• The Journal of the Korea Contents Association
• /
• v.6 no.3
• /
• pp.12-19
• /
• 2006

In this paper, we describe a deep analysis of question for question answering system. It is difficult to offer the correct answer because general question answering systems do not analyze the semantic of user's natural language question. We analyze user's question semantically and extract semantic features using the semantic feature extraction grammar and characteristics of natural language question. They are represented as semantic features and grammatical morphemes that consider semantic and syntactic structure of user's questions. We evaluated our approach using 100 questions whose answer type is a person in the web. We showed that a deep analysis of questions which are comparatively short but enough to mean can analysis the user's intention and extract semantic features.

• Nuclear Engineering and Technology
• /
• v.30 no.6
• /
• pp.541-554
• /
• 1998

A computer code COSMOS has been developed based on the CARO-D5 for the thermal analysis of LWR UO$_2$ and MOX fuel rod under steady-state and transient operating conditions. The main purpose of the COSMOS, which considers high turnup characteristics such as thermal conductivity degradation with turnup and rim formation at the outer part of fuel pellet, is to calculate temperature profile across fuel pellet and fission gas release up to high burnup. A new mechanistic fission gas release model developed based on physical processes has been incorporated into the code. In addition, the features of MOX fuel such as change in themo-mechanical properties and the effect of microscopic heterogeneity on fission gas release have been also taken into account so that it can be applied to MOX fuel. Another important feature of the COSMOS is that it can analyze fuel segment refabricated from base irradiated fuel rods in commercial reactors. This feature makes it possible to analyze database obtained from international projects such as the MALDEN and RISO, many of which were collected from refabricated fuel segments. The capacity of the COSMOS has been tested with some number of experimental results obtained from the HALDEN, RISO and FIGARO programs. Comparison with the measured data indicates that, although the COSMOS gives reasonable agreement, the current models need to be improved. This work is being performed using database available from the OECD/NEA.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.377-380
• /
• 2022

An application called an app can be downloaded and used on mobile devices. Among them, Android-based apps have the disadvantage of being implemented on an open source basis and can be exploited by anyone, but unlike iOS, which discloses only a small part of the source code, Android is implemented as an open source, so it can analyze the code. However, since anyone can participate in changing the source code of open source-based Android apps, the number of malicious codes increases and types are bound to vary. Malicious codes that increase exponentially in a short period of time are difficult for humans to detect one by one, so it is efficient to use a technique to detect malicious codes using AI. Most of the existing malicious app detection methods are to extract Features and detect malicious apps. Therefore, three ways to select the optimal feature to be used for learning after feature extraction are proposed. Finally, in the step of modeling with optimal features, ensemble techniques are used in addition to a single model. Ensemble techniques have already shown results beyond the performance of a single model, as has been shown in several studies. Therefore, this paper presents a plan to select the optimal feature and implement a learning model for Android app-based malicious code detection.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.1172-1175
• /
• 2006

Generally, the estimation of design flood uses basin rainfall data, water level data, and runoff data, and so forms rainfall-runoff model. Because owing to the lack of hydrological data, the decision of representative unit hydrograph about the basin is difficult, the estimation of design flood uses topography feature data, and so presumes variables, and then applies the presumed variables to the model. In estimating design flood by using the model, it is considerably difficult to analyze how the model input variables estimated by topography factors, or the design flood data estimated previously are related to basin feature factors as the basic data, and presume design flood in the unmeasured basins or the basins where river arrangement basic plan is not established. The purpose of this study is to analyze how the design flood estimated previously by river arrangement basic plan is correlated with topography factors in presuming design flood, and so examine the presumption measures of design flood by using topography feature data and probability rainfall data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.7
• /
• pp.1495-1504
• /
• 2012

This paper proposes an algorithm to classify and analyze facial features such as eyebrow, eye, mouth and chin based on the geometric features of the face. As a preprocessing process to classify and analyze the facial features, the algorithm extracts the facial features such as eyebrow, eye, nose, mouth and chin. From the extracted facial features, it detects the shape and form information and the ratio of distance between the features and formulated them to evaluation functions to classify 12 eyebrows types, 3 eyes types, 9 mouth types and 4 chine types. Using these facial features, it analyzes a face. The face analysis algorithm contains the information about pixel distribution and gradient of each feature. In other words, the algorithm analyzes a face by comparing such information about the features.

• Korean Institute of Interior Design Journal
• /
• v.21 no.3
• /
• pp.22-30
• /
• 2012

Nowadays the issue of environmental pollution and ecological destruction is not a simple issue but an important issue to be continuously considered. It is deemed that a study for recycled new materials is immediately required and this study is to analyze features and processing methods of new materials which can be used to interior space. We found the recycled new materials used for space through researching various web sits. And then we analyzed what the base materials are and classified that base materials are whether natural or artificial of the recycled materials. We classified processing methods of the recycled new materials after researching general processing methods. The result of this study would be an important material to the research and development of new finishing materials with consideration of environment and to the research for a guideline of applicable new materials. The results of this study are as follows : First, we could classify widely 2 categories into natural material and artificial material and then 10 subcategories into metal, glass, wood, rubber, stone, plastic, leather or fabric, ceramic, concrete and so on, and analyzed that which material is mostly used and whether it is single material or multiple material. In order to analyze the feature of processing method. Second, we could classify into 4 categories such as junction, surface process, molding, and insert, and found out which processing method is applied based on objects of research. Third, as an analysis result of the recycled new material feature, in order to develop various new materials, it is required to study on combination and application of 2 materials or more rather than single material. Four, as a analysis result of the processing method feature, I would like to suggest that development and application of various processing methods are required. Especially, it is necessary to grope for a way to develop new functional materials for interior space through a systemic research and analysis of processing method of other fields. Furthermore, a way to reuse recycled new materials should be considered in a stage of selection and application of processing method.

• Journal of the Korea Institute of Building Construction
• /
• v.21 no.2
• /
• pp.165-174
• /
• 2021

The construction industry causes the most accidents and fatalities among all industries. Although many efforts have been made to reduce safety accidents in construction, the study on the lost workdays that return to work place is insufficient. Therefore, this study proposes a model that classifies the lost workdays lost into moderate and severity, and derives the importance of variable and analyzes important factors through the trained random forest model. We analyze the learning process of the random forest which is a black box model, and extracted important variables that impact on the severity of the lost workdays through the extracted feature importance. The factors existing inside were analyzed through the extracted variables. The purpose of this study is to analyze the accident case data at the construction site through a random forest model and to review variables that have a high impact on the lost workdays. In the future, this sutdy can apply to improve construction safety management and reduce the accident of industrial accidents.

• The Journal of Engineering Geology
• /
• v.32 no.3
• /
• pp.377-388
• /
• 2022

Recently, several studies have utilized machine learning to efficiently and accurately analyze seismic data that are exponentially increasing. In this study, we expand earthquake information such as occurrence time, hypocentral location, and magnitude to produce a dataset for applying to machine learning, reducing the dimension of the expended data into dominant features through principal component analysis. The dimensional extended data comprises statistics of the earthquake information from the Global Centroid Moment Tensor catalog containing 36,699 seismic events. We perform data preprocessing using standard and max-min scaling and extract dominant features with principal components analysis from the scaled dataset. The scaling methods significantly reduced the deviation of feature values caused by different units. Among them, the standard scaling method transforms the median of each feature with a smaller deviation than other scaling methods. The six principal components extracted from the non-scaled dataset explain 99% of the original data. The sixteen principal components from the datasets, which are applied with standardization or max-min scaling, reconstruct 98% of the original datasets. These results indicate that more principal components are needed to preserve original data information with even distributed feature values. We propose a data processing method for efficient and accurate machine learning model to analyze the relationship between seismic data and seismic behavior.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.6
• /
• pp.77-87
• /
• 2011

In this paper, we propose a disparity correction technique to reduce the inherent visual discomfort while watching stereoscopic videos. The visual discomfort must be solved for commercial 3D display systems to provide natural stereoscopic videos to human eyes. The proposed disparity correction technique consists of horizontal and vertical disparity corrections. The horizontal disparity correction is implemented by controlling the depth budget of stereoscopic video using the geometric relations of a stereoscopic camera system. In addition, the vertical disparity correction is implemented by using a feature-based stereo matching algorithm. Conventional vertical disparity corrections have been done by only using camera calibration parameters, which still cause systematic errors in vertical disparities. In this paper, we minimize the vertical disparity as small as possible by using a feature-based correction algorithm. Through the comparisons of conventional feature-based correction algorithms, we analyze the performance of the proposed technique.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.1
• /
• pp.87-92
• /
• 1996

Transient signals in underwater show several characterisrics, that is, short duration, strong nonstationarity, various types of transient sources, which make it difficult to analyze and classify transient signals. In this paper, the feature vector extraction method for transient SOMAR signals is discussed by applying digital signal processing methods to the analysis of transient signals. A feature vector extraction methods using wavelet transform, which enable us to obtain better recognition rate than automatic classification using the classical method, are proposed. It is confirmed by simulation that the proposed method using wavelet transform performs better than the classical method even with smaller number of feature vectors. Especially, the feature vector extraction method using PR-QMF wavelet transform with the Daubechies coefficients is shown to perform well in noisy environment with easy implementation.