• International Journal of Human Ecology
• /
• v.12 no.2
• /
• pp.13-24
• /
• 2011

This study compared actual weight with perceived weight, described the prevalence of unhealthy weight control behavior, determined the differences in psychological and personal variables between participants that reported unhealthy weight control behavior and those who did not, and examined the relationship of eating habits to unhealthy weight control behavior for Korean adolescents. The study population consisted of a nationally representative sample of middle and high school students who completed the Fifth Korea Youth Risk Behavior Web-based Survey (KYRBWS): Fifth in 2009. Among the 75,066 participants of KYRBWS, 35,473 (n = 18,851 girls and 16,622 boys) were eligible for a research focused on unhealthy weight control behavior. The results of this research were as follows: First, there were considerable discrepancies (45.1% of girls and 32.8% of boys) between the perceived weight and the actual weight. Second, overall, unhealthy weight control behavior was more prevalent in girls and fasting was the most commonly reported behavior. Third, participants that reported unhealthy weight control behavior scored significantly lower on scaled measures of happiness, health, academic achievement, and economic status; in addition, they scored higher on stress measures. Fourth, girls and boys shared common protective factors of having breakfast and vegetables more often, perceiving their weight as underweight rather than overweight, and having a correct weight conception. Protective factors unique to girls were having lunch and dinner more often. Girls and boys shared common risk factors of the consumption of soda, fast food, instant noodles, and snacks more often, while consumption of fruit more often was a risk factor only for girls. The improvement of protective factors and minimization of risk factors through Home Economics classes (and other classes relevant to health) may mitigate unhealthy weight control behavior of adolescents.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.5
• /
• pp.33-39
• /
• 2011

In modern society, in business decisions of our customers are continually increasing in importance, and owing to the development of information and communication technology effectively on a computer to measure the preferences of key customer techniques are being studied. However, this preference reflects significantly on personal ideas, and therefore, it is difficult to commercialize a measure calculated according to the ambiguous results. In this paper, by using biometric information that has been measure; we have configured the multi-sensitivity models based on customer preferences to evaluate the proposed system. This system consists of multiple biometric information of multi-dimensional vector model for learning through the use of structured emotional to apply the same criteria to evaluate customer preferences. In addition, by studying the specific subject-specific emotion model, it is shown to improve accuracy with further experiments.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.251-256
• /
• 2021

Unlike general cameras, a high-speed camera capable of capturing a large number of frames per second can enable the advancement of some image processing technologies that have been limited so far. This paper proposes a method of removing undesirable noise from an high-speed input color image, and then detecting a human face from the noise-free image. In this paper, noise pixels included in the ultrafast input image are first removed by applying a bidirectional filter. Then, using RetinaFace, a region representing the person's personal information is robustly detected from the image where noise was removed. The experimental results show that the described algorithm removes noise from the input image and then robustly detects a human face using the generated model. The model-based face-detection method presented in this paper is expected to be used as basic technology for many practical application fields related to image processing and pattern recognition, such as indoor and outdoor building monitoring, door opening and closing management, and mobile biometric authentication.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.85-110
• /
• 2018

A chatbot is an interactive assistant that utilizes many communication modes: voice, images, video, or text. It is an artificial intelligence-based application that responds to users' needs or solves problems during user-friendly conversation. However, the current version of the chatbot is focused on understanding and performing tasks requested by the user; its ability to generate personalized conversation suitable for relationship-building is limited. Recognizing the need to build a relationship and making suitable conversation is more important for social chatbots who require social skills similar to those of problem-solving chatbots like the intelligent personal assistant. The purpose of this study is to propose a text analysis method that evaluates relationships between chatbots and users based on content input by the user and adapted to the communication situation, enabling the chatbot to conduct suitable conversations. To evaluate the performance of this method, we examined learning and verified the results using actual SNS conversation records. The results of the analysis will aid in implementation of the social chatbot, as this method yields excellent results even when the private profile information of the user is excluded for privacy reasons.

• Research in Community and Public Health Nursing
• /
• v.30 no.3
• /
• pp.295-306
• /
• 2019

Purpose: There has been a growing recognition that person-centered care enhances the quality of life of nursing home residents with dementia. This study was conducted to develop a person-centered dementia care online education program for direct care staff in long-term care facilities. Methods: Delphi method with expert group was used to validate contents. We developed 61 draft items based on literature review. Twenty experts participated in consecutive three round surveys including 5-point Likert scale questions and open-ended questions. Based on experts' opinions, the content validity ratio for content validity and the coefficient of variation for stability were calculated. Results: Three-round Delphi surveys and additional feedback from the expert panel established a consensus of core contents: 1) dementia (7 categories), 2) person-centered care (6 categories), 3) communication (8 categories), and 4) behavioral and psychological symptoms of dementia (6 categories). Specific sub-categories in each category were differentiated according to the job qualifications (65 sub-categories for registered nurses, 64 sub-categories for nursing aids, and 41 sub-categories for personal care workers). Conclusion: This delphi study identified person-centered dementia education curricula, in which the person-centered approach should be a key policy priority in Korean long-term care system. Now it is urgently needed to develop education programs utilizing online platforms that enable efficient and continuous learning for long-term care staff, which can contribute to behavior changes in the person-centered dementia care approach and improvement of care quality in long-term care facilities.

• The korean journal of orthodontics
• /
• v.51 no.2
• /
• pp.77-85
• /
• 2021

Objective: To evaluate the accuracy of a multi-stage convolutional neural network (CNN) model-based automated identification system for posteroanterior (PA) cephalometric landmarks. Methods: The multi-stage CNN model was implemented with a personal computer. A total of 430 PA-cephalograms synthesized from cone-beam computed tomography scans (CBCT-PA) were selected as samples. Twenty-three landmarks used for Tweemac analysis were manually identified on all CBCT-PA images by a single examiner. Intra-examiner reproducibility was confirmed by repeating the identification on 85 randomly selected images, which were subsequently set as test data, with a two-week interval before training. For initial learning stage of the multi-stage CNN model, the data from 345 of 430 CBCT-PA images were used, after which the multi-stage CNN model was tested with previous 85 images. The first manual identification on these 85 images was set as a truth ground. The mean radial error (MRE) and successful detection rate (SDR) were calculated to evaluate the errors in manual identification and artificial intelligence (AI) prediction. Results: The AI showed an average MRE of 2.23 ± 2.02 mm with an SDR of 60.88% for errors of 2 mm or lower. However, in a comparison of the repetitive task, the AI predicted landmarks at the same position, while the MRE for the repeated manual identification was 1.31 ± 0.94 mm. Conclusions: Automated identification for CBCT-synthesized PA cephalometric landmarks did not sufficiently achieve the clinically favorable error range of less than 2 mm. However, AI landmark identification on PA cephalograms showed better consistency than manual identification.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.2
• /
• pp.201-210
• /
• 2023

Deep learning-based face verificattion model show high performance and are used in many fields, but there is a possibility the user's face image may be leaked in the process of inputting the face image to the model. Althoughde-identification technology exists as a method for minimizing the exposure of face features, there is a problemin that verification performance decreases when the existing technology is applied. In this paper, after combining the face features of other person, a de-identified face image is created through StyleGAN. In addition, we propose a method of optimizingthe combining ratio of features according to the face verification model using HopSkipJumpAttack. We visualize the images generated by the proposed method to check the de-identification performance, and evaluate the ability to maintain the performance of the face verification model through experiments. That is, face verification can be performed using the de-identified image generated through the proposed method, and leakage of face personal information can be prevented.

• Advanced Industrial SCIence
• /
• v.3 no.1
• /
• pp.30-36
• /
• 2024

Recently, the Internet of Things (IoT), which has been applied to various industrial fields, is constantly evolving in the process of automation and digitization. However, in the network where IoT devices are built, research on IoT critical information-related data sharing, personal information protection, and data integrity among intermediate nodes is still being actively studied. In this study, we propose a blockchain-based IoT critical information management technique that is easy to implement without burdening the intermediate node in the network environment where IoT is built. The proposed technique allocates a random value of a random size to the IoT critical information arriving at the intermediate node and manages it to become a decentralized P2P blockchain. In addition, the proposed technique makes it easier to manage IoT critical data by creating licenses such as time limit and device limitation according to the weight condition of IoT critical information. Performance evaluation and proposed techniques have improved delay time and processing time by 7.6% and 10.1% on average compared to existing techniques.

• The Journal of the Korea Contents Association
• /
• v.18 no.10
• /
• pp.453-463
• /
• 2018

An analysis including ASE model accessing based on the intention of behavior performance of online university students is a new approach to improve academic persistence considering the characteristics of students with extensive personal variables, a uniqueness of learning environment. This study aimed to identify the relationship between ASE model including academic stress and academic persistence, and the effect of these factors on academic persistence of online university students. Data were collected from 181 sophomores in K open university from March to June, 2018. Frequency analysis, ${\chi}^2-test$, t-test, F-test, Pearson's correlation analysis, and multiple regression analysis used for data analysis. For factors affecting academic persistence, academic stress (${\beta}=-.16$, p=.016), online learning attitude (${\beta}=.44$, p<.001), and social support among social influential factors (${\beta}=.16$, p=.045) were statistically significant and the prediction model of academic persistence showed 29% explanation power (F=15.76, p<.001). To enhance academic persistence of online university students, it is needed to develop programs to reduce academic stress, improve attitude toward online learning, and improve social support.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.4
• /
• pp.153-163
• /
• 2017

This research is based on the previous research that personally preferred safe distance, rotating angle and speed are differentiated. Thus, we use machine learning model for recognizing maneuvering modes trained per personal or per similar driving pattern groups, and we evaluate automatic driving according to maneuvering modes. By utilizing driving knowledge, we subdivided 8 kinds of longitudinal modes and 4 kinds of lateral modes, and by combining the longitudinal and lateral modes, we build 21 kinds of maneuvering modes. we train the labeled data set per time stamp through RNN, LSTM and Bi-LSTM models by the trips of drivers, which are supervised deep learning models, and evaluate the maneuvering modes of automatic driving for the test data set. The evaluation dataset is aggregated of living trips of 3,000 populations by VTTI in USA for 3 years and we use 1500 trips of 22 people and training, validation and test dataset ratio is 80%, 10% and 10%, respectively. For recognizing longitudinal 8 kinds of maneuvering modes, RNN achieves better accuracy compared to LSTM, Bi-LSTM. However, Bi-LSTM improves the accuracy in recognizing 21 kinds of longitudinal and lateral maneuvering modes in comparison with RNN and LSTM as 1.54% and 0.47%, respectively.