• 한국정보교육학회:학술대회논문집
• /
• 2021.08a
• /
• pp.181-185
• /
• 2021

As part of an effort to derive measures to prevent school violence, which is continuously emphasized in the school field, this study tried to examine the topic that has recently become an issue related to school violence from the perspective of data science. In particular, it was attempted to crawl posts related to school violence using online SNS data and examine the characteristics of each type by using the topic modeling method. As a result of arranging the keywords for each topic derived from the topic modeling analysis by type, it was possible to divide the contents into three main categories: prevention of school violence, punishment of perpetrators, and measures to be taken. First, as the contents of school violence prevention activities, it is the contents of the role of specialized organizations for the prevention of school violence. Second, it was derived from the contents of measures and procedures for school violence. Third, it was possible to examine the contents of recent issues of school violence. In future research, it is necessary to conduct research that is used to solve the social problems facing based on data-based prediction.

• Geotechnical Engineering
• /
• v.11 no.2
• /
• pp.19-28
• /
• 1995

Based on the various test data acquired in the field, the large pressure chamber and the small pressure chamber, uplift behaviors and method of determining the ultimate uplift capacity of pile driven in small pressure chamber were studied. After uplift pile experienced 2 or 3 sudden slip due to increase of uplift load, complete pullout failure was occurred. Thus, it appears that the ultimate uplift capacity could be identified as the load at displacement where first slip occurs. The ultimate uplift capacity might be determined in every test and the disturbance after first uplift test could be recovered by adding one blow of the drop hammer, which had to depend on the model pile capacity.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.7
• /
• pp.1083-1091
• /
• 2017

As big data technologies have been developed and massive data have exploded from users through various channels, CEO of global IT enterprise mentioned core importance of data in next generation business. Therefore various machine learning technologies have been necessary to apply data driven services but especially recommendation has been core technique in viewpoint of directly providing summarized information or exact choice of items to users in information flooding environment. Recently evolved recommendation techniques have been proposed by many researchers and most of service companies with big data tried to apply refined recommendation method on their online business. For example, Amazon used item to item collaborative filtering method on its sales distribution platform. In this paper, we develop a commercial web service for suggesting music contents and implement three representative collaborative filtering methods on the service. We also produce recommendation lists with three methods based on real world sample data and evaluate the usefulness of them by comparison among the produced result. This study is meaningful in terms of suggesting the right direction and practicality when companies and developers want to develop web services by applying big data based recommendation techniques in practical environment.

• ETRI Journal
• /
• v.35 no.6
• /
• pp.1029-1037
• /
• 2013

This paper introduces a novel and fast synthesizing method for 3D motions of quadrupedal animals that uses only a small set of motion capture data. Unlike human motions, animal motions are relatively difficult to capture. Also, it is a challenge to synthesize continuously changing animal motions in real time because animals have various gait types according to their speed. The algorithm proposed herein, however, is able to synthesize continuously varying motions with proper limb configuration by using only one single cyclic animal motion per gait type based on the biologically driven Froude number. During the synthesis process, each gait type is automatically determined by its speed parameter, and the transition motions, which have not been entered as input, are synthesized accordingly by the optimized asynchronous motion blending technique. At the start time, given the user's control input, the motion path and spinal joints for turning are adjusted first and then the motion is stitched at any speed with proper transition motions to synthesize a long stream of motions.

• MALSORI
• /
• no.53
• /
• pp.93-102
• /
• 2005

The performance of a speech recognition system is generally degraded in telephone environment because of distortions caused by background noise and various channel characteristics. In this paper, data-driven temporal filters are investigated to improve the performance of a specific recognition task such as telephone speech. Three different temporal filtering methods are presented with recognition results for Korean connected-digit telephone speech. Filter coefficients are derived from the cepstral domain feature vectors using the principal component analysis. According to experimental results, the proposed temporal filtering method has shown slightly better performance than the previous ones.

• Journal of Aerospace System Engineering
• /
• v.9 no.4
• /
• pp.62-66
• /
• 2015

During the conceptual design of turboprop aircraft, the power effect driven from rotating propeller is typically obtained from empirical data. In the present paper, propeller power effect was obtained by using unsteady three-dimensional Navier-Stokes solver with $k-{\omega}$ turbulence model for the accurate prediction of turboprop aircraft performance. In order to simulate the relative motion between propeller and fuselage, unsteady sliding mesh method was used. During simulation, three flow conditions such as climb, cruise and descending flight were selected considering the flight envelop of the real turboprop aircraft. For the correction of aerodynamic coefficients, the thrust effect of engine exhaust gas was included based on the engine manufacturer's data. Using the computational results, the correction table for the aerodynamic coefficient of turboprop aircraft was suggested for the performance analysis of turboprop aircraft.

• Journal of the Korean Statistical Society
• /
• v.30 no.3
• /
• pp.453-465
• /
• 2001

It is often the case that one wants to estimate parameters of the distribution which follows certain parametric model, while the dta are contaminated. it is well known that the maximum likelihood estimators are not robust to contamination. Basuet al.(1998) proposed a robust method called the minimum density power divergence estimation. In this paper, we investigate data-driven selection of the tuning parameter $\alpha$ in the minimum density power divergence estimation. A criterion is proposed and its performance is studied through the simulation. The simulation includes three cases of estimation problem.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.27 no.1
• /
• pp.46-52
• /
• 2013

The current distribution passing through grounding electrode is required for calculating an impedance of grounding electrode using the electromagnetic field model. In this paper the numerical calculation for currents passing through a grounding electrode as a function of frequency was given. The proposed approach is based on the wire antenna model(AM) in the frequency domain. The Pocklington's equation driven from the wire antenna theory was numerically calculated by the Galerkin's method. The triangle function was applied to both the basis function and the weighting function. The current distribution of a horizontal ground electrode was simulated in MATLAB. Also these results were compared with the data obtained from the CDEGS HIFREQ calculation.

• Environmental Engineering Research
• /
• v.10 no.2
• /
• pp.88-103
• /
• 2005

In this paper, data-driven modeling and multiresolution analysis (MRA) are applied for a full-scale wastewater treatment plant (WWTP). The proposed method is based on modeling by partial least squares (PLS) and multiscale monitoring by a generic dissimilarity measure (GDM), which is suitable for nonstationary and non-normal process monitoring such as a biological process. Case study in an industrial plant showed that the PLS model could give good modeling performance and analyze the dynamics of a complex plant and MRA was useful to detect and isolate various faults due to its multiscale nature. The proposed method enables us to show the underlying phenomena as well as to filter out unwanted and disturbing phenomena.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.6
• /
• pp.1058-1062
• /
• 2008

In clinical decision support system(CDSS), unlike rule-based expert method, appropriate data-driven machine learning method can easily provide the information of individual feature(clinical test) for disease classification. However, currently developed methods focus on the improvement of the classification accuracy for diagnosis. With the analysis of feature importance in classification, one may infer the novel clinical test sets which highly differentiate the specific diseases or disease states. In this background, we introduce a novel CDSS that integrate a classifier and feature selection module together. Random forest algorithm is applied for the classifier and the feature importance measure. The system selects the significant clinical tests discriminating the diseases by examining the classification error during backward elimination of the features. The superior performance of random forest algorithm in clinical classification was assessed against artificial neural network and decision tree algorithm by using breast cancer, diabetes and heart disease data in UCI Machine Learning Repository. The test with the same data sets shows that the proposed system can successfully select the significant clinical test set for each disease.