• 대기
• /
• 제24권3호
• /
• pp.403-417
• /
• 2014

Future changes in seasonal mean temperature and precipitation over East Asia under anthropogenic global warming are investigated by comparing the historical run for 1979~2005 and the Representative Concentration Pathway (RCP) 4.5 run for 2006~2100 with 20 coupled models which participated in the phase five of Coupled Model Inter-comparison Project (CMIP5). Although an increase in future temperature over the East Asian monsoon region has been commonly accepted, the prediction of future precipitation under global warming still has considerable uncertainties with a large inter-model spread. Thus, we select best five models, based on the evaluation of models' performance in present climate for boreal summer and winter seasons, to reduce uncertainties in future projection. Overall, the CMIP5 models better simulate climatological temperature and precipitation over East Asia than the phase 3 of CMIP and the five best models' multi-model ensemble (B5MME) has better performance than all 20 models' multi-model ensemble (MME). Under anthropogenic global warming, significant increases are expected in both temperature and land-ocean thermal contrast over the entire East Asia region during both seasons for near and long term future. The contrast of future precipitation in winter between land and ocean will decrease over East Asia whereas that in summer particularly over the Korean Peninsula, associated with the Changma, will increase. Taking into account model validation and uncertainty estimation, this study has made an effort on providing a more reliable range of future change for temperature and precipitation particularly over the Korean Peninsula than previous studies.

• International Journal of Computer Science & Network Security
• /
• 제22권11호
• /
• pp.265-271
• /
• 2022

Social media is a form of communication based on the internet to share information through content and images. Their choice of profile images and type of image they post can be closely connected to their personality. The user posted images are designated as personality traits. The objective of this study is to predict five factor model personality dimensions from profile images by using deep learning and neural networks. Developed a deep learning framework-based neural network for personality prediction. The personality types of the Big Five Factor model can be quantified from user profile images. To measure the effectiveness, proposed two models using convolution Neural Networks to classify each personality of the user. Done performance analysis among two different models for efficiently predict personality traits from profile image. It was found that VGG-69 CNN models are best performing models for producing the classification accuracy of 91% to predict user personality traits.

• Geomechanics and Engineering
• /
• 제25권1호
• /
• pp.1-16
• /
• 2021

Machine learning models have been widely used for landslide susceptibility assessment (LSA) in recent years. The large number of inputs or conditioning factors for these models, however, can reduce the computation efficiency and increase the difficulty in collecting data. Feature selection is a good tool to address this problem by selecting the most important features among all factors to reduce the size of the input variables. However, two important questions need to be solved: (1) how do feature selection methods affect the performance of machine learning models? and (2) which feature selection method is the most suitable for a given machine learning model? This paper aims to address these two questions by comparing the predictive performance of 13 feature selection-based machine learning (FS-ML) models and 5 ordinary machine learning models on LSA. First, five commonly used machine learning models (i.e., logistic regression, support vector machine, artificial neural network, Gaussian process and random forest) and six typical feature selection methods in the literature are adopted to constitute the proposed models. Then, fifteen conditioning factors are chosen as input variables and 1,017 landslides are used as recorded data. Next, feature selection methods are used to obtain the importance of the conditioning factors to create feature subsets, based on which 13 FS-ML models are constructed. For each of the machine learning models, a best optimized FS-ML model is selected according to the area under curve value. Finally, five optimal FS-ML models are obtained and applied to the LSA of the studied area. The predictive abilities of the FS-ML models on LSA are verified and compared through the receive operating characteristic curve and statistical indicators such as sensitivity, specificity and accuracy. The results showed that different feature selection methods have different effects on the performance of LSA machine learning models. FS-ML models generally outperform the ordinary machine learning models. The best FS-ML model is the recursive feature elimination (RFE) optimized RF, and RFE is an optimal method for feature selection.

• 한국식품저장유통학회지
• /
• 제3권1호
• /
• pp.39-53
• /
• 1996

Ginseng, one of the important economic crops, is processed into medicine, teas, beverages and even foods. Drying is the most important and burdensome work in the processing of ginseng, so development of ginseng dryer is needed for efficient drying and good quality of ginseng. Investigation of drying model is essential for development of ginseng dryer. Drying models for peeled ginseng were investigated to determine dominant drying factors and fitted with five selected drying models and an empirical model. Thompson and the empirical model showed best fit with the experimental data. Pother experiment is necessary to prove the superiority of the empirical models.

• 한국해안·해양공학회논문집
• /
• 제34권3호
• /
• pp.72-81
• /
• 2022

본 연구는 제주도 남서부 해역의 표류체 이동 예측을 위해 2020년 8월 제주도 남서부 5개 지점에서 투하된 표층 뜰개 위치자료와 수치모델 예측자료를 학습자료로 이용한 인공지능 기반 입자추적 모델 5개를 구축하였다. 구축된 AI 기법은 기계학습 3종(Extra Trees, LightGBM, Support Vector Machine)과 딥러닝 2종(DNN, RBFN)이다. 또한 해수유동 수치모델 입자추적 예측자료 1종 및 AI 기법 입자추적 예측자료 5종을 표층 뜰개 관측자료와 비교하여 각 예측모델별 예측 정확도를 평가하였다. 6종 모델의 예측 정확도를 평가하기 위해, 5개 정점에 대한 3개 스킬량(MAE, RMSE, NCLS)의 평균값을 비교 검토하였다. 최종적인 결과로서 딥러닝 DNN 모델이 MAE, RMSE, NCLS에서 다른 모델보다 가장 우수하게 나타났다.

• Structural Engineering and Mechanics
• /
• 제89권3호
• /
• pp.283-300
• /
• 2024

Machine learning (ML) models based on artificial neural network (ANN) and decision tree (DT) were developed for estimation of axial capacity of concrete columns reinforced with fiber reinforced polymer (FRP) bars. Between the design codes, the Canadian code provides better formulation compared to the Australian or American code. For empirical models based on elastic modulus of FRP, Hadhood et al. (2017) model performed best. Whereas for empirical models based on tensile strength of FRP, as well as all empirical models, Raza et al. (2021) was adjudged superior. However, compared to the empirical models, all ML models exhibited superior performance according to all five performance metrics considered. The performance of ANN and DT models were comparable in general. Under the present setup, inclusion of the transverse reinforcement information did not improve the accuracy of estimation with either ANN or DT. With selective use of inputs, and a much simpler ANN architecture (4-3-1) compared to that reported in literature (Raza et al. 2020: 6-11-11-1), marginal improvement in correlation could be achieved. The metrics for the best model from the study was a correlation of 0.94, absolute errors between 420 kN to 530 kN, and the range being 0.39 to 0.51 for relative errors. Though much superior performance could be obtained using ANN/DT models over empirical models, further work towards improving accuracy of the estimation is indicated before design of FRP reinforced concrete columns using ML may be considered for design codes.

• 대기
• /
• 제25권2호
• /
• pp.249-260
• /
• 2015

The changes in thermodynamic and dynamic aspects on near (2025~2049) and long-term (2075~2099) future climate changes between the historical run (1979~2005) and the Representative Concentration Pathway (RCP) 4.5 run with 20 coupled models which employed in the phase five of Coupled Model Inter-comparison Project (CMIP5) over East Asia (EA) and the Korean Peninsula are investigated as an extended study for Moon et al. (2014) study noted that the 20 models' multi-model ensemble (MME) and best five models' multi-model ensemble (B5MME) have a different increasing trend of precipitation during the boreal winter and summer, in spite of a similar increasing trend of surface air temperature, especially over the Korean Peninsula. Comparing the MME and B5MME, the dynamic factor (the convergence of mean moisture by anomalous wind) and the thermodynamic factor (the convergence of anomalous moisture by mean wind) in terms of moisture flux convergence are analyzed. As a result, the dynamic factor causes the lower increasing trend of precipitation in B5MME than the MME during the boreal winter and summer over EA. However, over the Korean Peninsula, the dynamic factor causes the lower increasing trend of precipitation in B5MME than the MME during the boreal winter, whereas the thermodynamic factor causes the higher increasing trend of precipitation in B5MME than the MME during the boreal summer. Therefore, it can be noted that the difference between MME and B5MME on the change in precipitation is affected by dynamic (thermodynamic) factor during the boreal winter (summer) over the Korean Peninsula.

• 한국의상디자인학회지
• /
• 제10권1호
• /
• pp.125-134
• /
• 2008

Consumers' need for uniqueness reflects individual differences in counterconformity and related to the attitude toward brands as well as purchase behavior. To understand the relationship between consumer's personal characteristics and purchase behavior, the study investigated the effect of consumers' need for uniqueness and clothing interest on the brand consciousness, loyalty and purchase intention. Survey was utilized to collect the data and subjects were 271 college students. Measures consisted of five main constructs: Consumer's need for uniqueness, clothing interest, brand consciousness, brand loyalty, and purchase intention. The measurement and structural models were evaluated using PRELIS 2 and LISREL 8.53. Consumer's need for uniqueness was confirmed to have three constructs: creative, unpopular, and avoidance. The researcher tested Model 1 and developed five other models-Models 2 through 6-based on the results from Model 1 evaluation. The additional Models 2 through 6 were nested in Model 1. To select a best model, the researcher compared the value of chi-square, RMSEA, GFI, AIC, and ECVI. Since Model 6 also illustrated conceptually or theoretically reasonable relationships among constructs as well, it was finally selected as a best model. In the Model 6, the creative dimension of consumer's need for uniqueness had a negative relationship with brand loyalty, while the avoidance dimension of consumer's need for uniqueness had positive relationship. The unpopular dimension of consumer's need for uniqueness and clothing interest had significant positive effects on the brand consciousness. The brand consciousness was significantly related to brand loyalty and brand loyalty to purchase intention.

• 천문학회지
• /
• 제22권1호
• /
• pp.1-24
• /
• 1989

By applying population synthesis method, stellar populations in the nuclei of M31 and M32 are studied. We obtained five and four models for M31 and M32 respectively, for different main sequence turn-offs and keeping the astrophysical constraints as loose as possible. The best models for M31 and M32 are thought to have G0-5 and F5-8 main sequence trun-offs respectively. These models show that the main sequence stars outnumber the giants, which indicates the dwarf-dominance in external galactic nuclei. Even though there are some computational difficulties because of non-uniqueness in solution, two major points can be pointed out when compared to the previous papers. First, the ultraviolet deficiency expected from the conventional metal rich population models is not detected in our models, Instead ultraviolet radiation turns out to be somewhat higher than that of observation. Second one is the minor contribution from the Super Metal Rich (SMR) K giants to the integrated light of the program galaxies. That is, in our models, the SMR contribution is at best the same level as normal giants contrary to the SMR dominance of previous models. Since the loose astrophysical constraints are the major difference of our study from the previous ones, one should re-examine carefully for their validity further.

• 대한교통학회지
• /
• 제14권2호
• /
• pp.7-29
• /
• 1996

Traffic flow characteristics is analysed on eight multi-lane roads which are unsignalized in urban areas. Data of traffic flow rates by classification and average speed were gathered every ten minutes interval for twenty-four hours. Machine (NC-90A) was used to acquire the field data. The major purpose of this study is to build up speed-density models on urban arterial roads. Five different kinds of models were tested. Those models are Greenshields' model, Greenberg's model, modified Greenberg's model, Underwood's model and Drake's model. The modified Greenberg's model fits best at six points and the Greenshield's model fits best two points out of eight points. The breakpoint(Kb) of modified Greenberg's model is between 10 and 32 pcphpl. Capacity drawn from speed-volume relationships were appeared to be arround 2,000 and 2,200 pcphpl at the Hannam Bridge and the Hannam Overpass and 1,100 and 1,700 pcphpl at Namsan Tunnel(No1) and the beginning point of Gyeong-Bu Expressway.