• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.6
• /
• pp.245-254
• /
• 2022

Proteins are the basic unit of all life activities, and understanding them is essential for studying life phenomena. Since the emergence of the machine learning methodology using artificial neural networks, many researchers have tried to predict the function of proteins using only protein sequences. Many combinations of deep learning models have been reported to academia, but the methods are different and there is no formal methodology, and they are tailored to different data, so there has never been a direct comparative analysis of which algorithms are more suitable for handling protein data. In this paper, the single model performance of each algorithm was compared and evaluated based on accuracy and speed by applying the same data to CNN, LSTM, and GRU models, which are the most frequently used representative algorithms in the convergence research field of predicting protein functions, and the final evaluation scale is presented as Micro Precision, Recall, and F1-score. The combined models CNN-LSTM and CNN-GRU models also were evaluated in the same way. Through this study, it was confirmed that the performance of LSTM as a single model is good in simple classification problems, overlapping CNN was suitable as a single model in complex classification problems, and the CNN-LSTM was relatively better as a combination model.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.1
• /
• pp.127-134
• /
• 2022

Recently, policies and research to prevent increasing construction accidents have been actively conducted in the domestic construction industry. In previous studies, the prediction model developed to prevent construction accidents mainly used only structured data, so various characteristics of construction sites are not sufficiently considered. Therefore, in this study, we developed a machine learning-based construction accident prediction model that enables the characteristics of construction sites to be considered sufficiently by using both structured and text-type unstructured data. In this study, 6,826 cases of construction accident data were collected from the Construction Safety Management Integrated Information (CSI) for machine learning. The Decision forest algorithm and the BERT language model were used to train structured and unstructured data respectively. As a result of analysis using both types of data, it was confirmed that the prediction accuracy was 95.41 %, which is improved by about 20 % compared to the case of using only structured data. Conclusively, the performance of the predictive model was effectively improved by using the unstructured data together, and construction accidents can be expected to be reduced through more accurate prediction.

• Journal of the Korean Institute of Gas
• /
• v.23 no.5
• /
• pp.52-58
• /
• 2019

In this study, we have developed a forecasting model for city- gas acceptance. City-gas corporations have to report about city-gas sale volume next year to KOGAS. So it is a important thing to them. Factors influenced city-gas have differences corresponding to usage classification, however, in city-gas acceptence, it is hard to classificate. So we have considered tha outside temperature as factor that influence regardless of usage classification and the model development was carried out. ARIMA, one of the traditional time series analysis, and LSTM, a deep running technique, were used to construct forecasting models, and various Ensemble techniques were used to minimize the disadvantages of these two methods.Experiments and validation were conducted using data from JB Corp. from 2008 to 2018 for 11 years.The average of the error rate of the daily forecast was 0.48% for Ensemble LSTM, the average of the error rate of the monthly forecast was 2.46% for Ensemble LSTM, And the absolute value of the error rate is 5.24% for Ensemble LSTM.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.10 no.1
• /
• pp.133-141
• /
• 1999

In this paper, we present an indoor propagation prediction model which is based on a three-dimensional ray-tracing technique. In this model, instead of considering all obstacles such as furnitures and fixtures, etc., only main obstacles to the propagation such as walls, ceiling and floors are modeled as slabs with finite thickness and conductivity, and the significant phenomena of propagation are considered, so we can calculate simply and predict accurately the propagation losses. The propagating rays are considered to be reflected and transmitted specularly at the boundaries of obstacles, and diffracted at edges. The reflection and transmission losses on flat obstacles are calculated by using ray tracing method, and the diffraction losses at edges are calculated by using the uniform theory of diffraction (UTD) for finite conductivity media. The results simulated for some cases by this propagation model good agree with the measured value of pathloss.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.4
• /
• pp.653-658
• /
• 2015

Cloud service is one of major challenges in IT industries. In cloud environment, service providers predict dynamic user demands and provision resources to guarantee the QoS to cloud users. The conventional prediction models guarantee the QoS to cloud user, but don't guarantee profit of service providers. In this paper, we propose a new resource allocation mechanism using Q-learning algorithm to provide the QoS to cloud user and guarantee profit of service providers. To evaluate the performance of our mechanism, we compare the total expense and the VM provisioning delay with the conventional techniques with real data.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.179-179
• /
• 2018

최근 기후변화에 대한 관심이 급증하면서 기후변화로 인한 여러 가지 문제점들이 드러나며 가뭄에 대한 관심도 증가하고 있다. 수자원 관리에 있어 가뭄 예측은 반드시 필요한 항목이다. 우리나라는 기후변화로 인해 강수량과 기온이 변화할 것으로 보이며, 이는 증발산량의 변화를 초래한다. 증발산량은 가뭄에 대한 중요한 인자 중 하나이며, 따라서 효율적인 수자원 관리를 위해 잠재증발산량(Potential Evapotranspiration, PET)의 변화를 예측하는 것은 반드시 필요하다고 할 수 있다. 미래의 잠재증발산량을 분석하고 예측하기 위해서는 주로 기후모델을 이용한 미래예측자료가 사용된다. 이에 본 연구에서는 다중 RCMs를 이용하여 미래 잠재증발산량의 변화를 추정하고자 하였다. 독일의 전지구기후모델(Global Climate Model)인 MPI-ESM-LR를 기반으로 다양한 지역기후모델(Regional Climate Model)로부터 생산된 미래 자료를 사용하였다. 사용된 RCM은 MM5, RSM, WRF이며, RCP 8.5 시나리오에 대하여 부산 지점에 해당하는 격자로부터 잠재증발산량 추정을 위한 기온, 풍속, 일사량, 상대습도를 추출하였다. 추출된 각 기상자료에 대해 Penman 방법을 적용하여 미래 잠재증발산량을 산정한 후 Quantile Mapping 기법을 이용하여 편의보정을 수행하였다. 산정된 미래 잠재증발산량을 분석한 결과, 부산지점의 경우 미래 잠재증발산량이 현재대비 다소 증가 할 것으로 나타났다. 따라서 이에 대한 대비가 필요할 것으로 판단된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.8-8
• /
• 2015

기후변화에 따른 집중호우 및 태풍 발생의 증가로 강우레이더를 이용한 홍수예경보시스템의 필요성이 증대되고 있다. 그러나 현재 국내에서 주로 활용되고 있는 단일편파 레이더는 정확도의 한계로 인해 홍수예보 활용에 어려움을 야기해왔다. 최근에는 수직반사도, 차등반사도, 비차등반사도 등 다양한 변수 취득을 통해 강우입자의 형태를 더욱 정확하게 추정할 수 있는 이중편파 레이더의 활용이 높아지고 있다. 본 연구에서는 홍수예보 활용을 위해 이중편파 레이더 실황강우 및 예측강우의 정확도를 평가하고자 한다. 평가를 위해 비슬산 레이더 자료를 활용하였으며, 2012~2014년의 강우사상을 선정하였다. 단일 및 이중편파 레이더 강우를 각각 추정하고, 강우예측을 위해 추정된 레이더 강우를 이류모델(Translation model)에 연계하여 선행 6시간까지의 예측강우를 생산하였다. 강우의 탐지능력 평가를 위해 Hit rate를 이용하였으며, 레이더 관측반경 증가 및 강우강도의 증가에 따른 정확도 분석을 수행하였다. 강수추정 정확도 평가를 위해 상관계수와 평균제곱근 오차를 이용하였으며, 비슬산 강우레이더 100 km 반경 내에 속한 국토교통부 관할의 지상관측강우와비교하였다. 그 결과, 이중편파 레이더 실황강우가 단일편파 레이더에 비해 지상관측강우의 거동과 더욱 유사하게 나타났으며, 양적인 오차도 더 적은 것으로 확인되었다. 또한, 레이더 예측강우는 선행시간이 증가함에 따라 정확도가 감소하였으나, 선행시간 1시간까지는 활용이 가능하다고 판단된다.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.450-452
• /
• 2020

기술의 발전과 함께 사용자에게 가까이 자리 잡은 소셜 네트워크 서비스는 이미지, 동영상, 텍스트 등 활용 가능한 데이터의 수를 폭발적으로 증가시켰다. 작성자의 감정을 포함하고 있는 텍스트 데이터는 시장 조사, 주가 예측 등 다양한 분야에서 이용할 수 있으며, 이로 인해 긍부정의 이진 분류가 아닌 다중 감정 분석의 필요성 또한 높아지고 있다. 본 논문에서는 딥러닝 기반 감정 분류에 심리학 이론의 기반 감정 모델을 활용한 결합 모델과 단일 모델을 비교한다. 학습을 위해 AI Hub에서 제공하는 데이터와 노래 가사 데이터를 복합적으로 사용하였으며, 결과에서는 대부분의 경우에 결합 모델이 높은 결과를 보였다.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.24 no.2
• /
• pp.193-200
• /
• 2011

A BOR(Boil-Off Rate) prediction model for the NO96 membrane-type LNG insulation containment filled with superlite powders during laden voyage is presented in this paper. Finite element model for the unsteady-state heat transfer analysis is constructed by considering the air and water conditions and by employing the homogenization method to simplify the complex insulation material composition. BOR is evaluated in terms of the total amount of heat invaded into LNGCC and its variation to the major variables is investigated by the parametric heat transfer analysis. Based upon the parametric results, a BOR prediction model which is in function of the LNG tank size, the insulation layer thickness and the powder thermal conductivity is derived. Through the verification experiment, the accuracy of the derived prediction model is justified such that the maximum relative difference is less than 1% when compared with the direct numerical estimation using the FEM analysis.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.9 no.1
• /
• pp.57-64
• /
• 2009

This study intends to evaluate of the characteristics of pavement deformation and develop the model for prediction model in the asphalt layer using a regression analysis. In test, there are two different asphalt binders and 5 different aggregate types. The air voids of hot mix asphalt are 6% and 10% for target value. Repeated triaxial compression test with 3 different confining pressures was used for test at 3 different test temperatures. It is going to verify the main parameters for permanent deformation of HMA and to develop the distress model. This paper is to figure out the factor affecting the pavement deformation, and then to develop model the pavement deformation for asphalt mixture. Also, the reliability of prediction model has been studied. The permanent deformation prediction model for asphalt mixtures with temperature, loading time, and air voids has been developed and the proposed permanent deformation prediction model has been validated by using the multiple regression approach which is called Statistical Package for the Social Sciences(SPSS).