• Proceedings of the Korean Environmental Health Society Conference
• /
• 2005.11a
• /
• pp.169-174
• /
• 2005

의약품은 일반적으로 치료를 목적으로 제조되었기 때문에 독특한 약리학적 작용을 띤다. 의약품잔류물이 환경 중으로 배출되어 비표적 생물(non-target organism)에 노출될 경우 의도하지 않은 독성영향이 나타날 가능성이 있다. 본 연구에서는 우리나라에서 널리 사용되는 10개의 의약품(4종의 일반 의약품 acetaminophen, carbamazepine, diltiazem, cimetidine과 6종의 설파계 항생제 sulfamethoxazole, sulfamethazine, trimethoprim, sulfachloropyridazine, sulfadimethoxine)을 대상으로 환경중 예상잔류농도와 생태 무영향농도를 예측하여 대상의약품의 생태위해성을 평가하였다. 연구대상 의약품의 예측환경농도는 0.14 ${\sim}$ 16.5 ppb이었으며, 예측환경농도와 예측무영향농도비(PEC/PNEC ratio)를 산출한 결과 acetaminophen과 suifamethoxazole이 각각 1.8과 6.3으로 나타나 이 의약품들이 물생태계에 미치는 위해성에 대한 정밀한 추가연구의 필요성이 제시되었다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.263-268
• /
• 2023

백채널은 화자의 말에 언어 및 비언어적으로 반응하는 것으로 상대의 대화 참여를 유도하는 역할을 한다. 백채널은 보편형 대화 참여와 반응형 대화 참여로 나뉠 수 있다. 보편형 대화 참여는 화자에게 대화를 장려하도록 하는 단순한 반응이다. 반면에 반응형 대화 참여는 화자의 발화 의도를 파악하고 그에 맞게 반응하는 것이다. 이때 발화의 의미를 파악하기 위해서는 표면적인 의미뿐만 아니라 대화의 맥락을 이해해야 한다. 본 논문에서는 대화 맥락을 반영한 백채널 예측 모델을 제안하고 예측 성능을 개선하고자 한다. 대화 맥락을 요약하기 위한 방법으로 전체 요약과 선택 요약을 제안한다. 한국어 상담 데이터를 대상으로 실험한 결과는 현재 발화만 사용했을 때보다 제안한 방식으로 대화 맥락을 반영했을 때 성능이 향상되었다.

• The Journal of the Korea Contents Association
• /
• v.18 no.7
• /
• pp.536-550
• /
• 2018

This paper examine how acceptance of AI robots can be achieved according to occupational groups when the discourse on human labor and occupation changes due to the new industrial revolution is spreading steadily. Previous research on the acceptance of new technologies and products has predicted use behavior through subjective beliefs and values that do not change well over the short term. Therefore, this study compares the beliefs, values, and use intention of AI robots according to occupation. As a result, the subjective belief factor for AI robots was classified into belief in rationality(reason) and belief in benevolence(emotion). The value factors were divided into acceptance value(role performance, communication, social comparison) and avoidance value(risk, complexity). There was a significant difference in the effect of these on the use intention of AI robot by occupation and employment types. This result suggests that there are gaps in the occupation group at the rate of technology acceptance, as opposed to the existing prediction that AI robots will be rapidly expanded by professionals.

• Journal of Korean Academy of Nursing
• /
• v.35 no.6
• /
• pp.1063-1071
• /
• 2005

Purpose: This study was done to develop and test validity and reliability of on instrument for predicting nursing intention for SARS patient care. Method: The psychometric properties of a SARS patient care attrition prediction tool, based on the Theory of Planned Behavior, were examined in this study. The Three-phase design involved a) salient beliefs generated from clinical nurses (n=43) b) content validation by expert panel evaluations(n=5) c) face validation by plot testing (n=10) d) and instrument validation in a cross sectional survey (n=299). Psychometric analysis of survey data provided empirical evidence of the construct validity and reliability of the instrument. Result: Principal component analysis verified the hypothesized 6-factor solution, explaining $68.2\%$ of variance, and Alpha coefficients of .7538 to .9389 indicated a high internal consistency of the instrument. Conclusion: The instrument can be used by nurse administrators and researcher to assess clinical nurses' salient beliefs about caring for SARS patients, guide tailored intervention strategies to effective caring, and evaluate the effectiveness of interventions.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.36-40
• /
• 2021

다양한 Masked Language Modeling을 통해 학습한 사전 학습 모델들은 질의응답 시스템에서 매우 높은 성능을 보여주고 있다. 이러한 강력한 성능에도 불구하고 그러한 모델들이 질의를 정확히 이해하고 정답을 예측하는 것인지, 혹은 질의에 등장하는 특정 단어와 잘 나타나는 단어들을 기반으로 정답을 예측하는 것인지에 대한 분석은 아직 충분하지 않다. 이러한 사전학습 모델의 질의 이해 능력을 밝히기 위하여, 본 연구에서는 클레버 한스 테스트를 제안한다. 클레버 한스 테스트에서는 의미적 구조적, 의도 유무 측면의 여러 질의 변형이 된 데이터 셋들이 포함되어 있다. 본 연구에서는 클레버 한스 테스트를 통하여 사전학습 모델들이 의미적으로 달라진 질의나 의도가 제거된 질의를 입력으로 받아도 성능이 크게 떨어지지 않는 것을 확인하였고 모델의 질의 이해능력 부족을 실험적으로 시사하였다.

• 한국체육학회지인문사회과학편
• /
• v.58 no.1
• /
• pp.217-228
• /
• 2019

The purpose of this study is to test the mediating effect of coping plan and action plan in the relation between leisure-time physical activity(LTPA) intention and exercise behavior and to extend the literature in theory of planned behavior. We examined the mediating role of implementation plan-namely coping plan and action plan in the effect of intention to physical activity on exercise behavior. To attain the goal of study, we asked collegiate students (n=253; male=118, female=105) report their intention toward LTPA, coping plan, action plan, and self-reported exercise behavior. Collected data was analyzed using statistical program software (i.e., SPSS, AMOS) for SEM and mediation analyses. The results revealed that intention toward LTPA was positively related to implementation plan (coping plan and action plan) and exercise behavior. Collegiate students' intention toward LTPA positively predicted their exercise behavior mediated by implementation plans. Specifically, LTPA intention among collegiate students predicted their exercise behavior via coping plan and action plan. The findings showed that coping plan and action plan partially mediated in the relation between LTPA intention and exercise behavior. In conclusion, students' intention to be getting physical active in leisure-time physical activity explains lifetime physical activity or the level of recent exercise behavior possibly via coping plan (e.g., how to overcome barriers to exercise) and action plan (e.g., when and where I exercise and get physically active). The conceptualization of coping plan and action plan in implementation plans and test of its model better to explain the intention-behavior gap would help exercise instructors or practitioners effectively develop their plans and strategies toward targeted exercise behavior.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.387-390
• /
• 2021

최근 전자 상거래 시장이 급격한 성장을 이루면서 고객들의 급변하는 니즈를 파악하는 것이 기업들의 수익에 직결되는 요소로 인식되고 있다. 이에 기업들은 고객들의 니즈를 신속하고 정확하게 파악하기 위해, 기축적된 고객 관련 각종 데이터를 활용하려는 시도를 강화하고 있다. 기존 시도들은 주로 구매 행동 예측에 중점을 두었으나 고객 행동의 전후 과정을 해석하는데 있어 어려움이 존재했다. 본 연구에서는 고객이 구매한 상품을 확정 또는 환불하는 행동을 취할 때 해당 행동이 발생하는데 있어 어떤 요소들이 작용하였는지를 파악하고, 어떤 고객이 환불할 지를 예측하는 예측 모형을 새롭게 제시한다. 예측 모형 구현에는 트리 기반 앙상블 방법을 사용해 예측력을 높인 XGBoost 기법을 적용하였으며, 고객 의도에 영향을 미치는 요소들을 파악하기 위하여 대표적인 설명가능한 인공지능(XAI) 기법 중 하나인 SHAP 기법을 적용하였다. 이를 통해 특정 고객 행동에 대한 각 요인들의 전반적인 영향 뿐만 아니라, 각 개별 고객에 대해서도 어떤 요소가 환불결정에 영향을 미쳤는지 파악할 수 있었다. 이를 통해 기업은 고객 개개인의 의사 결정에 영향을 미치는 요소를 파악하여 개인화 마케팅에 사용할 수 있을 것으로 기대된다.

• Journal of Digital Convergence
• /
• v.16 no.3
• /
• pp.311-319
• /
• 2018

This research attempted to identify the factors associated with the intention of human papilloma virus vaccination among mothers of elementary school daughters. The subject of study is 132 mothers of elementary school students. Data collection was conducted from July 1 to August 30 in 2017, and analyzed using SPSS 23.0 Program. Results showed that 94.7% children of the participants had not been vaccinated, whose reasons were the low knowledge about HPV vaccination, concerns about its side effects, burden for cost. The attitude toward HPV vaccination appeared to be the most important predictor of vaccination, which was followed by perceived behavior control and subjective norm as meaningful predictors, as well. Based on these results, further researches should be conducted to develop educational programs, which are able to offer exact information about the effect and side effect of HPV vaccination, and verify the effectiveness.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.13 no.2 s.29
• /
• pp.161-167
• /
• 2007

The goal of this paper is to develop the speech recognition system which can control the ship's auto pilot. The feature parameters predicting the speaker's intention was extracted from the sample wheel orders written in SMCP(IMO Standard Marine Communication Phrases). And we designed the post-recognition procedure based on the parameters which could make a final decision from the list of candidate words. To evaluate the effectiveness of these parameters and the procedure, the basic experiment was conducted with total 525 wheel orders. From the experimental results, the proposed pattern recognition procedure has enhanced about 42.3% over the pre-recognition procedure.

• Korean Journal of Construction Engineering and Management
• /
• v.25 no.1
• /
• pp.23-31
• /
• 2024

This study highlights the importance of understanding the fair bidding behavior of bid practitioners in order to eliminate bid-rigging, which has a detrimental impact on the construction industry and the overall economy. The research collected survey data from bid practitioners in the Daegu and Gyeongbuk regions of South Korea and analyzed the causal relationships between attitudes towards bid-rigging, subjective norms, perceived behavioral control, and the intention to engage in fair bidding using PLS-SEM analysis. The analysis results confirm that attitudes towards bid-rigging and perceived behavioral control are significant variables predicting the intention to engage in fair bidding among bid practitioners. This indicates that bid practitioners' perceptions of bid-rigging and personal behavioral control influence their willingness and actions towards fair bidding. The insights gained from this research provide valuable insights into bid practitioners' behavioral changes and can aid in the development of policies and measures to promote fair bidding and prevent bid-rigging.