• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2005년도 추계학술발표대회 및 정기총회
• /
• pp.197-200
• /
• 2005

본 논문은 유해한 동영상을 실시간으로 분석하고 차단하기 위하여, 동영상의 비주얼 특징으로서 그룹 프레임(Group of Frame) 특징을 추출하여 SVM 학습모델을 활용하는 유해 동영상 분류에 관한 것이다. 지금까지 동영상 분류에 관한 연구는 주로 입력 동영상을 뉴스, 스포츠, 영화, 뮤직 비디오, 상업 비디오 등 사전에 정의한 몇 개의 장르에 자동으로 할당하는 기술이었다. 그러나 이러한 분류 기술은 미리 정의한 장르에 따른 일반적인 분류 모델을 사용하기 때문에 분류의 정확도가 높지 않다. 따라서, 유해 동영상을 실시간으로 자동 분류하기 위해서는, 신속하고 효과적인 동영상 내용분석에 적합한 유해 동영상 특화의 특징 추출과 분류 모델 연구가 필요하다. 본 논문에서는 유해 동영상에 대하여 신속하고, 정확한 분류를 위하여 유해 동영상의 대표 특징으로서 그룹프레임 특징을 정의하고, 이를 추출하여 SVM 학습 모델을 생성하고 분류에 활용하는 매우 높은 성능의 분석 방법을 제시하였다. 이는 최근 인터넷 뿐만 아니라 다양한 매체를 통하여 급속도로 번지고 있는 유해 동영상 차단 분야에 적극 활용될 수 있을 것으로 기대된다.

• Smart Structures and Systems
• /
• 제5권4호
• /
• pp.329-344
• /
• 2009

Ultrasonic chaotic excitations combined with sensor prediction algorithms have shown the ability to identify incipient damage (loss of preload) in a bolted joint. In this study we examine a physical experiment on a single-bolt aluminum lap joint as well as a three-dimensional physics-based simulation designed to model the behavior of guided ultrasonic waves through a similarly configured joint. A multiple bolt frame structure is also experimentally examined. In the physical experiment each signal is imparted to the structure through a macro-fiber composite (MFC) patch on one side of the lap joint and sensed using an equivalent MFC patch on the opposite side of the joint. The model applies the waveform via direct nodal displacement and 'senses' the resulting displacement using an average of the nodal strain over an area equivalent to the MFC patch. A novel statistical classification feature is developed from information theory concepts of cross-prediction and interdependence. This damage detection algorithm is used to evaluate multiple damage levels and locations.

• 대한조선학회 특별논문집
• /
• 대한조선학회 2005년도 특별논문집
• /
• pp.31-37
• /
• 2005

An attempt to improve the speed performance through the minimizing in wave resistance has been done by an application of gooseneck and no bulb type to bulbous bow for the DSME 78,500 Class LPG Carrier on the basis of the CFD calculation and comparatives model tests. The hydrodynamic characteristics according to the variation of the shape of Cp-curve, design load water line, frame line and bulbous bow that have an important effect on the wave resistance has been evaluated/calculated by ship-flow code. A wide variety in hull variation have been tried to have a good hull form with three types of fore-body hull forms mainly classified by the shape of bulbous bow. The speed performances for the three final hull forms with different bulbous bows have been evaluated through the model tests.

• 대한조선학회논문집
• /
• 제40권6호
• /
• pp.12-19
• /
• 2003

Corrugated bulkheads for a bulk carrier are divided into watertight bulkheads and deep tank bulkheads. Design of the watertight bulkheads is principally determined by the permissible limit of Classification and IACS requirements. But, the verification of strength through finite element analysis is indispensable for design of the deep tank bulkheads. A stage for stress evaluation of corrugated part is required for optimum structural design of the deep tank bulkheads. Since the finite element analysis for real model requires excessive amount of calculation time, in this study one corrugated structure is replaced with beam element and is idealized as 2 dimensional frame structure connected to upper and lower stool Minimum weight design of the deep tank bulkheads is performed through generalized sloped deflection method(GSDM) as direct calculation method. The purpose of this study is the development of design system for the minimization of steel weight of deep tank bulkheads as well as watertight bulkheads. Discrete variables are used as design variables for the practical design. Evolution strategies(ES) is used as an optimization technique.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2008년도 춘계학술대회 논문집
• /
• pp.579-587
• /
• 2008

Promotion of the line no.2 in Seoul Metro was changing from the existing signaling facilities for ATS(Automatic Train Stop) vehicles to the up-to-date signaling facilities for ATO(Automatic Train Operation). But, in consequence of conducting a trial run after being equipped with the ATO signaling facilities, the matter related to mix-operation with the existing ATS signaling facilities appeared. The operation of the existing ATS signaling system in combination with the ATO signaling system has made improper working related to frequency recognition of the ATS On-board Computerized Equipment. This obstructs operation of a working ATS vehicle. That is, as barring operation of an ATS vehicle that should proceed, it may make the proceeding ATS vehicle stop suddenly and after all, it will cause safety concerns. In this paper, we designed a wayside track occupancy detector that previously prevents improper working related to frequency recognition of the ATS On-board Computerized Equipment by gripping classification and working processes of operating trains throughout transmission of local signaling information from the existing facilities, which does not need to change or replace the existing signaling facilities. Furthermore, we described general characteristics of the wayside track occupancy detector and modeled the IFC(InterFace Contrivance) device and the logical circuit recognizing signal information. Then, we made an application program of PLC(programmable Logic Computer) based on the stated model. We, in relation to data transfer method, used the frame in TCP/IP transfer mode as the standard, and we demonstrated that ATO transmission frequency is intercepted.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -3
• /
• pp.1527-1530
• /
• 2002

Video summary is one of the tools which can provide the fast and effective browsing fur a lengthy video. Video summary consists of many key-frames that could be defined differently depending on the video genre it belongs to. Consequently, the video summary constructed by the uniform manner might lead into inadequate result. Therefore, identifying the video genre is the important first step in generating the meaningful video summary. We propose a new method that can classify the genre of the video data in MPEG compressed bit-stream domain. Since the proposed method operates directly on the com- pressed bit-stream without decoding the frame, it has merits such as simple calculation and short processing time. In the proposed method, only the visual information is utilized through the spatial-temporal analysis to classify the video genre. Experiments are done for 6 genres of video: Cartoon, Commercial, Music Video, News, Sports, and Talk Show. Experimental result shows more than 90% of accuracy in genre classification for the well-structured video data such as Talk Show and Sports.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2006년도 제18회 한글 및 한국어 정보처리 학술대회
• /
• pp.254-261
• /
• 2006

형용사 분류에 격틀이 중요한 역할을 한다는 주장은 여러 연구에서 제기된 바 있다. 본 연구에서는 격틀이 의미 분류에 기여하는 바를 보다 체계적으로 검토하기 위하여 '격틀집합'을 활용한다. 격틀집합은 한 개의 어휘가 취할 수 있는 격틀의 집합을 말한다. 격틀집합에 근거하여 형용사를 분류할 경우, 의미적으로 연관성이 높은 그룹으로 나뉠 수 있다는 가설을 바탕으로 이러한 가설의 타당성을 검증하고 이를 입증하는 것이 본 연구의 목적이다. 아울러 본 연구에서는 그러한 가설을 검증하기 위한 구체적인 방법론을 제시한다. 격틀집합정보는 세종전자사전에 들어있는 어휘별 격틀정보를 추출하여 활용한다. 본 연구 결과 도출된 총 101개의 격틀집합 중에서 한 개의 격틀만을 갖는 유형과 어휘목록이 5개미만인 유형을 제외한 12개의 격틀집합이 주요 분석 대상으로, 본 연구에서는 그 중에서 6개를 자세히 분석한다. 격틀집합별 어휘들을 살펴보면 의미적 연관성이 파악되지 않는 어휘들도 일부 포함되어 있기는 하나, 대부분은 의미적으로 상관관계가 있음을 확인할 수 있었다 이와 같은 방법론을 통해 국어 형용사 전체의 유형, 더 나아가 국어 용언을 분류하는데 본 연구의 가설과 방법론이 활용될 수 있다.

• 대한음성학회지:말소리
• /
• 제58호
• /
• pp.67-81
• /
• 2006

For a large corpus of time-aligned data, HMM based approaches are most widely used for automatic segmentation, providing a consistent and accurate phone labeling scheme. There are two methods for training in HMM. Flat starting method has a property that human interference is minimized but it has low accuracy. Bootstrap method has a high accuracy, but it has a defect that manual segmentation is required In this paper, a new algorithm is proposed to minimize manual work and to improve the performance of automatic segmentation. At first phase, voiced, unvoiced and silence classification is performed for each speech data frame. At second phase, the phoneme sequence is aligned dynamically to the voiced/unvoiced/silence sequence according to the acoustic phonetic rules. Finally, using these segmented speech data as a bootstrap, phoneme model parameters based on HMM are trained. For the performance test, hand labeled ETRI speech DB was used. The experiment results showed that our algorithm achieved 10% improvement of segmentation accuracy within 20 ms tolerable error range. Especially for the unvoiced consonants, it showed 30% improvement.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.337-351
• /
• 2021

Automatically recognizing facial expressions in video sequences is a challenging task because there is little direct correlation between facial features and subjective emotions in video. To overcome the problem, a video facial expression recognition method using spatiotemporal recurrent neural network and feature fusion is proposed. Firstly, the video is preprocessed. Then, the double-layer cascade structure is used to detect a face in a video image. In addition, two deep convolutional neural networks are used to extract the time-domain and airspace facial features in the video. The spatial convolutional neural network is used to extract the spatial information features from each frame of the static expression images in the video. The temporal convolutional neural network is used to extract the dynamic information features from the optical flow information from multiple frames of expression images in the video. A multiplication fusion is performed with the spatiotemporal features learned by the two deep convolutional neural networks. Finally, the fused features are input to the support vector machine to realize the facial expression classification task. The experimental results on cNTERFACE, RML, and AFEW6.0 datasets show that the recognition rates obtained by the proposed method are as high as 88.67%, 70.32%, and 63.84%, respectively. Comparative experiments show that the proposed method obtains higher recognition accuracy than other recently reported methods.

• Architectural research
• /
• 제22권4호
• /
• pp.105-112
• /
• 2020

The purpose of this study is to establish a method for assessing a building's risk against disaster, tentatively named the Korean integrated disaster evaluation simulator (K-IDES). Based on previous studies, FEMA's risk management series and FEMA IRVS are selected as case studies for developing a frame work of K-IDES, through the comparative analysis of domestic building design guides, codes, and special acts related to disasters, in order to develop a risk assessment methodology for quantitative results. The assessment method consists of a classification system and calculating risk, and a simulation applying the developed checklist in K-IDES to similar types of high-rise buildings will be conducted to validate its accuracy. The final goal is to systemize an integrated risk management in a high-rise building against disasters for the purpose of recognizing vulnerable areas from the beginning of the design process and reinforcing it from potential threats after construction.