• 한국안전학회지
• /
• 제38권1호
• /
• pp.1-8
• /
• 2023

It is extremely important to design safety-guaranteed industrial processes because such process determine the ultimate outcomes of industrial activities, including worker safety. Application of artificial intelligence (AI) in industrial safety involves modeling industrial safety systems by using vast amounts of safety-related data, accident prediction, and accident prevention based on predictions. As a preliminary step toward realizing AI-based industrial safety in Korea, this study discusses neural network-based modeling of industrial safety systems. The input variables that are the most discriminatory relative to the output variables of industrial safety processes are selected using two information-theoretic measures, namely entropy and cross entropy. Normalized frequency and severity of industrial accidents are selected as the output variables. Our simulation results confirm the effectiveness of the proposed neural network model and, therefore, the feasibility of extending the model to include more input and output variables.

• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1301-1306
• /
• 2018

Artificial intelligence is one of the key technologies of the Fourth Industrial Revolution. This paper introduces the diverse kinds of approaches to subjects that tackle diverse kinds of research fields such as model-based MS approach, deep neural network model, image edge detection approach, cross-layer optimization model, LSSVM approach, screen design approach, CPU-GPU hybrid approach and so on. The research on Superintelligence and superconnection for IoT and big data is also described such as 'superintelligence-based systems and infrastructures', 'superconnection-based IoT and big data systems', 'analysis of IoT-based data and big data', 'infrastructure design for IoT and big data', 'artificial intelligence applications', and 'superconnection-based IoT devices'.

• Bulletin of the Korean Chemical Society
• /
• 제25권12호
• /
• pp.1917-1923
• /
• 2004

Although the proteolytic activity of the Cu(II) complex of cyclen (Cyc) is greatly enhanced upon attachment to a cross-linked polystyrene (PS), the Cu(II)Cyc-containing PS derivatives reported previously hydrolyzed only a very limited number of proteins. The PS-based artificial metalloproteases can overcome thermal, mechanical, and chemical instabilities of natural proteases, but the narrow substrate selectivity of the artificial metalloproteases limits their industrial application. In the present study, artificial metalloproteases exhibiting broad substrate selectivity were synthesized by attaching Cu(II)Cyc to a PS derivative using linkers with various structures in an attempt to facilitate the interaction of various protein substrates with the PS surface. The new artificial metalloproteases hydrolyzed all of the four protein substrates (albumin, myoglobin, ${\gamma}$-globulin, and lysozyme) examined, manifesting $k_{cat}/K_m$ values of 28-1500 $h_{-1}M_{-1}$ at 50 $^{\circ}C$. The improvement in substrate selectivity is attributed to steric and/or polar interaction between the bound protein and the PS surface as well as the hydrophobicity of the microenvironment of the catalytic centers.

• 대한의용생체공학회:의공학회지
• /
• 제9권2호
• /
• pp.251-252
• /
• 1988

To develop an artificial bone substitute that is gradually degraded and replaced by the regenerated natural bone, the authors designed a composite that is consisted of calcium phosphate and collagen. To use as the structural matrix of the composite, collagen was purified from human umbilical cord. The obtained collagen was treated by pepsin to remove telopeptides, and finally, the immune-free atelocollagen was produced: The cross linked atelocollagen was highly resistant to the collagenase induced collagenolysis. The cross linked collagen demonstrated an improved tensile strength.

• Journal of the Korean Data and Information Science Society
• /
• 제20권5호
• /
• pp.949-954
• /
• 2009

The autoregressive process is applied in this paper to kernel regression in order to infer nonlinear models for predicting responses. We propose a kernel method for the autoregressive data which estimates the mean function by kernel machines. We also present the model selection method which employs the cross validation techniques for choosing the hyper-parameters which affect the performance of kernel regression. Artificial and real examples are provided to indicate the usefulness of the proposed method for the estimation of mean function in the presence of autocorrelation between data.

• 대한의용생체공학회:의공학회지
• /
• 제15권3호
• /
• pp.341-346
• /
• 1994

To develop an artificial bone substitute that is gradually degraded and replaced by the regenerated natural bone, the authors designed a composite that is consisted of calcium phosphate and collagen. To use as the structural matrix of the composite, collagen was purified from human umbilical cord. The obtained collagen was treated by pepsin to remove telopeptides, and finally, the immune-free atel- ocollagen was produced. The cross linked atelocollagen was highly resistant to the collagenase induced collagenolysis. The cross linked collagen demonstrated an improved tensile strength.

• 한국전자파학회논문지
• /
• 제21권6호
• /
• pp.610-616
• /
• 2010

본 논문에서는 주파수 선택 구조를 기반으로 하는 인공 자기 도체 구조를 설계하기 위하여 최적화 알고리즘 중 하나인 particle swarm optimization(PSO) 기법을 이용하였다. 주파수 선택 구조로서 Jerusalem Cross를 갖는 인공 자기 도체의 등가 회로 모델에 PSO를 적용하여, 원하는 공진 주파수 대역을 갖는 최적의 설계값을 얻어낼 수 있음을 확인하였다. 우선 유도한 등가 회로 모델로부터 공진 주파수와 반사 계수 위상 특성을 구하여 상용 소프트웨어로 얻은 값과 일치하는 것을 확인하여 본 논문의 유효함을 확인하였으며, 이로부터 원하는 공진 주파수에 대해 최적화 과정을 통하여 설계 파라미터를 추출하였다. 본 논문에서 유도한 최적화 과정을 이용한 주파수 선택 구조 기반 인공 자기 도체 구조 설계 방법을 이용하여 여러 다른 종류의 주파수 선택 구조 형태를 갖는 인공 자기 도체 구조뿐만 아니라, 인공 자기 도체 구조를 이용한 소형 안테나 접지면 설계 등 마이크로파 회로 설계에 유용하게 사용할 수 있다.

• 한국구조물진단유지관리공학회 논문집
• /
• 제25권5호
• /
• pp.135-140
• /
• 2021

본 연구에서는 일반강도 범위 콘크리트의 단면에서 골재 형상의 특성을 추출하고 이를 인공신경망과 이미지 프로세싱 기술에 적용하여 콘크리트의 압축강도를 예측하였다. 이를 위하여 면적, 둘레, 길이 등과 같은 일반적인 골재 형상 특성과 함께 골재의 거리-각도 특징을 수치적으로 표현하고 물성치 예측에 활용하였다. 그 결과, 콘크리트 압축강도에 영향을 미치는 주요변수를 사용하지 않고 단면의 골재 형상 특성만을 사용하여 압축강도 예측이 가능하였으며, 인공신경망 알고리즘 구축을 통해 예측 강도와 실제 강도의 상대오차 4.43% 이내의 범위에서 콘크리트 압축강도를 예측할 수 있었다. 본 연구에서 도출된 결과를 기반으로 골재의 거리-각도 특징을 활용하여 콘크리트의 유동성, 휨·인장강도 등 다양한 특성을 예측도 가능할 것으로 판단된다.

• Restorative Dentistry and Endodontics
• /
• 제17권2호
• /
• pp.383-397
• /
• 1992

The purpose of this study was to evaluate the influence of artificial saliva contamination on bonding of several dentin adhesives to dentin. Sixty - three human molar teeth extracted within a month were used. Each tooth was sectioned longitudinally in a buccolingual direction to obtain 126 specimens. These specimens were randomly divided into three groups and were treated by Scotchbond 2, Gluma and All bond. Each group was subdivided into three subgroups; normal group not contaminated with artificial saliva, contaminated with artificial saliva and dried group, and contaminated with artificial saliva and washed and dried group. Enamel/dentin bonding agent(Dental Adhesive of Scotchbond 2) was applied and light cured on the treated dentin surfaces. Thereafter P - 50 were cured on them, and specimens were stored in $37^{\circ}C$ artificial saliva for 24 hours before measuring shear bond strength. Shear bond strengths were determined using an universal testing machine with cross head speed 1mm/min and SEM examinations were conducted to evaluate the resin - dentin interface and degree of penetrating resin string into the dentinal tubules. The following results were obtained. 1. Normal groups not contaminated with artificial saliva showed greater shear bond strength than any other group contaminated with artificial saliva(P<0.01). 2. The shear bond strengths showed no significant difference between washed groups with distilled water and not washed groups after contamination with artificial saliva(P>0.05). 3. In normal groups, the shear bond strength of A group was significantly greater than in any other group(P<0.01). 4. In Sand G groups, fractures after shear bond strength tests occured adhesively on resintooth interface in all specimens. But in A groups, fracture of the normal group occured cohesively in dentin and fracture of the contaminated groups occured adhesively and cohesively. 5. On SEM examination, the number of resin strings penetrated into dentinal tubules were the greatest in normal groups, followed by, in descending order, washed groups and not washed groups after contamination with artificial saliva.

• 한국제4기학회지
• /
• 제16권1호
• /
• pp.17-27
• /
• 2002

순창에서 대강, 곡성에 이르는 섬진강 본류에서 건설부 (1978)가 설정한 199∼145번 횡단측선에서 측량을 실시하고, 이를 1978년과 1989년에 건설부에서 조사한 횡단측선과 비교하여 시간에 따르는 하상지형의 변화를 고찰하였다 그 결과, 본 연구지역은 전체적으로 하방침식이 우세한 환경이며, 일부 구간에서는 측방침식과 함께 최심선이 제방측으로 이동하는 경향을 나타내는 것으로 나타났다. 이렇게 침식이 우세하게 나타나는 원인으로서 다음 두가지를 들 수 있다. 첫 번째로 유속이 증가하였다는 점이다. 습지 파괴, 구하도 파괴, 인공제방 축조 등 인간간섭에 의하여 하도폭이 축소·고정되었으며 하도가 직강화되었으며, 이에 따라 유속이 크게 증가하였다. 유속 증가는 하상 퇴적물에 자갈 및 극조립∼조립질 모래가 우세하게 분포하고 있다는 사실에서도 확인할 수 있다. 두 번째로, 1980~1990년대에 본 연구구간과 연구구간의 하류측에서 집중적으로 골재채취가 이루어졌다는 점이다. 이러한 원인으로 인하여 본 연구구간은 침식이 우세하게 나타나게 되는데, 특히 188∼187번 측선의 우안 일대와 155번 측선의 좌안 일대에서 인공제방 하부의 침식이 크게 진행되고 있으며 최심선도 제방쪽으로 이동하고 있는 양상이 관찰되어, 홍수시에 제방이 파괴되는 파제의 위험성이 큰 것으로 사료된다.