• The Journal of the Korea institute of electronic communication sciences
• /
• 제17권6호
• /
• pp.1137-1144
• /
• 2022

In this study, an artificial intelligence(AI) was developed to help with facial expression practice in order to express emotions. The developed AI used multimodal inputs consisting of sentences and facial images for deep neural networks (DNNs). The DNNs calculated similarities between the emotions predicted by the sentences and the emotions predicted by facial images. The user practiced facial expressions based on the situation given by sentences, and the AI provided the user with numerical feedback based on the similarity between the emotion predicted by sentence and the emotion predicted by facial expression. ResNet34 structure was trained on FER2013 public data to predict emotions from facial images. To predict emotions in sentences, KoBERT model was trained in transfer learning manner using the conversational speech dataset for emotion classification opened to the public by AIHub. The DNN that predicts emotions from the facial images demonstrated 65% accuracy, which is comparable to human emotional classification ability. The DNN that predicts emotions from the sentences achieved 90% accuracy. The performance of the developed AI was evaluated through experiments with changing facial expressions in which an ordinary person was participated.

• Journal of The Korean Association of Information Education
• /
• 제24권3호
• /
• pp.243-254
• /
• 2020

In order to cultivate AI(artificial intelligence) manpower, major countries are making efforts to apply AI education from elementary school. In order to introduce AI education in elementary school, it is necessary to have a curriculum and educational content for elementary school level. This study developed educational contents to experience the principle of AI learning at the unplugged level for the purpose of AI education for elementary school students. The educational content developed was selected as an AI that evaluates the emotion of sentences. In addition, to solve the problem, data attributes were derived and collected, and the process of AI learning was simulated to solve the problem. As a result of the study, the attitude of elementary school students to AI increased post than before. In addition, the task performance rate was averaged at 85%, showing that the proposed AI education content has educational significance.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.773-777
• /
• 2009

In recent years, the field of synthesizing voice has been developed rapidly, and the technologies such as reading aloud an email or sound guidance of a car navigation system are used in various scenes of our life. The sound quality is monotonous like reading news. It is preferable for a text such as a novel to be read by the voice that expresses emotions wealthily. Therefore, we have been trying to develop a system reading aloud novels automatically that are expressed clear emotions comparatively such as juvenile literature. At first it is necessary to identify emotions expressed in a sentence in texts in order to make a computer read texts with an emotionally expressive voice. A method on the basis of the meaning interpretation that utilized artificial intelligence technology for a method to specify emotions of texts is thought, but it is very difficult with the current technology. Therefore, we propose a method to determine only emotion every sentence in a novel by a simpler way. This method determines the emotion of a sentence according to an emotion that words such as a verb in a Japanese verb sentence, and an adjective and an adverb in a adjective sentence, have. The emotional characteristics that these words have are prepared beforehand as a emotional words dictionary by us. The emotions used here are seven types: "joy," "sorrow," "anger," "surprise," "terror," "aversion" or "neutral."

• Journal of the Korea Society of Computer and Information
• /
• 제28권3호
• /
• pp.35-43
• /
• 2023

Emotion recognition while driving is an essential task to prevent accidents. Furthermore, in the era of autonomous driving, automobiles are the subject of mobility, requiring more emotional communication with drivers, and the emotion recognition market is gradually spreading. Accordingly, in this research plan, the driver's emotions are classified into seven categories using psychological and behavioral data, which are relatively easy to collect. The latent vectors extracted through the auto-encoder model were also used as features in this classification model, confirming that this affected performance improvement. Furthermore, it also confirmed that the performance was improved when using the framework presented in this paper compared to when the existing EEG data were included. Finally, 81% of the driver's emotion classification accuracy and 80% of F1-Score were achieved only through psychological, personal information, and behavioral data.

• KIISE Transactions on Computing Practices
• /
• 제23권6호
• /
• pp.386-391
• /
• 2017

In this paper, we propose a system that automatically assigns user's experience-based emotion tags from wearable sensor data collected in real life. Four types of emotional tags are defined considering the user's own emotions and the information which the user sees and listens to. Based on the collected wearable sensor data from multiple sensors, we have trained a machine learning-based tagging system that combines the known auxiliary tools from the existing affective computing research and assigns emotional tags. In order to show the usefulness of this multi-modality-based emotion tagging system, quantitative and qualitative comparison with the existing single-modality-based emotion recognition approach are performed.

• Journal of IKEEE
• /
• 제22권3호
• /
• pp.816-821
• /
• 2018

Recently, machine learning algorithms based on artificial neural networks started to be used widely as classifiers in the field of EEG research for emotion analysis and disease diagnosis. When a machine learning model is used to classify EEG data, if training data is composed of only data having similar characteristics, classification performance may be deteriorated when applied to data of another group. In this paper, we propose a method to construct training data set by selecting several groups of data using semi-supervised learning algorithm to improve these problems. We then compared the performance of the two models by training the model with a training data set consisting of data with similar characteristics to the training data set constructed using the proposed method.

• Proceedings of the Korean Institute of Interior Design Conference
• /
• 한국실내디자인학회 2007년도 추계학술발표대회 논문집
• /
• pp.216-219
• /
• 2007

New paradigm of modern society today - environmentally sound and sustainable development - led to the attempt on the introduction of natural elements in various spaces by people's interest in the quality of life. As one of the distinguished space marketing in designing the outer space of resort, this plan attempts to limit artificial boundary within open scenery, thus creating nature within nature - interior theme garden. In addition, this plan is aimed to obtain location property of inner garden through limited boundary, to promote the identity of resort by endowing it with new values in space and to form emotion care garden and culture garden for users. The plan has proceeded under the following concepts. 1) Differentiation from outer space has been made by creating a theme garden with unique theme garden - landscape elements and an attempt have been made to increase the values of interior garden through the introduction of new species of plants and the state-of-the-art facilities. 2) Emotion care garden - The garden has been created to get emotion purified systematically within nature and let people take a rest and enjoy their spare time. 3) Culture garden - The garden has been planned where culture could be created through various experience activities as a space with education and entertainment by providing a variety of interesting elements.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 한국감성과학회 2000년도 춘계 학술대회 및 국제 감성공학 심포지움 논문집 Proceeding of the 2000 Spring Conference of KOSES and International Sensibility Ergonomics Symposium
• /
• pp.318-327
• /
• 2000

Managerial intuition is a well-recognized cognitive ability but still poorly understood for the purpose of developing effective decision support systems. this research investigates whether the differences in accuracy of "time series forecasting" are related to the differences in one's cognitive style, using statistical test The hypotheses established in the research model did not have positive correlation The lack of correlation between "cognitive style and physiological measures" and accuracy in forecasting may be caused by uncontrolled external variable. Thus, further analyses on physiological characteristics and brainwaves are needed. The approaches such as neural network and data mining are proposed.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 한국감성과학회 2002년도 춘계학술대회 논문집
• /
• pp.30-33
• /
• 2002

There are several methods to implement the logical machine reasoning such as a frame theory and a production system of artificial intelligence. And these algorithms can explain the obtained result through the inference processes. However, emotional (KANSEI) patterns are not so easily implement. One of reason is that some emotional expression is the result of process from unconscious level to conscious level, and not easily identified the original unconscious causes. Therefore, a function of KANSEI database needs to structuralize unconscious level. Our approach is to develop the computerized counseling support system which can structuralize the unconscious brain functions from the view point of the psychology with focusing physiological and emotional responses. Especially, development of the algorithm that can form the network from unconscious to conscious using the image recollection is the application of the structured association technique (SAT). The developed system was implemented on the Web using CGI and emotional network database.

• Science of Emotion and Sensibility
• /
• 제1권2호
• /
• pp.133-147
• /
• 1998

이 글은 영구의 자동차내부 소음연구와 보버르트(Bobbert)의 첫 번재 독일어로 쓰인 연구를 다루고 있다. 승용차내부소음은 높은 적외파음향(infra sound)으로 특징지어 진다. 그런 까닭으로 그러한 종류의 소음을 A-평가계측(A-rated measurement)으로 그 영향을 파알하는 것은 한계가 있다. 자동차음향공학은 특히 인공청각(artificial head)기술의 발전, 소리의 합성적 제조 및 다양한 자동차 내부 음색(timbre)에 대한 일본연구가들 (하쉬모토, 쿠와노, 남바)에 의해 상당산 성취를 경험하였다. 위의 연구들은 무엇보다도 의미분별기법(Semantic Differentials)과 다차원측정방법(Multidimen-sional Scaling)을 사용하고 있다. 그러한 기법의 사용은 심리측정방법을 심리음향학(Psycho-acoustics), 특히 츠뷔커학파(Zwicker school)의 심리음향학 방법론과 결합한 것으로 볼 수 있다.