• Journal of the Korean Society of Child Welfare
• /
• no.56
• /
• pp.195-220
• /
• 2016

The purpose of this study was to compare between two-parent and single-parent families the relationship between perceived parental monitoring/affection and adolescent offline/online delinquency. we analyzed 1,812 cases of high school students (1,628 cases of two-parent families and 184 cases of single-parent families) using the $4^{th}$-and $5^{th}$-year data from the 'Korean Children and Youth Panel Survey'. We used structural equation modeling to understand the correlation between variables, and conducted multi-group analysis to confirm the distinction between family structures. The results of the study were as follows. First, perceived parental monitoring influenced offline adolescent delinquency only among two parent families, while perceived parental affection did not influence either family type. Second, perceived parental affection influenced online adolescent delinquency only among single-parent families, and the path also had a greater negative effect than two-parent families. In the case of perceived parental monitoring, it did not influence online adolescent delinquency regardless of family type, but the path had a greater negative effect on two-parent families than single-parent families. Based on these results-, more concrete social-welfare practical and political implications about adolescent delinquency proposed.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.01a
• /
• pp.15-18
• /
• 2020

특정 영화의 스크린 독과점이 꾸준히 논란이 되고 있다. 본 논문에서는 영화 스크린 분배의 불평등성을 지적하고 이에 대한 개선을 요구할 근거로 머신러닝 기법을 활용한 영화 관람객 예측 모델을 제안한다. 이에 따라 KOBIS, 네이버 영화, 트위터, 구글 트렌드에서 수집한 3,143개의 영화 데이터를 이용하여 랜덤포레스트와 그라디언트 부스팅 기법을 활용한 영화 관람객 예측 모델을 구현하였다. 모델 평가 결과, 그라디언트 부스팅 모델의 RMSE는 600,486, 랜덤포레스트 모델의 RMSE는 518,989로 랜덤포레스트 모델의 예측력이 더 높았다. 예측력이 높았던 랜덤포레스트 모델을 활용, 상영관을 크게 확보하지 못 했던 봉준호 감독의 영화 '옥자'의 상영관 수를 조절하여 관람객 수를 예측, 6,345,011명이라는 결과를 제시한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.259-261
• /
• 2002

대부분의 자동문서분류 시스템은 문서에 사용된 단어의 분포만 고려하고, 또 하나의 중요한 정보인 통사 정보는 무시한다. 본 논문에서는 통사정보와 어휘정보를 모두 사용함으로써 대규모의 비구조 문서를 분류하는 방법을 제시한다. 이를 위해, 학습 데이터에 대해 독립된 두 개의 관점을 요구하는 일종의 부분 감독 학습 알고리즘인 co-training 알고리즘을 사용한다. 어휘정보와 통사정보가 각각 문서의 독립된 관점이 될 수 있으므로, 이 두 정보와 레이블이 없는 문서를 사용하여 문서 분류의 성능을 높일 수 있다. Reelers-21578 문서집합과 TREC-7 filtering 문서집합에 대한 실험 결과는 제시된 방법의 유효성을 보인다.

• The Journal of the Korea Contents Association
• /
• v.20 no.8
• /
• pp.418-428
• /
• 2020

This study aims to identify the impacts of parenting attitude, self-esteem and depression on school life adaptation in multicultural family adolescents focusing on the mediating effects of self-esteem and depression. To achieve this purpose, the seventh year of the 2016 Multicultural Youth Panel Survey(MAPS) data was used and among all respondents 1,236 multicultural adolescents under 16 years old whose mothers are foreign were collected. Our study findings are as follows: First, supervision and self-esteem had a positive effect, and neglect and depression had a negative effect on school life adaptation. Second, supervision and neglect had a partial influence on school life adaptation through the mediation of self-esteem and depression. Based on these findings, some practical implications was presented to enhance the adaptability of multicultural familiy adolescents to school life adaptation.

• Journal of the Korean Society for information Management
• /
• v.25 no.3
• /
• pp.273-296
• /
• 2008

This study conducted meta-analysis of librarians' job satisfaction using the Hedges & Olkin's Effect Size Model. Sex and Marrage as group variables, and Total Satisfaction and 7 sub-variables(Work Itself, Salary, Promotion, Supervision, Working Conditions, Social Recognition, Self-actualization) as dependent variables were selected from 27 studies. The effect sizes between men and women were significantly different on Supervision, Working conditions, Promotion, and Social Recognition, of which first two were homogeneous. But the difference of Social Recognition was not significant in Random Effect Model. The effect sizes difference between married and unmarried were significant on Self Recognition, Salary, and Work Itself. However the difference of Work Itself was not significant in Random Effect Model. Study Year could not be a moderator.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.181-188
• /
• 2024

Traditional profanity detection methods have limitations in identifying intentionally altered profanities. This paper introduces a new method based on Named Entity Recognition, a subfield of Natural Language Processing. We developed a profanity detection technique using sequence labeling, for which we constructed a dataset by labeling some profanities in Korean malicious comments and conducted experiments. Additionally, to enhance the model's performance, we augmented the dataset by labeling parts of a Korean hate speech dataset using one of the large language models, ChatGPT, and conducted training. During this process, we confirmed that filtering the dataset created by the large language model by humans alone could improve performance. This suggests that human oversight is still necessary in the dataset augmentation process.

• Journal of Digital Convergence
• /
• v.20 no.3
• /
• pp.35-40
• /
• 2022

With the advent of the internet age and the outbreak of COVID-19, many companies have embraced online trade. However, due to the way the cyber economy works, the number of companies engaged in financial fraud by falsifying their transaction amounts and customer numbers has been gradually increasing. The purpose of this study is to analyze financial fraud of companies in the Internet era and to present solutions. Therefore, this study analyzed the financial fraud behavior of Luckin Coffee in China as an example and studied the causes and countermeasures of financial fraud. As a result, it was found that the cause of financial fraud lies in the opacity of cash flows from online transactions. The recommendations proposed by this study is to improve internal control systems in companies, develop risk management system, and establish comprehensive external supervision system

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.809-816
• /
• 2023

The purpose of this study is to implement a device using the Raspberry Pi that can transmit and supervise data between devices and servers using the oneM2M standard platform, Mobius. Operating under the same concept as a Gateway or Router, this device performs the role of forwarding packets sent from end nodes to other networks. Theoretical functionality has been achieved to concurrently connect and supervise up to 65536 devices. The communication methods for end nodes connected to the Gateway include ZigBee and WiFi, and for long-distance communication, tests were conducted using LoRa modules.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.6 no.2
• /
• pp.80-91
• /
• 2003

In this research, re-using band ratio data was proposed and examined as a method of raising the accuracy in landcover classification which is using satellite data.In order to determine the band which is used to calculation in the classified item, the six bands except the band 6 were combined with the band in which combination is possible and the landcover classification by MLC of supervised classification was carried out. In the result of landcover classification which is combined with forty nine combination, Two bands which were mostly used by band combination in the accuracy belonged inside the 10th place of a higher rank were selected and also calculated. landcover classification were performed again after the calculation result had been recombinated from the research. In addition, the new landcover classification result was compared and examined with the landcover classification using the old data. From the result of which was compared and examined the new landcover classification data recombinated calculation result with landcover classification using the original data, The classification accuracy of the new landcover classification data recombinated calculation result became low in ground but became improved in the all class. Specially The accuracy to urban area is very improved. therefore, it determined that reusing band ratio data is very useful when we need to analyze landcover classification and land information to urban area after that.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.4
• /
• pp.472-476
• /
• 2007

Learning rule affects importantly the performance of neural network. This paper proposes a new fuzzy learning rule that uses the learning rate considering the distance between the input vector and the prototypes of classes. When the learning rule updates the prototypes of classes, this consideration reduces the effect of outlier on the prototypes of classes. This comes from making the effect of the input vector, which locates near the decision boundary, larger than an outlier. Therefore, it can prevents an outlier from deteriorating the decision boundary. This new fuzzy learning rule is integrated into IAFC(Integrated Adaptive Fuzzy Clustering) fuzzy neural network. Iris data set is used to compare the performance of the proposed fuzzy neural network with those of other supervised neural networks. The results show that the proposed fuzzy neural network is better than other supervised neural networks.