• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.11a
• /
• pp.271-276
• /
• 2000

본 논문은 칼라 성분들간의 차분 영상과 휘도 영상을 이용하여 산출한 색차 휘도합 영상을 대상으로 블록에 기반한 영상 분할을 수행하여 객체의 형상 정보를 추출함으로써 분할 특성을 개선한 블록 기반 칼라 영상 분할 기법에 관한 것이다. 우선, R, G, B 영상들 간의 차분 성분들을 구하여 합산한 후, 이를 정규화하여 색차합 영상을 구한다. 다음으로 화소 단위로 휘도 영상의 상위 2비트와 정하화된 색차합 영상의 하위 6비트를 결합하여 색차 휘도합 영상을 얻는다. 이후, 기설정된 크기의 블록으로 분할된 색차 휘도합 영상의 각 블록을 질감 블록과 단순 블록 및 에지 블록으로 분류하고 각 유형의 블록별로 병합한 후, 기설정된 마커 배정 규칙에 따라 선택적으로 마커를 부여한다. 마지막으로, 마커가 부여되지 않은 블록을 대상으로 화소 단위의 워터쉐드 알고리즘을 적용함으로써 자연스러운 형상 정보를 얻을 수 있다. 컴퓨터 시뮬레이션 결과를 통해 고찰할 때, 제안된 방범은 질감 영역에서의 과분할의 문제와 과도한 연산량의 부담을 효과적으로 경감시킬 수 있으나, 더불어, 영상 분할용 파라미터들의 민감도가 낮아 서로 다른 화소 분포 특성온 갖는 영상들에 전역적인 파라미터들사용할 수 있을 뿐만 아니라 특히, 색차 휘도합 영상에 반영된 색차 성분에 힘입어 저대조 경계면에서의 분할 특성을 현저히 개선시킬 수 있는 이점이 있다.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.2
• /
• pp.199-208
• /
• 2003

Continuously variable transmission (CVT) mechanisms considered here combine the functions of a K-H-V type differential gear unit and a V-belt type continuously variable unit (CVU). As combining the functions of a K-H-V type differential gear unit and a V-belt type CVU, 24 different mechanisms are presented. Some useful theoretical formula related to speed ratio, power flow and efficiency are derived and analyzed. These mechanisms have many advantages which are the decrease of CVT size, the increase of overall efficiency, the extension of speed ratio range, and the generation of geared neutral.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.5
• /
• pp.1360-1371
• /
• 1998

There are many implementation methods according to models integrating TMN Agent into an ATM switch. In this paper, we evaluate the integrating models for integrating the Agent into an ATM switch in the aspects of the size of MIB(Management Information Base), the internal protocol profiles and the facility of implementation. Based on the evaluation, we choose an integrating model and implment the Agent. To ensure merit of the model, we propose an interface for exchanging management information between the Agent and an ATM switch. We also show the feasibility of our Agent system through some filed testes for the average processing time.

• The Journal of the Korea Contents Association
• /
• v.17 no.11
• /
• pp.600-608
• /
• 2017

Recently data growth rates are growing exponentially according to the rapid expansion of internet. Since users need some of all the information, they carry a heavy workload for examination and discovery of the necessary contents. Therefore information retrieval must provide hierarchical class information and the priority of examination through the evaluation of similarity on query and documents. In this paper we propose an Multi-class support vector machines model based clustering for hierarchical document categorization that make semantic search possible considering the word co-occurrence measures. A combination of hierarchical document categorization and SVM classifier gives high performance for analytical classification of web documents that increase exponentially according to extension of document hierarchy. More information retrieval systems are expected to use our proposed model in their developments and can perform a accurate and rapid information retrieval service.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.6
• /
• pp.687-696
• /
• 2019

Conventional feature of seismic classification focuses on strong seismic classification, while it is not suitable for classifying micro-seismic waves. We propose a feature extraction method based on histogram and Principal Component Analysis (PCA) in frequency-time space suitable for classifying seismic waves including strong, micro, and artificial seismic waves, as well as noise classification. The proposed method essentially employs histogram and PCA based features by concatenating the frequency and time information for binary classification which consist strong-micro-artificial/noise and micro/noise and micro/artificial seismic waves. Based on the recent earthquake data from 2017 to 2018, effectiveness of the proposed feature extraction method is demonstrated by comparing it with existing methods.

• Journal of Korean Society of Forest Science
• /
• v.82 no.4
• /
• pp.431-440
• /
• 1993

This study was carried out to clarify a taxonomical relationships of the Korean Theaceae using characters from morphological, anatomical, electrophoretic and numerical methods. The results are summarized as follows ; Morphological data were cluster analysis by Euclidean distance, the complete and average linkage cluster were most distinctly classified into subfamily level. At the principal components analysis(PCA), the commutative contribution rate of three principal components showed to 91.1% total variance. By the leaf venation were classified semicraspedromous type of Theoideae and brochidodromous type of Ternstroemioideae. The stomatal types were classified Paracytic of Theoideae and Anomocytic type of Ternstroemioideae ; the former has founded subsideary cell the latter has not found. All taxa possessed common isozyme bands did not found out of Theaceae banding patterns. But, the activity of Theoideae were existed in below No.5(Rf. 4.0-4.4), in contrast to Ternstroemioideae were existed in more than No.7(Rf. 5.7-6.2). The cluster analysis of leaf characters and peroxidase isozymes were similarity between two methods.

• Journal of the Korean Society for information Management
• /
• v.25 no.1
• /
• pp.211-233
• /
• 2008

This study examines various weighting methods for improving the performance of automatic classification based on Rocchio algorithm on two collections(LISA, Reuters-21578). First, three factors for weighting are identified as document factor, document factor, category factor for each weighting schemes, the performance of each was investigated. Second, the performance of combined weighting methods between the single schemes were examined. As a result, for the single schemes based on each factor, category-factor-based schemes showed the best performance, document set-factor-based schemes the second, and document-factor-based schemes the worst. For the combined weighting schemes, the schemes(idf*cat) which combine document set factor with category factor show better performance than the combined schemes(tf*cat or ltf*cat) which combine document factor with category factor as well as the common schemes (tfidf or ltfidf) that combining document factor with document set factor. However, according to the results of comparing the single weighting schemes with combined weighting schemes in the view of the collections, while category-factor-based schemes(cat only) perform best on LISA, the combined schemes(idf*cat) which combine document set factor with category factor showed best performance on the Reuters-21578. Therefore for the practical application of the weighting methods, it needs careful consideration of the categories in a collection for automatic classification.

• Restorative Dentistry and Endodontics
• /
• v.30 no.3
• /
• pp.204-214
• /
• 2005

This study compared the microtensile bond strength (${\mu}$TBS) and microscopic change of two 2-step and two 1-step self-etching adhesives to dentin according to storage times in distilled water. Occlusal dentin was exposed in 48 human molars. They were divided to four groups by different adhesives: SE Bond group (Clearfil SE Bond), AdheSE group (AdheSE). Adper group (Adper Prompt L-Pop), and Xeno group (Xeno III) . Each group was stored in 37$^{\circ}C$ distilled water for 1, 15, and 30 days. Resin-bonded specimens were sectioned into beams and subjected to ${\mu}$TBS testing with a crosshead speed of 1 mm/minute. For SEM observation, one specimen was selected and sectioned in each group after each stroage time. Resin-dentin interface was observed under FE-SEM. In all storage times, mean ${\mu}$TBS of SE group was significantly higher than those of other groups (p < 0.05). There was no significant difference between mean ${\mu}$TBS of SE group and AdheSE group among all storage times, but significant difference between 1- and 30-day storage in mean y${\mu}$TBS of Adper group and Xeno group (p > 0.05). For 1-and 15-day storage, all groups showed the close adaptation between resin-dentin interfaces. For 30-day storage, resin-dentin interfaces showed wide gap in Adper group and separate pattern in Xeno III group.

• Journal of Dental Rehabilitation and Applied Science
• /
• v.39 no.4
• /
• pp.187-194
• /
• 2023

Purpose: A mismatched size in the post and post space is a common problem during post-fixation. Since this discordance affects the bonding strength of the fiber-reinforced composite resin post (FRC Post), a corresponding luting agent is required. The aim of this study was to evaluate the bonding strength of the FRC post according to the fitness of the fiber post and the type of luting agent. Materials and Methods: Thirty mandibular premolar were endodontic-treated and assigned to two groups according to their prepared post space: Fitting (F) and Mismatching (M). These groups were further classified into three subgroups according to their luting agent: RelyX Unicem (ReX), Luxacore dual (Lux), and Duolink (Duo). A push-out test was performed to measure the push-out bond strengths. The fractured surfaces of each cross-section were then examined, and the fracture modes were classified. Results: In the ReX and Duo subgroups, the F group had a higher mean bond strength; however, the Lux subgroup had no significant difference between the F and M groups. In the analysis of the failure modes, the ReX subgroup had only adhesive failures between the cement and dentin. Conclusion: The result of this study showed that the bond strength of an FRC post was influenced by the type of luting agent and the mismatch between the diameter of the prepared post space and that of the post.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.3
• /
• pp.473-482
• /
• 2022

Wearing a mask is also necessary to limit the risk of infection in today's era of COVID-19 and wearing a helmet is inevitable for the safety of personnel who works in a dangerous working environment such as construction sites. This paper proposes an effective deep learning model, HelmetMask-Net, to classify both Helmet and Mask. The proposed HelmetMask-Net is based on CNN which consists of data processing, convolution layers, max pooling layers and fully connected layers with four output classifications, and 4 classes for Helmet, Mask, Helmet & Mask, and no Helmet & no Mask are classified. The proposed HelmatMask-Net has been chosen with 2 convolutional layers and AdaGrad optimizer by various simulations for accuracy, optimizer and the number of hyperparameters. Simulation results show the accuracy of 99% and the best performance compared to other models. The results of this paper would enhance the safety of personnel in this era of COVID-19.