• Journal of The Korean Association For Science Education
• /
• v.25 no.4
• /
• pp.441-449
• /
• 2005

The purpose of this study was to examine the degree of cognitive conflict by learner personality and the method of presenting anomalous data to induce cognitive conflict. The participants of this study were 461 high school students. To arose cognitive conflict, an actual demonstration was done for half of the participants and a logical article for the rest. MBTI (Myers-Briggs Type Indicator) was used to find the learner personality types, and CCLT (Cognitive Conflict Level Test) was used to measure the degree of cognitive conflict aroused when anomalous data was confronted. The results of this study indicated that learner personality types influence the degree of cognitive conflict. First, participants were divided into two personality types via preferences on each of the four preference indices; extraversion (E) or introversion (I), sensing (S) or intuition (N), thinking (T) or feeling (F), judgment (J) or perception (P). The cognitive conflict scores of the thinking types were significantly higher than those of the feeling types. Participants were also divided four personality types according to personality functional types: ST, SF, NT and NF. SF type showed a significantly lower cognitive conflict score than any of the other types. According to the type of learner personality, cognitive conflict was influenced differently by the method of presenting anomalous data. For example, the judgment types had a higher cognitive conflict score by logical argument, and the perception types showed a higher score by demonstration. In conclusion, learner cognitive conflicts were influenced by personality types and the methods of presenting anomalous data.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.44 no.4
• /
• pp.610-618
• /
• 2015

The purpose of this study was to analyze differences in emotional labor strategies, burnout, and work engagement according to general characteristics of school foodservice employees as well as verify differential effects of two emotional labor strategies on burnout and work engagement. Our survey was administered to 400 school foodservice employees in Gyeongbuk from March 3 to April 25, 2014. A total of 358 completed questionnaires were returned, and 350 questionnaires were used for final analysis. For verification of mean differences, the mean scores for surface acting, deep acting, burnout, and work engagement were shown to be 2.38/5.00, 3.46, 2.67, and 3.41, respectively. The mean surface acting was significantly different according to cooking certification (P<0.001), turnover number (P<0.001), salary (P<0.001), and school level (P<0.01). The mean deep acting was significantly different according to educational background (P<0.001), cooking certification (P<0.001), employment status (P<0.001), salary (P<0.001), school level (P<0.01), and meal service time (P<0.05). The mean burnout was significantly different according to educational background (P<0.01), cooking certification (P<0.05), employment status (P<0.001), school level (P<0.001), and meal service time (P<0.001). The mean work engagement was significantly different according to cooking certification (P<0.001), employment satus (P<0.001), salary (P<0.001), school level (P<0.01), and meal service time (P<0.05). Verification of causal models found that surface acting and deep acting increased burnout and deep acting, respectively (research model). Additionally, surface acting did not influence work engagement, and deep acting did not influence burnout (alternative models). In other words, we identified that emotional labor strategies have differential influences on burnout and work engagement. Finally, implications and limitations of this study are discussed.

• Proceedings of the Korea Contents Association Conference
• /
• 2012.05a
• /
• pp.239-240
• /
• 2012

This study is purposed to examine the effect of motion play on the change of the body movement of a mental disabled child. The motion play program was performed by 5times, 1 hour/week for 6 mental disabled children in a special school. As the result of study, there was difference in learning capacity and learning attitude depending on the degree of the disability but it was noted that the capacity of play, behavior and motility of the physical areas was developed, and the capacity related with expression depending on self-emotion, positive aspects of the self and expression activity was improved among social areas.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.140-142
• /
• 2000

인간과 기계가 효과적인 상호작용을 하기 위해서는 컴퓨터 시스템이 인간의 행동을 인식할 수 있어야 한다. 본 연구에서는 인공 신경망을 사용하여 컴퓨터 시스템이 인간의 움직임을 관찰한 후 행위자의 성별을 인식하도록 하는 시스템을 구현하였다. 두 가지 감정상태(보통상태, 화난 상태) 하에서 일어난 인간의 세 가지 동작(문 두드리기, 손 흔들기, 물건 들어올리기)을 대상으로 하여 인간 동작 데이터를 통해 만들어진 학습 데이터를 통해 98.0%의 인식률을 보일 때까지 학습시키고 나서, 이전에 사용하지 않았던 새로운 데이터에 대해 얼마나 설별을 잘 구별해 내는지 실험하였다. 동작이 일어나는 동안 행위자의 몸 여섯 군데에서 속도 데이터를 얻어내서 신경망의 입력값으로 사용하였다. 그 결과 최저 62.3%이상 최고 94.3%까지 인간 성별을 구분해 낼 수 있었고 이는 같은 데이터에 대해서 사람을 통해 실험한 것보다 훨씬 나은 것이다.

• Annual Conference on Human and Language Technology
• /
• 2010.10a
• /
• pp.42-45
• /
• 2010

본 연구에서는 한국의 대중가요의 가사 정보를 형태소 단위로 분석하고 이 정보를 기반으로 노래의 감정을 분류하여 추천하는 시스템을 제안한다. 이 시스템을 구축하기 위해서 수집된 노래의 가사는 형태소를 분석하여 각 형태소를 자질로 결정하고, 사용되는 분류기는 ME 모델을 이용해서 학습된다. 이 학습된 분류기는 자질의 수에 따라 그 성능이 분석되고, 분류기를 사용한 추천 시스템은 랜덤하게 생성된 데이터 집합에 대해서 얼마나 정확하게 노래를 추천하는 지를 분석한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.627-629
• /
• 2023

생체 신호를 분석하여 사용자의 건강과 정신 상태를 예측하고, 관련 질병에 관해 예방하는 연구가 늘어나고 있다. 생체 신호 중 심박은 사람의 육체, 정신적인 상태를 반영하는 대표적인 신호이지만 기존의 접촉 패드를 통한 ECG나 광학 센서를 통한 PPG로 심박을 예측할 때는 구속적인 환경이 필요하여 일상적인 상황 속에 적용하기 어려웠다. 이러한 단점을 해결하고자 본 논문은 UBFC-RPPG 데이터셋의 동영상 프레임을 RGB 채널마다 다른 가중치를 적용하는 전처리를 하여 학습 데이터의 크기를 줄이면서 정확도를 높이고, 3D-CNN을 활용한 딥러닝으로 순간적인 영상에서도 PPG 신호를 예측할 수 있도록 1초 전처리 영상을 학습한 후, 신호를 예측하는 것을 목표로 한다. 이렇게 비접촉식으로 취득된 신호는 더 다양한 환경에서의 감정분류, 우울증 진단, 질병 감지 등 다양한 분야에 활용될 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.737-738
• /
• 2024

본 연구는 사용자의 감정을 인식하고, 개인화된 행동을 학습하는 AI 반려동물 시스템을 제안한다. DQN 을 이용한 강화학습을 통해 사용자의 피드백에 따라 행동을 변화시키며, 보다 자연스럽고 흥미로운 상호작용을 가능하게 한다. 이를 통해 기존의 정형화된 로봇 반려동물의 한계를 극복하고 사용자에게 맞춤형 경험을 제공하는 AI 반려동물 개발에 기여하고자 한다.

• Journal of Digital Convergence
• /
• v.18 no.9
• /
• pp.49-56
• /
• 2020

This study aims to examine the effects of CF about learners' English writing through FL on English improvement and the factors that influence class satisfaction. For achieving this purpose, response to CF and feelings about CF were selected as predictive variables. It is intended to investigate how these variables predict learners' satisfaction. A total of 94 university students were placed into two groups: 48 experimental group, who received CF on their writing through FL, and 46 control group given traditional instruction. All the participants took pre/post tests including writing tasks, and the experimental group completed a questionnaire after the instructional treatment. The findings indicated that FL affected English improvement and both response to CF and feelings about CF predicted class satisfaction. Based on the findings, this study sheds light on the implications of how to manage the FL class efficiently.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.5
• /
• pp.518-524
• /
• 2022

In this paper, we propose a method for combining convolutional neural networks and attention mechanism to improve the recognition performance of emotional stress from Electroencephalogram (EGG) signals. In the proposed method, EEG signals are decomposed into five frequency domains, and spatial information of EEG features is obtained by applying a convolutional neural network layer to each frequency domain. As a next step, salient frequency information is learned in each frequency band using a gate transformer-based attention mechanism, and complementary frequency information is further learned through inter-frequency mapping to reflect it in the final attention representation. Through an EEG stress recognition experiment involving a DEAP dataset and six subjects, we show that the proposed method is effective in improving EEG-based stress recognition performance compared to the existing methods.

• Journal of Software Assessment and Valuation
• /
• v.16 no.2
• /
• pp.127-133
• /
• 2020

As the usages of artificial intelligence is increased, the demand to algorithms for small portable devices increases. Also as the embedded system becomes high-performance, it is possible to implement algorithms for high-speed computation and machine learning as well as operating systems. As the machine learning algorithms process repetitive calculations, it depend on the cloud environment by network connection. For an stand alone system, low power consumption and fast execution by optimized algorithm are required. In this study, for the purpose of smart control, an energy measurement sensor is connected to an embedded system, and a real-time monitoring system is implemented to store measurement information as a database. Continuously measured and stored data is applied to a learning algorithm, which can be utilized for optimal power control, and a system interfacing various sensors required for energy measurement was constructed.