• 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%.

• Proceedings of the Korea Database Society Conference
• /
• 1999.06a
• /
• pp.281-287
• /
• 1999

Decision class analysis (DCA) is viewed as a classification problem where a set of input data (situation-specific knowledge) and output data (a topological leveled influence diagram (ID)) is given. Situation-specific knowledge is usually given from a decision maker (DM) with the help of domain expert(s). But it is not easy for the DM to know the situation-specific knowledge of decision problem exactly. This paper presents a methodology fur sensitivity analysis of DCA under incomplete information. The purpose of sensitivity analysis in DCA is to identify the effects of incomplete situation-specific frames whose uncertainty affects the importance of each variable in the resulting model. For such a purpose, our suggested methodology consists of two procedures: generative procedure and adaptive procedure. An interactive procedure is also suggested based the sensitivity analysis to build a well-formed ID. These procedures are formally explained and illustrated with a raw material purchasing problem.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.03a
• /
• pp.281-287
• /
• 1999

Decision class analysis (DCA) is viewed as a classification problem where a set of input data (situation-specific knowledge) and output data(a topological leveled influence diagram (ID)) is given. Situation-specific knowledge is usually given from a decision maker (DM) with the help of domain expert(s). But it is not easy for the DM to know the situation-specific knowledge of decision problem exactly. This paper presents a methodology for sensitivity analysis of DCA under incomplete information. The purpose of sensitivity analysis in DCA is to identify the effects of incomplete situation-specific frames whose uncertainty affects the importance of each variable in the resulting model. For such a purpose, our suggested methodology consists of two procedures: generative procedure and adaptive procedure. An interactive procedure is also suggested based the sensitivity analysis to build a well-formed ID. These procedures are formally explained and illustrated with a raw material purchasing problem.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.04a
• /
• pp.104-107
• /
• 1996

This paper focuses on a automation selection of optimal cutting conditions and cycle time for multi-spindle metal cutting machines based on machining parameters and tool change schemes which are the two most common terms used in the metal cutting. In this research we used two step generative approach, step 1 is mathematical modeling for the selection fo optimal cutting conditions and the other is GMDH-Type modeling to estimate the system performance evaluation. We developed computer programs for these models and the fitting manufacturing examples are applied to this model and it was shown that the proposed approach has a good potential and offers a valuable tools to analyse the metal cutting system.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.10a
• /
• pp.439-444
• /
• 2004

A new efficient intelligent machining strategy named the Steepest Directed Tree method is presented in this study, which makes surface model discrete with triangulation meshes and the cutter paths track along the tree directions. In order to formulate these algorithms practically, it is deduced the multi-stage machining approach of uncut volume caused by cutter gouging in the course of milling using flat end mill. It is systematized the checking process the cutter interference by grouping the 6 kinds of gouging types, which yields the environment of connectivity data lists including CL-data, and then the multi-stage machining strategy, that minimizes uncut area by continuously sequencing the generative subsequent CL-paths, is shamed to determine the second tool path for the next uncut area and to compose the operating multi-stage cutting processes. The completed machining system of curved surfaces is evaluated by testing the practical machining experiments which have various kinds of shape conditions.

• MALSORI
• /
• no.29_30
• /
• pp.43-60
• /
• 1995

Standard generative phonologists assumed that there were no orders or hierarchies among distinctive features. This means that the distinctive features which make up a segment are independent and unordered. The unordered linear matrix cannot explain phonological phenomena such as complex segments as hierarchical representation does neatly. The hierarchical feature representation theory which embodies the concept of multi-tiered phonological representation organizes distinctive features in the appearance of hierarchical dominance. This paper aims to show how we can solve some problems of the linear feature representation. As regard underlying representation the theory of underspecification is discussed. I propose a feature hierarchy similar to that of Sagey(1986) but slightly different. I show English consonantal assimilation in feature hierarchical model compared with that of feature changing theory of linear representation.

• Lingua Humanitatis
• /
• v.5
• /
• pp.7-36
• /
• 2003

In this paper I am arguing in favour of more vigilance on the part of the Korean linguistics' melieu and, if deemed necessary, a more solid epistemological foundation of the Korean Linguistics. The purpose of this work consist in providing some epistemological inquiry on the major orientations and tendencies which are manifested in the reception of western linguistic theories. I might call this point of view as a critical approach to the philosophy and history of Korean linguistics. In the first section, I gave a short description of the model of the linguistic historiography which can be applied to the history of the Korean linguistics. In the second section, I am concerned with the comparative epistemology of the development of linguistic ideas produced in the West and East. In the final section, I made some critical reflections on the limits of Korean linguistics.

• Environmental Sciences Bulletin of The Korean Environmental Sciences Society
• /
• v.1 no.1
• /
• pp.45-50
• /
• 1997

Understanding the nonlinear flow caused by orographic effects can be valuable in siting of new businesses, industries, and transportation facilities. In spite of recent work on large-amplitude waves and wave breaking, the studies of flow around large scale mountains have just begun. The generative mechanism of lee vortices in the lee of large scale mountain is investigated by Ertel's theorem. The CSU RAMS is used as a numerical model. According to the numerical results, the isentropes are depressed behind the large scale mountains. This means the vortex lines must run upward and downward along the depression surface because vortex lines adhere to isentropic surfaces. Therefore, the vertically oriented vorticity can be formed in the lee of the large scale mountain. This vorticity plays an important role for orographic precipitation, because strong vertical velocity and cloud bands are developed along isothermal deformation surface.

• Journal of Environmental Science International
• /
• v.1 no.1
• /
• pp.45-50
• /
• 1992

Understanding the nonlinear flow caused by orographic effects can be valuable in siting of new businesses, industries, and transportation facilities. In spite of recent work on large-amplitude waves and wave breaking, the studies of flow around large scale mountains have just begun. The generative mechanism of lee vortices in the lee of large scale mountain Is investigated by Ertel's theorem. The CSU RAMS is used as a numerical model. According to the numerical results, the isentropes are depressed behind the large scale mountains. This means the vortex lines must run upward and downward along the depression surface because vortex lines adhere to isentropic surfaces. Therefore, the vertically oriented vorticity can be formed in the lee of the large scale mountain. This vorticity plays an important role for orographic Precipitation, because strong vertical velocity and cloud bandy are developed along isothermal deformation surface.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.504-507
• /
• 2019

모바일 광고 기술(AD Tech)분야에서 기계학습은 사용자별 CTR(Click Through Ratio) 예측[1]에 국한되어 왔으며 2016 년도부터 시행된 GDPR(General Data Protection Regulation)[2] 정책으로 인하여 AD Tech 관련 사업자의 사용자 개인정보 접근이 제한되어왔다. 그 결과 Feature Data 에 기반한 사용자 타겟팅 및 Ad Tech 산업에서 기계 학습 기술을 적용하는데 현실적 어려움을 가져왔다. 본 논문에서는 기존 연구와 현실적 한계를 극복하기 위하여 사용자가 아닌 매체별 클릭 분포를 예측하는 Hawkes Process 에 기반한 생성모델을 제안하고 그 가능성을 살펴본다.