• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.563-568
• /
• 2016

The word sense disambiguation problem is to find the correct sense of an ambiguous word having multiple senses in a dictionary in a sentence. We regard this problem as a multi-class classification problem and classify the ambiguous word by using Support Vector Machines. Context words of the ambiguous word, which are extracted from Sejong sense tagged corpus, are represented to two kinds of vector space. One vector space is composed of context words vectors having binary weights. The other vector space has vectors where the context words are mapped by word embedding model. After experiments, we acquired accuracy of 87.0% with context word vectors and 86.0% with word embedding model.

• Journal of Korean Institute of Industrial Engineers
• /
• v.21 no.3
• /
• pp.329-343
• /
• 1995

Traditionally, machining process sequence was influenced and constrained by the design information obtained from CAD data base, i.e., class of operations, geometric shape, tooling, geometric tolerance, etc. However, even though all the constraints from design information are considered, there may exist more than one way to feasibly machine parts. This research is focused on the integrated problem of operations sequencing and machine tools selection in the presence of the product mix and their production volumes. With the transitional costs among machining operations, the operation sequencing problem can be formulated as a well-known Traveling Salesman Problem (TSP). The transitional cost between two operations is expressed as the sum of total machining time of the parts on a machine for the first operation and transportation time of the parts from the first machine to a machine for the second operation. Therefore, the operation sequencing problem formulated as TSP cannot be solved without transitional costs for all operation pairs. When solved separately or serially, their mutual optima cannot be guaranteed. Machining operations sequencing and machine tool selection problems are two core problems in process planning for discretely machined parts. In this paper, the interrelated two problems are integrated and analyzed, zero-one integer programming model for the integrated problem is formulated, and the solution methods are developed using a Tabu Search technique.

• Journal of applied mathematics & informatics
• /
• v.32 no.1_2
• /
• pp.211-225
• /
• 2014

A new class of smoothing functions is introduced in this paper, which includes some important smoothing complementarity functions as its special cases. Based on this new smoothing function, we proposed a smoothing Newton method. Our algorithm needs only to solve one linear system of equations. Without requiring the nonemptyness and boundedness of the solution set, the proposed algorithm is proved to be globally convergent. Numerical results indicate that the smoothing Newton method based on the new proposed class of smoothing functions with ${\theta}{\in}(0,1)$ seems to have better numerical performance than those based on some other important smoothing functions, which also demonstrate that our algorithm is promising.

• The korean journal of orthodontics
• /
• v.29 no.3 s.74
• /
• pp.327-337
• /
• 1999

Patients with skeletal class III can be succesfully treated by either orthognathic surgery or orthodontic treatment owing to unavoidable circumstances. Systers were treated , elder syster by orthognathic surgery and younger one by compromised treatment. For the ideal treatment goal, orthognathic surgery will be inevitable in skeletal problem case, but by the patient's private situations orthodontist cannot help doing compromised treatment. It could be another option if correct biomechanical approach is used.

• Honam Mathematical Journal
• /
• v.25 no.1
• /
• pp.95-115
• /
• 2003

Consider the problem of estimating a $p{\times}1$ mean vector ${\theta}(p{\geq}4)$ under the quadratic loss, based on a sample $X_1,\;{\cdots}X_n$. We find an optimal decision rule within the class of Lindley type decision rules which shrink the usual one toward the mean of observations when the underlying distribution is that of a variance mixture of normals and when the norm $||{\theta}-{\bar{\theta}}1||$ is known, where ${\bar{\theta}}=(1/p)\sum_{i=1}^p{\theta}_i$ and 1 is the column vector of ones. When the norm is restricted to a known interval, typically no optimal Lindley type rule exists but we characterize a minimal complete class within the class of Lindley type decision rules. We also characterize the subclass of Lindley type decision rules that dominate the sample mean.

• Journal of applied mathematics & informatics
• /
• v.27 no.3_4
• /
• pp.501-515
• /
• 2009

A second order nonlinear ordinary differential equation is obtained by solving the initial-boundary value problem of a class of elas-todynamics equations, which models the radially symmetric motion of a incompressible hyper-elastic solid sphere under a suddenly applied surface tensile load. Some new conclusions are presented. All existence conditions of nonzero solutions of the ordinary differential equation, which describes cavity formation and motion in the interior of the sphere, are presented. It is proved that the differential equation has singular periodic solutions only when the surface tensile load exceeds a critical value, in this case, a cavity would form in the interior of the sphere and the motion of the cavity with time would present a class of singular periodic oscillations, otherwise, the sphere remains a solid one. To better understand the results obtained in this paper, the modified Varga material is considered simultaneously as an example, and numerical simulations are given.

• Korean Journal of Child Studies
• /
• v.23 no.3
• /
• pp.149-169
• /
• 2002

The focus of this research was to understand the socio-demographic characteristics, pregnancy conditions, social support, and future plan of teenage unwed mothers in Korea. Among the unwed mother, the teenage group was a higher percentage (53.7%) than the over-twenties group (46.3%). In the distribution of teenage unwed mothers, the major part, 94.6%, was in the 16- to 17- year-old age range, and 5.4% were under 15 years of age. This indicates that the age of unwed mothers is getting lower. Most teenage unwed mothers were from intact(72.3%) and/or low-class(62.3%) families. A significant percentage (37.7%)was from middle- and upper-middle class families, signifying that teenage pregnancy is not a problem only of disadvantaged and lower class families. The education of one-third of the teenage unwed mothers in this study was only up to first year of middle school(7th grade), indicating that pregnancy may be a reason they dropped out of school.

• Journal of Korean Institute of Industrial Engineers
• /
• v.18 no.2
• /
• pp.109-121
• /
• 1992

In this paper, we address a layout design problem for determining a K-class-based dedicated storage layout in an automated storage retrieval system. K-class-based dedicated storage employs K zones in which lots from a class of products are stored randomly. Zones form a partition of storage locations. Our objective function is to minimize the expected single command travel time, which is expressed as a set function of space requirements for zones, average demand rates from classes, and one-way travel times from the pickup/deposit station to locations. We construct a heuristic algorithm based on analytical results and a local search method, the methodology deveolped can be used with easily-available data by warehouse planners to improve the throughput capacity of a conventional warehouse as well as an AS/RS.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.244-247
• /
• 2020

Data augmentation has been helpful in improving the performance in deep learning, when we have a limited data and random erasing is one of the augmentations that have shown impressive performance in deep learning in multiple domains. But the main issue is that sometime it loses good features when randomly selected region is erased by some random values, that does not improve performance as it should. We target that problem in way that good features should not be lost and also want random erasing at the same time. For that purpose, we introduce new augmentation technique named Intra-Class Random Erasing (ICRE) that focuses on data to learn robust features of the same class samples by randomly exchanging randomly selected region. We perform multiple experiments by using different models including resnet18, VGG16 over variety of the datasets including ESC10, UrbanSound8K. Our approach has shown effectiveness over others methods including random erasing.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.585-587
• /
• 2023

Long-tailed datasets have an imbalanced distribution because they consist of a different number of data samples for each class. However, there are problems of the performance degradation in tail-classes and class-accuracy imbalance for all classes. To address these problems, this paper suggests a learning method for training of long-tailed dataset. The proposed method uses and combines two methods; one is a resampling method to generate a uniform mini-batch to prevent the performance degradation in tail-classes, and the other is a reweighting method to address the accuracy imbalance problem. The purpose of our proposed method is to train the learning models to have uniform accuracy for each class in a long-tailed dataset.