• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.277-283
• /
• 2022

사주 풀이란 주어진 사주에 대해서 그에 맞는 해석 글을 생성해주는 작업을 의미한다. 전통적으로 사주 풀이는 온전한 사람의 영역으로 인식되어왔으나, 우리는 본 연구를 통해 사주 풀이 영역도 인공지능으로 대체할 수 있을 것이라는 가능성을 탐구한다. 본 연구에서 우리는 최근 연구되고 있는 자연어 생성분야의 연구들에서 영감을 받아, 사주 유형과 사주 풀이 내에 포함할 명사 키워드를 기반으로 풀이글을 생성하는 인공지능 모델 SaJuTeller를 설계한다. 특히 이전 문맥을 고려하여 풀이글을 생성하는 모델과 단순 사주 유형 및 명사 키워드를 기반으로 풀이글을 생성하는 두가지 모델을 제안하며, 이들 각각의 성능을 분석함으로써 각 모델의 구체적인 활용 방안을 제안한다. 본 연구는 우리가 아는 한 최초의 인공지능 기반 사주풀이 연구이며, 우리는 이를 통해 사주풀이에 요구되는 전문인력의 노력을 경감시킴과 동시에, 다양한 표현을 가진 사주 풀이 글을 생성할 수 있음을 제안한다.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.10
• /
• pp.407-420
• /
• 2014

In general, the Korean morpheme analysis procedure is divided into two steps. In the first step as an ambiguity generation step, an Eojeol is analyzed into many morpheme sequences as candidates. In the second step, one appropriate candidate is chosen by using contextual information. Hidden Markov Model(HMM) is typically applied in the second step. This paper proposes Sub-word Conditional Probability(SCP) model as an alternate algorithm. SCP uses sub-word information of adjacent eojeol first. If it failed, then SCP use morpheme information restrictively. In the accuracy and speed comparative test, HMM's accuracy is 96.49% and SCP's accuracy is just 0.07% lower. But SCP reduced processing time 53%.

• Smart Media Journal
• /
• v.10 no.4
• /
• pp.28-34
• /
• 2021

Drape is one of the factors that determine the shape of clothes and is one of the very important factors in the textile and fashion industry. At a time when non-face-to-face transactions are being activated due to the impact of the coronavirus, more and more companies are asking for drape value. However, in the case of small and medium-sized enterprises (SMEs), it is difficult to measure the drape, because they feel the burden of time and money for measuring the drape. Therefore, this study aimed to generate a drape image for the material property value input using a conditional adversarial neural network through 3D simulation images generated by measuring digital properties. A drape image was created through the existing 736 digital property values, and this was used for model training. Then, the drape value was calculated for the image samples obtained through the generative model. As a result of comparing the actual drape experimental value and the generated drape value, it was confirmed that the error of the peak number was 0.75, and the average error of the drape value was 7.875

• Journal of KIISE:Software and Applications
• /
• v.30 no.1_2
• /
• pp.81-92
• /
• 2003

Generalized LR parsing is one of the enhanced LR parsing methods so that it overcome the limit of one-way linear stack of the traditional LR parser using graph-structured stack, and it has been playing an important role of a firm starting point to generate other variations for NL parsing equipped with various mechanisms. In this paper, we propose a conditional Action Model that can solve the problems of conventional probabilistic GLR methods. Previous probabilistic GLR parsers have used relatively limited contextual information for disambiguation due to the high complexity of internal GLR stack. Our proposed model uses Surface Phrasal Types representing the structural characteristics of the parse for its additional contextual information, so that more specified structural preferences can be reflected into the parser. Experimental results show that our GLR parser with the proposed Conditional Action Model outperforms the previous methods by about 6-7% without any lexical information, and our model can utilize the rich stack information for syntactic disambiguation of probabilistic LR parser.

• The KIPS Transactions:PartD
• /
• v.15D no.4
• /
• pp.441-450
• /
• 2008

Recently, access control on form-based web information systems has become one of the useful methods for implementing client systems in a service-oriented architecture. In particular, XForms language is being adopted in many systems as a description language for XML-based user interfaces and server interactions. In this paper, we propose an efficient algorithm for the evaluation of XPath-based access rules for XForms pages. In this model, an XForms page is a sequence of queries and the client system performs user interface realization along with XPath rule evaluations. XPath rules have instance-dependent predicates, which for the most part are shared between rules. For the efficient evaluation of shared predicate expressions in access control rules, we proposed a predicate graph model that reuses the previously evaluated results for the same context node. This approach guarantees that each predicate expression is evaluated for the relevant xml node only once.

• Economic and Environmental Geology
• /
• v.54 no.1
• /
• pp.77-89
• /
• 2021

In this study, a method has been proposed to improve the performance of hydraulic property estimation model developed by Jeong et al. (2020). In their study, low-dimensional features of the annual groundwater level (GWL) fluctuation patterns extracted based on a Denoising autoencoder (DAE) was used to develop a regression model for predicting hydraulic properties of an aquifer. However, low-dimensional features of the DAE are highly dependent on the precipitation pattern even if the GWL is monitored at the same location, causing uncertainty in hydraulic property estimation of the regression model. To solve the above problem, a process for generating the GWL fluctuation pattern for conditioning the precipitation is proposed based on a conditional variational autoencoder (CVAE). The CVAE trains a statistical relationship between GWL fluctuation and precipitation pattern. The actual GWL and precipitation data monitored on a total of 71 monitoring stations over 10 years in South Korea was applied to validate the effect of using CVAE. As a result, the trained CVAE model reasonably generated GWL fluctuation pattern with the conditioning of various precipitation patterns for all the monitoring locations. Based on the trained CVAE model, the low-dimensional features of the GWL fluctuation pattern without interference of different precipitation patterns were extracted for all monitoring stations, and they were compared to the features extracted based on the DAE. Consequently, it can be confirmed that the statistical consistency of the features extracted using CVAE is improved compared to DAE. Thus, we conclude that the proposed method may be useful in extracting a more accurate feature of GWL fluctuation pattern affected solely by hydraulic characteristics of the aquifer, which would be followed by the improved performance of the previously developed regression model.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.183-188
• /
• 2006

본 논문에서는 베이지안 네트워크를 기반으로 생성하고 평가한 가상예제를 활용하여 범주속성 및 수치속성 데이터에 대한 분류 성능을 향상시키는 방안을 제안한다. 가상예제를 활용하는 종래의 연구들은 주로 수치 속성 데이터를 대상으로 한 반면 본 연구에서는 범주속성 데이터에 대해서도 가상예제를 적용하여 효과를 확인하였다. 그리고 대상 도메인에 특화된 지식을 활용하여 특정 학습 알고리즘의 성능을 향상시키는 것을 목표로 한 기존 연구들과는 달리 본 연구에서는 도메인에 특화된 지식을 활용하는 대신 주어진 훈련 집합을 기반으로 만든 베이지안 네트워크로부터 가상예제를 생성하고, 그 예제가 네트워크의 조건부 우도를 증가시키는데 기여할 경우 유용한 것으로 선별한다. 이러한 생성 및 선별과정을 반복하여 적절한 크기의 가상예제 집합을 수집하여 사용한다. 범주 속성 데이터와 수치 속성을 포함한 데이터를 대상으로 한 실험 결과, 여러 가지 학습 모델의 성능이 향상됨을 확인하였다.

• Journal of KIISE:Software and Applications
• /
• v.33 no.12
• /
• pp.1052-1061
• /
• 2006

This paper presents a method of using virtual examples to improve the classification accuracy for data with nominal attributes. Most of the previous researches on virtual examples focused on data with numeric attributes, and they used domain-specific knowledge to generate useful virtual examples for a particularly targeted learning algorithm. Instead of using domain-specific knowledge, our method samples virtual examples from a naive Bayesian network constructed from the given training set. A sampled example is considered useful if it contributes to the increment of the network's conditional likelihood when added to the training set. A set of useful virtual examples can be collected by repeating this process of sampling followed by evaluation. Experiments have shown that the virtual examples collected this way.can help various learning algorithms to derive classifiers of improved accuracy.

• Journal of KIISE
• /
• v.41 no.11
• /
• pp.927-934
• /
• 2014

In this paper, we propose an effective method for recognizing daily human activities from a stream of three dimensional body poses, which can be obtained by using Kinect-like RGB-D sensors. The body pose data provided by Kinect SDK or OpenNI may suffer from both the view variance problem and the scale variance problem, since they are represented in the 3D Cartesian coordinate system, the origin of which is located on the center of Kinect. In order to resolve the problem and get the view-invariant and scale-invariant features, we transform the pose data into the spherical coordinate system of which the origin is placed on the center of the subject's hip, and then perform on them the scale normalization using the length of the subject's arm. In order to represent effectively complex internal structures of high-level daily activities, we utilize Hidden state Conditional Random Field (HCRF), which is one of probabilistic graphical models. Through various experiments using two different datasets, KAD-70 and CAD-60, we showed the high performance of our method and the implementation system.

• Journal of the Korean earth science society
• /
• v.35 no.1
• /
• pp.69-87
• /
• 2014

This paper suggests a conditional simulation framework based on multiple data transformations for geostatistical simulation of compositional data. First, log-ratio transformation is applied to original compositional data in order to apply conventional statistical methodologies. As for the next transformations that follow, minimum/maximum autocorrelation factors (MAF) and indicator transformations are sequentially applied. MAF transformation is applied to generate independent new variables and as a result, an independent simulation of individual variables can be applied. Indicator transformation is also applied to non-parametric conditional cumulative distribution function modeling of variables that do not follow multi-Gaussian random function models. Finally, inverse transformations are applied in the reverse order of those transformations that are applied. A case study with surface sediment compositions in tidal flats is carried out to illustrate the applicability of the presented simulation framework. All simulation results satisfied the constraints of compositional data and reproduced well the statistical characteristics of the sample data. Through surface sediment classification based on multiple simulation results of compositions, the probabilistic evaluation of classification results was possible, an evaluation unavailable in a conventional kriging approach. Therefore, it is expected that the presented simulation framework can be effectively applied to geostatistical simulation of various compositional data.