• Earthquakes and Structures
• /
• 제25권1호
• /
• pp.15-26
• /
• 2023

It is of great importance to assess the residual displacement demand in the performance-based seismic design. In this paper, a hybrid deep learning model for predicting the residual displacement spectra under near-fault (NF) ground motions is proposed by combining the long short-term memory network (LSTM) and back-propagation (BP) network. The model is featured by its capacity of predicting the residual displacement spectrum under a given NF ground motion while considering the effects of structural parameters. To construct this model, 315 natural and artificial NF ground motions were employed to compute the residual displacement spectra through elastoplastic time history analysis considering different structural parameters. Based on the resulted dataset with a total of 9,450 samples, the proposed model was finally trained and tested. The results show that the proposed model has a satisfactory accuracy as well as a high efficiency in predicting residual displacement spectra under given NF ground motions while considering the impacts of structural parameters.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2004년도 추계학술대회 논문집
• /
• pp.1671-1676
• /
• 2004

This thesis watches for the present condition of both economic exchange and goods transport between South and North Korea focused on material side as a provision for the railway connection between them. This is also a predicting thesis for a smooth goods transport in case of setting up a goods transport system between south and North Korea predicting transport demand for the connection of a railway and road studying fundamental facilities and transport related laws.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2003년도 춘계학술대회 논문집
• /
• pp.190-195
• /
• 2003

This thesis watches for the present condition of both economic exchange and goods transport between South and North Korea focused on material side as a provision for the railway connection between them. This is also a predicting thesis for a smooth goods transport in case of setting up a goords transport system between south and North Korea predicting transport demand for the connection of a railway and road studying fundamental facilities and transport related laws.

• Structural Engineering and Mechanics
• /
• 제23권2호
• /
• pp.177-193
• /
• 2006

Determining the hysteretic energy demand and dissipation capacity and level of damage of the structure to a predefined earthquake ground motion is a highly non-linear problem and is one of the questions involved in predicting the structure's response for low-performance levels (life safe, near collapse, collapse) in performance-based earthquake resistant design. Neural Network (NN) analysis offers an alternative approach for investigation of non-linear relationships in engineering problems. The results of NN yield a more realistic and accurate prediction. A NN model can help the engineer to predict the seismic performance of the structure and to design the structural elements, even when there is not adequate information at the early stages of the design process. The principal aim of this study is to develop and test multi-layered feedforward NNs trained with the back-propagation algorithm to model the non-linear relationship between the structural and ground motion parameters and the hysteretic energy demand in steel moment resisting frames. The approach adapted in this study was shown to be capable of providing accurate estimates of hysteretic energy demand by using the six design parameters.

• 한국IT서비스학회지
• /
• 제14권4호
• /
• pp.185-197
• /
• 2015

As the uncertainty of demand in B2B electronics market has increased, firms need a strong method to estimate the market demand. An accurate prediction on the market demand is crucial for a firm not to overproduce or underproduce its goods, which would influence the performance of the firm. However, it is complicated to estimate the demand in a B2B market, particularly for the private sector, because firms are very diverse in terms of size, industry, and types of business. This study proposes both qualitative and quantitative demand forecasting approaches for B2B PC products. Four different measures for predicting PC products in B2B market with consideration of the different PC uses-personal work, common work, promotion, and welfare-are developed as the qualitative model's input variables. These measures are verified by survey data collected from experts in 139 firms, and can be applied when individual firms estimate the demand of PC goods in a B2B market. As the quantitative approach, the multiple regression model is proposed and it includes variables of region, type of industry, and size of the firm. The regression model can be applied when the aggregated demand for overall domestic PC market needs to be estimated.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제3권7호
• /
• pp.263-270
• /
• 2014

본 논문에서는 영화의 흥행을 예측하기 위한 방법을 제안한다. 최근 영화시장이 성장함에 따라 시장의 수요를 예측하기 위한 다양한 연구들이 수행되고 있다. 영화는 비교적 수명주기가 짧은 문화상품이다. 따라서 안정적인 수익을 창출하기 위해 개봉 전 마케팅비용 및 개봉 후 스크린 수 등에 대한 설계가 필요하다. 이를 위해서는 상품의 수요와 경제적인 수익규모에 대한 계산이 선행되어야 한다. 기존 관련 연구들의 경우 예측을 위한 변수로서 주로 영화 자체의 속성들이나 시장에서의 경쟁요인 등을 이용한다. 그러나 정작 상품을 구매하는 주체인 잠재관객들에 대한 비중은 비교적 미비하다. 따라서 본 논문에서는 사람들이 가진 영화에 대한 인지도를 고려하기 위해 트위터를 하나의 설문표본으로서 활용했다. 기존에 사용된 변수들과 트위터에서 추출한 정보를 오프라인 요소와 온라인 요소로 정의하고, 두 요소를 취합하여 기계학습을 적용했다. 실험을 통해 본 논문에서 제시하는 예측기법을 검증했으며, 실험결과 약 95%의 정확도로 영화의 흥행을 예측했다.

• 한국인공지능학회지
• /
• 제10권1호
• /
• pp.27-32
• /
• 2022

As the need for eco-friendly transportation increases due to the deepening climate crisis, many local governments in Korea are introducing shared bicycles. Due to anxiety about public transportation after COVID-19, bicycles have firmly established themselves as the axis of daily transportation. The use of shared bicycles is spread, and the demand for bicycles is increasing by rental offices, but there are operational and management difficulties because the demand is managed under a limited budget. And unfortunately, user behavior results in a spatial imbalance of the bike inventory over time. So, in order to easily operate the maintenance of shared bicycles in Seoul, bicycles should be prepared in large quantities at a time of high demand and withdrawn at a low time. Therefore, in this study, by using machine learning, the linear regression algorithm and MS Azure ML are used to predict and analyze when demand is high. As a result of the analysis, the demand for bicycles in 2018 is on the rise compared to 2017, and the demand is lower in winter than in spring, summer, and fall. It can be judged that this linear regression-based prediction can reduce maintenance and management costs in a shared society and increase user convenience. In a further study, we will focus on shared bike routes by using GPS tracking systems. Through the data found, the route used by most people will be analyzed to derive the optimal route when installing a bicycle-only road.

• 한국태양광발전학회지
• /
• 제4권2호
• /
• pp.45-53
• /
• 2018

Natural gas demand for power generation continued to increase until 2013 due to the expansion of large-scale LNG power plants after the black-out of 2011. However, natural gas demand for power generation has decreased sharply due to the increase of nuclear power and coal power generation. But demand for power generation has increased again as energy policies have changed, such as reducing nuclear power and coal power plants, and abnormal high temperatures and cold waves have occurred. If the gas pipeline pressure can be properly maintained by predicting these fluctuations, it can contribute to enhancement of operation efficiency by minimizing the operation time of facilities required for production and supply. In this study, we have developed a regression model with daily power demand and base power generation capacity as explanatory variables considering characteristics by day of week. The model was constructed using data from January 2013 to December 2016, and it was confirmed that the error rate was 4.12% and the error rate in the 90th percentile was below 8.85%.

• 한국수소및신에너지학회논문집
• /
• 제33권5호
• /
• pp.591-597
• /
• 2022

Recently, technologies for efficient power grid operation have become important due to climate change. For this reason, predicting power demand using deep learning is being considered, and it is necessary to understand the influence of characteristics of each region, industrial structure, and climate. This study analyzed the power demand of New Jersey in US, with a high urbanization rate and a large service industry, and West Virginia in US, a low urbanization rate and a large coal, energy, and chemical industries. Using recurrent neural network algorithm, the power demand from January 2020 to August 2022 was learned, and the daily and weekly power demand was predicted. In addition, the power grid operation based on the power demand forecast was discussed. Unlike previous studies that have focused on the deep learning algorithm itself, this study analyzes the regional power demand characteristics and deep learning algorithm application, and power grid operation strategy.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2022년도 학술발표회
• /
• pp.156-156
• /
• 2022

Explicitly spatially distributed and reliable data on industrial water demand is very much important for both policy makers and researchers in order to carry a region-specific analysis of water resources management. However, such type of data remains scarce particularly in underdeveloped and developing countries. Current research is limited in using different spatially available socio-economic, climate data and geographical data from different sources in accordance to predict industrial water demand at finer resolution. This study proposes a random forest regression (RFR) model to predict the industrial water demand at 0.50× 0.50 spatial resolution by combining various features extracted from multiple data sources. The dataset used here include National Polar-orbiting Partnership (NPP)/Visible Infrared Imaging Radiometer Suite (VIIRS) night-time light (NTL), Global Power Plant database, AQUASTAT country-wise industrial water use data, Elevation data, Gross Domestic Product (GDP), Road density, Crop land, Population, Precipitation, Temperature, and Aridity. Compared with traditional regression algorithms, RF shows the advantages of high prediction accuracy, not requiring assumptions of a prior probability distribution, and the capacity to analyses variable importance. The final RF model was fitted using the parameter settings of ntree = 300 and mtry = 2. As a result, determinate coefficients value of 0.547 is achieved. The variable importance of the independent variables e.g. night light data, elevation data, GDP and population data used in the training purpose of RF model plays the major role in predicting the industrial water demand.