• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.22 no.9
• /
• pp.628-634
• /
• 2010

This paper presents a feasibility study of a fresh air load reduction system by using an underground double floor space. The fresh air is introduced into the double slab space and passes through the opening bored into the footing beam. The air is cooled by the heat exchange with the inside surface of the double slab space in summer, and heated in winter. This system not only reduces sensible heat load of the fresh air by heat exchange with earth but also reduces latent heat load of the fresh air by ad/de-sorption of underground double slab concrete. In this paper, we proposed a simplified presumption method for the prediction of cooling and heating performance in the system. In conclusion the proposed method has been verified by comparing with the calculated value of the numerical analysis model by using nonlinear two-dimension hygroscopic question.

• Tunnel and Underground Space
• /
• v.9 no.4
• /
• pp.306-314
• /
• 1999

In underground spaces including nuclear waste repository, prediction of air quantity, temperature/humidity and pollutant concentration is utmost important for space construction and management during the normal state as well as for determining the measures in emergency cases such as underground fires. This study aims at developing a model for underground space environment which has capabilities to take into account the effects of autocompression for the natural ventilation head calculation, to find the optimal location and size of fans and regulators, to predict the temperature and humidity by calculating the convective heat transfer coefficient and the sensible and latent heat transfer rates, and to estimate the pollutant levels throughout the network. The temperature/humidity prediction model was applied to a military storage underground space and the relative differences of dry and wet temperatures were 1.5 ~ 2.9% and 0.6 ~ 6.1%, respectively. The convection-based pollutant transport model was applied to two different vehicle tunnels. Coefficients of turbulent diffusion due to the atmospheric turbulence were found to be 9.78 and 17.35$m^2$/s, but measurements of smoke and CO concentrations in a tunnel with high traffic density and under operation of ventilation equipment showed relative differences of 5.88 and 6.62% compared with estimates from the convection-based model. These findings indicate convection is the governing mechanism for pollutant diffusion in most of the tunnel-type spaces.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.7
• /
• pp.303-314
• /
• 2023

Voice conversion, a technology that allows an individual's speech data to be regenerated with the acoustic properties(tone, cadence, gender) of another, has countless applications in education, communication, and entertainment. This paper proposes an approach based on the StarGAN-VC model that generates realistic-sounding speech without requiring parallel utterances. To overcome the constraints of the existing StarGAN-VC model that utilizes one-hot vectors of original and target speaker information, this paper extracts feature vectors of target speakers using a pre-trained version of Rawnet3. This results in a latent space where voice conversion can be performed without direct speaker-to-speaker mappings, enabling an any-to-any structure. In addition to the loss terms used in the original StarGAN-VC model, Wasserstein distance is used as a loss term to ensure that generated voice segments match the acoustic properties of the target voice. Two Time-Scale Update Rule (TTUR) is also used to facilitate stable training. Experimental results show that the proposed method outperforms previous methods, including the StarGAN-VC network on which it was based.

• Journal of information and communication convergence engineering
• /
• v.21 no.2
• /
• pp.139-144
• /
• 2023

Engineers prefer deep neural networks (DNNs) for solving computer vision problems. However, DNNs pose two major problems. First, neural networks require large amounts of well-labeled data for training. Second, the covariate shift problem is common in computer vision problems. Domain adaptation has been proposed to mitigate this problem. Recent work on adversarial-learning-based unsupervised domain adaptation (UDA) has explained transferability and enabled the model to learn robust features. Despite this advantage, current methods do not guarantee the distinguishability of the latent space unless they consider class-aware information of the target domain. Furthermore, source and target examples alone cannot efficiently extract domain-invariant features from the encoded spaces. To alleviate the problems of existing UDA methods, we propose the mixup regularization in adversarial discriminative domain adaptation (ADDA) method. We validated the effectiveness and generality of the proposed method by performing experiments under three adaptation scenarios: MNIST to USPS, SVHN to MNIST, and MNIST to MNIST-M.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.40 no.10
• /
• pp.862-871
• /
• 2012

The numerical simulations on 500-N class rocket engine using 96% hydrogen peroxide and kerosene have been conducted, considering atomization, evaporation, mixing and combustion of its propellants. The grid containing 1/6 part of combustion chamber has been generated and it is assumed that 3 kinds of liquid-phase propellants (kerosene, hydrogen peroxide and water) were injected as hollow cone spray pattern, using Rosin-Rammler function for distribution of droplet diameter. For the calculation of combustion the eddy-dissipation model was applied. Owing to small size of combustion chamber and large specific heat / latent heat of hydrogen peroxide and water the propulsion characteristics were highly influenced by the size of droplet particles, and in this analysis the engine with droplet particles of 30 micron in average has shown the best propulsion performance.

• The KIPS Transactions:PartA
• /
• v.12A no.6 s.96
• /
• pp.539-546
• /
• 2005

Recently, as the number of Internet users are growing explosively, e-learning has been applied spread, as well as remote evaluation of intellectual capacity However, only the multiple choice and/or the objective tests have been applied to the e-learning, because of difficulty of natural language processing. For the intelligent marking of short-essay typed answer papers with rapidness and fairness, this work utilize heterogenous linguistic knowledges. Firstly, we construct the semantic kernel from un tagged corpus. Then the answer papers of students and instructors are transformed into the vector form. Finally, we evaluate the similarity between the papers by using the semantic kernel and decide whether the answer paper is correct or not, based on the similarity values. For the construction of the semantic kernel, we used latent semantic analysis based on the vector space model. Further we try to reduce the problem of information shortage, by integrating Korean Word Net. For the construction of the semantic kernel we collected 38,727 newspaper articles and extracted 75,175 indexed terms. In the experiment, about 0.894 correlation coefficient value, between the marking results from this system and the human instructors, was acquired.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.3
• /
• pp.209-219
• /
• 2013

Epidemiological models on disease spread attempt to simulate disease transmission and associated control processes and such models contribute to greater understanding of disease spatial diffusion through of individual's contacts. The objective of this study is to develop an agent-based modeling(ABM) approach that integrates geographic information systems(GIS) to simulate the spread of FMD in spatial environment. This model considered three elements: population, time and space, and assumed that the disease would be transmitted between farms via vehicle along the roads. The model is implemented using FMD outbreak data in Andong city of South Korea in 2010 as a case study. In the model, FMD is described with the mathematical model of transmission probability, the distance of the two individuals, latent period, and other parameters. The results show that the GIS-agent based model designed for this study can be easily customized to study the spread dynamics of FMD by adjusting the disease parameters. In addition, the proposed model is used to measure the effectiveness of different control strategies to intervene the FMD spread.

• Science of Emotion and Sensibility
• /
• v.13 no.1
• /
• pp.47-60
• /
• 2010

Most of the researches about classification usually have used kNN(k-Nearest Neighbor), SVM(Support Vector Machine), which are known as learn-based model, and Bayesian classifier, NNA(Neural Network Algorithm), which are known as statistics-based methods. However, there are some limitations of space and time when classifying so many web pages in recent internet. Moreover, most studies of classification are using uni-gram feature representation which is not good to represent real meaning of words. In case of Korean web page classification, there are some problems because of korean words property that the words have multiple meanings(polysemy). For these reasons, LSA(Latent Semantic Analysis) is proposed to classify well in these environment(large data set and words' polysemy). LSA uses SVD(Singular Value Decomposition) which decomposes the original term-document matrix to three different matrices and reduces their dimension. From this SVD's work, it is possible to create new low-level semantic space for representing vectors, which can make classification efficient and analyze latent meaning of words or document(or web pages). Although LSA is good at classification, it has some drawbacks in classification. As SVD reduces dimensions of matrix and creates new semantic space, it doesn't consider which dimensions discriminate vectors well but it does consider which dimensions represent vectors well. It is a reason why LSA doesn't improve performance of classification as expectation. In this paper, we propose new LSA which selects optimal dimensions to discriminate and represent vectors well as minimizing drawbacks and improving performance. This method that we propose shows better and more stable performance than other LSAs' in low-dimension space. In addition, we derive more improvement in classification as creating and selecting features by reducing stopwords and weighting specific values to them statistically.

• Journal of Korean Society of Transportation
• /
• v.24 no.6 s.92
• /
• pp.119-127
• /
• 2006

Recently. there are demanding a better sidewalk environment considering side of psychic as well as physical factors as the rapid growth of cities and improvement of traffic consciousness. Also. it needs to give a better sidewalk environment because those pedestrians evade a sidewalk space with minimum Physical design standards. So. we think very important that get a grip what makes Pedestrian feel a comfort and amenity in sidewalk above all. In this study, we carried out a cognition experiment of sidewalk environment on considering the human's psychic with Sensibility Ergonomics and the survey method using SD (Semantic Differential) scale. And we made a recognition evaluation model of sidewalk landscape and sensibility recognition model of sidewalk design factors using LISREL model that analysis sensibility recognition of sensibility adjective by SD scale. In results, we found out a possibility of the design with comfort and amenity in sidewalk environment as considering Sensibility Ergonomics, and an importance of harmonious green environment as a roadside tree etc. above all.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.9 no.3
• /
• pp.410-425
• /
• 1997

Buildings are mostly under part load conditions causing an inefficient system operation in terms of energy consumption. It is critical to operate building air-conditioning system with a scientific or optimal manner which minimizes energy consumption and maintains thermal comfort by matching building sensible and latent loads. Little research has been performed in developing general methodologies for the optimal operation of air-conditioning system. Based on this research motivation, system simulation program was developed by adopting various equipment operating strategies which are energy efficient especially for humidity control in summer. A numerical optimization technique was utilized to search optimal solution for multi-independent variables and then linked to the developed system simulation model within a mam program. The main goal of the study is to provide a systematic framework and guideline for the optimal operation of air-conditioning system focusing on air-side. For given cooling loads and ambient outdoor conditions the optimal operating strategies of a commercial building are determined by minimizing a constrained objective function by a nonlinear programming technique. Desired space setpoint conditions were found through evaluating the trade-offs between comfort and system power consumption. The results show that supply airflow rate and compressor fraction play main roles in the optimization process. It was found that variable setpoint optimization technique could produce lower indoor humidity level demanding less power consumption which will be benefits for building applications of humidity problem.