• Korean Chemical Engineering Research
• /
• v.61 no.1
• /
• pp.123-141
• /
• 2023

A sufficient amount of data with quality is needed for training artificial neural networks (ANNs). However, developing ANN models with a small amount of data often appears in engineering fields. This paper presented an ANN model to improve prediction performance of the ammonia emission amount with 83 data. The ammonia emission rate included eleven inputs and two outputs (maximum ammonia loss, N_max and time to reach half of N_max, K_m). Categorical input variables were transformed into multi-dimensional equal-distance variables, and 13 data were added into 66 training data using a generative adversarial network. Hyperparameters (number of layers, number of neurons, and activation function) of ANN were optimized using Gaussian process. Using 17 test data, the previous ANN model (Lim et al., 2007) showed the mean absolute error (MAE) of K_m and N_max to 0.0668 and 0.1860, respectively. The present ANN outperformed the previous model, reducing MAE by 38% and 56%.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.111-118
• /
• 2023

The purpose of this study is to study jewelry designs presented to general consumers who seek new products and diversity. We would like to present a modular jewelry design with a structure and combination method that is distinct from jewelry in a multimodal replacement method that allows various product modules sold in the past to be worn interchangeably. Problems are likely to occur when a number of existing rather small parts are manufactured in a complex combination method, and difficulties may follow when consumers replace decorative parts and lose them in the process of assembling small fixture parts. Therefore, in order to reduce these problems, we try to make it different from jewelry products made with a simple and simple design so that it can be easily replaced and worn without the need for other coupling parts, and produced using the latest 3D printer (Rapid Prototyping). In this study, based on the experience and know-how gained while engaging in field work, it was possible to make a real object and focused on minimizing problems during the production process, and through this, time and economic loss can be reduced. The purpose of the study is to produce improved jewelry products by expressing more sophisticated and differentiated shapes by using 3D programs (CAD).

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.179-188
• /
• 2023

Recently, fake news disguises the form of news content and appears whenever important events occur, causing social confusion. Accordingly, artificial intelligence technology is used as a research to detect fake news. Fake news detection approaches such as automatically recognizing and blocking fake news through natural language processing or detecting social media influencer accounts that spread false information by combining with network causal inference could be implemented through deep learning. However, fake news detection is classified as a difficult problem to solve among many natural language processing fields. Due to the variety of forms and expressions of fake news, the difficulty of feature extraction is high, and there are various limitations, such as that one feature may have different meanings depending on the category to which the news belongs. In this paper, emotional change patterns are presented as an additional identification criterion for detecting fake news. We propose a model with improved performance by applying a convolutional neural network to a fake news data set to perform analysis based on content characteristics and additionally analyze emotional change patterns. Sentimental polarity is calculated for the sentences constituting the news and the result value dependent on the sentence order can be obtained by applying long-term and short-term memory. This is defined as a pattern of emotional change and combined with the content characteristics of news to be used as an independent variable in the proposed model for fake news detection. We train the proposed model and comparison model by deep learning and conduct an experiment using a fake news data set to confirm that emotion change patterns can improve fake news detection performance.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.1
• /
• pp.192-207
• /
• 2023

Commercialization of level-4 (Lv.4) autonomous driving applications requires the definition of a safe road environment under which autonomous vehicles can operate safely. Thus, a risk assessment model is required to determine whether the operation of autonomous vehicles can provide safety to is sufficiently prepared for future real-life traffic problems. Although the risk factors of autonomous vehicles were selected and graded, the decision-making method was applied as qualitative data using a survey of experts in the field of autonomous driving due to the cause of the accident and difficulty in obtaining autonomous driving data. The fuzzy linguistic representation of decision-makers and the fuzzy analytic hierarchy process (AHP), which converts uncertainty into quantitative figures, were implemented to compensate for the AHP shortcomings of the multi-standard decision-making technique. Through the process of deriving the weights of the upper and lower attributes, the road alignment, which is a physical infrastructure, was analyzed as the most important risk factor in the operation risk of autonomous vehicles. In addition, the operation risk of autonomous vehicles was derived through the example of the risk of operating autonomous vehicles for the 5 areas to be evaluated.

• Journal of the Korean Geotechnical Society
• /
• v.23 no.6
• /
• pp.97-102
• /
• 2007

Though the stability analysis of soil slopes widely employs the limit equilibrium method, the study on the jointed rock slopes must consider the direction of joint and the characteristics of Joint at the same time. This study analyzes the result of the change in the factors which show the characteristics of discontinuity and the shape factor of rock slopes, and so on, in an attempt to validate the propriety as to the interpretation of jointed rock slope stability which uses the general finite element program. First, the difference depending on the flow rules was compared, and the factor effect study was conducted. The selected independent variables included the direction of joint which displays the mechanical characteristics of discontinuity, adhesive cohesion, friction angle, the inclination and height of rock slope which reveal the shape of slope and surcharge load. And the horizontal displacement was numerically interpreted at the 1/3 point below the slope, a dependent variable, to compare the relative degree of factor effects. The findings of study on factor effects led to the validation that the result of horizontal displacement for each factor satisfied various engineering characteristics, making it possible to be applied to stability interpretation of jointed rock slope. A modelling is possible, which considers the application of the result of real geotechnical surveys & laboratory studies and the non-linear characteristics when designing the rock slope. In addition, the stress change which may result from the natural disaster, such as precipitation, and the construction, can be expressed. Furthermore, as the complicated rock condition and the ground supporting effect can be considered through FEM, it is considered to be very useful in making an engineering decision on the cut-slope, reinforcement and so on.

• Journal of the Korean Geotechnical Society
• /
• v.23 no.5
• /
• pp.143-151
• /
• 2007

The factors affecting the geotechnical properties of cemented sands are known to be relative density, cementation level, stress level, and particle characteristics such as particle size, shape and surface conditions. It has been widely accepted that the friction angle of cemented sands is not affected by cementation while the cohesion of cemented sands was significantly influenced by cementation. The cementation that is a critical component of the strength of cemented sands will be broken with increasing confining pressure and great caution is required in evaluating the cohesion of cemented specimens due to their fragilities. In this study, a series of drained shear tests were performed with specimens at various cementation levels and confining stresses to evaluate the strength parameters of cemented sands. From the experiments, it was concluded that the cohesion intercept of cemented sand experiences three distinctive zone(cementation control zone, transition zone, and stress control zone), as the cementation level and the confining stress varies. In addition, for accurate evaluation of the strength parameters, the level of confining stress triggering the breakage of cementation bond should be determined. In this study, the relationship between the maximum confining stresses capable of maintaining the cementation bond intact and unconfined compression strength of the cemented sand was established.

• Journal of the Korean Geotechnical Society
• /
• v.22 no.11
• /
• pp.47-54
• /
• 2006

Shear wave velocity of uncemented soil can be expressed as the function of effective stresses when capillary phenomena are negligible. However, the terms of effective stresses are divided into the direction of wave propagation and polarization because stress states are generally anisotropy. The shear wave velocities are affected by ${\alpha}$ parameters and ${\beta}$ exponents that are experimentally determined. The ${\beta}$ exponents are controlled by contact effects of particulate materials (sizes, shapes, and structures of particles) and the ${\alpha}$ parameters are changed by contact behaviors among particles, material properties of particles, and type of packing (i.e., void ratio and coordination number). In this study, consolidation tests are performed by using clay, mica and sand specimens. Shear wave velocities are measured during consolidation tests to investigate the stress-induced and inherent anisotropies by using bender elements. Results show the shear wave velocity depends on the stress-induced anisotropy for round particles. Furthermore, the shear wave velocity is dependent on particle alignment under the constant evvective stress. This study suggests that the shear wave velocity and the shear modulus should be carefully estimated and used for the design and construction of geotechnical structures.

• Journal of the Korean Geotechnical Society
• /
• v.22 no.9
• /
• pp.37-43
• /
• 2006

Dynamic numerical analysis of geotechnical problems requires a way to simulate the decrease of energy as the domain of interest gets larger. This phenomenon is usually referred to as radiation damping or geometric attenuation and it is distinguished from material damping in which elastic energy is actually dissipated by viscous, hysteretic, or other mechanism. The fact that the domain of analysis in numerical modeling must be chosen, however, causes a need for special attention at the boundary. This observation leads directly to the idea of determining the dynamic response of the interior region from a finite model consisting of the interior region subjected to a boundary condition which ensures that all energy arriving at the boundary is absorbed. This paper presents a simple methodology to simulate transmitting boundaries condition using viscoelastic infinite elements within the recently developed "OpenSees" finite element code. The methodology used here provides that the level of absorption for traveling waves is efficient enough for practical purposes, but unsatisfactory for the case of sharp incident angles. The effectiveness of the infinite elements for the absorption of incident waves at boundaries is evaluated via example analysis.

• Journal of the Korean Geotechnical Society
• /
• v.26 no.7
• /
• pp.7-16
• /
• 2010

Stress history increases the residual horizontal stress of granular soil and, consequently, the penetration resistance. This study analyzes the effect of stress history on the cone resistance ($q_c$), horizontal stress index ($K_D$) and dilatometer modulus ($E_D$) of CPT and DMT from calibration chamber specimen in OC as well as NC state. Test results show that the normalized cone resistance by mean effective stress correlates well with the relative density and the state parameter, whereas the normalized cone resistance by vertical effective stress is a little affected by stress history. The influence of stress history is more reflected on $K_D$ than $E_D$ and $q_c$. The $K_D/K_0$, in which the effect of stress history on $K_D$ is compensated by the at-rest coefficient of earth pressure, $K_0$, is related to relative density, state parameter and the normalized cone resistance by mean effective stress. It is also observed that the normalized dilatometer modulus by mean effective stress ($E_D/{\sigma}_m'$) shows a unique correlation with the state parameter, regardless of stress history.

• Journal of the Korean Geotechnical Society
• /
• v.26 no.4
• /
• pp.27-36
• /
• 2010

In this study, a series of flat dilatometer tests are performed for Busan sand reconstituted in a large calibration chamber to evaluate the state parameter ($\Psi$). Experimental result shows that the horizontal amplification factor ($K_D/K_0$) is linearly related with state parameter in semi-logarithmic space, but the $K_D/K_0$ of OC specimen is smaller than that of NC specimen because of the horizontal residual stress by stress history of OC specimen. The relation between the normalized dilatometer modulus ($E_D/\sigma_m'$) and the state parameter is also linearly expressed in semi-logarithmic space, and the effect of stress history is relatively insignificant in this relation. However, the variation in $E_D/\sigma_m'-\Psi$ relation of NC state is slightly higher than that of OC state due to the effect of the stress level, and the correlation curve is descending with increase of confining stress. The comparison of test result with previous results of Ticino and Toyoura sands shows that the $E_D/\sigma_m'-\Psi$ relation of Toyoura sand is located on upper side than that of Busan and Tieino sands due to the effect of the higher compressibility, whereas the $K_D/K_0-\Psi$ relation of each sand is irregularly distributed.