• 방송공학회논문지
• /
• 제18권5호
• /
• pp.771-774
• /
• 2013

본 연구는 감정상태와 음색특성의 관계를 확인하고, 추가로 cepstral 피쳐와 조합하여 감정인식을 진행하였다. Open quotient, harmonic-to-noise ratio, spectral tilt, spectral sharpness를 포함하는 특징들을 음색검출을 위해 적용하였고, 일반적으로 사용되는 피치와 에너지를 기반한 운율피쳐를 적용하였다. ANOVA분석을 통해 각 특징벡터의 유효성을 살펴보고, sequential forward selection 방법을 적용하여 최종 감정인식 성능을 분석하였다. 결과적으로, 제안된 피쳐들으로부터 성능이 향상되는 것을 확인하였고, 특히 화남과 기쁨에 대하여 에러가 줄어드는 것을 확인하였다. 또한 음색관련 피쳐들이 cepstral 피쳐와 결합할 경우 역시 인식 성능이 향상되었다.

• 말소리와 음성과학
• /
• 제4권2호
• /
• pp.105-114
• /
• 2012

This paper will discuss the difference between self assessment of voice disorders and the hearer voice assessment of a comparative group of normal subjects. The study was conducted on 25 voice disorder subjects and 32 hearers of a comparative group of normal subjects. The results are as follows. Firstly, in K-VHI and VHI-H, the hearers of the comparative group of normal subjects perceived more serious voice disorders than the voice disorder group in all sub-domains. Likewise, in K-VQOL and VRQOL-H, the hearers of the comparative group of normal subjects perceived more serious voice disorders than the voice disorder group in all sub-domains. Secondly, the hearer voice assessment of the comparative group of normal subjects showed no difference in gender regarding the perception of the severity of voice disorder issues. Thirdly, the hearer voice assessment of the comparative group of normal subjects states that in the emotional aspects of VHI-H, professional voice users perceive more serious voice disorders than others. Accordingly, in VRQOL-H, there was no difference in use of the voice between professionals and others.

• 전기학회논문지
• /
• 제62권6호
• /
• pp.811-817
• /
• 2013

In this study we present a system for pulse-rate period detection and human sensibility evaluation based on the wireless medical telemetry service (WMTS) used for transmission of data from medical telemetry devices to various medical facilities and services. We develop a medical-purpose specific WMTS communication module to transmit biometric signals. From the pulse rate variability(PRV) signal, we attempt to classify positive and negative emotional states based on analysis of the ratio of LF/HF in the frequency domain. We measure the data reception rate according to distance in order to test the performance of the WMTS module and analyze the effects on human sensibility evaluation.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 1999년도 추계학술대회 논문집
• /
• pp.211-215
• /
• 1999

It is well known that a long-term exposure to a loud noise environment affects performance, since it distracts attention, and also is able to evoke stress accompanied by negative emotional states. The purpose of this study was to analyze dynamics of subjective and physiological variables during long-lasting (30 min) exposure to intensive white noise (85 dB[A]). Physiological signals on 23 college students were recorded by BIOPAC, Grass Neurodata systems and AcqKnowledge 3.5 software. Autonomic variables, namely skin conductance level (SCL), non-specific SCR number (N-SCR), inter-beat intervals in ECG (RR intervals), heart rate variability index (HF/LF ratio of HRV), respiration rate (RESP), and skin temperature (SKT) were analyzed on 5 min epoch basis. Psychological assessment (subjective rating of stress level) was also repeated on every 5 min basis. Regression and correlation analyses were employed to trace the time course of the dynamics of the subjective and autonomic physiological variables and their relationship. Results showed that intense noise evokes subjective stress with associated autonomic nervous system responses. However, it was shown that physiological variables endure specific changes in the process of exposure to loud white noise. Discussed are probable psychophysiological mechanisms mediating reactivity to long-term auditory stimulation of high intensity.

• 한국정보통신학회논문지
• /
• 제12권3호
• /
• pp.438-444
• /
• 2008

본 논문에서는 애니메이션 캐릭터의 표정 연출의 효율성을 높이기 위해 정서 상태의 변화에 따라 다양하고 주어진 상황에 부합하는 표정을 쉽게 구현할 수 있는 표정생성 프로그램을 제안하고자 한다. 이를 위해 우선, Russell의 내적 정서 상태의 차원 모형을 근거로 쾌-불쾌, 각성-비각성의 내적 정서 상태 정보를 포함한 9가지 표정을 정의하였다. 그리고 각각의 표정에 대해 본 연구에서 제안한 표정생성 프로그램을 이용하여 두 차원의 중앙에 위치하는 무표정 자극을 8가지의 가능한 표정 변화 방향으로 이동시킴으로써 정서 차원에서의 미묘한 위치 변화에 따라서도 다양한 표정 생성이 구현될 수 있음을 확인하였다. 향후 이러한 프로그램은 복잡한 정서를 가진 표정을 쉽고 다양하게 구현할 수 있는 표정 자동생성 시스템 설계의 기초적 프로그램으로 활용될 수 있을 것이다.

• 정신간호학회지
• /
• 제27권4호
• /
• pp.380-393
• /
• 2018

Purpose: The purpose of this study was to explore psychiatric nurses' decision making in the use of seclusion and restraint (SR). Methods: Data were collected using focus group interviews. Two focus group interviews were held with a total of 10 psychiatric nurse participants. All interviews were recorded and transcribed, and data were analyzed using qualitative content analysis. Results: Eleven categories emerged from three main themes. All the themes describe factors that participants took into account when deciding whether to implement SR: 1) Personal factors area: 'Personal attributes of nurses,' 'Attitude of nurses regarding SR,' 'Nurses' physical and emotional states,' 'Negative experiences of nurses related to SR'; 2) Relational factors area: 'The level of cooperation between nurses and doctors,' 'Role models created by seniors and colleagues,' 'The level of support by nursing assistants,' 'Therapeutic relations with patients'; and 3) Environmental factors area: 'Poor nursing work environment,' 'Atmosphere of ward regarding SR,' and 'Social atmosphere to raise alarm about SR.' Conclusion: These findings should be considered in the evaluation of the use of SR in psychiatric hospital settings and appropriate strategies used to help minimize the use of restraint.

• Journal of Preventive Medicine and Public Health
• /
• 제54권5호
• /
• pp.376-379
• /
• 2021

Elemental mercury exposure can result in significant toxicity. Source decontamination and remediation are often required after larger elemental mercury exposures, but the details of these processes are infrequently reported. In the case described herein, a 64-year-old woman and her husband were exposed to elemental mercury in their home after the husband purchased it online for the purpose of recreational barometer calibration. After the mercury reportedly spilled during the calibration process, a vacuum cleaner was used to decontaminate the affected surface; this led to extensive mercury contamination of the home. The couple was relocated from the home while remediation occurred over the course of several weeks. Vacuum cleaning of an elemental mercury spill can lead to extensive volatilization and recirculation of mercury vapor. For smaller mercury spills, careful removal of visible mercury beads by using an eyedropper, cardboard, and masking tape is recommended. Larger spills require professional decontamination and remediation and may necessitate involvement of governmental resources. Vacuum cleaning should not be used as an initial method of decontamination after elemental mercury exposure. Careful attention to source decontamination can reduce the emotional and financial costs associated with extensive remediation after elemental mercury exposure.

• 한국치위생학회지
• /
• 제19권2호
• /
• pp.241-249
• /
• 2019

Objectives: This study aimed to investigate the effects of verbal violence experience on stress and positive psychological capital as well as the mediating effects of positive psychological capital. Methods: A survey was conducted with dental hygienists working at university hospitals, general hospitals, and dental hospitals and clinics in Busan, Gyeongnam, and Ulsan areas.Of the 230 questionnaires distributed, 206 were used in the analysis after excluding 24 completed questionnaires that had errors or missing answers. Results: As a result of identifying the relationships between verbal violence damage, positive psychological capital, and stress, verbal violence damage was negatively correlated with positive psychological capital (r=-0.28, p<0.001) and positively correlated with stress (r=0.40, p<0.001). Positive psychological capital had a negative correlation with stress (r=-0.25, p<0.001). As a result of verifying the mediating effects of positive psychological capital on the relationship between verbal violence damage and stress among dental hygienists, it was found that verbal violence had a significant effect on stress and positive psychological capital in the first and second stages. In the third stage, the effect of positive psychological capital on stress was significant, showing that there was a mediating effect. Conclusions: Therefore, sound work environments should aim to reduce verbal violence while increasing support systems to reduce negative emotional and psychological states.

• International Journal of Advanced Culture Technology
• /
• 제10권3호
• /
• pp.272-280
• /
• 2022

During last few years, pandemic of COVID-19 has been a global issue. Under the COVID-19, global events have been restricted or canceled to secure public hygiene and safety. Since one of the largest global events is Olympic Games, we selected recent Olympic Games as our case of analysis. Tokyo Olympic Games (TOG) was held in 2021, but it encountered a millennium disaster, the pandemic of COVID-19. In such a special period, it is of great significance to explore the emotional tendency of global views before and TOG via artificial intelligence. This paper vastly collects the TOG comment data of mainstream websites in South Korea, China, and the United States by implementing crawler program for sentiment analysis (SA). And we use a variety of sentiment analysis models to compare the accuracy of the experimental results, to obtain more reliable SA results. In addition, in the prediction results, to reduce the distortion of opinion by a minority, we introduce an algorithm called "Removing Biased Minority Opinions (RBMO)" and provide how to apply this method to the interpretation domain. Through our method, more authoritative SA results were obtained, which in turn provided a basis for predicting the sentiment tendency of countries around the world in TOG during the COVID-19 epidemic.

• 디지털산업정보학회논문지
• /
• 제19권3호
• /
• pp.245-251
• /
• 2023

Facial expression recognition plays a significant role in understanding human emotional states. With the advancement of AI and computer vision technologies, extensive research has been conducted in various fields, including improving customer service, medical diagnosis, and assessing learners' understanding in education. In this study, we develop a model that can infer emotions in real-time from a webcam using transfer learning with TensorFlow.js and MobileNet. While existing studies focus on achieving high accuracy using deep learning models, these models often require substantial resources due to their complex structure and computational demands. Consequently, there is a growing interest in developing lightweight deep learning models and transfer learning methods for restricted environments such as web browsers and edge devices. By employing MobileNet as the base model and performing transfer learning, our study develops a deep learning transfer model utilizing JavaScript-based TensorFlow.js, which can predict emotions in real-time using facial input from a webcam. This transfer model provides a foundation for implementing facial expression recognition in resource-constrained environments such as web and mobile applications, enabling its application in various industries.