• Journal of Fashion Business
• /
• v.8 no.3
• /
• pp.10-19
• /
• 2004

The purpose of this research is to reveal the antimicrobial activity of pet-dog clothes by investigating the bacteria resistance of 4 kinds of pet-dog clothes materials. 1. Investigation Results of Pet-Dog Clothes 64.7% of 150 survey participants, revealed they had pet-dog clothes. Hand laundering was 67.0%, while the laundering of both human and animal clothes was 9.2%. The greatest washing frequency was once every 2 weeks. So, the subjects didn't seem to think high of hygienic matters. Even though no if any relations were reported by 34.7% of the subjects, there were some experiences like sneezing or coughing (41.3%), slight itching (20.7%), and acute skin allergies. There were such hugging methods as heart to heart to the center (22.7%), face to face and around the mouth (16.7%), and below the heart with the dog's face outward (15.3%). Thus, hugging the dog near the pet-lover's face seems to be the cause of respiratory diseases including sneezes and coughs. 2. Results of the Anti-Bacteria Experiment of Pet-Dog Clothes Materials According to the analysis of the germs collected and cultured in this study to reveal the properness of pet-dog clothes materials, they were bacteria or bacilli in shapes. Spore growth was active in the order of such experimental materials as artificial leather > cotton > cotton/ nylon > polyester (finest thread). In terms of germ groups, the order was polyester(finest thread) > cotton > cotton/ nylon > artificial leather.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.437-440
• /
• 2020

최근 자연어 처리에서는 사전 학습과 전이 학습을 통하여 다양한 과제에 높은 성능 향상을 성취하고 있다. 사전 학습의 대표적 모델로 구글의 BERT가 있으며, 구글에서 제공한 다국어 모델을 포함해 한국의 여러 연구기관과 기업에서 한국어 데이터셋으로 학습한 BERT 모델을 제공하고 있다. 하지만 이런 BERT 모델들은 사전 학습에 사용한 말뭉치의 특성에 따라 이후 전이 학습에서의 성능 차이가 발생한다. 본 연구에서는 소셜미디어에서 나타나는 구어체와 신조어, 특수문자, 이모지 등 일반 사용자들의 문장에 보다 유연하게 대응할 수 있는 한국어 뉴스 댓글 데이터를 통해 학습한 KcBERT를 소개한다. 본 모델은 최소한의 데이터 정제 이후 BERT WordPiece 토크나이저를 학습하고, BERT Base 모델과 BERT Large 모델을 모두 학습하였다. 또한, 학습된 모델을 HuggingFace Model Hub에 공개하였다. KcBERT를 기반으로 전이 학습을 통해 한국어 데이터셋에 적용한 성능을 비교한 결과, 한국어 영화 리뷰 코퍼스(NSMC)에서 최고 성능의 스코어를 얻을 수 있었으며, 여타 데이터셋에서는 기존 한국어 BERT 모델과 비슷한 수준의 성능을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.458-460
• /
• 2023

가공식품이라는 특정 도메인에서는 기존 검색엔진에서 많이 활용되는 BM25 만을 가지고 최저가 검색하는 데는 어려움이 있다. 본 논문에서는 BM25 외에도 검색의 정확성을 높이기 위해 HuggingFace 에 공개되어 있는 KoELECTRA 를 활용하여 개체명 인식(Named Entity Recognition 과 이진 분류모델(Binary Classification)을 Fine-tuning 하고 BM25 와 연계하여 구축한 검색시스템을 제안한다. 기존의 BM25 대비 성능 평가를 통해 효과를 검증하였다.

• International Journal of Advanced Culture Technology
• /
• v.11 no.4
• /
• pp.442-448
• /
• 2023

Artificial Intelligence (AI) technology has recently grown explosively and is being used in a variety of application fields. Accordingly, the number of AI models is rapidly increasing. AI models are adapted and developed to fit a variety of data types, tasks, and environments, and the variety and volume of models continues to grow. The need to share models and collaborate within the AI community is becoming increasingly important. Collaboration is essential for AI models to be shared and improved publicly and used in a variety of applications. Therefore, with the advancement of AI, the introduction of Model Hub has become more important, improving the sharing, reuse, and collaboration of AI models and increasing the utilization of AI technology. In this paper, we collect data on the model hub and analyze the characteristics of the model hub and the AI models provided. The results of this research can be of great help in developing various multimodal AI models in the future, utilizing AI models in various fields, and building services by fusing various AI models.

• Smart Media Journal
• /
• v.10 no.2
• /
• pp.76-83
• /
• 2021

With the development and use of smart devices such as smartphones and tablets increases, the mobile application market based on mobile devices is growing rapidly. Mobile application users write reviews to share their experience in using the application, which can identify consumers' various needs and application developers can receive useful feedback on improving the application through reviews written by consumers. However, there is a need to come up with measures to minimize the amount of time and expense that consumers have to pay to manually analyze the large amount of reviews they leave. In this work, we propose to collect delivery application user reviews from Google PlayStore and then use machine learning and deep learning techniques to classify them into four categories like application feature advantages, disadvantages, feature improvement requests and bug report. In the case of the performance of the Hugging Face's pretrained BERT-based Transformer model, the f1 score values for the above four categories were 0.93, 0.51, 0.76, and 0.83, respectively, showing superior performance than LSTM and GRU.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.161-166
• /
• 2021

본 연구는 한국어 문장 임베딩(embedding)에 담겨진 언어적 속성을 평가하기 위한 프로빙 태스크(Probing Task)를 소개한다. 프로빙 태스크는 임베딩으로부터 문장의 표층적, 통사적, 의미적 속성을 구분하는 문제로 영어, 폴란드어, 러시아어 문장에 적용된 프로빙 테스크를 소개하고, 이를 기반으로하여 한국어 문장의 속성을 잘 보여주는 한국어 문장 임베딩 프로빙 태스크를 설계하였다. 언어 공통적으로 적용 가능한 6개의 프로빙 태스크와 한국어 문장의 주요 특징인 주어 생략(SubjOmission), 부정법(Negation), 경어법(Honorifics)을 추가로 고안하여 총 9개의 프로빙 태스크를 구성하였다. 각 태스크를 위한 데이터셋은 '세종 구문분석 말뭉치'를 의존구문문법(Universal Dependency Grammar) 구조로 변환한 후 자동으로 구축하였다. HuggingFace에 공개된 4개의 다국어(multilingual) 문장 인코더와 4개의 한국어 문장 인코더로부터 획득한 임베딩의 언어적 속성을 프로빙 태스크를 통해 비교 분석한 결과, 다국어 문장 인코더인 mBART가 9개의 프로빙 태스크에서 전반적으로 높은 성능을 보였다. 또한 한국어 문장 임베딩에는 표층적, 통사적 속성보다는 심층적인 의미적 속성을 더욱 잘 담고 있음을 확인할 수 있었다.

• Korean Journal of Social Welfare
• /
• v.44
• /
• pp.146-177
• /
• 2001

One of the difficulties of female-headed families face is economic hardship. Low-income single mothers work long hours, become isolated and feel burdened for dual roles. And many of them don't have relatives to share parenting roles. As a result, children of low-income female-headed families are easy to be neglected and left to form a delinquency-prone group in neighborhood. Traditionally, it has been viewed that children in female-headed families have problems due to the loss of father role. However, study indicates that these children can adjust well if the relationship between mothers and children is consistent and adequate. An Intervention program for low-income female-headed elementary children was developed and delivered in two community social welfare centers. The purpose of the program is to raise self-esteem. Two goals were 1) management of daily living habits and 2) improvement of family relations. Social workers maintained contact with mothers to talk about children's behaviors and to prompt hugging and touching. In addition, workers helped children to form good relationships with peers and school teachers. Children were satisfied with the program. Their family relations were improved statistically significantly after the program(wilcoxon signed rant test z=-2.934 p<.05). However, their self esteem were not improved significantly (wilcoxon signed test z=-1.173 p>.05). Qualitative analysis of each children were also discussed. The implications of the study are the followings: Intervention programs need to be delivered separately for low-grade and high grade elementary children because they have different developmental needs. The program also need to include education on sex and marriage as well as aggression reduction. Society needs to provide more support to single mothers for their personal and parenting needs.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.30 no.3
• /
• pp.341-347
• /
• 2003

Smith-Magenis syndrome (SMS) is a clinically recognizable multiple congenital anomaly and mental retardation syndrome caused by an interstitial deletion of chromosome 17 p11.2. Physical features include short stature, characteristic facial appearance: flattened mid-face, down-turned mouth, prominent and often rosy cheeks; prominent jaw in older children and adults, chronic ear infections, hearing impairment, eye problems, including: strabismus (an eye which turns in or out) and myopia (nearsightedness), hoarse voice, short fingers and toes, heart defects or murmurs, problems related to the urinary system, scoliosis (curvature of the spine), an unusual gait (walking pattern), and decreased sensitivity to pain. Behavioral and developmental characteristics include speech delay and articulation problems, developmental delay, learning disability, mental retardation, hyperactivity, self-injury, including: head banging; hand biting; picking at skin, sores and nails; pulling off finger- and toenails; inserting foreign objects into ears, nose, or other body orifices, explosive outbursts, prolonged tantrums, destructive and aggressive behavior, excitability, arm hugging or hand squeezing when excited. This report is the case of a Korean 3-year-3-month old male with Smith-Magenis syndrome referred from local clinic for the treatment of dental caries. The patient was treated by physical restraint after prophylatic administration of antibiotic(Amoxacillin 50mg/kg).