• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4426-4442
• /
• 2020

Since scene segmentation is becoming a hot topic in the field of autonomous driving and medical image analysis, researchers are actively trying new methods to improve segmentation accuracy. At present, the main issues in image semantic segmentation are intra-class inconsistency and inter-class indistinction. From our analysis, the lack of global information as well as macroscopic discrimination on the object are the two main reasons. In this paper, we propose a Densely connected residual Attention network (DA-Res2Net) which consists of a dense residual network and channel attention guidance module to deal with these problems and improve the accuracy of image segmentation. Specifically, in order to make the extracted features equipped with stronger multi-scale characteristics, a densely connected residual network is proposed as a feature extractor. Furthermore, to improve the representativeness of each channel feature, we design a Channel-Attention-Guide module to make the model focusing on the high-level semantic features and low-level location features simultaneously. Experimental results show that the method achieves significant performance on various datasets. Compared to other state-of-the-art methods, the proposed method reaches the mean IOU accuracy of 83.2% on PASCAL VOC 2012 and 79.7% on Cityscapes dataset, respectively.

• 한국수학교육학회지시리즈C:초등수학교육
• /
• 제22권1호
• /
• pp.1-12
• /
• 2019

본 연구는 수학 패턴의 유형에 따른 패턴 발견에 대한 일반학생과 수학영재학생의 주의집중과 주의전환을 알아 보았다. 이를 위해 초등학교 5학년 일반학생과 수학영재 학생의 문제해결과정 중의 시선움직임을 시선추적기를 이용하여 분석하였다. 그 결과 첫째, 두 집단 간 표현양식에 따른 주의집중은 유의한 차이가 없었으나 주의전환은 두 집단 모두 숫자 표현양식에서 더 많았다. 둘째, 두 집단간의 생성방식에 따른 주의집중은 유의한 차이가 없었다. 주의전환은 두 집단 모두 증가변형 생성방식에서 더 많았다. 셋째, 일반학생들은 두 속성 모두에서 인접하지 않은 항 간의 비교에 더 많이 집중했다. 일반학생과 다르게 수학영재학생은 기하적 속성에서 주의전환이 더 많았다. 다양한 유형의 수학 패턴을 효과적으로 지도하기 위해서 두 집단 간 주의집중과 주의전환의 차이를 고려해야 할 것이다.

• 전기전자학회논문지
• /
• 제27권3호
• /
• pp.251-257
• /
• 2023

본 논문에서는 비전 트랜스포머의 셀프 어텐션이 갖는 지역적 특징 부족을 개선하는 이중 구조 셀프 어텐션 방법을 제안한다. 객체 분류, 객체 분할, 비디오 영상 인식에서 합성곱 신경망보다 연산 효율성이 높은 비전 트랜스포머는 상대적으로 지역적 특징 추출능력이 부족하다. 이 문제를 해결하기 위해 윈도우 또는 쉬프트 윈도우를 기반으로 하는 연구가 많이 이루어지고 있으나 이러한 방법은 여러 단계의 인코더를 사용하여 연산 복잡도의 증가로 셀프 어텐션 기반 트랜스포머의 장점이 약화 된다. 본 논문에서는 기존의 방법보다 locality inductive bias 향상을 위해 self-attention과 neighborhood network를 이용하여 이중 구조 셀프 어텐션을 제안한다. 지역적 컨텍스트 정보 추출을 위한 neighborhood network은 윈도우 구조보다 훨씬 단순한 연산 복잡도를 제공한다. 제안된 이중 구조 셀프 어텐션 트랜스포머와 기존의 트랜스포머의 성능 비교를 위해 CIFAR-10과 CIFAR-100을 학습 데이터를 사용하였으며 실험결과 Top-1 정확도에서 각각 0.63%과 1.57% 성능이 개선되었다.

• Communications for Statistical Applications and Methods
• /
• 제28권1호
• /
• pp.39-57
• /
• 2021

Time series prediction is an area of great interest to many people. Algorithms for time series prediction are widely used in many fields such as stock price, temperature, energy and weather forecast; in addtion, classical models as well as recurrent neural networks (RNNs) have been actively developed. After introducing the attention mechanism to neural network models, many new models with improved performance have been developed; in addition, models using attention twice have also recently been proposed, resulting in further performance improvements. In this paper, we consider time series prediction by introducing attention twice to an RNN model. The proposed model is a method that introduces H-attention and T-attention for output value and time step information to select useful information. We conduct experiments on stock price, temperature and energy data and confirm that the proposed model outperforms existing models.

• Physical Therapy Rehabilitation Science
• /
• 제1권1호
• /
• pp.13-16
• /
• 2012

Objective: Electroencephalogram (EGG)-feedback is a training procedure aimed at altering brain activity, and is used as a treatment for disorders like attention. The purpose of this study was to determine the effects of external focus of attention by EGG-feedback on balance in young adults. Design: Cross-sectional study. Methods: Subject were students in Sahmyook University. Fifty young adults in their twenties and thirties. Subjects were performed both with and without external focus of attention by EEG-feedback on the posture of standing and tandem standing. Participants were educated effort to maintain static posture when they were under internal focus of attention. Good Balance System was used for measurement of postural consistency upon the following force platforms. Results: Body sway decreased significantly both normal standing and tandem standing with external focus of attention by EEG-feedback (p<0.05). Conclusions: The results demonstrate that the benefits of an external attentional focus are generalizable to young adults. The external focus of attention outperformed the internal focus of attention on the postural balance (p<0.05). It is showed that external focus of attention significant effects on balance by revoked automatic postural control of movement. Furthermore balance might be improved by training with an external focus. Further study is required to develop for training as a method of preventing fall in elderly peoples.

• 한국의류학회지
• /
• 제17권3호
• /
• pp.428-435
• /
• 1993

The purpose of this study was to investigate the difference of the visual evaluation about clothing texture, the state of wearing and the method of presentation. The data from observation were analyzed by factor analysis, t-test, ANOVA, Scheffe test and MCA. The results of this study were as follows ; 1. 17 pairs of discriptors used for the visual evaluation of clothing stimuli were found to include four factor dimensions(total variance 65.6%) ; Attention, Appearance, Texture, Maturity. 2. For the image of clothing texture, there were significant differences in the attention and texture. 3. For the image of the state of wearing, there were significant differences in the attention and appearance. 4. For the image of the method of presentation, there were significant differences in the clothing texture and the state of wearing. 5. According to clothing texture, the state of wearing and the method of presentation, the interaction effect was significant in the attention and appearance.

• 한국멀티미디어학회논문지
• /
• 제20권3호
• /
• pp.446-455
• /
• 2017

A color image compression based on saliency map was proposed. The proposed method provides higher quality in saliency blocks on which people's attention focuses, compared with non-saliency blocks on which the attention less focuses at a given bitrate. The proposed method uses 3 different quantization tables according to each block's saliency level. In the experiment using 6 typical images, we compared the proposed method with JPEG and other conventional methods. As the result, it showed that the proposed method (Qup=0.5*Qx) is about 3.1 to 1.2 dB better than JPEG and others in saliency blocks in PSNR at the almost similar bitrate. In the comparison of result images, the proposed one also showed less error than others in saliency blocks.

• 대한의용생체공학회:의공학회지
• /
• 제23권2호
• /
• pp.155-163
• /
• 2002

Attention Deficit Hyperactivity Disorder(ADHD) is a childhood syndrome characterized by short attention span. impulsiveness, and hyperactivity, which often leadㄴ to learning disabilities and various behavioral problems. For the treatment of ADHD, medication and cognitive-behavior therapy is applied in recent yearn Although psycho-stimulant medication has been widely used for many rears. current findings suggest that, as the sole treatment for ADHD, it is an inadequate form of intervention in that parents don't want their child to use drug and the effects are limited to the period in which the drugs are physiologically active. On the other hand, EEG biofeedback treatment studies for ADHD have reported promising results not only in significant reductions in hyperactive, inattentive, and disruptive behaviors, but also improvements in academic performance and IQ scores. However it is too boring for children to finish the whole treatment. The recent increase in computer usage in medicine and rehabilitation has changed the way health care is delivered. Virtual Reality technology provides specific stimuli that can be used in removing distractions and providing environments that get the subjects'attention and increasing their ability to concentrate. VR technology can hold a patient's attention for a longer period of time than other methods can, because VR is immersive, interactive and imaginal. Based on these aspects, we developed Attention Enhancement System (AES) using VR technology, EEG biofeedback, and cognitive training method for enhancing attention and made a clinical trial to people who have attention difficulty and behavioral problems.

• 한국항행학회논문지
• /
• 제27권2호
• /
• pp.182-189
• /
• 2023

깊이 추정은 차량, 로봇, 드론의 자율주행을 위한 3차원 지도 생성의 핵심 기술이다. 기존의 센서 기반 깊이 추정 방식은 정확도는 높지만 가격이 비싸고 해상도가 낮다. 반면 카메라 기반 깊이 추정 방식은 해상도가 높고 가격이 저렴하지만 정확도가 낮다. 본 연구에서는 무인항공기 카메라의 깊이 추정 성능 향상을 위해 Self-Attention 기반의 비지도 단안 카메라 영상 깊이 추정을 제안한다. 네트워크에 Self-Attention 연산을 적용하여 전역 특징 추출 성능을 향상시킨다. 또한 카메라 파라미터를 학습하는 네트워크를 추가하여 카메라 칼리브레이션이 안되어있는 이미지 데이터에서도 사용 가능하게 한다. 공간 데이터 생성을 위해 추정된 깊이와 카메라 포즈는 카메라 파라미터를 이용하여 포인트 클라우드로 변환되고, 포인트 클라우드는 Octree 구조의 점유 그리드를 사용하여 3D 맵으로 매핑된다. 제안된 네트워크는 합성 이미지와 Mid-Air 데이터 세트의 깊이 시퀀스를 사용하여 평가된다. 제안하는 네트워크는 이전 연구에 비해 7.69% 더 낮은 오류 값을 보여주었다.

• Journal of Information Processing Systems
• /
• 제19권1호
• /
• pp.130-138
• /
• 2023

The traffic flow in an urban area is affected by the date, weather, and regional traffic flow. The existing methods are weak to model the dynamic road network features, which results in inadequate long-term prediction performance. To solve the problems regarding insufficient capacity for dynamic modeling of road network structures and insufficient mining of dynamic spatio-temporal features. In this study, we propose a novel traffic flow prediction framework called shared spatio-temporal attention convolution optimization network (SSTACON). The shared spatio-temporal attention convolution layer shares a spatio-temporal attention structure, that is designed to extract dynamic spatio-temporal features from historical traffic conditions. Subsequently, the graph optimization module is used to model the dynamic road network structure. The experimental evaluation conducted on two datasets shows that the proposed method outperforms state-of-the-art methods at all time intervals.