• 수산해양기술연구
• /
• 제53권2호
• /
• pp.160-168
• /
• 2017

In this study, we propose a method of optimal placement technique of artificial reef considering characteristics of sea areas and provide basic data for efficient budget execution. In addition, we will contribute to increasing the economic efficiency by improving the fisheries productivity by suggesting the scientific basis for the policy data and the increase of the catch through the resource creation based on the ecological information about the biology. Especially, in order to establish the effective disposition (optimum separation distance) of artificial reef considering characteristics of biological and engineering factors, it is necessary to review the artificial reef installation management regulations and investigate the biological effects of artificial reef facilities, is needed. Through this, it is expected that the ground data of the direction of the policy promotion will be derived by suggesting the placement condition of the artificial reef complex which can maximize the resource composition effect according to the target fish species.

• 한국수산과학회지
• /
• 제46권3호
• /
• pp.266-272
• /
• 2013

The objective of this study was to monitor and evaluate the schooling characteristics, including the distribution density (volume backscattering strength) and acoustic size (target strength), of commercially valuable species swimming in response to artificial reefs installed at Suyeong Man, Busan, Korea. Fish aggregations at two artificial reef areas and at a nearby natural rocky reef habitat were recorded and analyzed using a 70 kHz split-beam echo sounder and 330 kHz side-scan sonar from August to September, 2006. An underwater CCTV camera system was also used to observe marine organisms in physical contact with and swimming very close to artificial reefs. During the acoustic observations at three reef sites, useful information about schooling characteristics of fish aggregations responding to artificial reefs were obtained, but more trials are needed to confirm significant differences in schooling behavior and geographical distributions in areas containing natural reef structures and artificial reefs.

• BMB Reports
• /
• 제41권12호
• /
• pp.852-857
• /
• 2008

Little attention has been paid to the specificity between E2 and the target protein during ubiquitination, although RING-E3 induces a potential intra-molecular reaction by mediating the direct transfer of ubiquitin from E2 to the target protein. We have constructed artificial E2 fusion proteins in which a target protein (p27) is tethered to one of six E2s via a flexible linker. Interestingly, only three E2s (UbcH5b, hHR6b, and Cdc34) are able to ubiquitinate p27 via an intra-molecular reaction in this system. Although the first ubiquitination of p27 (p27-Ub) by Cdc34 is less efficient than that of UbcH5b and hHR6b, the additional ubiquitin attachment to p27-Ub by Cdc34 is highly efficient. The E2 core of Cdc34 provides specificity to p27, and the residues 184-196 are required for possessive ubiquitination by Cdc34. We demonstrate direct E2 specificity for p27 and also show that differential ubiquitin linkages can be dependent on E2 alone.

• Molecules and Cells
• /
• 제21권3호
• /
• pp.376-380
• /
• 2006

Gene expression is regulated in large part at the level of transcription under the control of sequence-specific transcriptional regulatory proteins. Therefore, the ability to affect gene expression at will using sequencespecific artificial transcription factors would provide researchers with a powerful tool for biotechnology research and drug discovery. Previously, we isolated 56 novel sequence-specific DNA-binding domains from the human genome by in vivo selection. We hypothesized that these domains might be more useful for regulating gene expression in higher eukaryotic cells than those selected in vitro using phage display. However, an unpredictable factor, termed the "context effect", is associated with the construction of novel zinc finger transcription factors--- DNA-binding proteins that bind specifically to 9-base pair target sequences. In this study, we directly selected active artificial zinc finger proteins from a zinc finger protein library. Direct in vivo selection of constituents of a zinc finger protein library may be an efficient method for isolating multi-finger DNA binding proteins while avoiding the context effect.

• 한국공작기계학회논문집
• /
• 제14권4호
• /
• pp.22-31
• /
• 2005

The purpose of this study is to design a flexural structure that has a function of pan and tilt for an artificial eyeball. The artificial eyeball system has a function of image stabilization, which compensate panning and tilting vibration of the body on which the artificial eyeball is attached. The target closed loop control bandwidth is 50Hz, so the mechanical resonance frequency is required to be more than the control bandwidth, which is a tough design problem because of a big mass of camera and actuator. In this study, the design process including the selection of the principal parameters by numerical analysis with ANSYS will be described, as well as the design results and frequency response.

• 정보처리학회논문지B
• /
• 제14B권7호
• /
• pp.531-540
• /
• 2007

본 논문에서는 주가예측의 정확도를 향상시키기 위하여 공적분 검정(Cointegration Tests)과 인공 신경망(Artificial Neural Networks)을 사용한 2단계 하이브리드 예측 모델을 제시한다. 기존의 연구에서는 예측을 시도하고자 하는 종목의 일자별 개별 레코드를 인공 신경망과 같은 방법으로 학습함으로써 주식 데이터가 가지는 시계열적 특성을 충분히 반영하지 못하였는데, 새로 제안한 모형에서는 주식자료의 과거시차들의 값들도 인공 신경망의 속성(feature)으로 사용하여 기존 연구의 한계를 보완하였다. 또한, 예측대상종목의 정보들 외에도 장기적으로 높은 시계열 유사성을 보유한 종목들을 선발한 후 속성으로 사용하여 모형의 예측성능을 향상 시켰다. 구체적으로 1단계는 Johansen의 공적분 검정을 통하여 예측대상종목과 장기적 관계(long-term relationship)에 있는 종목을 추출하고, 2단계는 이 선발된 종목들과 예측대상종목의 시계열 정보 특성을 속성으로 구축한 인공 신경망으로 학습하여 관심 종목을 예측한다. 제안된 모델의 성능을 확인하기 위하여 KOSPI 지수의 방향성을 예측하는 시스템을 구현하였으며, 시가총액 상위 종목군을 대상으로 지수와의 공적분 검정을 하였다. 성능을 살펴보기 위하여 본 연구에서는 시계열 정보가 속성으로 반영된 단순 인공 신경망 모델, 공적분 검정을 통과한 종목들의 시계열 속성이 포함된 모델, 그리고 그 모델과 속성의 개수를 동일하게 하기 위하여 임의로 종목을 선택하여 이들의 시계열 속성이 포함된 모델을 구축하였다. 실험 결과 공적분 검정을 통과한 종목군의 속성이 결합된 모델은 단순 인공 신경망만으로 학습된 기존 모델에 비하여 평균적으로는 11.29% (최대 29.98%) 정확도가 향상되었고, 임의로 선택된 종목군의 속성이 결합된 모델에 비해서는 평균적으로는 10.59% (최대 25.78%) 가 향상된 예측 정확도를 보여주었다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.538-540
• /
• 2021

본 논문에서는 드론의 표적탐지 임무 수행 시 상대운동 정보 제공을 위하여 지정된 표적을 탐지하고 인식하는 스마트 표적탐지 시스템을 제안하였다. 제안된 시스템은 적절한 정확도(i.e. mAP, IoU) 및 높은 실시간성을 동시에 확보할 수 있는 알고리즘을 개발하는데 중점을 두었다. 제안된 시스템은 Google Inception V2 딥러닝 모델의 100k 학습 후 test 결과가 1.0에 가까운 정확성을 보였고 실시간성도 Nvidia GTX 2070 Max-Q를 기반으로 한 고성능 노트북 활용 시에 추론 속도가 약 60-80[Hz]를 기록하였다. 제안된 스마트 표적탐지 시스템은 드론과 같이 운용되어 컴퓨터 영상처리를 활용하여 표적을 자동으로 인식하고 표적을 따라가면서 감시정찰 임무를 성공적으로 수행하는데 도움이 될 것이다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2000년도 춘계 학술대회 논문집 통권 3호 Proceedings of the 2000 KSRS Spring Meeting
• /
• pp.9-9
• /
• 2000

For the planning of future land use for economic activities, an essential component is the identification of the vulnerable areas for natural hazard and environmental impacts from the activities. Also, exploration for mineral and energy resources is carried out by a step by step approach. At each step, a selection of the target area for the next exploration strategy is made based on all the data harnessed from the previous steps. The uncertainty of the selected target area containing undiscovered resources is a critical factor for estimating the exploration risk. We have developed not only spatial prediction models based on adapted artificial intelligence techniques to predict target and vulnerable areas but also validation techniques to estimate the uncertainties associated with the predictions. The prediction models will assist the scientists and decision-makers to make two critical decisions: (i) of the selections of the target or vulnerable areas, and (ii) of estimating the risks associated with the selections.

• 반도체디스플레이기술학회지
• /
• 제20권1호
• /
• pp.83-87
• /
• 2021

By the increase of internet usage, communicating online became an everyday thing. Thereby various people have experienced profanity by anonymous users. Nowadays lots of studies tried to solve this problem using artificial intelligence, but most of the solutions were for non-real time situations. In this paper, we propose a Telegram plugin that detects swear words using word2vec, and an algorithm to find the target of the sentence. We vectorized the input sentence to find connections with other similar words, then inputted the value to the pre-trained CNN (Convolutional Neural Network) model to detect any swears. For target recognition we proposed a sequential algorithm based on KoNLPY.

• 반도체디스플레이기술학회지
• /
• 제21권3호
• /
• pp.110-113
• /
• 2022

Non-playable game character plays an important role in improving the concentration of the game and the interest of the user, and recently implementation of NPC with reinforcement learning has been in the spotlight. In this paper, we estimate an AI target tracking method via reinforcement learning, and implement an AI-based tracking agency of specific target object with avoiding traps through Unity ML-Agents Toolkit. The implementation is built in Unity game engine, and simulations are conducted through a number of experiments. The experimental results show that outstanding performance of the tracking target with avoiding traps is shown with good enough results.