딥러닝 예측 결과 정보를 적용하는 복합 미생물배양기를 위한 딥러닝 구조 개발

김홍직,이원복,이승호 한국전기전자학회 2023 전기전자학회논문지 Vol.27 No.1

In this paper, we develop a deep learning structure for a complex microbial incubator that applies deep learning prediction result information. The proposed complex microbial incubator consists of pre-processing of complex microbial data, conversion of complex microbial data structure, design of deep learning network, learning of the designed deep learning network, and GUI development applied to the prototype. In the complex microbial data preprocessing, one-hot encoding is performed on the amount of molasses, nutrients, plant extract, salt, etc. required for microbial culture, and the maximum-minimum normalization method for the pH concentration measured as a result of the culture and the number of microbial cells to preprocess the data. In the complex microbial data structure conversion, the preprocessed data is converted into a graph structure by connecting the water temperature and the number of microbial cells, and then expressed as an adjacency matrix and attribute information to be used as input data for a deep learning network. In deep learning network design, complex microbial data is learned by designing a graph convolutional network specialized for graph structures. The designed deep learning network uses a cosine loss function to proceed with learning in the direction of minimizing the error that occurs during learning. GUI development applied to the prototype shows the target pH concentration (3.8 or less) and the number of cells (10⁸ or more) of complex microorganisms in an order suitable for culturing according to the water temperature selected by the user. In order to evaluate the performance of the proposed microbial incubator, the results of experiments conducted by authorized testing institutes showed that the average pH was 3.7 and the number of cells of complex microorganisms was 1.7 × 10⁸. Therefore, the effectiveness of the deep learning structure for the complex microbial incubator applying the deep learning prediction result information proposed in this paper was proven.

A review on deep learning-based structural health monitoring of civil infrastructures

X.W. Ye,T. Jin,C.B. Yun 국제구조공학회 2019 Smart Structures and Systems, An International Jou Vol.24 No.5

In the past two decades, structural health monitoring (SHM) systems have been widely installed on various civil infrastructures for the tracking of the state of their structural health and the detection of structural damage or abnormality, through long-term monitoring of environmental conditions as well as structural loadings and responses. In an SHM system, there are plenty of sensors to acquire a huge number of monitoring data, which can factually reflect the in-service condition of the target structure. In order to bridge the gap between SHM and structural maintenance and management (SMM), it is necessary to employ advanced data processing methods to convert the original multi-source heterogeneous field monitoring data into different types of specific physical indicators in order to make effective decisions regarding inspection, maintenance and management. Conventional approaches to data analysis are confronted with challenges from environmental noise, the volume of measurement data, the complexity of computation, etc., and they severely constrain the pervasive application of SHM technology. In recent years, with the rapid progress of computing hardware and image acquisition equipment, the deep learning-based data processing approach offers a new channel for excavating the massive data from an SHM system, towards autonomous, accurate and robust processing of the monitoring data. Many researchers from the SHM community have made efforts to explore the applications of deep learning-based approaches for structural damage detection and structural condition assessment. This paper gives a review on the deep learning-based SHM of civil infrastructures with the main content, including a brief summary of the history of the development of deep learning, the applications of deep learning-based data processing approaches in the SHM of many kinds of civil infrastructures, and the key challenges and future trends of the strategy of deep learning-based SHM.

Deep learning classifier for the number of layers in the subsurface structure

Ho-Chan Kim,Min-Jae Kang 한국인터넷방송통신학회 2021 Journal of Advanced Smart Convergence Vol.10 No.3

In this paper, we propose a deep learning classifier for estimating the number of layers in the Earth's structure. When installing a grounding system, knowledge of the subsurface in the area is absolutely necessary. The subsurface structure can be modeled by the earth parameters. Knowing the exact number of layers can significantly reduce the amount of computation to estimate these parameters. The classifier consists of a feedforward neural network. Apparent resistivity curves were used to train the deep learning classifier. The apparent resistivity at 20 equally spaced log points in each curve are used as the features for the input of the deep learning classifier. Apparent resistivity curve data sets are collected either by theoretical calculations or by Wenner's measurement method. Deep learning classifiers are coded by Keras, an open source neural network library written in Python. This model has been shown to converge with close to 100% accuracy.

딥러닝 예측 기반의 OLED 재료 분자구조 가상 스크리닝

전예린,이규황,이호경,Jeon, Yerin,Lee, Kyu-Hwang,Lee, Hokyung 한국화학공학회 2020 Korean Chemical Engineering Research(HWAHAK KONGHA Vol.58 No.2

딥러닝 기법을 활용하여 분자 구조로부터 물성을 예측하는 시스템은 화학, 생물학, 재료 연구에 적용하기 위해 개발되었다. 분자 구조와 물성 정보가 축적된 데이터베이스를 기반으로, 구조와 물성간의 관계식을 찾는 딥러닝 모형을 구축한 후 최종적으로는 새로운 분자 구조에 대한 물성 예측값을 제공할 수 있다. 또한 선정된 분자 구조의 실제 물성값에 대한 실험을 병행하여 지속적인 검증 및 모형 업데이트를 수행하게 된다. 이를 통해 다량의 분자구조로부터 물성이 우수한 분자 구조를 빠른 시간 안에 스크리닝할 수 있으며, 연구의 효율성 및 성공률을 높일 수 있다. 본 논문에서는 딥러닝을 활용한 물성 예측 시스템의 전반적인 구성과 LG화학에서 실제 신규 구조 발굴에 적용된 사례를 중심으로 소개하고자 한다. A system that uses deep-learning techniques to predict properties from molecular structures has been developed to apply to chemical, biological and material studies. Based on the database where molecular structure and property information are accumulated, a deep-learning model looking for the relationship between the structure and the property can eventually provide a property prediction for the new molecular structure. In addition, experiments on the actual properties of the selected molecular structure will be carried out in parallel to carry out continuous verification and model updates. This allows for the screening of high-quality molecular structures from large quantities of molecular structures within a short period of time, and increases the efficiency and success rate of research. In this paper, we would like to introduce the overall composition of the materiality prediction system using deep-learning and the cases applied in the actual excavation of new structures in LG Chem.

Computer vision and deep learning-based post-earthquake intelligent assessment of engineering structures: Technological status and challenges

X.W. Ye,T. Jin,W.M. Que,S.Y. Ma 국제구조공학회 2023 Smart Structures and Systems, An International Jou Vol.31 No.4

Ever since ancient times, earthquakes have been a major threat to the civil infrastructures and the safety of human beings. The majority of casualties in earthquake disasters are caused by the damaged civil infrastructures but not by the earthquake itself. Therefore, the efficient and accurate post-earthquake assessment of the conditions of structural damage has been an urgent need for human society. Traditional ways for post-earthquake structural assessment rely heavily on field investigation by experienced experts, yet, it is inevitably subjective and inefficient. Structural response data are also applied to assess the damage; however, it requires mounted sensor networks in advance and it is not intuitional. As many types of damaged states of structures are visible, computer vision-based post-earthquake structural assessment has attracted great attention among the engineers and scholars. With the development of image acquisition sensors, computing resources and deep learning algorithms, deep learning-based post-earthquake structural assessment has gradually shown potential in dealing with image acquisition and processing tasks. This paper comprehensively reviews the state-of-the-art studies of deep learning-based postearthquake structural assessment in recent years. The conventional way of image processing and machine learning-based structural assessment are presented briefly. The workflow of the methodology for computer vision and deep learning-based postearthquake structural assessment was introduced. Then, applications of assessment for multiple civil infrastructures are presented in detail. Finally, the challenges of current studies are summarized for reference in future works to improve the efficiency, robustness and accuracy in this field.

지배권력에 잠재된 프레임 구조의 표층과 심층구조

선미라 ( Sun Mi-ra ) 한국기호학회 2020 기호학연구 Vol.65 No.-

이 논문은 지배권력에 잠재된 프레임 구조의 표층과 심층 구조에 대한 연구다. 권력은 생산되는 것이 아니고 생성을 원칙으로 한다. 하지만 통제와 감시 그리고 처벌을 위주로 하는 모순된 구조 속에서는 이 관계를 역행하는 프레임으로 작동한다. 자발적 참여가 결여되고 표층적 구조의 생산물 위주로 전체주의적 틀 속으로 빨려드는 형상을 초래하여 기의는 사라지고 기표 속에서 생활하게 된다. 이런 구조적 모순에서 발생하는 억압과 통제는 권태와 허무를 생산하고 이데아의 세계를 꿈꾸며 행복하려는 출구를 찾으려는 의지가 생성된다. 이 의지를 통해 이데아의 다리를 만들고 과거와 현재 그리고 미래를 소통할 장치를 찿게 된다. 이것을 사회적 담론에서 찾으려 하며 심층 구조를 제시함으로서 지속적으로 그 이데아의 상징성을 제시하고자 한다. This paper is a study on the surface and deep structures of the frame structure potential to the dominant power. The power is not produced, but it’s a to be produced the basis of creation. However, in a contradictory structure centering on control, surveillance, and punishment, it acts as a frame that reverses this relationship. Voluntary participation is lacking in such a society. So, it causes the shape to be sucked into the totalitarian frame, mainly for the products of the surface structure, and the signifiant disappears and lives in the signifier. Repression and control arising out of these structural contradictions produce boredom and vainness. And here, a willingness to find an exit to be happy while dreaming of the world of Idea is created. Through this will, the bridge of Idea is created and a device to communicate the past, present and future is found. In this study, we try to find that in social discourse and continuously suggest the symbolism of the idea by presenting the in deep structure.

아이폰의 시공과 그 심층구조

선미라 ( Mi Ra Sun ) 한국기호학회 2014 기호학연구 Vol.39 No.-

이 논문은 아이폰의 시공과 그 심층구조에 대한 연구 논문이다. 이 논문 구조는 아이폰과 시공 그리고 심층구조의 통시적 관계성에 대해 기술되는 양상을 특징으로 하고 있다. 이 구조 속에서 아이폰의 출현이 사회적 절규에서 발현된 것이라면 아이폰과 그 시공의 문제는 인간 욕망의 확장에 대한 절규로 볼 수 있다. 이러한 절규와 욕망 확장은 수평적인 사회적 관계망을 가능하게 하고 또한 주관적 공간세계에 대한 접근을 가능하게 한다. 이를 위해서 아이폰의 인식론적 발전 과정이 출현하며 이에 대한 방법으로는 아이폰의 시공적 서비스를 언급함으로서 그 구체적인 사용처를 밝히고 있다. 이러한 관점에서 검토되는 아이폰의 정체성과 언어형태 그리고 모달리떼는 아이폰의 아이콘 구조는 물론 그 심층구조의 내재적 맥락을 동시에 설명하는 방식을 제시하고 있다. In this paper, the research is a about the iPhone and the deep structure. The structure of the paper is characterized a deep structure of the iPhone and the construction described relationships which are describing the attributes by an aspect. In this structure, the enonciation of the iPhone is expressed in the cry of the social construction of the problem, in that the iPhone and the expansion of the human desire to be seen as a cry. This desire to scream and expansion of social networks to enable horizontal and subjective space also enables access to the world. To do this, the advent of the iPhone and the evolution of epistemological methods such as the construction of the iPhone applications tempolality services referred to by its specific states. Review of the iPhone in this respect, and all forms of identity and language described the structure of the iPhone``s icon, as well as it``s a deep structure inherent structure at the same time explaining how the context presented.

설화 <엎질러진 물>의 남북한 이본 비교를 통해 본 ‘서사의 논리’

나지영(Na, Ji Young) 건국대학교 글로컬문화전략연구소 2018 문화콘텐츠연구 Vol.0 No.12

이 글에서는 설화 <엎질러진 물>의 남북한 이본 비교를 통해 작품의 기저에 존재하는 ‘심층구조’가 어떻게 ‘서사의 논리’를 구성하고 있는지 살펴보았다. 먼저 2절에서는 <엎질러진 물>의 여러 각편에서 드러나는 남편의 잔인한 면모와 아내가 맞이하는 비극적 결말을 대조하면서, 남편의 모진 모습과 아내가 겪는 불행 사이의 관련성에 주목하였다. 그런데 북한에서 전해지고 있는 <엎질러진 물>의 또 다른 이본에서는 남편의 캐릭터가 지니는 속성이 완전히 바뀌어 있었다. 북한 설화 속 남편은 아내에 대한 용서와 포용의 길을 어느 정도 열어 둔 인물로 그려지고 있는 것이다. 그럼에도 불구하고 여전히 북한 설화에서도 아내의 삶은 불행하게 끝난다. 아무리 남편이 포용적이며 도량이 넓어졌다 한들 아내는 행복해질 수 없는 것이다. 이것이 의미하는 바는 무엇인가. 이는 <엎질러진 물>에 내재되어 있는 서사의 논리가 아내의 행복을 구조적으로 가로막고 있다는 뜻으로 이해할 수 있다. 그러니까 텍스트 상에서 캐릭터가 지니는 속성이 완전히 변한다 하더라도 절대 건드릴 수 없는 이야기의 심층구조가 존재한다는 것이다. 다음으로 3절에서는 <엎질러진 물>이 여전히 <엎질러진 물>로서의 서사적 정체성을 지니기 위해 견지하고 있어야 하는 심층구조를 밝히고자 하였다. 또한 작품의 심층구조가 어떠한 서사의 논리를 구조화하고 있는 지도 논의하였다. <엎질러진 물>에서 제기되고 있는 근본적 문제 상황은 ‘가난’이며, 궁극적인 문제 해결 방안은 ‘과거 급제’에 있다. 남편은 단 한 번의 흔들림 없이 문제의 근본적 해결을 위해 노력한 인물이다. 공부에만 몰두한 남편의 행동은 아내에 비해 ‘정적’으로 보였지만 이야기의 전체 구조 속에서는 문제의 근본적 해결을 이끌어 낸 가장 ‘동적’인 행동이었다. 반면, 아내는 끊임없이 움직이는 모습을 보여주면서 남편보다 훨씬 동적인 인물로 비춰졌지만, 실상 문제의 근본적 해결에 있어서는 별다른 영향을 주지 못한 정적 인물이었다. 결정적 순간에 근본적인 문제 해결을 위한 노력에 동참하지 않았기에 그녀의 행복은 불가능했던 것이다. 설화 <엎질러진 물>의 텍스트 상에서 아무리 아내의 입장을 이해할 만한 정황이 나타나고, 남편의 행동을 비판할 만한 정황이 나타난다 하더라도, 이 작품에서 남편만이 일방적으로 성공을 하고 아내는 철저하게 실패할 수밖에 이유는 바로 <엎질러진 물>의 심층구조가 구성하고 있는 서사의 논리에 의해서이다. 근본적 문제 해결을 위해 끝까지 노력한 자와 그렇지 않은 자의 대비가 뚜렷이 나타나는 것이다. In this study, ‘deep structure’ and ‘logic of epic’ of folktale <Spilt Water> are analyzed through the comparison of South and North Korean version of <Spilt Water>. In chapter 2, the relevance between the character of “husband”s cruelty and the character of “wife”s tragic end are studied. However, in North Korean version of <Spilt Water>, the character of husband is completely changed. Therefore it is difficult to find the relevance between the character of “husband” s cruelty and the character of “wife”s tragic end in North Korean version of <Spilt Water>. In North Korean version of <Spilt Water>, the character of husband is described as generous and magnanimous person. Yet, surprisingly, in North Korean version of <Spilt Water>, wife’s tragic end is not changed. Even though the character of husband is completely changed, the tragic end is inevitable. It menas that ‘deep structure’ and ‘logic of epic’ of folktale <Spilt Water> block the way of wife’s happiness structurally. In chapter 3, ‘deep structure’ and ‘logic of epic’ of folktale <Spilt Water> are analyzed. These ‘deep structure’ and ‘logic of epic’ make the distinct identity of folktale <Spilt Water>. In folktale <Spilt Water>, ‘poverty’ is the fundamental problem situation, and ‘pass the state examination’ is the ultimate problem solution. The character of husband is the one who tried the ultimate problem solution steadily. In the text level, the husband is described as a ‘static character’, and the wife is described as a ‘dynamic character’. However, in the deep structure lever, the husband is the ‘dynamic character’ who actually succeeds the ultimate problem solution, and the wife is the ‘static character’ who doesn’t contribute the ultimate problem solution. That is why the ‘logic of epic’ of <Spilt Water> only supports the husband"s success.

Roadway Engineering Mechanical Properties and Roadway Structural Instability Mechanisms in Deep Wells

Xiang-Rui Meng,Rui Peng,Guang-Ming Zhao,Ying-Ming Li 대한토목학회 2018 KSCE JOURNAL OF CIVIL ENGINEERING Vol.22 No.5

We proposed a new classification method for stress-bearing structures in very-deep roadways. We conducted tests for roadwayengineeringmechanical properties, including rock mechanical tests and ground stress measurement of two caverns in very-deepwells. We suggested a classification method for stress-bearing structures based on shear stress. Tests revealed that rock strength in theshear direction was the lowest; the stress distributions of acoustic emission and hollow inclusion were highly similar. Based on theroadway-engineering mechanical properties of two caverns and numerical simulation and in-situ tests, the key bearing structureswere classified based on the concentrated shear stress. In deep caverns, shear stress was more concentrated on the softer surroundingrock, the key bearing structure areas, and the more seriously fractured surrounding rocks. Using the loose circle in-situ test, wecompared the classification method of the key bearing structures with other classification methods. The results revealed agreementwith the classification methods used for the key bearing structures. The deformation in-situ test showed that the strata convergence ofconcentrated shear stress areas developed quickly. Therefore, the phenomena of concentrated shear stress and the expanded range ofkey bearing structures are the structural instability mechanisms of deep roadways.

Deep learning classifier for the number of layers in the subsurface structure

Kim, Ho-Chan,Kang, Min-Jae The Institute of Internet 2021 International journal of advanced smart convergenc Vol.10 No.3

In this paper, we propose a deep learning classifier for estimating the number of layers in the Earth's structure. When installing a grounding system, knowledge of the subsurface in the area is absolutely necessary. The subsurface structure can be modeled by the earth parameters. Knowing the exact number of layers can significantly reduce the amount of computation to estimate these parameters. The classifier consists of a feedforward neural network. Apparent resistivity curves were used to train the deep learning classifier. The apparent resistivity at 20 equally spaced log points in each curve are used as the features for the input of the deep learning classifier. Apparent resistivity curve data sets are collected either by theoretical calculations or by Wenner's measurement method. Deep learning classifiers are coded by Keras, an open source neural network library written in Python. This model has been shown to converge with close to 100% accuracy.