• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.60-79
• /
• 2022

The U-Net architecture-based segmentation models attained remarkable performance in numerous medical image segmentation missions like skin lesion segmentation. Nevertheless, the resolution gradually decreases and the loss of spatial information increases with deeper network. The fusion of adjacent layers is not enough to make up for the lost spatial information, thus resulting in errors of segmentation boundary so as to decline the accuracy of segmentation. To tackle the issue, we propose a new deep learning-based segmentation model. In the decoding stage, the feature channels of each decoding unit are concatenated with all the feature channels of the upper coding unit. Which is done in order to ensure the segmentation effect by integrating spatial and semantic information, and promotes the robustness and generalization of our model by combining the atrous spatial pyramid pooling (ASPP) module and channel attention module (CAM). Extensive experiments on ISIC2016 and ISIC2017 common datasets proved that our model implements well and outperforms compared segmentation models for skin lesion segmentation.

• Asia Marketing Journal
• /
• v.17 no.1
• /
• pp.55-67
• /
• 2015

Despite the well-known predictive power of Dirichlet model on customer loyalty, deviations of share of category requirement (SCR) predicted by Dirichlet model from actual SCR have been repeatedly reported. It has been shown that these deviations can be systematically explained by some factors such as brand's market share, product positioning strategy, purchase volume and retail marketing mix strategies. Presuming that brand equity would be additional sources of these deviations, current study assesses the incremental predictive power of brand equity by using over 4,000 brand-level observations for the consumer packaged goods industry in the U.S. Our model estimations indicate that brands that exhibit higher brand equity enjoy excess loyalty, with the primary driver being volume premium, rather than price premium. Overall, our findings support the notion that idiosyncratic brand properties can explain excess behavioral loyalty, a notion that is in stark contrast with the Dirichlet view of the world: brand equity does not exist.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.1
• /
• pp.105-115
• /
• 2016

Ensemble classification involves combining individually trained classifiers to yield more accurate prediction, compared with individual models. Ensemble techniques are very useful for improving the generalization ability of classifiers. The random subspace ensemble technique is a simple but effective method for constructing ensemble classifiers; it involves randomly drawing some of the features from each classifier in the ensemble. The instance selection technique involves selecting critical instances while deleting and removing irrelevant and noisy instances from the original dataset. The instance selection and random subspace methods are both well known in the field of data mining and have proven to be very effective in many applications. However, few studies have focused on integrating the instance selection and random subspace methods. Therefore, this study proposed a new hybrid ensemble model that integrates instance selection and random subspace techniques using genetic algorithms (GAs) to improve the performance of a random subspace ensemble model. GAs are used to select optimal (or near optimal) instances, which are used as input data for the random subspace ensemble model. The proposed model was applied to both Kaggle credit data and corporate credit data, and the results were compared with those of other models to investigate performance in terms of classification accuracy, levels of diversity, and average classification rates of base classifiers in the ensemble. The experimental results demonstrated that the proposed model outperformed other models including the single model, the instance selection model, and the original random subspace ensemble model.

• Smart Structures and Systems
• /
• v.29 no.5
• /
• pp.729-746
• /
• 2022

In this paper, a nonlinear structural model updating methodology based on the Deep Belief Network (DBN) is proposed. Firstly, the instantaneous parameters of the vibration responses are obtained by the discrete analytical mode decomposition (DAMD) method and the Hilbert transform (HT). The instantaneous parameters are regarded as the independent variables, and the nonlinear model parameters are considered as the dependent variables. Then the DBN is utilized for approximating the nonlinear mapping relationship between them. At last, the instantaneous parameters of the measured vibration responses are fed into the well-trained DBN. Owing to the strong learning and generalization abilities of the DBN, the updated nonlinear model parameters can be directly estimated. Two nonlinear shear-type structure models under two types of excitation and various noise levels are adopted as numerical simulations to validate the effectiveness of the proposed approach. The nonlinear properties of the structure model are simulated via the hysteretic parameters of a Bouc-Wen model and a Giuffré-Menegotto-Pinto model, respectively. Besides, the proposed approach is verified by a three-story shear-type frame with a piezoelectric friction damper (PFD). Simulated and experimental results suggest that the nonlinear model updating approach has high computational efficiency and precision.

• Korean Management Science Review
• /
• v.28 no.1
• /
• pp.141-158
• /
• 2011

This study concerns with an applicability of the management science approach to the score adjustment among the College Scholastic Aptitude Test(CSAT) optional subjects. A linear programming model is developed to minimize the sum of score distortions between optional subjects. Based on the analysis of the 377,089 CSAT(2010) applicants' performances in social science test section, this study proposes a new approach for the score equating or linking method of the educational measurement theory. This study makes up for the weak points in the previous linear programming model. First, the model utilize the standard score which we can get. Second, the model includes a goal programming concept which minimizes the gap between the adjusting goal and the result of the adjustment. Third, the objective function of the linear programing is the weighted sum of the score distortion and the number of applicants. Fourth, the model is applied to the score adjustment problem for the whole 11 optional subjects of the social science test section. The suggested linear programming model is a generalization of the multi-tests linking problem. So, the approach is consistent with the measurement theory for the two tests and can be applied to the optional three or more tests which do not have a common anchor test or a common anchor group. The college admission decision with CSAT score can be improved by using the suggested linear programming model.

• Environmental Engineering Research
• /
• v.14 no.4
• /
• pp.200-210
• /
• 2009

The modern era of water quality modeling in the United States began in the 1960s. Pushed by advances in computer technology as well as environmental sciences, water quality modeling evolved through five broad periods: (1) initial model development with mainframe computers (1960s - mid 1970s), (2) model refinement and generalization with minicomputers (mid 1970s - mid 1980s), (3) model standardization and support with microcomputers (mid 1980s - mid 1990s), (4) better model access and performance with faster desktop computers running Windows and local area networks linked to the Internet (mid 1990s - early 2000s), and (5) model integration and widespread use of the Internet (early 2000s - present). Improved computer technology continues to drive improvements in water quality models, including more detailed environmental analysis (spatially and temporally), better user interfaces and GIS software, more accessibility to environmental data from on-line repositories, and more robust modeling frameworks linking hydrodynamics, water quality, watershed and atmospheric models. Driven by regulatory needs and advancing technology, water quality modeling will continue to improve to better address more complicated water bodies and pollutant types, and more complicated management questions. This manuscript describes historical trends in water quality model development in the United States, reviews current efforts, and projects promising future directions.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2001.10a
• /
• pp.103-109
• /
• 2001

Soft sensor is an effective method to deal with the estimation of variables, which are difficult to measure because of the reasons of economy or technology. Fuzzy logic system can be used to develop the soft sensor model by infinite rules, but the fuzzy dividing of variable sets is a key problem to achieve an accurate fuzzy logic model, In this paper, we proposed a new method to develop soft sensor model based on fuzzy neural network. First, using a novel method to divide the variable fuzzy sets by the process input and output data. Second, developing the fuzzy logic model based on that fuzzy set dividing. After that, expressing the fuzzy system with a fuzzy neural network and getting the initial soft sensor model based FNN. Last, adjusting the relative parameters of soft sensor model by the BP learning method. The effectiveness of the method proposed and the preferable generalization ability of soft sensor model built are demonstrated by the simulation.

• Journal of the Korean Geotechnical Society
• /
• v.16 no.1
• /
• pp.65-73
• /
• 2000

An elasto-plastic constitutive model was proposed, in which the behavior at small-to-large strain level can be modeled. The proposed model is based on the anisotropic hardening description with the generalization of isotropic hardening rule and the total stress concept. From a mathematical approach it was proved that the model includes the previous successful models. The model was verified by a series of resonant column tests, torsional shear tests and triaxial tests, and the proposed model predicted small-to-large strain behavior more consistently and accurately than the hyperbolic model and the Ramberg-Osgood model for a weathered granitic soil. In addition, the nonlinearity under small strain condition was predicted appropriately for the torsional shear test results.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.6
• /
• pp.1103-1118
• /
• 2009

When we wish to estimate the mean or total of a finite population, the numbering of the population units is of importance. In this paper, we have proposed two methods for estimating the mean or total of a population having a linear trend, for the case when the reciprocal of the sampling fraction is an even number and the sample size is an odd number. The first method involves drawing a sample by using a method which is a generalization of Singh et al's (1968) modified systematic sampling, and using interpolation in determining the estimator. The second method involves selecting a sample by modified systematic sampling, and estimating the population parameters by the regression estimation method. Under the criterion of the expected mean square error based on Cochran's (1946) infinite superpopulation model, the proposed methods have been compared with existing methods. We have also made a comparison between the two proposed methods.

• The Journal of the Korea Contents Association
• /
• v.9 no.7
• /
• pp.379-389
• /
• 2009

In this paper, we analyzed the effect of u-learning model school which have been in forced by the Ministry of Education. We suggested a plan which we generalized the effects of u-learning. To analyzed the effects of u-learning, first of all, we set up indexes of u-learning effect - satisfaction measurement, efficacy measurement, the scholastic achievements, possibility of generalization. After we reanalyzed reports of model school and papers of u-learning, we looked for suggestions of the effects u-learning. We draw up a plan which we generalized the effects of u-learning according to suggestions. We devide a plan by 3 steps - introduction step, diffusion step, fixation step and every step by 4 field - policy of u-learning, teaching & learning, quality control, technology. Because we suggested a concrete plan which we generalized the effects of u-learning, we expect to use usefully our plan at school in the future.