• 한국가족관계학회지
• /
• 제23권1호
• /
• pp.3-24
• /
• 2018

Objective: This study examined the change of informal labeling self-respect, depression/anxiety, and aggression of adolescents over time and relationship between the intercept and the growth of the variables. Method: 4-year longitudinal panel data(n=2,699), Korea Youth Panel Survey (KYPS), were analyzed to verify the influence of informal labeling on self-respect, depression/anxiety, and aggression of adolescents. Through latent growth modeling, temporal change of the variables was examined. Results: Analytic results are as follow. First, the initial status of informal labeling had a negative impact on the initial status of self-respect. The slope of informal labeling also had a negative impact on the slope of self-respect. In contrast, the initial status of informal labeling did not have an significant impact on the slope of self-respect. Second, the initial status of informal labeling had a positive impact on the initial status of aggression. The slope of informal labeling had a negative impact on the slope of aggression. In contrast, the initial status of informal labeling did not have an significant impact on the slope of aggression. Third, the initial status of informal labeling had a positive impact on the initial status of depression/anxiety and a negative impact on the slope of depression/anxiety. The slope of informal labeling had a positive impact on the slope of self-respect. Conclusions: The results suggest the importance of informal labeling on self-respect, depression/anxiety, and aggression of adolescents.

• International Journal of Computer Science & Network Security
• /
• 제21권6호
• /
• pp.207-212
• /
• 2021

Clustering Unlabeled Spatial-datasets to convert them to Labeled Spatial-datasets is a challenging task specially for geographical information systems. In this research study we investigated the NYC Taxi Limousine Commission dataset and discover that all of the spatial-temporal trajectory are unlabeled Spatial-datasets, which is in this case it is not suitable for any data mining tasks, such as classification and regression. Therefore, it is necessary to convert unlabeled Spatial-datasets into labeled Spatial-datasets. In this research study we are going to use the Clustering Technique to do this task for all the Trajectory datasets. A key difficulty for applying machine learning classification algorithms for many applications is that they require a lot of labeled datasets. Labeling a Big-data in many cases is a costly process. In this paper, we show the effectiveness of utilizing a Clustering Technique for labeling spatial data that leads to a high-accuracy classifier.

• 한국식생활문화학회지
• /
• 제30권2호
• /
• pp.190-196
• /
• 2015

Restaurants implement menu labeling to provide nutritional information to customers in an attempt to help customers select healthy menu items. Considering the increase in food-away-from-home consumption, the purpose of this study was to identify motivators and barriers in restaurant customers regarding use of menu labeling. Data were collected from a survey on restaurant customers in Seoul, Korea. The findings of this study indicate that customers used menu labeling for health reasons. However, barriers to using menu labeling were identified as small font size, difficulty in locating nutritional information display, and difficulty in interpreting nutritional information. In addition, they also suggested expanding the scope of menu labeling for restaurants by including chain restaurants with less than 100 units. The findings of this study offer strategies for the government to improve menu labeling practices for customers.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제11권7호
• /
• pp.233-240
• /
• 2022

최근 대부분의 인공지능 연구는 AI 모델 개발에 중점을 두고 있다. 하지만 최근 인공지능 연구가 모델 중심에서 데이터 중심으로 점차 변경되고 이런 추세를 바탕으로 학습데이터의 중요성이 크게 주목 받고 있다. 그러나 학습데이터의 준비과정이 전체 과정의 상당 부분을 차지하고 라벨링 데이터 생성 또한 개발 목적에 따라 다르기 때문에 많은 시간과 노력이 필요하다. 따라서 기존의 미충족을 해결하기 위한 다양한 라벨링 기능을 갖는 도구 개발이 필요하다. 본 논문에서는 의료영상의 라벨링 데이터를 정교하고 빠르게 생성하기 위한 라벨링 시스템에 대해서 기술한다. 이를 구현하기 위해서 Back Projection, GrabCut 기법을 이용한 반자동 방식과 기계학습 모델을 통해서 예측한 자동 방식의 라벨링 기능을 구현하였다. 우리는 제안한 시스템의 라벨링 데이터 생성에 대한 수행시간의 장점을 보였을뿐만 아니라 정확성에 대한 비교평가를 통해 우수성을 보였다. 또한 1,000여명의 환자 영상 데이터셋을 분석하여 근감소증 진단에 남성과 여성에 의미있는 진단지표를 제시하였다.

• 한국인터넷방송통신학회논문지
• /
• 제24권1호
• /
• pp.175-180
• /
• 2024

본 논문에서는 딥러닝 기반의 주의환기 보상전략 시스템이 발달장애인의 데이터 라벨링 작업 생산성에 미치는 효과를 분석하였다. 연구 결과, 중재가 적용된 후 연구대상자 모두 자율작업 대비 작업 생산성에서 유의미한 향상이 관찰되었다. 특히 인공지능 기반의 중재가 적용되었을 때, 직무지도원 중재에 비해 상당한 향상을 보였다. 이러한 결과는 인공지능 기술이 발달장애인의 데이터 라벨링 작업 생산성 향상에 긍정적인 영향을 미칠 수 있음을 의미한다. 본 연구는 발달장애인의 데이터 라벨링 작업에 인공지능 기술을 접목한 최초의 연구이며, 발달장애인의 직업훈련과 작업 생산성 증진을 위한 딥러닝 기술의 적용 가능성을 탐색하는 데 중요한 시사점을 제공하리라 본다.

• 한국식품영양학회지
• /
• 제24권3호
• /
• pp.282-290
• /
• 2011

This study was performed to investigate the level and recognition and interest in nutrition labeling in restaurants according to consumer interest levels in health and to suggest its application to restaurant lunches. By considering various statistics and data on the frequency of reasons for dining-out, this study examined worker restaurant lunches and investigated the level of recognition of interest in nutrition labeling, the type of nutrition information that is of interest and the preferred format of labeling according to the level of interest in health. According to the results, while the frequency of dining-out by workers was high, their consideration for health and nutrition labeling in restaurants was low. However, a high percentage of consumers responded that nutrition labeling was a customer right and necessary to improve the quality of menu items as well as public health. Therefore, active promotion of nutrition labeling in the dining industry is necessary. Interest levels in additives, product origin and menu ingredients indicated in restaurant menus were higher than for nutritional information such as nutrients and calories. When the preferred format for providing nutrition information was investigated, consumers preferred information written on a menu board, and they wanted to broaden the range of information included in nutrition labeling for menu items beyond calories and nutritional facts. Based on these results, recognition of nutrition labeling in restaurants was found to below and the interest level in health was also lower than expected. However, most consumers responded that nutrition labeling was helpful in choosing menu items can be a tool for nutrition education and can play a role in improving the recognition of nutrition. Therefore, active promotion of nutrition labeling by the dining industry is necessary.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2005년도 한국컴퓨터종합학술대회 논문집 Vol.32 No.1 (B)
• /
• pp.106-108
• /
• 2005

XML is situating a standard fur data exchange in the Web. Most applications use database to manage XML documents of high-capacity efficiently. Therefore, most applications create label that expresses structure information of XML data and stores with information of XML document. A number of labeling schemes have been designed to label the element nodes such that the relationships between nodes can be easily determined by comparing their labels. With the increased popularity of XML data on the web, finding a labeling scheme that is able to support order-sensitive queries in the presence of dynamic updates becomes urgent. XML documents that most applications use have many properties as their application. So, in the thesis, we present the most efficient updating methods dependent on properties of XML documents in practical application by choosing a representative labeling method and applying these properties. The result of our test is based on XML data management system, so it expect not only used directly in practical application, but a standard to select the most proper methods for environment of application to develop a new exclusive XML database or use XML.

• 한국콘텐츠학회논문지
• /
• 제14권1호
• /
• pp.14-23
• /
• 2014

인터넷 상에서 광범위한 데이터 교환 및 저장의 수단으로 XML에 대한 많은 연구가 진행되어왔다. 특히, XML 문서에 대한 구조 정보를 검색하기 위해서 XML 트리의 각 노드에 레이블을 부여하는 레이블링 기법에 대한 연구가 요구되었다. 레이블링 기법은 각 노드에 레이블을 할당하여 XML 트리 상에서 조상-후손 또는 부모-자식 등의 구조 정보를 검색 할 수 있게 한다. 또한, 레이블링 기법은 기존의 레이블들에 영향을 주지 않도록 동적인 XML 문서 환경을 효율적으로 지원해야 하는 요구 사항을 가진다. 본 논문에서 제안하는 레이블링 기법은 벡터 표현 방식을 기반으로 동적인 XML 문서의 변경을 효율적으로 지원하고 레이블의 길이를 줄임으로서 XML 문서의 레이블 크기를 작게 하여 저장 공간을 적게 요구할 뿐 아니라 검색시간을 향상시킨다. 성능 실험을 통하여 기존의 레이블링 기법보다 레이블 크기와 검색 시간 등에서 우수함을 보인다.

• 대한영양사협회학술지
• /
• 제23권3호
• /
• pp.274-284
• /
• 2017

This study examined the awareness, understanding, attitudes, and purchase intention regarding food labeling on bakery products in the context of health consciousness. The purpose of the study was to provide basic data for bakery product labeling, which has been insufficient to date, and to develop measures to expand the labeling system. The results of the study showed that higher subjective understanding and better attitude towards bakery food labeling can positively increase the purchase intention. We believe that the bakery industry needs to promote food labeling proactively, while also developing products addressing health concerns. This study is also valuable to academia because it provides insights into the relationship between the consumer's understanding of and attitudes towards nutritional information and purchase intention. In addition, it is beneficial to the bakery industry because it establishes marketing strategies that increase the purchase intent among both consumers with high health consciousness and those who infrequently purchase baked goods.

• Smart Structures and Systems
• /
• 제29권6호
• /
• pp.757-766
• /
• 2022

To train deep learning algorithms, a sufficient number of data are required. However, in most engineering systems, the acquisition of fault data is difficult or sometimes not feasible, while normal data are secured. The dearth of data is one of the major challenges to developing deep learning models, and fault diagnosis in particular cannot be made in the absence of fault data. With this context, this paper proposes an anomaly detection methodology for rotating machines using only normal data with self-labeling. Since only normal data are used for anomaly detection, a self-labeling method is used to generate a new labeled dataset. The overall procedure includes the following three steps: (1) transformation of normal data to self-labeled data based on a pretext task, (2) training the convolutional neural networks (CNN), and (3) anomaly detection using defined anomaly score based on the softmax output of the trained CNN. The softmax value of the abnormal sample shows different behavior from the normal softmax values. To verify the proposed method, four case studies were conducted, on the Case Western Reserve University (CWRU) bearing dataset, IEEE PHM 2012 data challenge dataset, PHMAP 2021 data challenge dataset, and laboratory bearing testbed; and the results were compared to those of existing machine learning and deep learning methods. The results showed that the proposed algorithm could detect faults in the bearing testbed and compressor with over 99.7% accuracy. In particular, it was possible to detect not only bearing faults but also structural faults such as unbalance and belt looseness with very high accuracy. Compared with the existing GAN, the autoencoder-based anomaly detection algorithm, the proposed method showed high anomaly detection performance.