• The Journal of the Korea Contents Association
• /
• v.18 no.12
• /
• pp.62-74
• /
• 2018

This study was proposed to examine the mediating effect of basic psychological needs on how parenting attitude affect middle school students with over-dependence on smart phone. This study utilized 2017 survey research by National Information Society Agency (NIA), namely a long-term follow-up study of 901 people with over-dependence on internet and smart phone. This study showed two findings. First, over-dependence on smart phone had correlations with basic psychological needs- autonomy(r=-.22, p<.001) and competence(r=-.13, p<.001); with parenting attitude- positive parenting(r=-.21, p<.001) and negative parenting(r=.15, p<.001). Second, both parenting attitude and basic psychological needs had a causal relationship with over-dependence on smart phone. These results can provide a basis to reconsider social awareness on over-dependence on smart phone among middle school students. This study proposed few research directions for further study to prevent over-dependence on smart phone and to educate parents.

• Journal of Convergence for Information Technology
• /
• v.12 no.4
• /
• pp.47-55
• /
• 2022

This study was conducted to identify the correlation between dental hygiene students' overdependence on smartphones, sleep deprivation, and self-control, and factors influencing self-control. 267 college students in the department of dental hygiene located in the Chungcheong area were surveyed and analyzed. Smartphone overdependence was positively correlated with sleep deprivation and smartphone overdependence was negative correlated with self-control. The sleep deprivation was negative correlated with self-control. Factors affected to self-control were problematic results and sleep deprivation. Therefore, it is necessary to develop education and programs that can increase the self-control of dental hygiene students and to prepare measures to prevent sleep problems and overdependence on smartphone.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.4
• /
• pp.309-315
• /
• 2021

Purpose of this study is to analyze the correlation between the level of smartphone overdependence and depression among the high school student. Study subjects were 50 high school student. The assessment of the level of smartphone overdependence was used by the smartphone overdependence scale for adolescents and the assessment of the level of depression was used by Korean ver. of patient health questionnaire-9. As the results, the positive correlation was showed between the level of smartphone overdependence and depression and the statistically significant difference was showed. It was found that the higher the level of smartphone overdependence among high school students, the higher the level of depression. The smartphone overdependence among high school students could contribute to increase the level of depression. Thus, based on these results of this study, it is necessary to consider to reduce the level of smartphone overdependence and depression among high school students and subsequent studies should be conducted to clarify the casual relationship and influences of the level of smartphone overdependence and depression among high school students.

• Korean Journal of Cognitive Science
• /
• v.17 no.2
• /
• pp.119-138
• /
• 2006

It is widely known that chunking is beneficial to syntactic analysis. This paper introduces a method of chunking thai is useful for structural analysis of sentences in Korean. Dependent nouns in Korean usually tend to make sentences complex and long. By performing chunking operations related with dependent nouns, it is possible to reduce sentence complexity and thus make syntactic analysis easier. With this aim in mind we investigated techniques for chunking related with dependent nouns. We proposed a variety of chunking schemes according to the types of dependent nouns. The experiments showed that carrying out chunking leads to significant improvement of performance in syntactic analysis for Korean.

• Journal of KIISE:Software and Applications
• /
• v.31 no.5
• /
• pp.577-585
• /
• 2004

Storing and estimating the high order probability distribution of classifiers and class labels is exponentially complex and unmanageable without an assumption or an approximation, so we rely on an approximation scheme using the dependency. In this paper, as an extended study of the second-order dependency-based approximation, the probability distribution is optimally approximated by the third-order dependency. The proposed third-order dependency-based approximation is applied to the combination of multiple classifiers recognizing handwritten numerals from Concordia University and the University of California, Irvine and its usefulness is demonstrated through the experiments.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.12 no.5
• /
• pp.976-983
• /
• 1988

An efficient unbalance response analysis method for rotor-bearing systems with spin speed dependent parameters is developed by utilizing a generalized modal analysis scheme. The spin speed dependent eigenvalue problem of the original system is transformed into the spin speed independent eigenvalue problem by introducing a lambda matrix, assuming the bearing dynamic coefficients are well approximated by polynomial functions of spin speed. This method features that it requires far less computational effort in unbalance response calculations and that the influence coefficients are readily available. In addition, the critical speeds and the corresponding logarithmic decrements can be readily identified from the resulting eigenvalues.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.5
• /
• pp.684-690
• /
• 2007

We describe our method to predict the direction of conditional probabilistic dependencies between clusters of random variables. Selected variables called 'gateway variables' are used to predict the conditional probabilistic dependency relations between clusters. The direction of conditional probabilistic dependencies between clusters are predicted by finding directed acyclic graph (DAG)-shaped dependency structure between the gateway variables. We show that our method shows meaningful prediction results in determining directions of conditional probabilistic dependencies between clusters.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.289-294
• /
• 2022

의존구문분석은 문장을 의존관계(의존소-지배소)로 분석하는 구문분석 방법론이다. 현재 사전학습모델을 사용한 전이 학습의 딥러닝이 좋은 성능을 보이며 많이 연구되지만, 데이터셋에 의존적이며 그로 인한 자료부족 문제와 과적합의 문제가 발생한다는 단점이 있다. 본 논문에서는 언어학적 지식에 기반한 강화된 지배소-의존소 제약규칙 에지 알고리즘을 심층학습과 결합한 모델을 제안한다. TTAS 표준 가이드라인 기반 모두의 말뭉치로 평가한 결과, 최대 UAS 96.28, LAS 93.19의 성능을 보였으며, 선행연구 대비 UAS 2.21%, LAS 1.84%의 향상된 결과를 보였다. 또한 적은 데이터셋으로 학습했음에도 8배 많은 데이터셋 학습모델 대비 UAS 0.95%의 향상과 11배 빠른 학습 시간을 보였다. 이를 통해 심층학습과 언어지식의 결합이 딥러닝의 문제점을 해결할 수 있음을 확인하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.401-403
• /
• 2021

본 연구는 한국지능정보사회진흥원에서 제공한 2018년 스마트폰 과의존 실태조사에서 사용된 11개 변수와 스마트폰 과의존과의 관계를 탐색하고, 이를 통해 딥러닝 기반 스마트폰 과의존 분류 분석 모델을 개발하고자 시행되었다. 학습데이터셋은 전국 10,000개 가구내 만 3-69세 스마트폰 이용자 25,465명의 스마트폰 이용 형태 및 개인적 특성에 관한 데이터이다. 딥러닝은 심층신경망(DNN)을 설계하였으며, 은닉층(hidden layer)은 4개층으로 구성하였다. 입력한 데이터는 각각 200개, 150개, 100개, 50개, 2개 노드를 거치면서 최종 출력 정보인 스마트폰 과의존 분류율로 나타나는 모델이다. 이때 스마트폰 과의존 분류률을 높이기 위해 학습률(learning rate)과 같은 하이퍼 파라미터를 활용하여 세부조정하면서 가장 잘 학습하는 값을 찾아내었다. 연구결과, 학습횟수가 300번으로 학습율(learning.rate)이 0.01일때 훈련데이터에서 97.43%, 검증데이터에서 98.06%로 가장 높게 나타났다.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.533-536
• /
• 2019

의존 구문 분석은 문장 구성 성분 간의 의존 관계를 분석하는 태스크로, 자연어 이해의 대표적인 과제 중 하나이다. 본 논문에서는 한국어 의존 구문 분석의 성능 향상을 위해 Deep Bi-Affine Network와 Left to Right Dependency Parser를 적용하고, 새롭게 한국어의 언어적 특징을 반영한 Right to Left Dependency Parser 모델을 제안한다. 3개의 의존 구문 분석 모델에 단어 표현을 생성하는 방법으로 ELMo, BERT 임베딩 방법을 적용하고 여러 종류의 모델을 앙상블하여 세종 의존 구문 분석 데이터에 대해 UAS 94.50, LAS 92.46 성능을 얻을 수 있었다.