• 한국터널지하공간학회 논문집
• /
• 제22권3호
• /
• pp.239-248
• /
• 2020

터널 굴착 시 정확한 암반 분류는 적합한 지보패턴을 설치하는 데 도움을 준다. 암반의 분류를 위해 주로 RMR (Rock Mass Ration)과 Q값을 산정하여 수행되며, 페이스 매핑(face mapping)을 바탕으로 산정된다. 점보드릴 및 프로브드릴의 기계 데이터을 활용하거나 딥러닝을 활용한 굴착면 사진 분석 등의 방법이 암반등급 분류를 예측하기 위해 사용되고 있으나, 분석 시 오랜 시간이 소요되거나, 굴착면 전방의 암반등급을 파악할 수 없다는 점에서 한계를 갖는다. 본 연구에서는 순환인공신경망(Recurrent neural network, RNN)을 활용하여 굴착면 전방의 Q값을 예측하는 방법을 개발하였고 페이스 매핑으로부터 획득한 Q값과 비교/검증하였다. 4,600여개의 굴착면 데이터 중 70%를 학습에 활용하였고, 나머지 30%는 검증에 사용하였다. 학습의 횟수와 학습에 활용한 이전굴착면의 개수를 변경하여 학습을 수행하였다. 예측된 Q값과 실제 Q값의 유사도는 RMSE (root mean square error)를 기준으로 비교하였다. 현재 굴착면과 바로 직전의 굴착면의 Q값을 활용하여 600회 학습하여 예측한 Q값의 RMSE값이 가장 작은 것을 확인하였다. 본 연구의 결과는 학습에 사용한 데이터 값 등이 변화하는 경우 변화할 수 있으나 터널에서의 이전 지반상태가 앞으로의 지반상태에 영향을 미치는 시스템을 이해하고, 이를 통해 터널 굴착면 전방의 Q값의 예측이 가능할 것으로 판단된다.

• 한방안이비인후피부과학회지
• /
• 제26권4호
• /
• pp.91-100
• /
• 2013

Background and Objective : Dyshidrotic Eczema is characterized by a pruritic vesicular eruption on the fingers, palms, and soles. It is an acute, chronic, or recurrent dermatosis. The causes of dyshidrosis are unknown. There are many treatments available for dyshidrosis including topical steroids but long term treatment of streoids may have side effects. The purpose of this study is to find out the effect of Fulinggancao-Tang on Dyshidrotic Eczema. Methods : We have diagnosed the patients through the Shanghanlun six meridian patterns diagnostic system and we treated the patients with Fulinggancao-Tang. The severity of Dyshidrotic Eczema was evaluated by visual analogue scale(VAS). Results : After the treatment itching and vesicles of hands and foots were all disappeared in both patients. Conclusions : Fulinggancao-Tang have improved the signs and symptoms of Dyshidrotic Eczema case. It is considered that Fulinggancao-Tang is considerably effective on the treatment of skin disease that especially vulnerable to water.

• 복식
• /
• 제53권2호
• /
• pp.137-151
• /
• 2003

Fashion photographs from leading monthly fashion magazines in 1990s were analyzed. The types and the formative feature characteristics and the aesthetic values of domestic retrospective fashion were studied. The major conclusions of the study are as follows 1. The types of domestic retro fashion were historicism, ethnic, ecology. Retro fashion was expressed through applying and reappearing silhouette, detail. fabric and image of the costumes of the past. 2. Renaissance. Baroque, Rococo styles and the costumes and styles of 1960s and 1970s were mainly applied in domestic fashion. 3. Orientalism was emphasized and Korean traditional styles and Chinese costumes were expressed mainly in domestic fashion. Fashion trends recurrent and intimate to the nature were expressed in patterns, fabrics, dyeing and silhouettes of nature. 4. The formative feature characteristics of domestic retro fashion were recurrence, purity. tradition and decoration. As retro fashion applies costumes of the past newly, it supplies unlimited possibilities to the present fashion which seeks versatility.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1997년도 추계학술대회발표논문집; 홍익대학교, 서울; 1 Nov. 1997
• /
• pp.181-184
• /
• 1997

Practical applications of learning systems usually involve complex domains exhibiting nonlinear behavior and dilution by noise. Consequently, an intelligent system must be able to adapt to nonlinear processes as well as probabilistic phenomena. An important class of application for a knowledge based systems in prediction: forecasting the future trajectory of a process as well as the consequences of any decision made by e system. This paper examines the robustness of data mining tools under varying levels of noise while predicting nonlinear processes in the form of chaotic behavior. The evaluated models include the perceptron neural network using backpropagation (BPN), the recurrent neural network (RNN) and case based reasoning (CBR). The concepts are crystallized through a case study in predicting a Henon process in the presence of various patterns of noise.

• 한국경영과학회지
• /
• 제23권1호
• /
• pp.109-141
• /
• 1998

Many processes in the industrial realm exhibit sstochastic and nonlinear behavior. Consequently, an intelligent system must be able to nonlinear production processes as well as probabilistic phenomena. In order for a knowledge based system to control a manufacturing processes as well as probabilistic phenomena. In order for a knowledge based system to control manufacturing process, an important capability is that of prediction : forecasting the future trajectory of a process as well as the consequences of the control action. This paper examines the robustness of data mining tools under varying levels of noise while predicting nonlinear processes, includinb chaotic behavior. The evaluated models include the perceptron neural network using backpropagation (BPN), the recurrent neural network (RNN) and case based reasoning (CBR). The concepts are crystallized through a case study in predicting a chaotic process in the presence of various patterns of noise.

• Clinical and Experimental Pediatrics
• /
• 제50권10호
• /
• pp.1018-1023
• /
• 2007

유전성 출혈성 모세혈관 확장증은 피부 점막 모세혈관확장증, 동정맥기형, 가족력을 3대 증상으로 하는 상염색체 우성 유전성 질환이다. 빈번한 코피가 가장 흔한 증상이며 폐, 뇌, 간 등에 동정맥기형이 동반될 수 있다. 저자들은 빈번한 코피, 폐와 뇌동정맥기형, 가족력을 가진 유전성 출혈성 모세혈관확장증 1례를 경험하고 이를 보고하는 바이다.

• Environmental Analysis Health and Toxicology
• /
• 제23권4호
• /
• pp.231-245
• /
• 2008

Various methods for detecting changes in response behaviors of indicator specimens are presented for monitoring effects of toxic treatments. The movement patterns of individuals are quantitatively characterized by statistical (i.e., ANOVA, multivariate analysis) and computational (i.e., fractal dimension, Fourier transform) methods. Extraction of information in complex behavioral data is further illustrated by techniques in ecological informatics. Multi-Layer Perceptron and Self-Organizing Map are applied for detection and patterning of response behaviors of indicator specimens. The recent techniques of Wavelet analysis and line detection by Recurrent Self-Organizing Map are additionally discussed as an efficient tool for checking time-series movement data. Behavioral monitoring could be established as new methodology in integrative ecological assessment, tilling the gap between large-scale (e.g., community structure) and small-scale (e.g., molecular response) measurements.

• Journal of Information Processing Systems
• /
• 제14권1호
• /
• pp.150-161
• /
• 2018

We propose a novel deep neural network model for detecting human activities in untrimmed videos. The process of human activity detection in a video involves two steps: a step to extract features that are effective in recognizing human activities in a long untrimmed video, followed by a step to detect human activities from those extracted features. To extract the rich features from video segments that could express unique patterns for each activity, we employ two different convolutional neural network models, C3D and I-ResNet. For detecting human activities from the sequence of extracted feature vectors, we use BLSTM, a bi-directional recurrent neural network model. By conducting experiments with ActivityNet 200, a large-scale benchmark dataset, we show the high performance of the proposed DeepAct model.

• 한국멀티미디어학회논문지
• /
• 제11권6호
• /
• pp.807-815
• /
• 2008

A simple efficient method of spotting and recognizing hand gestures in video is presented using a network of hidden Markov models and dynamic programming search algorithm. The description starts from designing a set of isolated trajectory models which are stochastic and robust enough to characterize highly variable patterns like human motion, handwriting, and speech. Those models are interconnected to form a single big network termed a spotting network or a spotter that models a continuous stream of gestures and non-gestures as well. The inference over the model is based on dynamic programming. The proposed model is highly efficient and can readily be extended to a variety of recurrent pattern recognition tasks. The test result without any engineering has shown the potential for practical application. At the end of the paper we add some related experimental result that has been obtained using a different model - dynamic Bayesian network - which is also a type of stochastic model.

• 한국수학교육학회지시리즈D:수학교육연구
• /
• 제23권4호
• /
• pp.219-233
• /
• 2020

Teachers' intervention in small groups is a research area that needs more research attention. Ehrenfeld and Horn (2020) identified teachers' group work monitoring routines that consist of four recurrent talk moves: 1) Initiation, 2) Entry, 3) Focus, and 4) Exit. To better understand prospective teachers' (PTs) intervention in small groups in mathematics classrooms, I investigated how PTs' intervention actions and purposes are related to the monitoring routines, particularly, in terms of Focus moves. I analyzed 26 PTs' responses to four written scenarios, each of which depicts interactions among students in a small group. I identified 1) types of PTs' math talk, 2) types of PTs' non-math talk, 3) types of intervention purposes, and 4) patterns of intervention actions and purposes by scenario. This study contributes to understanding PTs' intervention actions and purposes in mathematics instruction.