• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.406-413
• /
• 2020

In this paper, to improve the classification accuracy of bird and amphibian acoustic sound, we utilize GLU (Gated Linear Unit) and Self-attention that encourages the network to extract important features from data and discriminate relevant important frames from all the input sequences for further performance improvement. To utilize acoustic data, we convert 1-D acoustic data to a log-Mel spectrogram. Subsequently, undesirable component such as background noise in the log-Mel spectrogram is reduced by GLU. Then, we employ the proposed temporal self-attention to improve classification accuracy. The data consist of 6-species of birds, 8-species of amphibians including endangered species in the natural environment. As a result, our proposed method is shown to achieve an accuracy of 91 % with bird data and 93 % with amphibian data. Overall, an improvement of about 6 % ~ 7 % accuracy in performance is achieved compared to the existing algorithms.

• Journal of Welding and Joining
• /
• v.7 no.3
• /
• pp.1-6
• /
• 1989

응력집중의 원인은 여러 가지 있으며, 각각의 방지대책 또한 이론적으로는 밝혀져 있다. 그러나 실제 용접구조물에 있어서는 여러 가지 제약조건 때문에 유효한 방지대학을 적용할 수 없는 경우도 있어 이러한 경우에는 설계와 시공 등을 통하여 최적의 조건을 도출하는 것이 중요하다. 또한, 응력집중의 악영향은 사용조건이나 환경에 의하여 크게 변화하므로, 어떤 조건에서는 문제되지 않는 응력집중이 다른 조건에서는 손상의 원인이 되기도 한다. 빈약한 경험에 근거한 독단이나 지식부족에 의한 무분별은 극히 위험한 것이다. 응력집중의 악영향을 방지하는데는 설계기술자는 물론 용접시공을 담당하는 용접기술자, 용접지도자 등 넓은 범위의 관련기술자가 응력집중의 악영향과 그 방지대책의 기본에 대하여 바른 지식을 가지고 용접시공에 관련된 모든 공정 및 작업에 주의를 기울이고 적절한 조처를 취하는 것이 중요하다.

• 건강소식
• /
• v.34 no.6
• /
• pp.36-37
• /
• 2010

지금 당신의 자녀가 좋아하는 컴퓨터 게임은 한 시간이고 두시간이고 집중적으로 몰두하는데 숙제를 하기 위해 책상에 앉으면 채 5분도 못견딘다면? 집중하고 있을 때 외부의 자극에 금방 주의가 흐트러진다면? 특정한 과제나 활동에 필요한 물건들 장난감, 공책, 연필, 책 등의 도구를 자주 잃어버린다면? 주의력결핍 과잉행동장애가 아닌지 의심해봐야 한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.389-395
• /
• 2022

Because of improvement of deep learning techniques, deep learning using computer vision such as classification, detection and segmentation has also been used widely at many fields. Expecially, automatic driving is one of the major fields that applies computer vision systems. Also there are a lot of works and researches to combine multiple tasks in a single network. In this study, we propose the network that predicts the individual depth of pedestrians and vehicles. Proposed model is constructed based on YOLOv3 for object detection and Monodepth for depth estimation, and it process object detection and depth estimation consequently using encoder and decoder based on hard parameter sharing. We also used attention module to improve the accuracy of both object detection and depth estimation. Depth is predicted with monocular image, and is trained using self-supervised training method.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.16 no.6
• /
• pp.45-55
• /
• 2012

The road luminaires have been treated as subsidiary electric apparatuses in the road although they are indispensable facilities which people use the road safely. Because of this misunderstanding, there are not many researches on luminaire supports against the wind loads. Therefore, a typhoon has overturned or damaged many luminaire supports without having sufficient structural safeties. The purpose of this study is to review the current design criteria and to suggest the improvement of design methods based on the structural safety and compatible with the site conditions of luminaire supports. The stress concentration around the inspection hole, which causes the collapse of luminaire supports, is analyzed and stress reduction method is suggested with the improved design methods.

• The Journal of the Korea Contents Association
• /
• v.11 no.7
• /
• pp.179-191
• /
• 2011

This study aims to elucidate the relationship between the characteristics of adult learners and flow in cyber-class along with relationships among flow, stress, and problem-solving ability. The research subjects were 1044 enrolled students at Cyber University located in Seoul through voluntary on-line questionnaire. The analysis is following: The components of flow on cyber-class including enjoyment, engagement, focused attention, and time-distortion show the significant difference upon the characteristics of adult learners such as school grade, age, marital status, and number of registered classes. In addition, the flow on cyber-class has the negative relationship with stress and the positive relationship with problem-solving ability. To improve the level of flow on cyber-class, it is important to develop the new on-line class and class materials with the consideration of characteristics and diverse backgrounds of adult learners. The incorporation of various interactive evaluation can also improve the flow level of adult learners in cyber class. Finally, the learning counselling service might be essential for adult learners to experience flow on cyber-class.

• Journal of the Korean School Mathematics Society
• /
• v.13 no.3
• /
• pp.459-483
• /
• 2010

This study aims to develop materials related to math education for the aged and to identify the effects of application as part of active measures to the aging society with its growing elderly population which is one of the greatest changes in our society. In this purpose, the necessity and objectives for development of materials of 'Silver Math' as education for the aged are explained. Developing and disseminating materials with a role as a program for intelligent needs and physical and spiritual health of the aged presents standards for development of more systemic and meaningful educational materials at this point of time when the importance of education of the aged increases to help the old enjoy qualitatively successful lives in later years in the perspective of lifelong education. Also it aims to present standards of contents and requirements in learning that are adequate and meaningful to old learners at the actual learning sites where education takes place only in terms of making good use of spare time while at the same time suggesting plans of teaching and learning as well as conditions for learning environment. Next, the effectiveness of 'Silver Math' are explored by applying developed materials to the aged. materials of 'Silver Math' for the aged with contents that are appropriate to the definitive and cognitive level of the aged are presented. The developed materials for mathematical activities are divided into 'computation of basic numbers' for those wishing to learn calculation and concepts of numbers, 'active math' that corresponds to definitive factors of old learners, facilitates leisure time through mathematical activities, and Improves communication abilities through cooperative learning among learners, and 'math with thinking power' to solve simple calculation problems by applying to various actual situations.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.1641-1645
• /
• 2006

수문순환과 수질오염과정의 제반 기작들이 완벽하게 규명되지 않은 상황에서 인위적 또는 자연적 조건에 따른 수질의 평가는 수질모형으로서 추정하는 것이 유일한 대안이며, 다양한 관리대안에 따른 수질환경변화를 예측함으로서 합리적인 관리방안을 도출하는데 유용한 수단이 되고 있다. 현재 시행 중인 수질오염총량관리제에서 또한 수질모형은 핵심적인 역할을 담당하고 있으며, 보다 구체적으로는 단위유역의 목표수질을 결정하는 것에서부터 기본계획 또는 시행계획에 따른 오염부하량 등 환경요인의 변화와 이에 따른 목표수질 설정지점의 수질 변화 등을 모의하는데 이용되고 있다. 그러나 모형에 사용되는 입력 매개변수의 불확실성과 이에 관련된 수질 모형 자체의 불확실성은 수질오염총량관리제와 같이 많은 이해당사자가 관여된 정책의 결정 시에는 공학적으로 많은 부담으로 작용하고 있는 것 또한 현실이다. 실제로 미국의 오염총량관리제의 경우를 살펴보면 모형의 불확실성 분석이 전체 과정의 진행에서 가장 핵심적인 지위를 차지하고 있다고 볼 수 있다. 많은 연구들이 수질모형에 있어서의 불확실성을 정량화하기 위하여 수행되어 왔으며, 특히 미국의 오염총량관리계획의 수립 시에는 이러한 불확실성 분석을 토대로 하여 안전율을 산정하도록 되어있다. 그러나 이러한 연구들의 대부분은 수질모형의 매개변수 중 수질기작에 관련된 매개변수들(예를 들어, DO, BOD, N, P 등에 대한 반응계수)에 대한 연구에 집중되어 있다. 하천의 수질을 적절하게 모델링하기 위해서는 이러한 수질에 직접적으로 관련한 매개변수들 이외에 하천의 수리특성에 관한 올바른 이해를 바탕으로 그와 관련된 수리학적 매개변수들에 대한 연구가 뒷받침되어야 한다. 그동안 수행되어온 수질 모델링의 적용 사례를 살펴본 바에 따르면 하천을 모델링하기 위해서는 현장 특성 자료의 중요성, 특히 하천수리특성에 관련된 기초 자료의 가용성 여부가 모형의 성패에 매우 중요한 역할을 함을 알 수 있다. 이는 유량, 유속 및 폭과 깊이로 대변되는 하천 지형은 물질 이송에 대한 주요 외력 함수이며, 다른 모든 예측치들은 이들에 의존적일 수밖에 없기 때문이다. 따라서 이들의 정확한 표현은 올바른 수질 예측에 있어서 필수적일 수밖에 없다. 많은 모형매개변수들이 유속과 깊이에 의존적이나, 이들에 관한 정보는 종종 현장관측에서 조차 무시되는 경우가 많다. 이에 본 연구에서는 수질모형의 매개변수 중 특히 수리특성에 관련된 매개변수들이 수질에 미치는 영향을 파악하는 것을 목적으로 하고 있다. 이를 위해 적용된 수질모형은 QualKo를 사용하였으며, 대상 하천은 낙동강 본류 경남구간 시점 부근인 회천 합류 전부터 낙동강 본류 경남구간 종점 부근인 밀양강 합류 전까지의 경남 오염총량관리 기본계획 시 구축된 모형 매개변수를 바탕으로 분석을 수행하였다. 일차오차분석을 이용하여 수리매개변수와 수질매개변수의 수질항목별 상대적 기여도를 파악해 본 결과, 수리매개변수는 DO, BOD, 유기질소, 유기인 모든 항목에 일정 정도의 상대적 기여도를 가지고 있는 것을 알 수 있었다. 이로부터 수질 모형의 적용 시 수리 매개변수 또한 수질 매개변수의 추정 시와 같이 보다 세심한 주의를 기울여 추정할 필요가 있을 것으로 판단된다.

• Science of Emotion and Sensibility
• /
• v.21 no.1
• /
• pp.71-82
• /
• 2018

Stress involves changes in behavior, autonomic function and the secretion of hormones. Autonomic nervous system (ANS) contributes to physiological adaptive process in short durations. In particular, heart rate variability (HRV) analysis is commonly used as a quantitative marker depicting the ANS activity related to mental stress. The aim of this study is to investigate correlations between psychological responses to stress and HRV indices induced by the cognitive stressor. Thirty-three participants rated their mental and physical symptoms occurred during the past two weeks on Stress Response Inventory (SRI), which is composed of seven stress factors that may influence the status of mental stress levels. Then, they underwent the psychophysiological procedures, which are collected electrocardiogram (ECG) signals during a cognitive stress task. HRV indices, the standard deviation of R-R interval (SDNN), root mean square of successive R-R interval difference (RMSSD) and low frequency (LF)/high frequency (HF) ratio were extracted from ECG signals. Physiological responses were calculated stress responses by subtracting mean of the baseline from the mean of recovery. Stress factors such as tension, aggression, depression, fatigue, and frustration were positively correlated to HRV indices. In particular, aggression had significant positive correlations to SDNN, RMSSD and LF/HF ratio. Increased aggressive responses to stress correlated with the increases of all HRV indices. This means the increased autonomic coactivation. Additionally, tension, depression, fatigue, and frustration were positively associated with RMSSD reflecting increases in parasympathetic activation. The autonomic coactivation may represent an integrated response to specific cognitive reactions such as the orienting response.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.9-16
• /
• 2023

Recently, a convolutional neural network (CNN) based system is being developed to overcome the limitations of human resources in the apple quality classification of farmhouse. However, since convolutional neural networks receive only images of the same size, preprocessing such as sampling may be required, and in the case of oversampling, information loss of the original image such as image quality degradation and blurring occurs. In this paper, in order to minimize the above problem, to generate a image patch based graph of an original image and propose a random walk-based positional encoding method to apply the graph transformer model. The above method continuously learns the position embedding information of patches which don't have a positional information based on the random walk algorithm, and finds the optimal graph structure by aggregating useful node information through the self-attention technique of graph transformer model. Therefore, it is robust and shows good performance even in a new graph structure of random node order and an arbitrary graph structure according to the location of an object in an image. As a result, when experimented with 5 apple quality datasets, the learning accuracy was higher than other GNN models by a minimum of 1.3% to a maximum of 4.7%, and the number of parameters was 3.59M, which was about 15% less than the 23.52M of the ResNet18 model. Therefore, it shows fast reasoning speed according to the reduction of the amount of computation and proves the effect.