• 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 the Korean Institute of Educational Facilities
• /
• v.26 no.3
• /
• pp.15-23
• /
• 2019

This study aims to suggest a Biophilic classroom design of high school to obtain attention restoration for students. The learning space for youth in the modern society is composed of dry artificial structures. This space is considered to be a space that can not relieve stress caused by learning. "The Attention Restoration Theory" is divided into "Directed Attention" of humans, which is the cause of fatigue and stress, and "Involuntary Attention" as a solution to it. "Involuntary Attention" takes place in a rest state and helps the brain recover when exposed to nature. And the core of "Biophilic-Design Theory" is that humans can recover physical and mental conditions when exposed to nature. The purpose of this study is to apply "The Biophilic-Design Theory" that emphasizes the importance of exposure to nature to the educational space and plan the space where the 'Attention Restoration' can be achieved. The research method is as follows. First, we review previous studies related to "The Biophilic-Design Theory" and "The Attention Restoration Theory". Second, we analyze the application examples of "The Biophilic-Design Theory" and "The Attention Restoration Theory" in domestic and foreign educational spaces. Third, the concept of educational space is set up based on the elements derived from previous studies. Finally, we propose the planning direction of classroom design based on Biophilic-Design. The following conclusions were drawn. First, The creation of the education space to restore the learner's attention requires a visual space plan that utilizes natural elements such as natural light, artificial light, plants, and natural materials that can directly experience nature. Second, the direction in which students in the classroom can be "The Attention Restoration Theory" should consider the use of indirect natural elements that bring the surrounding natural landscape into the interior. This study will be used as the baseline data for the spatial design and planning of education facilities based on Biophilic-Design.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.5
• /
• pp.518-524
• /
• 2022

In this paper, we propose a method for combining convolutional neural networks and attention mechanism to improve the recognition performance of emotional stress from Electroencephalogram (EGG) signals. In the proposed method, EEG signals are decomposed into five frequency domains, and spatial information of EEG features is obtained by applying a convolutional neural network layer to each frequency domain. As a next step, salient frequency information is learned in each frequency band using a gate transformer-based attention mechanism, and complementary frequency information is further learned through inter-frequency mapping to reflect it in the final attention representation. Through an EEG stress recognition experiment involving a DEAP dataset and six subjects, we show that the proposed method is effective in improving EEG-based stress recognition performance compared to the existing methods.

• Communications for Statistical Applications and Methods
• /
• v.25 no.4
• /
• pp.373-383
• /
• 2018

The spatial scan statistic is a widely used method to detect spatial clusters. The method imposes a large number of scanning windows with pre-defined shapes and varying sizes on the entire study region. The likelihood ratio test statistic comparing inside versus outside each window is then calculated and the window with the maximum value of test statistic becomes the most likely cluster. The results of cluster detection respond sensitively to the shape and the maximum size of scanning windows. The shape of scanning window has been extensively studied; however, there has been relatively little attention on the maximum scanning window size (MSWS) or maximum reported cluster size (MRCS). The Gini coefficient has recently been proposed by Han et al. (International Journal of Health Geographics, 15, 27, 2016) as a powerful tool to determine the optimal value of MRCS for the Poisson-based spatial scan statistic. In this paper, we apply the Gini coefficient to normal-based spatial scan statistics. Through a simulation study, we evaluate the performance of the proposed method. We illustrate the method using a real data example of female colorectal cancer incidence rates in South Korea for the year 2009.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.34 no.4
• /
• pp.45-55
• /
• 2018

The purpose of this study is to analyze common features and methodological differences of PN-spatial characteristics found in architectural theories and works of contemporary young architects in Japan, such as Sou Fujimoto, Yo shimada, Keisuke Maeda and Junya Ishigami. These architects have paid attention to space between nature and inner space and have tried to establish their own architectural theory on that. Such space is ambiguous and PN-spatial in a way that it has features of both nature and inner space. Ambiguousness is a characteristic of modern architecture and PN-spatial characteristics are one of the features of Japanese architecture. This study aims to analyze the architectural theories and works of contemporary young architects in Japan from the perspective of PN-space and to draw methodological differences and common features. Their theories and works have common features in terms of 'ambiguous spatial boundary', 'unregulated spatial territory', 'detoured circulation' and 'architectural motifs', but each has their own methodology. To sum up, the works and theories of the Japanese young architects contain the philosophy and discourse of modern architecture in general. To be sure, they clearly have characteristics of Japanese architecture, which needs to be studied constantly.

• The KIPS Transactions:PartB
• /
• v.17B no.1
• /
• pp.55-62
• /
• 2010

Human visual attention system has a remarkable ability to interpret complex scenes with the ease and simplicity by selecting or focusing on a small region of visual field without scanning the whole images. In this paper, a novel feature map generation and integration method for attention based visual information processing system is proposed. The depth information obtained from a stereo pair of images is exploited as one of spatial visual features to form a set of topographic feature maps in our approach. Comparative experiments show that correct detection rate of visual attention regions improves by utilizing depth feature compared to the case of not using depth feature.

• Journal of Information Processing Systems
• /
• v.19 no.4
• /
• pp.427-438
• /
• 2023

Plenty of works have indicated that single image super-resolution (SISR) models relying on synthetic datasets are difficult to be applied to real scene text image super-resolution (STISR) for its more complex degradation. The up-to-date dataset for realistic STISR is called TextZoom, while the current methods trained on this dataset have not considered the effect of multi-scale features of text images. In this paper, a multi-scale and attention fusion model for realistic STISR is proposed. The multi-scale learning mechanism is introduced to acquire sophisticated feature representations of text images; The spatial and channel attentions are introduced to capture the local information and inter-channel interaction information of text images; At last, this paper designs a multi-scale residual attention module by skillfully fusing multi-scale learning and attention mechanisms. The experiments on TextZoom demonstrate that the model proposed increases scene text recognition's (ASTER) average recognition accuracy by 1.2% compared to text super-resolution network.

• Korean Institute of Interior Design Journal
• /
• v.25 no.2
• /
• pp.41-49
• /
• 2016

The purpose of this study is to analyze the change and to compare to the difference of 'selective elements' and 'space-memory' focusing on the theory, 'selective attention' through the survey results. In this study, In this study, the lighting is considered a important factor in the change of 'selective elements'. this survey is to find the selective elements of participants and to measure the spatial sensitivity of respondents through 'self- test'. The analysis in this study is conducted by descriptive statistics, t-test and one way ANOVA by SPSS program 22. The results of this study are as following; Firstly, 'attention-element' could be classified with 4 types, 'shape', 'material', 'contrast' and 'combination'. 'shape' could divide into 'structure' and' furniture and object'. In case of 'material', it could section with 'pattern' and 'color'. Secondly, through the results of study, 'attention-element' is different each space during the day in detail. But we could know that 'shape' is the important element of the 'attention-elements' during the day through comparison of this result. That means users consider this as a important factor when they evaluate the space. Therefore, it is effective way designers to consider 'shape' as the first element when they want to conduct the special sensitivity of users in the space through planning. On the other hand, what selective elements of users are different by the lighting situation should be acknowledged by designers. And they should think the kinds of selective elements are more various when lighting turns on than turns off.. Thirdly, through the results such as the meaningful difference of space-memory of users according to the change of 'attention-elements', designers should judge about which kind of feeling of users to the space do you want lead in the design process. For the effective feedback between spaces and users to induce the same emotion of users, designers need to consider the unified design and the individual design both. Also, we will regard the differences in the users' emotion to the space according to the lighting situation when we design the space.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.1061-1070
• /
• 2021

In this manuscript, we tried to improve the performance of the FC-DenseNet by applying an attention gate for the classification of cropping areas. The attention gate module could facilitate the learning of a deep learning model and improve the performance of the model by injecting of spatial/spectral weights to each feature map. Crop classification was performed in the onion and garlic regions using a proposed deep learning model in which an attention gate was added to the skip connection part of FC-DenseNet. Training data was produced using various PlanetScope satellite imagery, and preprocessing was applied to minimize the problem of imbalanced training dataset. As a result of the crop classification, it was verified that the proposed deep learning model can more effectively classify the onion and garlic regions than existing FC-DenseNet algorithm.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.399-401
• /
• 2022

POI (Point-of-Interest) 추천은 다양한 위치 기반 서비스에서 중요한 역할을 있다. 기존 연구에서는 사용자의 모바일 선호도를 모델링하기 위해 과거의 체크인의 공간-시간적 관계를 추출한다. 그러나 사용자 궤적에 숨겨진 개인 방문 경향을 반영할 수 있는 structured feature 는 잘 활용되지 않는다. 이 논문에서는 궤적 그래프를 결합한 시공간 인식 attention 네트워크를 제안한다. 개인의 선호도가 시간이 지남에 따라 변할 수 있다는 점을 고려하면 Dynamic GCN (Graph Convolution Network) 모듈은 POI 들의 공간적 상관관계를 동적으로 집계할 수 있다. LBSN (Location-Based Social Networks) 데이터 세트에서 검증된 새 모델은 기존 모델보다 약 9.0% 성능이 뛰어나다.