• Smart Media Journal
• /
• v.12 no.5
• /
• pp.28-35
• /
• 2023

In this study, we propose a new light-weight model RoutingConvNet with fewer parameters to improve the applicability and practicality of speech emotion recognition. To reduce the number of learnable parameters, the proposed model connects bidirectional MFCCs on a channel-by-channel basis to learn long-term emotion dependence and extract contextual features. A light-weight deep CNN is constructed for low-level feature extraction, and self-attention is used to obtain information about channel and spatial signals in speech signals. In addition, we apply dynamic routing to improve the accuracy and construct a model that is robust to feature variations. The proposed model shows parameter reduction and accuracy improvement in the overall experiments of speech emotion datasets (EMO-DB, RAVDESS, and IEMOCAP), achieving 87.86%, 83.44%, and 66.06% accuracy respectively with about 156,000 parameters. In this study, we proposed a metric to calculate the trade-off between the number of parameters and accuracy for performance evaluation against light-weight.

• Journal of the Korean Geographical Society
• /
• v.41 no.5 s.116
• /
• pp.561-581
• /
• 2006

Machines, cities and bodies have been evolved together for a long time, and the recent development of information and communication technologies has transformed cities and bodies into new forms. Concerned with the relations between machines, cities and bodies, this paper explores how mobile networks are related with the physical space of the city and the psychological space of the body. The paper is organised into four main sections. First, it provides a theoretical review of the ways in which mobile networks transform urban spaces and human bodies. Secondly, it explains the generation of mobile networks through technological and institutional changes in Korea. Thirdly, it looks at the socio-spatial scales and time-space landscapes of mobile networks in relation to mobile users' motions and practices in their everyday lives. Finally, it attends to the ways in which mobile networks involve the production of paradoxical emotional spaces in relation to mobile users' emotions and desires to be dis/connected with mobile networks.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.6
• /
• pp.710-715
• /
• 2003

In this paper, we propose the new emotion recognition method for intelligently recognizing the human's emotion using the template vector and neural network. In the proposed method, human's emotion is divided into four emotion (surprise, anger, happiness, sadness). The proposed method is based on the template vector extraction and the template location recognition by using the color difference. It is not easy to extract the skin color area correctly using the single color space. To solve this problem, we propose the extraction method using the various color spaces and using the each template vectors. And then we apply the back-propagation algorithm by using the template vectors among the feature points). Finally, we show the practical application possibility of the proposed method.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.105-112
• /
• 2024

In contemporary society, the expression of emotions and self-reflection are considered pivotal factors with a positive impact on stress management and mental well-being, thereby highlighting the significance of journaling. However, traditional journaling methods have posed challenges for many individuals due to constraints in terms of time and space. Recent rapid advancements in chatbot and emotion analysis technologies have garnered significant attention as essential tools to address these issues. This paper introduces an artificial intelligence chatbot that integrates the GPT-3 model and emotion analysis technology, detailing the development process of a system that automatically generates journals based on users' chat data. Through this system, users can engage in journaling more conveniently and efficiently, fostering a deeper understanding of their emotions and promoting positive emotional experiences.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.3
• /
• pp.210-216
• /
• 2015

It is well known that the structure of brain and consciousness of human have a phenomena of complex system. The human emotion have a many kind. The love is one of human emotion, which have been studied in sociology and psychology as a matter of great interested thing. In this paper, we consider a same and different time delay in love equation of Romeo and Juliet. We represent a behavior of love as a time series and phase portrait, and analyze the difference of behaviors between a same and different time delay.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.2
• /
• pp.155-160
• /
• 2015

We say that human have an animal of emotion. There are various kind in the emotion of human. One of among them, love has been studied in sociology and psychology as a matter of great concern. In this paper, we propose a novel love model with the delay time as response time for love. We also consider it in the Romeo and Juliet of love model to analyze their romantic behaviors. First we consider the Juliet only have a time delay, Romeo only have a time delay, and both Romeo and Juliet have a time delay. We represent their behaviors as time series and phase portrait, and we analyze their difference.

• The Journal of the Korea Contents Association
• /
• v.10 no.9
• /
• pp.9-17
• /
• 2010

Nowadays, many research have been conducted on robots or interactive characters that properly respond to the users affection. In this paper, we develop an intelligent messenger that provides appropriate responses to text inputs according to user's intention and affection. In order to properly respond, the intelligent messenger adapts methods to recognize user's speech act and affection. And it uses an AIML-based interactive script to which tags are additionally attached to express affection and speech act. If the intelligent messenger finds a proper reply in the interactive scripts, it displays the reply in a dialog window, and an animation character expresses emotion assimilated with a user's affection. If the animation character is synchronized with a content robot through a wireless link, the robot in the same space with the user can provide emotional response.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.05a
• /
• pp.172-175
• /
• 2006

최근 다양한 게임 문화가 급속도로 성장함에 따라 보다 새로운 개념의 게임을 찾는 사용자의 요구가 증대 되고 있다. 기존의 게임은 획일화 되고 일방적인 사용자 환경으로 사용자가 일방적으로 게임을 하는 방식이었다. 때문에 사용자의 감성 데이터를 이용하여 사용자에게 게임 환경이 맞춰지는 "사용자 맞춤형" 게임은 기존의 게임에서 보다 진보한 새로운 방식이 될 것이다. 이 방식을 사용하기 위해서는 우선 사용자의 생체 데이터나 감성데이터를 포함한 뇌파를 획득하는 방법이 필요하며 다음으로 획득된 뇌파를 통하여 현재 사용자의 감성 상태를 규명하는 패턴인식 기법이 중요한 문제가 된다. 본 논문에서는 뇌파를 통하여 현재 사용자의 감성 상태를 규명하고 인식할 수 있는 패턴인식 기법으로 Multi Layer Perceptron(MLP)을 사용한 감성인식모델을 제안한다. 본 논문에서 제안한 감성인식 모델의 실험을 위하여 특정 공간 내에서 여러 사용자의 감정별 뇌파를 측정하고 실험을 통하여 획득한 데이터로 감정 DB를 구축한다. 구축된 DB를 본 논문에서 제안한 감성인식 모델로 학습을 하고 학습이 완료된 후 새로운 사용자의 뇌파를 입력 받은 후 현재 사용자의 감성을 인식한다. 감성인식과 더불어 집중도를 측정 하는 실험도 병행 한다. 본 논문에서 제안한 감성인식 모델의 성능을 측정하기 위하여 사용자의 수에 따른 감성 인식률을 측정함으로서 본 논문에서 제안한 감성인식 모델의 성능을 확인한다.

• Journal of Intelligence and Information Systems
• /
• v.18 no.1
• /
• pp.39-57
• /
• 2012

Recently, due to the introduction of high-tech equipment in interactive exhibits, many people's attention has been concentrated on Interactive exhibits that can double the exhibition effect through the interaction with the audience. In addition, it is also possible to measure a variety of audience reaction in the interactive exhibition. Among various audience reactions, this research uses the change of the facial features that can be collected in an interactive exhibition space. This research develops an artificial neural network-based prediction model to predict the response of the audience by measuring the change of the facial features when the audience is given stimulation from the non-excited state. To present the emotion state of the audience, this research uses a Valence-Arousal model. So, this research suggests an overall framework composed of the following six steps. The first step is a step of collecting data for modeling. The data was collected from people participated in the 2012 Seoul DMC Culture Open, and the collected data was used for the experiments. The second step extracts 64 facial features from the collected data and compensates the facial feature values. The third step generates independent and dependent variables of an artificial neural network model. The fourth step extracts the independent variable that affects the dependent variable using the statistical technique. The fifth step builds an artificial neural network model and performs a learning process using train set and test set. Finally the last sixth step is to validate the prediction performance of artificial neural network model using the validation data set. The proposed model is compared with statistical predictive model to see whether it had better performance or not. As a result, although the data set in this experiment had much noise, the proposed model showed better results when the model was compared with multiple regression analysis model. If the prediction model of audience reaction was used in the real exhibition, it will be able to provide countermeasures and services appropriate to the audience's reaction viewing the exhibits. Specifically, if the arousal of audience about Exhibits is low, Action to increase arousal of the audience will be taken. For instance, we recommend the audience another preferred contents or using a light or sound to focus on these exhibits. In other words, when planning future exhibitions, planning the exhibition to satisfy various audience preferences would be possible. And it is expected to foster a personalized environment to concentrate on the exhibits. But, the proposed model in this research still shows the low prediction accuracy. The cause is in some parts as follows : First, the data covers diverse visitors of real exhibitions, so it was difficult to control the optimized experimental environment. So, the collected data has much noise, and it would results a lower accuracy. In further research, the data collection will be conducted in a more optimized experimental environment. The further research to increase the accuracy of the predictions of the model will be conducted. Second, using changes of facial expression only is thought to be not enough to extract audience emotions. If facial expression is combined with other responses, such as the sound, audience behavior, it would result a better result.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.4
• /
• pp.1-6
• /
• 2023

To enhance immersive experiences for metaverse environements, background music is often used. However, the background music is mostly pre-matched and repeated which might occur a distractive experience to users as it does not align well with rapidly changing user-interactive contents. Thus, we implemented a system to provide a more immersive metaverse conversation experience by 1) developing a regression neural network that extracts emotions from an utterance using KEMDy20, the Korean multimodal emotion dataset 2) selecting music corresponding to the extracted emotions from an utterance by the DEAM dataset where music is tagged with arousal-valence levels 3) combining it with a virtual space where users can have a real-time conversation with avatars.