• 설비공학논문집
• /
• 제26권5호
• /
• pp.231-239
• /
• 2014

This paper represents a method of existing building energy simulation using energy audit data. Energy audit must be carried out for reasonable analysis, because characteristics of existing buildings such as efficiency of fan, pump, flow rate, pressure, COP and operating schedule could be changed during the building operation. These building characteristics should be measured to estimate actual energy consumption of the existing building. In this study, we conducted energy audit and calculated energy savings for a 7-stories building as a case-study. The energy audit data were used to calibrate the building model of EnergyPlus simulation. Baseline model validated according to M&V guideline index. As a result, building characteristics are significant parameters making a big impact on energy savings in existing buildings.

• 한국IT서비스학회지
• /
• 제21권5호
• /
• pp.15-28
• /
• 2022

Recently, government agencies are actively adopting the platform model as a means of public policy. However, existing studies on the public platform are minimal and have focused on user experiences or the possibility of public usage of the platform model. Now the research concerning building governance structure and utilizing network effects of the platform after adopting the platform model in the public sector is keenly required. This study intended to ignite academic dialogue on the governance of public platforms in the context of digital transformation. This study focused on a case of the 'Special delivery,' a public delivery app established by Gyeonggi-do. In order to analyze the characteristics of the public platform and its governance structure, data were collected from press releases, policy reports, and news articles. Data was analyzed using the frame of Hagui's platform design factors and Ansell & Gash's collaborative governance model. The results of the public platform analyses showed 1) incompleteness in the value trade-off accounting, which was designed for platform business based on general cost-benefit analysis, and 2) a closed governance structure that limits direct participation of diverse user groups(i.e., service provider, customer) in order to enhance providers' utility by preventing customers' excessive online activities. The results of this study provided theoretical and policy implications regarding designing the strategy for accounting for value trade-offs and functioning governance structure for public platforms.

• 한국군사과학기술학회지
• /
• 제25권5호
• /
• pp.513-521
• /
• 2022

This study deals with an AI architecture model for collecting battlefield data using the tactical C4I system. Based on this model, the artificial staff can be utilized in tactical echelon. In the current structure of the Army's tactical C4I system, Servers are operated by brigade level and above and divided into an active and a standby server. In this C4I system structure, the AI server must also be installed in each unit and must be switched when the C4I server is switched. The tactical C4I system operates a server(DB) for each unit, so data matching is partially delayed or some data is not matched in the inter-working process between servers. To solve these issues, this study presents an operation concept so that all of alternate server can be integrated based on virtualization technology, which is used as an source data for AI Meta DB. In doing so, this study can provide criteria for the AI architectural model of the ground tactical echelon.

• Structural Engineering and Mechanics
• /
• 제88권5호
• /
• pp.493-500
• /
• 2023

The multiparameter eigenvalue method can be used to solve the damped finite element model updating problems. This method transforms the original problems into multiparameter eigenvalue problems. Comparing with the numerical methods based on various optimization methods, a big advantage of this method is that it can provide all possible choices of physical parameters. However, when solving the transformed singular multiparameter eigenvalue problem, the proposed method based on the generalised inverse of a singular matrix has some computational challenges and may fail. In this paper, more details on the transformation from the dynamic model updating problem to the multiparameter eigenvalue problem are presented and the structure of the transformed problem is also exposed. Based on this structure, the rigorous mathematical deduction gives the upper bound of the number of possible choices of the physical parameters, which confirms the singularity of the transformed multiparameter eigenvalue problem. More importantly, we present a row and column compression method to overcome the defect of the proposed numerical method based on the generalised inverse of a singular matrix. Also, two numerical experiments are presented to validate the feasibility and effectiveness of our method.

• Membrane and Water Treatment
• /
• 제13권5호
• /
• pp.219-225
• /
• 2022

5th Assessment Report of the Intergovernmental Panel on Climate Change Weather (AR5) predicts that recent severe hydrological events will affect the quality of water and increase water pollution. To analyze changes in water quality due to future climate change, input data (precipitation, average temperature, relative humidity, average wind speed, and solar radiation) were compiled into a representative concentration curve (RC), defined using 8.5. AR5 and future use are calculated based on land use. Semi-distributed emission model Calculate emissions for each target period. Meteorological factors affecting water quality (precipitation, temperature, and flow) were input into a multiple linear regression (MLR) model and an artificial neural network (ANN) to analyze the data. Extensive experimental studies of flow properties have been carried out. In addition, an Acoustic Doppler Velocity (ADV) device was used to monitor the flow of a large open channel connection in a wastewater treatment plant in Ho Chi Minh City. Observations were made along different streams at different locations and at different depths. Analysis of measurement data shows average speed profile, aspect ratio, vertical position Measure, and ratio the vertical to bottom distance for maximum speed and water depth. This result indicates that the transport effect of the compound was considered when preparing the hazard analysis.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제5권2호
• /
• pp.95-106
• /
• 2016

생체 데이터는 사람에 따라 다르게 나타날 수 있고 사상의학과 밀접한 관계를 가지고 있다. 생체 데이터는 사람의 맥박과 혈압, 심박동 수와 과거의 병력, 노화의 정도, 체질량 지수 등을 의미하며, 이 생체 데이터는 사람의 건강상태를 판별하기 위한 기준 척도로 활용된다. 그렇기 때문에 생체 데이터는 사용하고자 하는 목적에 맞도록 가공되어야 한다. 기존 연구에서는 실시간으로 변화되고 있는 생체 데이터를 현재 시점의 스냅셧으로만 적용하고 있기 때문에 시간의 연속성이 배제되어 있다. 따라서 이 문제를 해결하기 위하여 본 논문에서는 생체 데이터들로 구성되는 Big Data 환경에서 시간의 연속성을 포함하는 생체데이터의 패턴분석 모델을 제안한다. 제안 모델은 치료와 건강증진을 위해 전자침을 사용할 때 침자리의 선정을 신중하게 결정하는데 도움을 줄 수 있다.

• 한국멀티미디어학회논문지
• /
• 제25권5호
• /
• pp.748-756
• /
• 2022

Thanks to the competition of AlphaGo and Sedol Lee, machine learning has received world-wide attention and huge investments. The performance improvement of computing devices greatly contributed to big data processing and the development of neural networks. Artificial intelligence not only imitates human beings in many fields, but also seems to be better than human capabilities. Although humans' creation is still considered to be better and higher, several artificial intelligences continue to challenge human creativity. The quality of some creative outcomes by AI is as good as the real ones produced by human beings. Sometimes they are not distinguishable, because the neural network has the competence to learn the common features contained in big data and copy them. In order to confirm whether artificial intelligence can express the inherent characteristics of different arts, this paper proposes a new neural network model called Humming. It is an experimental model that combines vgg16, which extracts image features, and DeepJ's architecture, which excels in creating various genres of music. A dataset produced by our experiment shows meaningful and valid results. Different results, however, are produced when the amount of data is increased. The neural network produced a similar pattern of music even though it was a different classification of images, which was not what we were aiming for. However, these new attempts may have explicit significance as a starting point for feature transfer that will be further studied.

• 대한치매학회지
• /
• 제22권4호
• /
• pp.121-129
• /
• 2023

Background and Purpose: As it becomes an aging society, interest in senile diseases is increasing. Alzheimer's dementia (AD) and osteoporosis are representative senile diseases. Various studies have reported that AD and osteoporosis share many risk factors that affect each other's incidence. This aimed to determine if active medication treatment of AD could affect the development of osteoporosis. Methods: The Health Insurance Review and Assessment Service provided data consisting of diagnosis, demographics, prescription drug, procedures, medical materials, and healthcare resources. In this study, data of all AD patients in South Korea who were registered under the national health insurance system were obtained. The cohort underwent conversion to an Observational Medical Outcomes Partnership-Common Data Model version 5 format. Results: This study included 11,355 individuals in the good persistent group and an equal number of 11,355 individuals in the poor persistent group from the National Health Claims database for AD drug treatment. In primary analysis, the risk of osteoporosis was significantly higher in the poor persistence group than in the good persistence group (hazard ratio, 1.20 [95% confidence interval, 1.09-1.32]; p<0.001). Conclusions: We found that the good persistence group treated with anti-dementia drugs for AD was associated with a significant lower risk of osteoporosis in this nationwide study. Further studies are needed to clarify the pathophysiological link in patients with two chronic diseases.

• 정보보호학회논문지
• /
• 제32권5호
• /
• pp.817-826
• /
• 2022

AI 기술이 여러 분야에 성공적으로 도입되는 추세이며, 서비스로 환경에 배포된 모델들은 지적 재산권과 데이터를 보호하기 위해 모델의 정보를 노출시키지 않는 블랙 박스 상태로 배포된다. 블랙 박스 환경에서 공격자들은 모델 출력을 이용해 학습에 쓰인 데이터나 파라미터를 훔치려고 한다. 본 논문은 딥러닝 모델을 대상으로 모델 종류에 대한 정보를 추론하는 공격이 없다는 점에서 착안하여, 모델의 구성 레이어 정보를 직접 알아내기 위해 모델의 종류를 추론하는 공격 방법을 제안한다. MNIST 데이터셋으로 학습된 ResNet, VGGNet, AlexNet과 간단한 컨볼루션 신경망 모델까지 네 가지 모델의 그레이 박스 및 블랙 박스 환경에서의 출력값을 이용해 모델의 종류가 추론될 수 있다는 것을 보였다. 또한 본 논문이 제안하는 방식인 대소 관계 피쳐를 딥러닝 모델에 함께 학습시킨 경우 블랙 박스 환경에서 약 83%의 정확도로 모델의 종류를 추론했으며, 그 결과를 통해 공격자에게 확률 벡터가 아닌 제한된 정보만 제공되는 상황에서도 모델 종류가 추론될 수 있음을 보였다.

• 한국빅데이터학회지
• /
• 제5권2호
• /
• pp.17-27
• /
• 2020

지역난방 시스템은 서비스 지역 내 열 수요처들을 네트워크로 연결하여 중앙의 저비용 고효율 열 생산설비를 통해 열을 공급하는 에너지 시스템이다. 효율적인 열 공급 시시스템 운영을 위하여 지역 내 열 수요를 정확하게 예측하고 이를 바탕으로 열 생산 계획을 최적화하는 것이 중요하다. 본 연구에서는 지역 내 열수요처별 열 사용량 패턴에 대한 빅데이터 정보로 기계실별 실시간 열량계 정보를 반영한 열수요 예측모형을 제시하였다. 기존에도 열 수요예측에 활용되던 지역 전체 열수요 실적 합계와 함께 수요처별로 설치되어 있는 열량계로부터 실시간으로 수집한 개별 열수요 실적을 예측모형에 반영함으로써 열 수요처별로 상이한 열사용 패턴을 반영한 열 수요 예측이 가능할 것으로 기대된다. 지역난방 기업의 실제 열수요 실적을 바탕으로 열수요 예측 정확도를 측정한 결과 계절에 상관없이 기본 모형 대비 열량계 빅데이터를 반영할 경우 정확도가 올라가는 것으로 분석되었으며, 향후 열수요처별 다양한 형태의 데이터를 추가로 반영함으로써 열 수요 예측 정확도 향상이 가능할 것으로 예측된다.