• Journal of Broadcast Engineering
• /
• v.27 no.4
• /
• pp.538-547
• /
• 2022

Recently introduced image classification methods using Transformers show remarkable performance improvements over conventional neural network-based methods. In order to effectively consider regional features, research has been actively conducted on how to apply transformers by dividing image areas into multiple window areas, but learning of inter-window relationships is still insufficient. In this paper, to overcome this problem, we propose a transformer structure that can reflect the relationship between windows in learning. The proposed method computes the importance of each window region through compression and a fully connected layer based on self-attention operations for each window region. The calculated importance is scaled to each window area as a learned weight of the relationship between the window areas to re-calibrate the feature value. Experimental results show that the proposed method can effectively improve the performance of existing transformer-based methods.

• Korean Journal of Cognitive Science
• /
• v.24 no.4
• /
• pp.365-391
• /
• 2013

Negative repetition effect (NRE) refers to the phenomenon that the accuracy of report is impaired when a target was flanked by the same distractor than when by alternative distractor. To probe the nature of NRE, this study introduced attention window(s) indicating the positions where a target might be presented, and non-attention window(s) where a target could not be presented. Attention windows are supposed to help participants detect targets readily. Two among three positions are indicated by attention windows in Exp. 1, and a single large attention window encompassing central two positions among four positions was used in Exp. 2, and either large or small attention window was used depending on the number of target candidates in Exp. 3. In the result of three experiments, NREs were consistently observed when both positions of a target and a distractor were indicated by previous attention windows. However, NREs (including its tendency) and its opposite, PREs were observed when a distractor was presented in the non-attention position, depending on its distance from the target and the size of attention window. It seems that this pattern of repetition effects is hard to be explained by repetition blindness hypothesis (Kanwisher, 1991), positional uncertainty hypothesis (Keren & Boer, 1985), and inhibitory attention capture hypothesis (Kwak et al., 1993). Instead it was proposed that shifting of spatial attention should be considered accordingly with the structure of stimulus display. The promising role of this task was discussed in studying the relation of attention and perception.

• The KIPS Transactions:PartB
• /
• v.14B no.2
• /
• pp.99-106
• /
• 2007

In this paper, we present an AAW(Adaptive Attention Window) based cell image segmentation method. For semantic AAW detection we create an initial Attention Window by using a luminance map. Then the initial AW is reduced to the optimal size of the real ROI(Region of Interest) by using a quad tree segmentation. The purpose of AAW is to remove the background and to reduce the amount of processing time for segmenting ROIs. Experimental results show that the proposed method segments one or more ROIs efficiently and gives the similar segmentation result as compared with the human perception.

• Journal of the Korean housing association
• /
• v.12 no.3
• /
• pp.133-140
• /
• 2001

This study investigated the heat transmission coefficient through the experiment that the skylight, slope window of 60 degree and 30 degree consisted of pair glass and the double window of external window and internal window paper were suitable for heat insulation. As the result of experiment, the heat transmission coefficient of slope window was 1.06 times in the 60 degree, 1.18 times in the 30 degree and 1.31 times in the skylight as a standard lateral window. The heat transmission coefficient in the double window of external window and internal window paper was 3.017$\textrm{㎉}$/$\textrm{m}^2$.hr.$^{\cire}C$. The slope window was not suitable for the prescription by the increase of the heat transmission coefficient, so the user must pay attention to the treatment. This study investigated only the slope window of 12mm and 16mm pair glass and the double window of external window and internal window paper, study on the various pattern of window must be achived in a future.

• KIISE Transactions on Computing Practices
• /
• v.23 no.4
• /
• pp.268-273
• /
• 2017

Recently, deep learning encoder-based approach has been actively applied in the field of sentiment classification. However, Long Short-Term Memory network deep learning encoder, the commonly used architecture, lacks the quality of vector representation when the length of the documents is prolonged. In this study, for effective classification of the sentiment documents, we suggest the use of attention method-based deep learning encoder that generates document vector representation by weighted sum of the outputs of Long Short-Term Memory network based on importance. In addition, we propose methods to modify the attention method-based deep learning encoder to suit the sentiment classification field, which consist of a part that is to applied to window attention method and an attention weight adjustment part. In the window attention method part, the weights are obtained in the window units to effectively recognize feeling features that consist of more than one word. In the attention weight adjustment part, the learned weights are smoothened. Experimental results revealed that the performance of the proposed method outperformed Long Short-Term Memory network encoder, showing 89.67% in accuracy criteria.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.7 no.1
• /
• pp.22-31
• /
• 2008

The operating window method is a novel approach in quality improvement. But it has not received deserved attention in academic research. If a critical factor for competing failure modes can be identified, the probability of failure can be reduced by widening the operating window of this factor. Traditional SN ratio for the operating window advocated by Taguchi has a critical shortcoming, which has been derived under the assumption that failure rates are determined by the operating window factor only. A new metric for robustness is given for the operating window method, which has relaxed the restrictive assumption of Taguchi's SN ratio. And procedures for determining optimal conditions based on the new metric is presented. The effectiveness of the proposed approach over the traditional practice is tested with the aid of a wave soldering process.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.12 no.1
• /
• pp.40-49
• /
• 2000

The flow and heat transfer characteristics of the exhaust airflow window system were studied numerically by a finite volume method. Attention was paid to see the decrease in indoor cooling load. The exhaust air flow rate, solar energy power and aspect ratio of window were considered as main variables. From the result of the comparison between the exhaust airflow window and the enclosed window, the indoor heat gain was reduced remarkably by 76%. It is also suggested that in the design of the exhaust airflow window optimum values of aspect ratio, H/W and exhaust air flow rate, Re were about 0.05 and 600, respectively.

• Architectural research
• /
• v.15 no.4
• /
• pp.201-206
• /
• 2013

Special attention is required for the design of windows due to their high thermal vulnerability. This paper examines the problems that might arise in the application of the u-value, by reflecting the changes in the u-value of the window, depending on the window-to-wall ratio obtained in an energy demand analysis. Research indicates that the u-value of a window increases with an increase in the difference between the u-values of the frames and the glass. Relative to the changes in the u-value of the windows, the energy demand varied from 1.3% to 9.3%. Windows with a g-value of 0.3 or 0.5 displayed a higher energy demand than windows with a g-value of 0.7. Therefore, when the difference between the performance of the glass and the frame is significant, especially when the g-value is small, a modified heat transmission coefficient should be applied to the window size during the evaluation of the building energy demand.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.855-870
• /
• 2020

Windows are key components of building facades. Detecting windows, crucial to 3D semantic reconstruction and scene parsing, is a challenging task in computer vision. Early methods try to solve window detection by using hand-crafted features and traditional classifiers. However, these methods are unable to handle the diversity of window instances in real scenes and suffer from heavy computational costs. Recently, convolutional neural networks based object detection algorithms attract much attention due to their good performances. Unfortunately, directly training them for challenging window detection cannot achieve satisfying results. In this paper, we propose an approach for window detection. It involves an improved Faster R-CNN architecture for window detection, featuring in a window region proposal network, an RoI feature fusion and a context enhancement module. Besides, a post optimization process is designed by the regular distribution of windows to refine detection results obtained by the improved deep architecture. Furthermore, we present a newly collected dataset which is the largest one for window detection in real street scenes to date. Experimental results on both existing datasets and the new dataset show that the proposed method has outstanding performance.

• Proceedings of the SAREK Conference
• /
• 2008.06a
• /
• pp.1036-1041
• /
• 2008

Double facade systems are often paid attention of as an effective energy saving measure for curtain wall buildings. However, it is not easy to install the system in existing buildings and requires substantial investment. An innovative double window system is proposed in this study which can be installed with exiting window systems in a cost effective way. the proposed system is connected to existing return ducts to make airflow between the existing window and the newly installed window. To ensure the best performance of the proposed system, simulation-based analysis was implemented in which airflow characteristics of inside double window were examined according to air pressures of return duct and window material by using computer simulation ESP-r. the overview of the proposed system and the results of the simulation-based analysis are presented in this paper.