• Proceedings of the Korean Aquaculture Society Conference
• /
• 한국양식학회 2002년도 춘계 한국양식학회 학술대회 발표요지
• /
• pp.239-239
• /
• 2002

• Informatization Policy
• /
• 제27권2호
• /
• pp.3-19
• /
• 2020

Artificial intelligence(AI) and blockchain are developing as the core technology leading the Fourth Industrial Revolution. However, AI is still showing limitations in securing and verifying data and explaining the evidence for the results, and blockchain also has some drawbacks such as excessive energy consumption and lack of flexibility in data management. This study analyzed technological limitations of AI and blockchain and convergence trends to overcome them, and finally suggested ways to improve Korea's related policies. Specifically, in terms of R&D reinforcement, we proposed 1) mid- and long-term AI /blockchain convergence research at the national level and 2) blockchain-based AI data platform development. In terms of creating an innovative ecosystem, we also suggested 3) development of AI/blockchain convergence applications by industry, and 4) Start-up support for developing AI/blockchain convergence business models. Lastly, in terms of improving the legal system, we insisted that 5) widening the application of regulatory sandboxes and 6) improving regulations related to privacy protection is necessary.

• Journal of Biomedical Engineering Research
• /
• 제10권2호
• /
• pp.117-124
• /
• 1989

The intelligent trajectory control method that controls moving direction and average velocity for a prosthetic arm is proposed by pattern recognition and force estimations using EMG signals. Also, we propose the real time trajectory planning method which generates continuous accelleration paths using 3 stage linear filters to minimize the impact to human body induced by arm motions and to reduce the muscle fatigue. We use combination of MLP and fuzzy filter for pattern recognition to estimate the direction of a muscle and Hogan`s method for the force estimation. EMG signals are acquired by using a amputation simulator and 2 dimensional joystick motion. The simulation results of proposed prosthetic arm control system using the EMf signals show that the arm is effectively followed the desired trajectory depended on estimated force and direction of muscle movements.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• 제14권4호
• /
• pp.195-204
• /
• 2009

In order to estimate sea surface current fields in the East Sea, we examined characteristics of mean dynamic topography (MDT) fields (or mean surface current field, MSC) generated from three different methods. This preliminary investigation evaluates the accuracy of surface currents estimated from satellite-derived sea level anomaly (SLA) data and three MDT fields in the East Sea. AVISO (Archiving, Validation and Interpretation of Satellite Oceanographic data) provides a MDT field derived from satellite observation and numerical models with $0.25^{\circ}$ horizontal resolution. Steric height field relative to 500 dbar from temperature and salinity profiles in the East Sea supplies another MDT field. Trajectory data of surface drifters (ARGOS) in the East Sea for 14 years provide another MSC field. Absolute dynamic topography (ADT) field is calculated by adding SLA to each MDT. Application of geostrophic equation to three different ADT fields yields three surface geostrophic current fields. Comparisons were made between the estimated surface currents from the three different methods and in-situ current measurements from a ship-mounted ADCP (Acoustic Doppler Current Profiler) in the southwestern East Sea in 2005. For offshore areas more than 50 km away from the land, the correlation coefficients (R) between the estimated versus the measured currents range from 0.58 to 0.73, with 17.1 to $21.7\;cm\;s^{-1}$ root mean square deviation (RMSD). For coastal ocean within 50 km from the land, however, R ranges from 0.06 to 0.46 and RMSD ranges from 15.5 to $28.0\;cm\;s^{-1}$. Results from this study reveal that a new approach in producing MDT and SLA is required to improve the accuracy of surface current estimations for the shallow costal zones of the East Sea.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• 제17권4호
• /
• pp.225-242
• /
• 2012

This is the first attempt to produce simultaneous surface current field from satellite altimeter data for the entire East Sea and to provide surface current information to users with formal description. It is possible to estimate surface geostrophic current field in near real-time because satellite altimeters and coastal tide gauges supply sea level data for the whole East Sea. Strength and location of the major currents and meso-scale eddies can be identified from the estimated surface geostrophic current field. The mean locations of major surface currents were explicated relative to topographic, ocean-surface and undersea features with schematic representation of surface circulation. In order to demonstrate the practical use of this surface current information, exemplary descriptions of annual, seasonal and monthly mean surface geostrophic current distributions were presented. In order to objectively classify surface circulation patterns in the East Sea, empirical orthogonal function (EOF) analysis was performed on the estimated 16-year (1993-2008) surface current data. The first mode was associated with intensification or weakening of the East Korea Warm Current (EKWC) flowing northward along the east coast of Korea and of the anti-cyclonic circulation southwest of Yamato Basin. The second mode was associated with meandering paths of the EKWC in the southern East Sea with wavelength of 300 km. The first and second modes had inter-annual variations. The East Sea surface circulation was classified as inertial boundary current pattern, Tsushima Warm Current pattern, meandering pattern, and Offshore Branch pattern by the time coefficient of the first two EOF modes.

• Journal of Yeungnam Medical Science
• /
• 제11권2호
• /
• pp.277-283
• /
• 1994

We studied the change in intraocular pressure (IOP) in 15 consecutive cataract patients who underwent extracapsular cataract extraction and posterior chamber lens implantation between Feb. 1993 and Apr. 1993 to evaluate the effect of this surgery on postoperative IOP. To evaluate the clinical usefulness of non-contact tonometer, the intraocular pressures were measured with Kowa non-contact tonometer (TM-2000, Japan) as well as Goldmann applanation tonometer. There was a decrease in IOP of $3.4{\pm}2.9$mmHg (p<0.00l) 3 months after this surgery and the intraocular pressure differences between pseudophakic eyes and contralateral phakic eyes at 3 months postoperatively were $2.4{\pm}3.8$mmHg (p<0.05). The correlation coefficient between non-contact tonometer and Goldmann tonometer was 0.8876 (p=0.001) in the postoperative 76 eyes. Therefore, our results suggest that extracapsular cataract extracion and posterior chamber lens implantation alone can be a useful surgical method in cataract patient with ocular hypertension, and non-contact tonometer was relatively accurate in measuring the postoperative intraocular pressure.

• Journal of the Korean Society of Radiology
• /
• 제10권8호
• /
• pp.637-643
• /
• 2016

Due to the popularity of artificial intelligent, medical image processing using artificial neural network is increasingly attracting the attention of academic and industry researches. Deep learning with a convolutional neural network has been proved to very effective representation of images. However, the training process requires high performance H/W platform. Thus, the realtime learning of a large number of high dimensional samples within low-power devices is a challenging problem. In this paper, we attempt to establish this possibility by presenting a realtime neural network method on Raspberry pi using online sequential extreme learning machine. Our experiments on high-dimensional dataset show that the proposed method records an almost real-time execution.

• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2018년도 추계학술발표대회
• /
• pp.839-841
• /
• 2018

인공지능 기술을 활용하여 동물 소리를 분석하고 그 종을 구별하는 기술은 지역의 야생동물 현황 파악이나 생태계 조사 등에 효과적으로 사용될 수 있다. 인공지능 기술을 활용하기 위해서는 많은 동물 소리 샘플이 필요하지만, 현재 그러한 데이터는 녹음 환경이 고도화되어 있는 상용 DB나 전문가 DB 형태로 존재한다. 이러한 데이터만을 학습한 인공지능의 경우 실제 환경에서 녹음된 동물 소리를 식별하는 데 많은 어려움이 예상된다. 따라서 본 논문에서는 다양한 동물 소리를 수집하기 위해 동물 관련 전문가나 일반 사용자 모두 자유롭게 사용할 수 있는 동물 울음소리 수집과 분류를 위한 오픈 플랫폼을 제안한다. 플랫폼에 업로드된 소리 파일은 인공지능의 학습 데이터로 사용하며, 이 인공지능은 사용자에게 소리 파일을 분석한 결과로 해당 동물종과 그에 대한 다양한 생태정보를 제공하고 부가적으로 지역별 동물 통계 및 소리 파일에서의 소리 구간 추출, 소리 파일 공유 등 다양한 기능을 제공한다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 한국수자원학회 2021년도 학술발표회
• /
• pp.216-216
• /
• 2021

해저지진, 해저붕괴 및 해저화산분출 등에 발생되는 지진해일은 파장이 수십에서 수백 km에 이르는 장파로서 에너지 손실없이 먼 거리를 전파할 수 있으며, 수심이 상대적으로 얕은 해안가에 도달하면 범람에 의해 인명 및 재산피해를 야기시킬 수 있다. 예를 들어, 2004년 12월 26일에 발생한 수마트라 지진해일은 약 30만명의 인명피해와 약 10조원의 재산피해를 가져왔으며, 2011년 3월 11일에 발생한 동일본 지진해일은 약 2만명의 인명피해와 약 330조의 재산피해를 유발시켰다. 더욱이, 지진해일에 의해 폭발한 후쿠시마 원자력발전소에서의 방사능 유출은 10년이 지난 현재도 생태계 교란, 방사능 피폭 등의 피해를 일으키고 있다. 우리나라도 1983년 5월 26일 발생한 동해 중부지진해일에 의해 삼척시 임원항 및 인근에서 인명피해(1명 사망, 2명 실종)와 약 2억원의 재산피해가 발생하였다. 최근, 4차 산업혁명으로서 빅데이터를 기반으로 한 다양한 인공지능기술이 개발되고 있으며, 많은 분야에서 이 기술을 적용하고자 노력하고 있다. 특히, 과학 및 공학분야에서도 이를 융합하는 연구 및 활용하는 사례가 증가하고 있다. 본 연구에서는 1983년 발생한 중부지진해일에 의해 인명 및 재산피해가 발생한 임원항을 대상으로 지진해일 수치모형실험을 수행하며, 수치모형실험 결과를 토대로 인공지능 모델 중 합성신경망 (Convolution Neural Network)을 활용하여 인공지능을 통한 지진해일 범람구역을 산정 및 평가하고자 한다.

• Korean Journal of Microbiology
• /
• 제43권1호
• /
• pp.40-46
• /
• 2007

For restoration of disturbed ecosystem in Lake Paro, artificial floating island (AFI) was installed. Even though the lake water was oligo-mesotrophic, the macrophytes, such as Iris ensata, Iris pseudoacorus, Phragmites communis were growing well in the rubberized coconut fiber media. For elucidating this process, total bacterial numbers, active bacterial numbers and exoenzymatic activities of ${\beta}-glucosidase$ and phosphatase of pore water of media and lake water were analyzed. The average of total bacterial numbers, active bacterial numbers and exoenzymatic activities of ${\beta}-glucosidase$ and phosphatase were $28.6{\times}10^{6}\;cells/ml,\;22.7{\times}10^{6}\;cells/ml,\;452.9nM/L/hr,\;and\;16381.9nM/L/hr$ which were 10, 15, 22 and 38 times higher than those of lake water, respectively. Moreover, the total phosphorus and total nitrogen concentration of media showed high values of 0.82 mg/L and 7.0 mg/L, respectively, while those of lake water 0.07 mg/L and 2.3 mg/L. This results suggest that the bacteria was playing an important role for restoration of disturbed ecosystem with newly created microbial ecosystem in media of artificial floating island.