• Journal of the Korea Society of Computer and Information
• /
• v.25 no.1
• /
• pp.55-61
• /
• 2020

With the development of deep learning technology and advances in computing power, video-based research is now gaining more and more attention. Video data contains a large amount of temporal and spatial information, which is the biggest difference compared with image data. It has a larger amount of data. It has attracted intense attention in computer vision. Among them, motion recognition is one of the research focuses. However, the action recognition of human in the video is extremely complex and challenging subject. Based on many research in human beings, we have found that artificial intelligence-like attention mechanisms are an efficient model for cognition. This efficient model is ideal for processing image information and complex continuous video information. We introduce this attention mechanism into video action recognition, paying attention to human actions in video and effectively improving recognition efficiency. In this paper, we propose a new 3D residual attention network using convolutional neural network based on two attention models to identify human action behavior in the video. An evaluation result of our model showed up to 90.7% accuracy.

• Journal of Broadcast Engineering
• /
• v.23 no.5
• /
• pp.598-605
• /
• 2018

Behavior awareness is a technology that recognizes human behavior through data and can be used in applications such as risk behavior through video surveillance systems. Conventional behavior recognition algorithms have been performed using the 2D camera image device or multi-mode sensor or multi-view or 3D equipment. When two-dimensional data was used, the recognition rate was low in the behavior recognition of the three-dimensional space, and other methods were difficult due to the complicated equipment configuration and the expensive additional equipment. In this paper, we propose a method of recognizing human behavior using only CCTV images without additional equipment using only RGB and depth information. First, the skeleton extraction algorithm is applied to extract points of joints and body parts. We apply the equations to transform the vector including the displacement vector and the relational vector, and study the continuous vector data through the RNN model. As a result of applying the learned model to various data sets and confirming the accuracy of the behavior recognition, the performance similar to that of the existing algorithm using the 3D information can be verified only by the 2D information.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.413-415
• /
• 2022

Since human joints can be used as useful information for analyzing human behavior as a component of the human body, many studies have been conducted on human action recognition using joint information. However, it is a very complex problem to recognize human action that changes every moment using only each independent joint information. Therefore, an additional information extraction method to be used for learning and an algorithm that considers the current state based on the past state are needed. In this paper, we propose a human action recognition technique considering the positional relationship of connected joints and the change of the position of each joint over time. Using the pre-trained joint extraction model, position information of each joint is obtained, and bone information is extracted using the difference vector between the connected joints. In addition, a simplified neural network is constructed according to the two types of inputs, and spatio-temporal features are extracted by adding LSTM. As a result of the experiment using a dataset consisting of 9 behaviors, it was confirmed that when the action recognition accuracy was measured considering the temporal and spatial relationship features of each joint, it showed superior performance compared to the result using only single joint information.

• Smart Media Journal
• /
• v.11 no.1
• /
• pp.46-57
• /
• 2022

In this paper, multi-region based Radial Graph Convolutional Network (MRGCN) algorithm which can perform end-to-end action recognition using the optical flow and gradient of input image is described. Because this method does not use information of skeleton that is difficult to acquire and complicated to estimate, it can be used in general CCTV environment in which only video camera is used. The novelty of MRGCN is that it expresses the optical flow and gradient of the input image as directional histograms and then converts it into six feature vectors to reduce the amount of computational load and uses a newly developed radial type network model to hierarchically propagate the deformation and shape change of the human body in spatio-temporal space. Another important feature is that the data input areas are arranged being overlapped each other, so that information is not spatially disconnected among input nodes. As a result of performing MRGCN's action recognition performance evaluation experiment for 30 actions, it was possible to obtain Top-1 accuracy of 84.78%, which is superior to the existing GCN-based action recognition method using skeleton data as an input.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.8 no.2
• /
• pp.273-286
• /
• 1997

Objective：This study was designed to evaluate effects of methylphenidate(MPH) on event-related potentials(ERP) and continuous performance test(CPT) in attention-deficit hyperactivity disorder (ADHD) and to see the correlation between changes in ERP and changes in performance. Method：ERP and CPT were used to examine the acute effects of MPH(0.5mg/kg) in eleven ADHD boys(89-103 months old). Results：1) After MPH administration, P3 latency to nontarget stimuli at Fz was significantly decreased (p<0.01) and P2 amplitudes to target stimuli at Pz and at Oz and P3 amplitude to target stimuli at Cz were significantly increased(p<0.05). 2) Commission error and omission error in the CPT-X and commission error in the CPT-AX were decreased(p<0.01), and hits and perceptual sensitivity(d') in the CPT-X and d′ in the CPT-AX were increased(p<0.01). 3) The change of P3 latency to nontarget stimuli at Fz and the change of d′ in the CPT-X were negatively correlated(p<0.05), and the change of P2 amplitude to target stimuli at Pz and d′ in the CPT-AX were positively correlated(p<0.05). Conclusion：MPH improves change orienting reaction, the delivery of task relevant information, accuracy and perceptual sensitivity in ADHD. And the increase of ability to discriminate targets from non-targets reflects reduced evaluation time in large memory component task and enhanced change orienting reaction in simple task.

• Journal of Korean Home Economics Education Association
• /
• v.17 no.2
• /
• pp.49-60
• /
• 2005

In this study, environmental knowledge and consciousness and eco-friendly behavior related to dietary life of middle school students were examined. Male and female students in Gyeongsan and Daegu Metropolitan City were selected for the study. Total of 490 questionnaires were delivered and collected, and 445 of them were analyzed by using SPSS Win Ver 12.0. Percentages of students who checked' don't know the answer' in 20 environmental knowledge assessment questions were $14.4\~41.8\%$, and those who gave correct answer to these responded to how the answer were $40.1\~93.3\%$. The average score of environmental consciousness was 3.45 and that of eco-friendly dietary behavior was 2.9 out of 5. When dietary behavior was divided by three categories, such as food purchasing, eating. and dish washing, the score of food purchasing behavior was 2.7, those of eating behavior and dish washing behavior were 3.0, 3.1, respectively. In the relationship between environmental knowledge. consciousness. and eco-friendly dietary behavior, there was significant positive correlation between howledge and consciousness, but no significant relation between consciousness and behavior. It showed that environmental knowledge and consciousness didn't always lead to eco-friendly dietary behavior. Therefore, education for practical betlavior must be emphasized even though the knowledge and consciousness education on environment are important.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.769-770
• /
• 2017

최근 데이터 기술의 발달에 따라, 기업에서는 중요 데이터를 서버와 같은 데이터 저장 장치에 보관하고 있다. 하지만 기업 내부 직원에 의해 기업의 기밀 데이터가 유출될 수 있는 위험성이 있기 때문에, 내부 직원에 의한 데이터 유출을 탐지 및 방지해야 할 필요성이 있다. 따라서 본 논문에서는 각 보안 솔루션에서 수집한 보안 로그를 데이터 유출 시나리오를 바탕으로 시계열 그래프로 작성하여, 이미지 인식에 뛰어난 성능을 보이는 합성곱 신경망을 통해 데이터 유출을 탐지하는 시스템을 제안한다. 실험 결과 유출된 데이터의 크기에 상관없이 95% 이상의 정확도를 보였으며, 복합적인 행동을 통해 데이터 유출을 시도한 경우에도 97% 이상의 정확도를 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.1129-1130
• /
• 2017

본 연구에서는 현대인들의 하루 중 많은 시간을 차지하는 착좌 생활을 관리하기 위한 롤러블(rollable) 스마트패드를 개발하였다. 이를 위해 PVDF(polyvinylidene fluoride) 필름을 이용한 압전센서(piezoelectric sensor)를 제작하였으며, 센서에서 데이터를 획득하고 및 햅틱 피드백(haptic feedback)을 주기 위한 측정시스템을 개발하였다. 또한, 스마트폰 어플리케이션을 통해 착좌 자세에 대한 정보를 실시간으로 제공하도록 하였다. 제작된 시스템의 착좌 자세 구분 정확도는 10명의 피험자를 대상으로 평가되었으며, 4가지 자세(상체를 좌, 우, 앞, 뒤로 기울인 앉은 자세)에 대한 실험결과 제작된 시스템은 92.5%의 정확도로 제시한 4가지의 자세를 구분하였다.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.496-497
• /
• 2021

감정 분류는 사람의 사고방식이나 행동양식을 구분하기 위한 중요한 열쇠로, 지난 수십 년간 감정 분석과 관련된 다양한 연구가 진행되었다. 감정 분류의 품질과 정확도를 높이기 위한 방법 중 하나로 단일 레이블링 대신 다중 레이블링된 데이터 세트를 감정 분석에 활용하는 연구가 제안되었고, 본 논문에서는 T5 모델을 한국어와 영어 코퍼스로 학습한 KE-T5 모델을 기반으로 한국어 발화 데이터를 단일 레이블링한 경우와 다중 레이블링한 경우의 감정 분류 성능을 비교한 결과 다중 레이블 데이터 세트가 단일 레이블 데이터 세트보다 23.3% 더 높은 정확도를 보임을 확인했다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.667-669
• /
• 2022

2차원 이미지를 통한 자세 추정의 경우 관절이 겹치거나 가려져 있는 등의 인식 저해 요소로 인하여 자세 추정 정확도가 감소하는 한계가 있다. 본 논문에서는 GAN을 통해 2차원 이미지를 3차원으로 증강한 뒤 자세를 추정하는 기법을 제안한다. 제안하는 방법은 2차원 이미지의 평면좌표 값에서 GAN을 통해 노이즈 벡터 z축 값과 피사체에 투영되는 빛의 방향 값을 반영한 3차원 이미지를 만든다. 이러한 이미지 합성 과정을 거친 후 DeepLabCut을 사용해 관절 좌표를 추출하고 자세 추정 및 분류를 진행한다. 이를 통해 2차원에서의 자세 추정 정확도 향상을 기대할 수 있으며, 향후 이를 기반한 이상행동 탐지 분야에서 적용할 수 있다.