• Korean Journal of Remote Sensing
• /
• v.36 no.5_2
• /
• pp.929-937
• /
• 2020

In this manuscript, the UNet++ model, which is one of the representative deep learning techniques for semantic segmentation, was used to detect changes in temporal satellite images. To analyze the learning results according to various loss functions, we evaluated the change detection results using trained UNet++ models by binary cross entropy and the Jaccard coefficient. In addition, the learning results of the deep learning model were analyzed compared to existing pixel-based change detection algorithms by using WorldView-3 images. In the experiment, it was confirmed that the performance of the deep learning model could be determined depending on the characteristics of the loss function, but it showed better results compared to the existing techniques.

• The Journal of the Korea Contents Association
• /
• v.12 no.6
• /
• pp.41-47
• /
• 2012

Various Korean word sense disambiguation methods have been proposed using small scale of sense-tagged corpra and dictionary definitions to calculate entropy information, conditional probability, mutual information and etc. for each method. This paper proposes a method using Korean Word Space model which builds word vectors from a large scale of sense-tagged corpus and disambiguates word senses with the similarity calculation between the word vectors. Experiment with Sejong morph sense-tagged corpus showed 94% precision for 200 sentences(583 word types), which is much superior to the other known methods.

• Preventive Nutrition and Food Science
• /
• v.20 no.3
• /
• pp.215-220
• /
• 2015

The moisture sorption isotherms of vacuum-dried edible green alga (Capsosiphon fulvescens) powders were determined at 25, 35, and $45^{\circ}C$ and water activity ($a_w$) in the range of 0.11~0.94. An inversion effect of temperature was found at high water activity (>0.75). Various mathematical models were fitted to the experimental data, and Brunauer, Emmett, and Teller model was found to be the most suitable model describing the relationship between equilibrium moisture content and water activity (<0.45). Henderson model could also provide excellent agreement between the experimental and predicted values despite of the intersection point. Net isosteric heat of adsorption decreased from 15.77 to 9.08 kJ/mol with an increase in equilibrium moisture content from 0.055 to $0.090kg\;H_2O/kg$ solids. The isokinetic temperature ($T_{\beta}$) was 434.79 K, at which all the adsorption reactions took place at the same rate. The enthalpy-entropy compensation suggested that the mechanism of the adsorption process was shown to be enthalpy-driven.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.20 no.12
• /
• pp.775-780
• /
• 2008

A dynamic model to simulate LNG reliquefaction process has been developed. The model was applied to two candidate cycles for LNG reliquefaction process, which are Reverse Brayton and Claude cycles. The simulation was intended to simulate the pilot plant under construction for operation of the two cycles and evaluate their feasibility. According to the simulation results, both satisfy control requirements for safe operation of brazed aluminum plate-fin type heat exchangers. In view of energy consumption, the Reverse Brayton cycle is more efficient than the Claude cycle. The latter has an expansion valve in addition to the common facilities sharing with the Reverse Brayton cycle. The expansion valve is a main cause to the efficiency loss. It generates a significant amount of entropy associated with its throttling and increases circulation flow rates of the refrigerant and power consumption caused by its leaking resulting in lowered pressure ratio. It is concluded that the Reverse Brayton cycle is more efficient and simpler in control and construction than the Claude cycle.

• International Journal of Air-Conditioning and Refrigeration
• /
• v.17 no.4
• /
• pp.135-140
• /
• 2009

A dynamic model to simulate LNG reliquefaction process has been developed. The model was applied to two candidate cycles for LNG reliquefaction process, which are Reverse Brayton and Claude cycles. The simulation was intended to simulate the pilot plant under construction for operation of the two cycles and evaluate their feasibility. According to the simulation results, both satisfy control requirements for safe operation of brazed aluminum plate-fin type heat exchangers. In view of energy consumption, the Reverse Brayton cycle is more efficient than the Claude cycle. The latter has an expansion valve in addition to the common facilities sharing with the Reverse Brayton cycle. The expansion valve is a main cause to the efficiency loss. It generates a significant amount of entropy associated with its throttling and increases circulation flow rates of the refrigerant and power consumption caused by its leaking resulting in lowered pressure ratio. It is concluded that the Reverse Brayton cycle is more efficient and simpler in control and construction than the Claude cycle.

• Computers and Concrete
• /
• v.23 no.5
• /
• pp.321-327
• /
• 2019

Experimental isotherm compressive tests show that concrete behaviour is dependent on temperature. The aim of such tests is to reproduce how concrete will behave under environmental changes within a moderate range of temperature. In this paper, a novel constitutive elastic damage behaviour law is proposed based on a free energy with an apparent damage depending on temperature. The proposed constitutive behaviour leads to classical theory of thermo-elasticity at small strains. Fixed elastic mechanical characteristics and fixed evolution law of damage independent of temperature and the material volume element size are considered. This approach is applied to compressive tests. The model predicts compressive strength and secant modulus of elasticity decrease as temperature increases. A power scaling law is assumed for specific entropy as function of the specimen size which leads to a volume size effect on the stress-strain compressive behaviour. The proposed model reproduces theoretical and experimental results from literature for tempertaures ranging between $20^{\circ}C$ and $70^{\circ}C$. The effect of the difference in the coefficient of thermal expansion between the mortar and coarse aggregates is also considered which gives a better agreement with FIB recommendations. It is shown that this effect is of a second order in the considered moderate range of temperature.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.37 no.7
• /
• pp.883-889
• /
• 2013

The distribution of a response usually depends on the distribution of a variable. When the distribution of a variable has two different modes, the response also follows a distribution with two different modes. In most reliability analysis methods, the number of modes is irrelevant, but not the type of distribution. However, in actual problems, because information is often provided with two or more modes, it is important to estimate the distributions with two or more modes. Recently, some reliability analysis methods have been suggested for bimodal distributions. In this paper, we review some methods such as the Akaike information criterion (AIC) and maximum entropy principle (MEP) and compare them with the Monte Carlo simulation (MCS) using mathematical examples with two different modes.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.1B
• /
• pp.21-27
• /
• 2012

The HLLL scheme, proposed by T. Linde, determines all the wave speeds from the initial states because the middle wave is evaluated by the introduction of a generalized entropy function. The scheme is considered a genuine successor to the original HLL scheme because it is completely separated form the Roe's linearization scheme unlike the HLLE scheme and does not rely on the exact solution unlike the HLLC scheme. In this study, a numerical model was configured by the HLLL scheme with the total energy as a generalized entropy function to solve governing equations, which are the one-dimensional shallow water equations without source terms and with an additional conserved variable relating a concentration. Despite the limitations of the first order solutions, results to three cases with the exact solutions were generally accurate. The HLLL scheme appeared to be superior in comparison with the other HLL-type schemes. In particular, the scheme gave fairly accurate results in capturing the front of wetting and drying. However, it revealed shortcomings of more time-consuming calculations compared to the other schemes.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.5
• /
• pp.531-540
• /
• 2010

In this paper, we present a two-phase shallow semantic parsing method based on a maximum entropy model. The first phase is to recognize semantic arguments, i.e., argument identification. The second phase is to assign appropriate semantic roles to the recognized arguments, i.e., argument classification. Here, the performance of the first phase is crucial for the success of the entire system, because the second phase is performed on the regions recognized at the identification stage. In order to improve performances of the argument identification, we incorporate syntactic knowledge into its pre-processing step. More precisely, boundaries of the immediate clause and the upper clauses of a predicate obtained from clause identification are utilized for reducing the search space. Further, the distance on parse trees from the parent node of a predicate to the parent node of a parse constituent is exploited. Experimental results show that incorporation of syntactic knowledge and the separation of argument identification from the entire procedure enhance performances of the shallow semantic parsing system.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.4 s.310
• /
• pp.50-57
• /
• 2006

In Electronic Commerce, the latest most of the personalized recommender systems have applied to the collaborative filtering technique. This method calculates the weight of similarity among users who have a similar preference degree in order to predict and recommend the item which hits to propensity of users. In this case, we commonly use Pearson Correlation Coefficient. However, this method is feasible to calculate a correlation if only there are the items that two users evaluated a preference degree in common. Accordingly, the accuracy of prediction falls. The weight of similarity can affect not only the case which predicts the item which hits to propensity of users, but also the performance of the personalized recommender system. In this study, we verify the improvement of the prediction accuracy through an experiment after observing the rule of the weight of similarity applying Vector similarity, Entropy, Inverse user frequency, and Default voting of Information Retrieval field. The result shows that the method combining the weight of similarity using the Entropy with Default voting got the most efficient performance.