• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2015년도 춘계 종합학술대회 논문집
• /
• pp.15-16
• /
• 2015

Measuring sensor, equipment, ICT facilities and their software have relatively short life time comparing to constructional structure so that we should exchange or fix them continuously in the process of maintenance and management. In this paper, we propose a novel design of integrated maintenance, management, and measuring monitoring system applying the concept of mobile cloud. For the sake of disaster prevention for constructional structures such as bridge, tunnel, and other traditional buildings in the village of local heritage, we analyze status of these structures in the long term or short term period as well as disaster situations. Collecting data based on mobile cloud and analyzing future expectations based on probabilistic and statistical techniques, we implement our integrated monitoring system for constructional structures to solve these existing problems. Final results of this design and implementation are basically applied to the monitoring system for more than 10,000 structures spread over national land in Korea. In addition, we can specifically apply the monitoring system presented here to a bridge of timber structure in Asan Oeam Village and a traditional house in Andong Hahoe Village to watch them from possible disasters. Total procedure of system design and implementation as well as development of the platform LinkSaaS and application services of monitoring functions implemented on the platform. We prove a good performance of our system by fulfilling TTA authentication test, web accommodation test, and operation test using real measuring data.

• ALGAE
• /
• 제30권4호
• /
• pp.303-312
• /
• 2015

The intimate physical interaction between food algae and sacoglossan sea slug is a pertinent system to test the theory that “you are what you eat.” Some sacoglossan mollusks ingest and maintain chloroplasts that they acquire from the algae for photosynthesis. The basis of photosynthesis maintenance in these sea slugs was often explained by extensive horizontal gene transfer (HGT) from the food algae to the animal nucleus. Two large-scale expressed sequence tags databases of the green alga Bryopsis plumosa and sea slug Placida dendritica were established using 454 pyrosequencing. Comparison of the transcriptomes showed no possible case of putative HGT, except an actin gene from P. dendritica, designated as PdActin04, which showed 98.9% identity in DNA sequence with the complementary gene from B. plumosa, BpActin03. Highly conserved homologues of this actin gene were found from related green algae, but not in other photosynthetic sea slugs. Phylogenetic analysis showed incongruence between the gene and known organismal phylogenies of the two species. Our data suggest that HGT is not the primary reason underlying the maintenance of short-term kleptoplastidy in Placida dendritica.

• 한국축산식품학회지
• /
• 제37권1호
• /
• pp.98-104
• /
• 2017

The objective of this study was to determine the effects of short-term presalting on pink color and pigment characteristics in ground chicken breasts after cooking. Four salt levels (0%, 1%, 2%, and 3%) were presalted and stored for 0 and 3 d prior to cooking. Cooking yield was increased as salt level was increased. However, no significant differences in pH values or oxidation reduction potential (ORP) of cooked chicken breasts were observed. Cooked products with more than 2% of salt level had less redder (lower CIE $a^*$ value) on day 3 than on those on day 0. As salt level was increased to 2%, myoglobin was denatured greatly. Myoglobin denaturation was leveled off when samples had 3% of salt. With increasing salt levels, residual nitrite contents were increased while nitrosyl hemochrome contents were decreased. These results demonstrate that salt addition to a level of more than 2% to ground meat may reduce the redness of cooked products and that presalting storage longer than 3 d should be employed to develop a natural pink color of ground chicken products when less than 1% salt is added to ground chicken meat.

• 한국태양에너지학회 논문집
• /
• 제38권1호
• /
• pp.1-11
• /
• 2018

In this work, we propose weather prediction models to estimate hourly outdoor temperatures and solar irradiance in the next day using forecasting information. Hourly weather data predicted by the proposed models are useful for setting system operating strategies for the next day. The outside temperature prediction model considers 3-hourly temperatures forecasted by Korea Meteorological Administration. Hourly data are obtained by a simple interpolation scheme. The solar irradiance prediction is achieved by constructing a dataset with the observed cloudiness and correspondent solar irradiance during the last two weeks and then by matching the forecasted cloud factor for the next day with the solar irradiance values in the dataset. To verify the usefulness of the weather prediction models in predicting a short-term building load, the predicted data are inputted to a TRNSYS building model, and results are compared with a reference case. Results show that the test case can meet the acceptance error level defined by the ASHRAE guideline showing 8.8% in CVRMSE in spite of some inaccurate predictions for hourly weather data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4246-4267
• /
• 2020

As the network goes deep into all aspects of people's lives, the number and the complexity of network traffic is increasing, and traffic classification becomes more and more important. How to classify them effectively is an important prerequisite for network management and planning, and ensuring network security. With the continuous development of deep learning, more and more traffic classification begins to use it as the main method, which achieves better results than traditional classification methods. In this paper, we provide a comprehensive review of network traffic classification based on deep learning. Firstly, we introduce the research background and progress of network traffic classification. Then, we summarize and compare traffic classification based on deep learning such as stack autoencoder, one-dimensional convolution neural network, two-dimensional convolution neural network, three-dimensional convolution neural network, long short-term memory network and Deep Belief Networks. In addition, we compare traffic classification based on deep learning with other methods such as based on port number, deep packets detection and machine learning. Finally, the future research directions of network traffic classification based on deep learning are prospected.

• 대기
• /
• 제31권1호
• /
• pp.73-83
• /
• 2021

Numerical weather prediction (NWP) models play an essential role in predicting weather factors, but using them is challenging due to various factors. To overcome the difficulties of NWP models, deep learning models have been deployed in weather forecasting by several recent studies. This study adapts long short-term memory (LSTM), which demonstrates remarkable performance in time-series prediction. The combination of LSTM model input of meteorological features and activation functions have a significant impact on the performance therefore, the results from 5 combinations of input features and 4 activation functions are analyzed in 9 Automated Surface Observing System (ASOS) stations corresponding to cities/islands/mountains. The optimized LSTM model produces better performance within eight forecast hours than Local Data Assimilation and Prediction System (LDAPS) operated by Korean meteorological administration. Therefore, this study illustrates that this LSTM model can be usefully applied to very short-term weather forecasting, and further studies about CNN-LSTM model with 2-D spatial convolution neural network (CNN) coupled in LSTM are required for improvement.

• Geomechanics and Engineering
• /
• 제34권1호
• /
• pp.43-49
• /
• 2023

Knowledge of minimum horizontal stress (S_hmin) is a significant step in determining full stress tensor. It provides crucial information for the production of sand, hydraulic fracturing, determination of safe mud weight window, reservoir production behavior, and wellbore stability. Calculating the S_hmin using indirect methods has been proved to be awkward because a lot of data are required in all of these models. Also, direct techniques such as hydraulic fracturing are costly and time-consuming. To figure these problems out, this work aims to apply the long-short-term memory (LSTM) algorithm to S_hmin time-series prediction. 13956 datasets obtained from an oil well logging operation were applied in the models. 80% of the data were used for training, and 20% of the data were used for testing. In order to achieve the maximum accuracy of the LSTM model, its hyper-parameters were optimized significantly. Through different statistical indices, the LSTM model's performance was compared with with other machine learning methods. Finally, the optimized LSTM model was recommended for S_hmin prediction in the well logging operation.

• 대한원격탐사학회지
• /
• 제38권6_1호
• /
• pp.1047-1056
• /
• 2022

지구 온난화의 중요한 지시자인 북극의 바다 얼음인 해빙은 기후 시스템, 선박의 항로 안내, 어업 활동 등에서의 중요성으로 인해 다양한 학문 분야에서 관심을 받고 있다. 최근 자동화와 효율적인 미래 예측에 대한 요구가 커지면서 인공지능을 이용한 새로운 해빙 예측 모델들이 전통적인 수치 및 통계 예측 모델을 대체하기 위해 개발되고 있다. 본 연구에서는 북극 해빙의 전역적, 지역적 특징을 학습할 수 있는 two-stream convolutional long- and short-term memory (TS-ConvLSTM) 인공지능 모델의 북극 해빙 면적이 최저를 보이는 9월에 대해 2001년부터 2021년까지 장기적인 성능 검증을 통해 향후 운용 가능한 시스템으로써의 가능성을 살펴보고자 한다. 장기 자료를 통한 검증 결과 TS-ConvLSTM 모델이 훈련자료의 양이 증가하면서 향상된 예측 성능을 보여주고 있지만, 최근 지구 온난화로 인한 단년생 해빙의 감소로 인해 해빙 농도 5-50% 구간에서는 예측력이 저하되고 있음을 보여주었다. 반면 TS-ConvLSTM에 의해 예측된 해빙 면적과 달리 Sea Ice Prediction Network에 제출된 Sea Ice Outlook (SIO)들의 해빙 면적 중간값의 경우 훈련자료가 늘어나더라도 눈에 띄는 향상을 보이지 않았다. 본 연구를 통해 TS-ConvLSTM 모델의 향후 북극 해빙 예측 시스템의 운용 가능 잠재성을 확인하였으나, 향후 연구에서는 예측이 어려운 자연 환경에서 더욱 안정성 있는 예측 시스템 개발을 위해 더 많은 시공간 변화 패턴을 학습할 수 있는 방안을 고려해야 할 것이다.

• 한국항만경제학회지
• /
• 제37권3호
• /
• pp.19-34
• /
• 2021

여수광양항은 부산항, 인천항, 울산항, 평택당진항과 함께 국내 5대 항만으로써 남해안의 무역 거점의 역할을 담당하고 있다. 부산항에 이어 물동량 2위의 규모이며, 수출입 물동량 기준으로는 국내 최대의 항만이다. 세계 최대 규모의 화학산업단지인 여수화학산업단지를 주요 배후로 하여 고도성장을 거듭하여 왔으나, 최근에는 물동량의 증가세가 감소하고 있다. 이에 본 연구에서는 여수광양항의 발전을 위한 주요 발전전략을 발굴하고, 전략의 우선순위를 도출하고자 하였다. 이를 위해 AHP 분석기법을 이용하여 여수광양항의 발전전략을 운영 활성화, 인프라 구축, 정책지원의 3가지 대분류로 나누고 다시 기간별로 단·중기와 장기의 두 가지 측면에서 분석하였다. 분석결과, 단/중기정책에서는 '컨테이너부두 통합운영 및 경쟁력 강화'가 가장 중요한 것으로 평가되었다. 컨테이너 운영사의 통합 및 초대형 선박 입항에 대비한 항로개설, 대형크레인 설치 등이 필요할 것으로 판단된다. 장기정책에서는 '지역산업기반 고부가가치산업 육성'이 가장 중요한 것으로 평가되었다. 정착지원금제도 등을 통해 외부 지역의 기업 유치하기 위한 전략이 필요할 것으로 사료 된다. 본 연구의 결과는 여수광양항의 발전전략을 수립하고, 투자 우선순위를 정립하는데 활용될 수 있을 것으로 기대된다.

• 한국환경과학회지
• /
• 제18권8호
• /
• pp.877-883
• /
• 2009

This study has analyzed the scale, location, resource potential and feasibility of offshore wind farm scientifically and systematically based on the national wind map and GIS. For long-term wind power development, this study pursues siting strategy building, selection of target area and deciding development priority as well as the presenting a basis for assessment that are necessary for policy decision making by making theme layers under GIS environment. According to the analysis after organizing technological development by stages, even if only the most suitable sites are developed among the area of offshore wind farm candidates that can be developed under the current technological standard, it has been evaluated as being able to develop about 3 times of the wind power dissemination target until 2012. It is expected that about 5% of territorial water area can be developed in a short-term future while the southern offshore area possessing relatively favorable wind resource than the western offshore has been identified as the most feasible site. While about 23% of territorial water area has been classified as potential area for offshore wind farm development in a long-term future, even Jeju Island and offshore of Ulsan possessing excellent wind resource have been analyzed as feasible sites. The feasibility assessment of offshore wind lam development established by this study is expected to assist national strategy building for accomplishing the wind power dissemination target.