increase the magnetic flux density important for polishing. We will investigate the influence of the Al6061-T6 specimen on the surface of the MR polishing machine based on the optimized design.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.2
• /
• pp.431-434
• /
• 2014

This paper shows the users' birthplace information can be inferred with only the public information in FaceBook SNS. Through experiments with various machine learning algorithms and various parameters, we have found that SVM algorithm with the location of the highschool, the current address, and the graduate year of highschool performs best for the inference, as this can infer 78% of users' birthplaces correctly. Since the birthplace information is used for various security purpose such as questions for getting the forgotten password and a part of korean residence registration number, this is a non-trival security breach and users need be cautious about it.

• The KIPS Transactions:PartB
• /
• v.15B no.1
• /
• pp.69-72
• /
• 2008

This study aims to identify dependency structures in Korean sentences with the cascaded chunking. In the first stage of the cascade, we find chunks of NP and guess grammatical relations (GRs) using Support Vector Machine (SVM) classifiers for all possible modifier-head pairs of chunks in terms of GR categories as subject, object, complement, adverbial, etc. In the next stages, we filter out incorrect modifier-head relations in each cascade for its corresponding GR using the SVM classifiers and the characteristics of the Korean language such as distance between relations, no-crossing and case property. Through an experiment with a parsed and GR tagged corpus for training the proposed parser, we achieved an overall accuracy of 85.7%.

• The KIPS Transactions:PartA
• /
• v.9A no.4
• /
• pp.589-594
• /
• 2002

In computer graphics, L-system is primarily used for the production of such natural shapes as flowers, trees, and grass. It is possible by iteratively applying the theory of multiple-reduction-copy-machine to an arbitrary initial shape. The purpose of this paper is to modify the shape of ordinary L-system trees so that more realistic trees can be generated. Instead of applying simple iterative function system of the L-system, we regard each branch of the trees as a living thing, and endow them with corresponding attributes. Such branch attributes as lifetime, growth speed, shape variation, attraction by environment are known to belong to the attributes of the particle system. We presented modeling methods as hypotheses for each of the attributes based on parameters, iud shown the resulting diverse tree shapes.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.22 no.6
• /
• pp.516-521
• /
• 2009

X-ray system which is usefully used in diagnosis of the patient, being bombed of radioactivity is a big weak point when irradiates a X-ray to the human body so that ICRP restricted the radiation exposure tolerance of the human body. In order to reduce being bombed, the many research and development is now advanced. A lots of diagnostic X-ray machines have currently used due to the increase of occurrence efficiency of X-ray and precisely the output control by using the inverter which is a high speed switching semiconductors. For getting the confidence of the X-ray machine, the same radiation occurrence, same evaluation, and same irradiation condition are necessary when evaluates X-ray irradiation. It is the most important part for the accuracy of the test result and the patient safety. This research has produced the high voltage occurrence system of full-wave rectification method by using the LC resonance inverter, and evaluated the irradiation reproducibility in order to use it in diagnosis of the patient.

• KSTLE International Journal
• /
• v.6 no.2
• /
• pp.45-50
• /
• 2005

Plasma ceramic spray that is applied on a machine part under severe work conditions has been investigated for tribological behavior. The application of ceramic coatings by plasma spray has become essential in tribosystems to produce wear resistance and long life in severe conditions. The purpose of this study was to investigate the wear characteristics of $8\%Y_{2}O_3-ZrO_2$ coating, in view of the effect of post-spay heat treatment. The plasma-sprayed $8\%Y_{2}O_3-ZrO_2$ coating was studied to know the relationship between phase transformations and wear behavior related to post-spray heat treatment. Wear test was carried out with ball on disk type on normal loads of 50N,70N and 90N under room temperature. The phase transformation of phase and the value of residual stress were measured by X-ray diffraction method(XRD). Tribological characteristics and wear mechanisms of coatings were observed by SEM. The tribological wear performance was discussed in the focusing of residual stress. Consequently, post-spray heat treatment plays an important role in decreasing residual stress. Residual stress in the coating system has a significant influence on the wear mechanism of coating.