• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.559-561
• /
• 2022

인공지능 시대에 들어서면서 개인 맞춤형 환경을 제공하기 위하여 사람의 감정을 인식하고 교감하는 기술이 많이 발전되고 있다. 사람의 감정을 인식하는 방법으로는 얼굴, 음성, 신체 동작, 생체 신호 등이 있지만 이 중 가장 직관적이면서도 쉽게 접할 수 있는 것은 표정이다. 따라서, 본 논문에서는 정확도 높은 얼굴 감정 식별을 위해서 Convolution Block Attention Module(CBAM)의 각 Gate와 Residual Block, Skip Connection을 이용한 Identity- CBAM Module을 제안한다. CBAM의 각 Gate와 Residual Block을 이용하여 각각의 표정에 대한 핵심 특징 정보들을 강조하여 Context 한 모델로 변화시켜주는 효과를 가지게 하였으며 Skip-Connection을 이용하여 기울기 소실 및 폭발에 강인하게 해주는 모듈을 제안한다. AI-HUB의 한국인 감정 인식을 위한 복합 영상 데이터 세트를 이용하여 총 6개의 클래스로 구분하였으며, F1-Score, Accuracy 기준으로 Identity-CBAM 모듈을 적용하였을 때 Vanilla ResNet50, ResNet101 대비 F1-Score 0.4~2.7%, Accuracy 0.18~2.03%의 성능 향상을 달성하였다. 또한, Guided Backpropagation과 Guided GradCam을 통해 시각화하였을 때 중요 특징점들을 더 세밀하게 표현하는 것을 확인하였다. 결과적으로 이미지 내 표정 분류 Task에서 Vanilla ResNet50, ResNet101을 사용하는 것보다 Identity-CBAM Module을 함께 사용하는 것이 더 적합함을 입증하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1183-1189
• /
• 2021

There have been recently an increasing number of people working out at home. However, many of them do not have face-to-face guidance from experts, so they cannot effectively correct their wrong pose. This may lead to strain and injury to those doing home training. To tackle this problem, this paper proposes a video data-based pose classification and correction system for home training. The proposed system classifies poses using the multi-layer perceptron and pose estimation model, and corrects poses based on joint angels estimated. A voting algorithm that considers the results of successive frames is applied to improve the performance of the pose classification model. Multi-layer perceptron model for post classification shows the highest accuracy with 0.9. In addition, it is shown that the proposed voting algorithm improves the accuracy to 0.93.

• The Journal of the Korea Contents Association
• /
• v.7 no.6
• /
• pp.154-160
• /
• 2007

The 'spatial sense' means an intuitive feel for one's surroundings and the objects in them. The early childhood is an important period to develop the 'spatial sense'. For young children, motion is a major way of extending their spatial awareness. Consequently, an important step in spatial sense instruction involves getting the children moving. This paper proposes four motion based-contents for improving the spatial sense of young children: a bubble game, a cyber goalkeeper game, a mud-huddle game, and a shape recognition game, The proposed four games are implemented to the virtual learning environments. Also, the virtual learning environments utilize the realistic interfaces which can recognize motions of young children and then interact with the games as they do the movement at the virtual environments provided. Using the realistic interfaces not only develops young children's spatial sense but also offers them the pleasure and interest of self-study.

• Korean Journal of Cognitive Science
• /
• v.21 no.2
• /
• pp.309-338
• /
• 2010

In this paper, we studied the brain-computer interface (BCI). BCIs help severely disabled people to control external devices by analyzing their brain signals evoked from motor imageries. The findings in the field of neurophysiology revealed that the power of $\beta$(14-26 Hz) and $\mu$(8-12 Hz) rhythms decreases or increases in synchrony of the underlying neuronal populations in the sensorymotor cortex when people imagine the movement of their body parts. These are called Event-Related Desynchronization / Synchronization (ERD/ERS), respectively. We implemented a BCI-based mouse interface system which enabled subjects to control a computer mouse cursor into four different directions (e.g., up, down, left, and right) by analyzing brain signal patterns online. Tongue, foot, left-hand, and right-hand motor imageries were utilized to stimulate a human brain. We used a non-invasive EEG which records brain's spontaneous electrical activity over a short period of time by placing electrodes on the scalp. Because of the nature of the EEG signals, i.e., low amplitude and vulnerability to artifacts and noise, it is hard to analyze and classify brain signals measured by EEG directly. In order to overcome these obstacles, we applied statistical machine-learning techniques. We could achieve high performance in the classification of four motor imageries by employing Common Spatial Pattern (CSP) and Linear Discriminant Analysis (LDA) which transformed input EEG signals into a new coordinate system making the variances among different motor imagery signals maximized for easy classification. From the inspection of the topographies of the results, we could also confirm ERD/ERS appeared at different brain areas for different motor imageries showing the correspondence with the anatomical and neurophysiological knowledge.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.859-864
• /
• 2022

Drowsy driving, one of the biggest causes of traffic accidents every year, is accompanied by various factors. As a general method to check whether or not there is drowsiness, a method of identifying a driver's expression and driving pattern, and a method of analyzing bio-signals are being studied. This paper proposes a driver fatigue detection system using deep learning technology and bio-signal measurement technology. As the first step in the proposed method, deep learning is used to detect the driver's eye shape, yawning presence, and body movement to detect drowsiness. In the second stage, it was designed to increase the accuracy of the system by identifying the driver's fatigue state using the pulse wave signal and body temperature. As a result of the experiment, it was possible to reliably determine the driver's drowsiness and fatigue in real-time images.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.04a
• /
• pp.437-440
• /
• 2000

복지형 정보단말장치로 청각장애인과 건청인과의 커뮤니케이션은 지원하는 것을 목적으로 수화 애니메이션 생성시스템을 제안, 개발하고 있다. 이 시스템에서는 신체의 각 부위의 움직임을 주목한수화 단어 기술방식을 기초로 하여 컴퓨터그래픽(CG) 애니메이션 수화 단어 동작을 생성하고 있다. 이 애니메이션에 대하여 실제로 청각장애인을 대상으로 수화단어 100단어 대하여 평가실험을 행한 결과 평균76%의 인식율을 얻을 수 있었다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.137-138
• /
• 2019

최근에는 청소년과 어른 대상으로한 운동을 많이 함으로써 운동은 그 어느 때 보다 인기를 얻고 있다. 하지만 그에 따른 사고도 점차 많이 일어나고 있다. 이는 신체활동 능력의 높이는 동시에 운동자세교정을 해주고 사고방지를 하고자 스포츠, 교육, 3D 가상현실 일부 사용되는 몰입형 프로그램으로 설계 했다. 본 프로그램에서는 사용자 동작을 효과적으로 인식 할 수 있는 키넥트(Kinect)를 사용하여 인터페이스를 제작하였고 향후 연구를 통해 운동자세효과를 검증하고 다양한 운동 그리고 재활치료등 개발할 필요가 있음을 시사한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.299-300
• /
• 2021

본 논문에서는 고령화 사회로 인한 치매 환자 증가 문제해결을 위해 웹(web) 기반으로 동작하는 치매 예방용 프로그램을 개발하는 것을 목적으로 하였다. 사전 준비단계로 치매 관련 시스템 및 기술고찰을 통해 개발범위를 규정하였고, 이를 근거로 프로그램을 작성하였다.

• The Journal of the Korea Contents Association
• /
• v.10 no.5
• /
• pp.296-302
• /
• 2010

The purpose of this study was to examine the oral injury experiences of sport players in a bid to raise awareness of the gravity of problems related to oral injuries and the necessity of mouth guards geared toward preventing mental, physical and economic loss triggered by oral injuries. The subjects in this study were 290 sport players. After their oral injury experiences and use of mouth guards were checked, the following findings were given: 28.6 percent had suffered an oral injury. But just 33.8 percent received education about how to cope with an oral injury. 93.4 percent had never used a mouth guard, and only 25.9 percent felt the need for that. And just 28.3 percent had an intention to use it. felt the need for that. And just 28.3 percent had an intention to use it. Concerning the impact of gender, the female players used more mouth guards. The players didn't use mouth guards a lot regardless of oral injury experiences and education about that, and there was no change in the way they looked at mouth guards, either. The findings of the study illustrated that sport players as well as non-players weren't aware of the importance of mouth guards, though sport players were exposed to the danger of an oral injury all the time. Not only players but non-players should learn about the seriousness of an oral injury, and the necessity of oral guards should be stressed to prevent it.

• Journal of Korea Game Society
• /
• v.14 no.1
• /
• pp.49-58
• /
• 2014

We have developed a serious game for the elderly named 'Paldokangsan3' as a next version of 'Paldokangsan2' which was a walking game with memorization in shopping streets using controllers of hand buttons and foot boards with PC developed in 2012. The interface of had buttons and food boards were changed into the interface of motion capture with the aid of Kinect. The expected effects are improvement of memorization, improvement of concentration ability to find out items in the vision, improvement of vitality through physical walking actions, as well as improvement of mental health through entertainment activities of game play. We have tested 25 volunteers of more than 65 years old in Cheonan city community center for the elderly for 2 weeks. We got the result that the game play was showing positive effectiveness on memorization, physical exercise and self-esteem in mental health area of the elderly.