• Journal of Internet of Things and Convergence
• /
• v.9 no.6
• /
• pp.37-44
• /
• 2023

As a primary technology of Industry 4.0, human-robot collaboration (HRC) requires additional measures to ensure worker safety. Previous studies on avoiding collisions between collaborative robots and workers mainly detect collisions based on sensors and cameras attached to the robot. This method requires complex algorithms to continuously track robots, people, and objects and has the disadvantage of not being able to respond quickly to changes in the work environment. The present study was conducted to implement a web-based platform that manages collaborative robots by recognizing the emotions of workers - specifically their perception of danger - in the collaborative process. To this end, we developed a web-based application that collects and stores emotion-related brain waves via a wearable device; a deep-learning model that extracts and classifies the characteristics of neutral, positive, and negative emotions; and an Internet-of-things (IoT) interface program that controls motor operation according to classified emotions. We conducted a comparative analysis of our system's performance using a public open dataset and a dataset collected through actual measurement, achieving validation accuracies of 96.8% and 70.7%, respectively.

• 한국체육학회지인문사회과학편
• /
• v.58 no.4
• /
• pp.447-459
• /
• 2019

This study was conducted to investigate the differences between emotional responses and neurotransmitters in moderate-intensity continuous exercise (MICE) and high-intensity interval exercise (HIIE) in 30 low-active women. Both groups performed a designed acute treadmill exercise and repeated the same exercise three times at intervals of one week. MICE performed a 25-minute continuous exercise at 90% VT(ventilation threshold) after a 5-minute warm-up session at 50% VT and then cooled down for 5 minutes at 50% VT level. The HIIE was repeated 6 times for 2 minutes at 115% VT level, and the intermediate active recovery was repeated 4 times for 2 minutes at 85% VT level. The results of the statistical analysis are as follows. MICE was showed positive effect for feeling scale and PACES after exercise in the first experiment, but negative effect in the third experiment. Conversely, HIIE was showed negative effect for feeling scale and PACES after exercise in the first experiment, but positive effect in the third experiment. Neurotransmitters were significantly increased in all three groups after 10 minutes of exercise compared to before exercise. In summary, HIIE exercise may be a strategy to increase exercise compliance for low-active women.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06c
• /
• pp.51-53
• /
• 2012

데이터 마이닝의 문서분류 기술에서 발전된 오피니언 마이닝은 이제 국외뿐만 아니라 국내의 학계 및 기업에서 중요한 관심분야로 자리잡아가고 있다. 오피니언 마이닝의 핵심은 문서에서 감정 단어를 추출하여 긍정/부정 여부를 얼마나 정확하게 자동적으로 판별하느냐를 평가하는 것이다. 국내에서도 이에 관련된 많은 연구가 이루어 졌으나 아직 실용적으로 적용할 만큼의 정확한 분류 정확도 보이지 않고 있다. 그 이유는 한국어의 경우 비문법적 표현, 감정단어의 다양성 등으로 인해 문서의 극성을 판별하기가 쉽지 않기 때문이다. 본 논문에서는 문법적 요소를 최대한 배제하고 단어 패턴의 빈도만을 고려한 영화평 분류기법을 제안한다. 제안된 방법에서는 문서를 단어들의 리스트로 추상화하여 패턴들의 빈도로 학습한 후 적절한 스코어 함수를 적용하여 문서의 극성을 판별한다. 또한 실험을 통해 제안된 기법의 정확도를 평가한다.

• Annual Conference of KIPS
• /
• 2019.10a
• /
• pp.806-808
• /
• 2019

인터넷 기술의 발전에 힘입은 전자상거래의 급격한 발전에 따라 소비자들의 소비습관은 오프라인에서 온라인으로 빠르게 바뀌었다. 이에 따라, 구매한 상품에 대한 평가를 작성하는 것 또한 만연해지면서 소비자들에게 구매 결정의 중요한 요인으로 작용하기 시작하였고 실제 판매량에도 직접적인 영항을 끼치기 시작하였다. 그러나, 현재 전자상거래 시스템에서는 상품에 대한 평가를 한눈에 알아볼 수 있는 기능이 부재하고 있어 소비자의 소비 전략과 판매 전략측면에서의 비효율을 야기하고 있다. 따라서, 본 논문에서는 LSTM 을 기반으로 한 딥러닝 모델을 이용해 감정분석을 하여 온라인 상품평을 긍정/부정에 따라 자동으로 분류하고자 한다. 이를 통해, 효율적인 반응 분석을 위한 기술 개발의 기반을 마련하여 소비자와 판매자 모두에게 더 나아진 전략 수립의 기회를 제공할 것으로 기대한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.239-240
• /
• 2021

본 논문에서는 나날이 발전하는 뉴미디어 시장에서 가장 대중적으로 사용되는 유튜브와 이에 업로드되는 콘텐츠들이 개인의 행동 의도에 어떠한 영향을 미쳤으며, 그 영향이 사회적 위험요인으로 어떻게 드러나는지에 대하여 분석한다. 셀레늄과 뷰티풀솝으로 유튜브 콘텐츠 정보를 가져오고, 트위터 에이피아이를 활용해 트위터에서 개인이 작성한 문장들을 받아 엔엘티케이의 배이더로 문장의 감정을 부정, 중립, 긍정으로 분류하여 연구를 진행하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.5
• /
• pp.563-569
• /
• 2012

The studies of opinion mining or sentiment analysis have been the focus with social web proliferation. Sentiment analysis requires sentiment resources to decide its polarity. In the existing sentiment analysis, they have been built resources designed with intensity of sentiment polarity and decided polarity of opinion using the ones. In this paper, I will present sentiment categories for not only polarity of opinion but also the basis of positive/negative opinion. I will define psychological emotions to primary sentiments for the reasonable classification. And I will extract the informations of sentiment from social web texts for the actual distribution of sentiments in social web. Re-classifying primary sentiments based on extracted sentiment information, I will organize sentiment categories for the social web. In this paper, I will present 23 categories of sentiment by using proposed method.

• Korean Journal of Psychosomatic Medicine
• /
• v.13 no.1
• /
• pp.32-40
• /
• 2005

Objectives : This study looked at the symptoms of alexithymia in schizophrenia and their association with clinical variables and schizophrenic symptomatology. Methods Consecutive fifty eight inpatients with DSM-IV diagnoses of schizophrenia completed 26item version of Toronto Alexithymia Scale (TAS), Symptom Checklist-90-Revised(SCL-90-R), and Positive and Negative Syndrome Scale(PANSS). Results : Authors did not find any correlation between scores of PANSS and TAS. However, all the subscale scores of SCL-90-R were significantly correlated with total score of TAS. Also, 'difficulty identifying and deistinguishing between feelings and bodily sensations' and 'difficulty describing feelings' significantly correlated with SCL-90-R subscale scores. 'Reduced daydreaming' had mixed findings and 'externally oriented thinking' did not correlate. Multiple regression model included Global Severity Index of SCL-90-R accounting 28.2% of variance for TAS scores. Conclusion : These findings together with discrepancy in results between objective and subjective tests suggest that alexithymia in schizophrenia may have two constructs, 'difficulty to describe and communicate feelings(state)' and 'externally oriented thinking(trait)' Authors suggest further study needs to confirm construct validity of TAS in this population.

• 동물약계
• /
• no.33
• /
• pp.4-5
• /
• 1996

1. 허가사항변경 2. 제1차 수출촉진 협의회 개최 3. 약사감시 결과안내 4. 가축질병병성감정 실시기관 지정 5. 사료내 잔류농약 및 동물용의약품의 허용기준 개정의견 수렴 6. 제21회 세계소동물 수의학대회 안내 7. 가축전염병 발생정보 8. 동물용의약품 판매에 관한 질의회신 9. 동물약품 안전사용홍보용 스티카 배포 10. 제조손모율 조사결과 안내 11. 동물약품 잔류방지 세부실천방안 홍보강화 12. 회장단회의 개최 13. 국가검정 절차관련 협의회 개최 14. 제3차 이사회개최 15. 부정$\cdot$불공정 수출입관련 정보협조 16. 동물용의약품 판매관리 철저 17. 염화코린수입관련 공청회 개최 18. 통합공고 개정

• Culinary science and hospitality research
• /
• v.19 no.1
• /
• pp.70-84
• /
• 2013

The study aimed at grasping the factors of sommelier service quality and analyzing how customers' emotional responses based on sommelier service quality had a big impact on the revisit intention for the customers who received sommelier service from food service industries located in Seoul. The findings are as follows. The effects of sommelier service quality on positive emotions were respectively significant in specialty factor(${\beta}$=.257, p<0.001), reliability factor(${\beta}$=.314, p<0.001), and responsiveness factor(${\beta}$=.387, p<0.001). And the effect on negative emotions was significant in specialty factor(${\beta}$=-.178, p<0.05). Meanwhile, the result of the effect on the revisit factor of sommelier service quality was significant in reliability factor(${\beta}$=.286, p<0.001). And the effects of customers' emotional response on revisit factor were significant in positive emotion factor(${\beta}$=.350, p<0.001) and negative emotion factor(${\beta}$=-.195, p<0.01) respectively. As the emotional responses based on sommelier service quality had a great impact on customers' revisit intention according to positive or negative emotions, it is necessary for food service industry operators to improve customer satisfaction with consolidating the factors to give customers positive emotions which eventually can lead them to revisit wine restaurants.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.687-692
• /
• 2023

We analyze the accuracy of emotion analysis of natural language processing deep learning model and propose to use it for emotional content development. After looking at the outline of the GPT-3 model, about 6,000 pieces of dialogue data provided by Aihub were input to 9 emotion categories: 'joy', 'sadness', 'fear', 'anger', 'disgust', and 'surprise'. ', 'interest', 'boredom', and 'pain'. Performance evaluation was conducted using the evaluation indices of accuracy, precision, recall, and F1-score, which are evaluation methods for natural language processing models. As a result of the emotion analysis, the accuracy was over 91%, and in the case of precision, 'fear' and 'pain' showed low values. In the case of reproducibility, a low value was shown in negative emotions, and in the case of 'disgust' in particular, an error appeared due to the lack of data. In the case of previous studies, emotion analysis was mainly used only for polarity analysis divided into positive, negative, and neutral, and there was a limitation in that it was used only in the feedback stage due to its nature. We expand emotion analysis into 9 categories and suggest its use in the development of emotional content considering it from the planning stage. It is expected that more accurate results can be obtained if emotion analysis is performed by additionally collecting more diverse daily conversations through follow-up research.