• Science of Emotion and Sensibility
• /
• v.21 no.1
• /
• pp.59-70
• /
• 2018

With the breakthrough of speech recognition technology, conversational agents have become pervasive through smartphones and smart speakers. The recognition accuracy of speech recognition technology has developed to the level of human beings, but it still shows limitations on understanding the underlying meaning or intention of words, or understanding long conversation. Accordingly, the users experience various errors when interacting with the conversational agents, which may negatively affect the user experience. In addition, in the case of smart speakers with a voice as the main interface, the lack of feedback on system and transparency was reported as the main issue when the users using. Therefore, there is a strong need for research on how users can better understand the capability of the conversational agents and mitigate negative emotions in error situations. In this study, we applied social strategies, "forewarning" and "apology", to conversational agent and investigated how these strategies affect users' perceptions of the agent in breakdown situations. For the study, we created a series of demo videos of a user interacting with a conversational agent. After watching the demo videos, the participants were asked to evaluate how they liked and trusted the agent through an online survey. A total of 104 respondents were analyzed and found to be contrary to our expectation based on the literature study. The result showed that forewarning gave a negative impression to the user, especially the reliability of the agent. Also, apology in a breakdown situation did not affect the users' perceptions. In the following in-depth interviews, participants explained that they perceived the smart speaker as a machine rather than a human-like object, and for this reason, the social strategies did not work. These results show that the social strategies should be applied according to the perceptions that user has toward agents.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.41 no.5
• /
• pp.783-795
• /
• 2017

This study measured consumer's recognition, reliability, emotion and images about current eco-marks as well proposed an eco-mark rating scale and mark designs to improve consumer's trust on the fashion product marks. We used a questionnaire survey to collect data from 150 persons about knowledge, interests, and practice on eco fashion products in relation to trustfulness and positive images for three domestic and three international eco-marks. We evaluated and gave eco scores to six fiber-type products (cotton, organic cotton, wool, polyester, biodegradable polyester and nylon) in terms of consumer's use, water & land consumption, waste amount, carbon footprint, and toxicity. We suggested a new 5-level rating scale for eco marks, which quantified the concept of environmental friendliness of fiber products. The design for eco-mark of rating scale showed the total grade with two sub scores of environmental sides and human sides developed with an improved visual understanding for consumers. The design is one through benchmarking the energy-consumption efficiency mark, which is familiar to consumers such as a half circle shape to save environment resources to alarm consumers to environment problems.

• Journal of Digital Contents Society
• /
• v.18 no.1
• /
• pp.35-46
• /
• 2017

The purpose of the study was to review the recent literature on applying augmented reality based educational contents for students with autism spectrum disorders and to identify research trends and implications. The search procedures through the Web-database system were implemented to find the proper research and a total of 12 studies were included in this review. The results indicated that most of subjects were elementary school-age children, also single subject design was mostly implemented. Mobile devices were used mostly for augmented reality, and most of data collection methods was behavioral observation. Results founded several contents types: objects manipulation, manipulation for self-modeling, on-site problem solving program, and location-based learning guide. Additionally, the results indicated that the educational effectiveness was the improvements of social behaviors, play and imitation behaviors, and emotion recognition. Furthermore, considerations to develop and apply augmented reality based educational contents for students with autism spectrum disorders were suggested.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.447-453
• /
• 2020

In this paper, we propose a system to extract effective speaker representations from a speech signal using a deep learning method. Based on the fact that speech signal contains identity unrelated information such as text content, emotion, background noise, and so on, we perform a training such that the extracted features only represent speaker-related information but do not represent speaker-unrelated information. Specifically, we propose an auto-encoder based disentanglement method that outputs both speaker-related and speaker-unrelated embeddings using effective loss functions. To further improve the reconstruction performance in the decoding process, we also introduce a discriminator popularly used in Generative Adversarial Network (GAN) structure. Since improving the decoding capability is helpful for preserving speaker information and disentanglement, it results in the improvement of speaker verification performance. Experimental results demonstrate the effectiveness of our proposed method by improving Equal Error Rate (EER) on benchmark dataset, Voxceleb1.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.271-273
• /
• 2006

본 논문에서는 신경망을 이용하여 텍스타일 영상으로부터 인간의 강성을 인식할 수 있는 시스템을 제안한다. 자동감성인식 시스템의 구현을 위해 220장의 텍스타일 영상을 수집한 후, 일반인 20명을 대상으로 설문조사를 실시하였다. 이를 통해 감성과 패턴간의 상관관계, 즉 특정 패턴이 사람의 감성에 영향을 준다는 것을 발견하였다. 따라서 본 연구에서는 영상에 포함된 패턴의 인식을 위해 신경망을 이용하였으며, 이때 패턴 정보의 추출을 위해 두 가지 특징 추출 방법을 사용한다. 첫 번째는 auto-regressive method를 이용한 raw-pixel data extraction scheme (RDES)을 사용하는 것이고, 두 번째는 wavelet transformed data extraction scheme (WTDES)을 사용하는 것이다. 제안된 시스템의 유용성을 증명하기 위해서 실제 100장의 텍스타일 영상에서의 감성을 인식하는데 사용했다. 그 결과 RDES와 WTDES를 사용했을 때 각각 71%와 90%의 인식률로, WTDES를 사용했을 때가 RDES를 사용했을 때보다 더 좋은 성능을 보였다. 데이터 추출방법에 따라 다소 차이가 있었지만 전체적으로 악 81%의 정확도를 보였다. 이러한 실험 결과는 제안된 방법이 감성인식 기반으로 텍스타일 데이터를 검색 할 수 있는 시스템 및 다양한 산업 분야에 응용 가능함을 보여주었다.

• Korean Journal of Family Social Work
• /
• no.60
• /
• pp.31-71
• /
• 2018

This study focused on analysis of experience for adults' reunion with original family members who had lived in child care facilities during the childhood and adolescence. It was researched based on the grounded theory from nineteen participants have interacted with their own separated family members for more than ten years after had been reunited with them. As written in the result section of the study using the paradigm model analysis showed that it was caused by feel regret by reunion, absence of belonging and repeated abandoned wound. The contextual condition appeared as sensitive memories as wounded and frustration of compensation mentality. The centralization phenomenon came in a whirlpool of emotion. The intervention condition appeared as recognition of filial piety, support system for parents and healing their parents mind. The action-interaction showed up as revenge with good will, setting own boding free, inspire of own pride, family reconciliation. The consequence appeared as family sublimation, successful execution of life task and getting living foundation. This research made practical and political proposals based on above result and described the limitations of the study and the proposals for the latter study.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.11
• /
• pp.159-166
• /
• 2014

In this paper, we examine the role of emotional acoustic cues including both prosody and voice quality parameters for the modification of a word sense. For the extraction of prosody parameters and voice quality parameters, we used 60 pieces of speech data spoken by six speakers with five different emotional states. We analyzed eight different emotional acoustic cues, and used a discriminant analysis technique in order to find the dominant sequence of acoustic cues. As a result, we found that anger has a close relation with intensity level and 2nd formant bandwidth range; joy has a relative relation with the position of 2nd and 3rd formant values and intensity level; sadness has a strong relation only with prosody cues such as intensity level and pitch level; and fear has a relation with pitch level and 2nd formant value with its bandwidth range. These findings can be used as the guideline for find-tuning an emotional spoken language generation system, because these distinct sequences of acoustic cues reveal the subtle characteristics of each emotional state.

• Science of Emotion and Sensibility
• /
• v.7 no.1
• /
• pp.65-81
• /
• 2004

With the arrival of the 21th century, the management environments such as the knowledge system, information system, and technology system surrounding small and medium enterprises are being rapidly changed. These rapidly changing the environment of enterprises like the above can be thought rather profitable for the elastic and resiling medium enterprises than large enterprises. Additionally, these environments are recognized as the management circumstances which provide with the change by which medium enterprises equipped with the trustworthy creativity in the 21th century are able to become the main player of the industrial development. The position and role of medium enterprises in the national economical system are very important. The execution of the local autonomy system and the policy to activate the local economy will generally enlarge the power of medium enterprises which are based on the concerned local society more ant more. But, by the standpoint of designer, it is pointed out that there is the problem that the effective application means or the availability of the industrial design was not sufficiently recognized or understood by the manager in enterprises. Notwithstanding the above problem, a lot of domestic small and medium enterprises became to apply the industrial design as the means for improving the competitiveness of their own products in the relatively short time powered by the governmental policy, and moreover both of the concerned partners(the manager and industrial designer) had the opportunity to newly recognize the industrial design and evaluate the availability or problem of the industrial design in the actual aspect. This event means very important change. With the understanding on the above situation, the purpose of this study is to recognize whether the design is strategically applied in the management level of domestic small and medium enterprises, whether the strategical establishment of the design management is performed without any problem, whether the field designer and CEO are well recognizing the design management and what their recognition level is in order to seek the new solution for plenty of problems. Therefore, the actual proof analysis was performed for the field designer and management CEO of small and medium enterprises with the questionnaire survey and direct interview method to understand the actuality of small and medium enterprises.

• Journal of Broadcast Engineering
• /
• v.25 no.4
• /
• pp.537-544
• /
• 2020

This paper proposes the creation of an android robot head based on the facial action coding system(FACS), and the generation of emotional expressions by FACS. The term android robot refers to robots with human-like appearance. These robots have artificial skin and muscles. To make the expression of emotions, the location and number of artificial muscles had to be determined. Therefore, it was necessary to anatomically analyze the motions of the human face by FACS. In FACS, expressions are composed of action units(AUs), which work as the basis of determining the location and number of artificial muscles in the robots. The android head developed in this study had servo motors and wires, which corresponded to 30 artificial muscles. Moreover, the android head was equipped with artificial skin in order to make the facial expressions. Spherical joints and springs were used to develop micro-eyeball structures, and the arrangement of the 30 servo motors was based on the efficient design of wire routing. The developed android head had 30-DOFs and could express 13 basic emotions. The recognition rate of these basic emotional expressions was evaluated at an exhibition by spectators.

• Journal of Haehwa Medicine
• /
• v.12 no.1
• /
• pp.79-102
• /
• 2003

It has been believed that the human body can be effected by color, sound, smell, and taste - each of them is based on the original character. Out of these elements, the color can be a mediation that absorbs energy into human body and adapts it to the creatures whose life are definitely based on the solar energy. This thesis makes a study of the possibility of applying the color to the oriental medical science by researching the color psychology and therapy which are studied in the west medical science, the recognition and application of color developed from orientalism, and the opinion of color in the oriental medical science. Color therapy is one of the psychological treatment techniques that are able to recover and maintain the health with the rays of the sun rays and the color. The light and the color have its energy that may relax, harmonize, encourage, or excite a human being. This is because the wavelength and the vibration of each color will take effects to human body. The core energy of absorbing and distributing the color vibration is made in the 7 "chakras" in the body, which are the pith and marrow of bio-energy directly connected with the center of the nervous system. There are several methods in the color therapy - the treatment of solar ray, the color-bath, the water-therapy using color energy, the inducement of the solar energy into the body, the acupuncture, the therapy of crystal and jewel, and the self-suggestion dependent upon the color. The color therapy can help us to keep our balance by changing the emotion into the positive energy that will cure the disease with color. As a result, this method not only must be useful to cure physical disease, or develop into good health but also will be used in conforming itself to the mental disease. The color therapy mainly uses the eight colors, which are made by mixing Red, Yellow and Blue basic colors in the field. They are never used in the treatment, but they will go along with complementary colors. This rule is closely connected with the theory of yin and yang which lies at the root of oriental philosophy, and with the treatment principle of oriental medical science whose field is focused on the balancing the body mentally as well as physically. In the East, it is the Obangsaek - the color of blue, red, yellow, white, and black in the theory of yin and yang and the five elements that have been used in helping people having trouble with their health for a long time. In the view of the oriental medical science, these five colors attached the theory of five-elements have been very useful to the physiology, the pathology, or the diagnosis, and been applied to the medical treatment, combining themselves with a five-taste in medicinal herbs. Since the study of color and human physiology has been made in some different interest and fields these days, it goes to prove that the different function of color we couldn't have got before becomes very useful to the medical science. The color must be worth researching the diversity for applying itself to the oriental medical science.