• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• 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.

• Korean Journal of Cognitive Science
• /
• v.10 no.3
• /
• pp.51-66
• /
• 1999

Selective attention induces perceptual distortions. ranging from repulsion of objects located near the attended area(Suzuki & Cavanagh. 1997) to magnification of the u unattended objects (Tsal & Shalev. 1996). Two hypothetical mechanisms have been p postulated: a shift of receptive fields' positions away from the locus of attention(receptive-field-recruitment hypothesis) or the enlargement of perceived space around the a attended location(space-enlargement hypothesis). The present study distinguished between these hypotheses by investigating the spatial and temporal properties of attention-induced d distortions. Perceptual judgements on vernier alignment. line tilt. line length were used to measure attention-induced changes in perception. Attention was induced exogenously(by blinking a specific set of dots around the test stimuli} or endogenously(by instructing the subject to selectively attend the dots). After inducing attention. the test stimuli were briefly flashed. A staircase method was used to measure the attentional effect. A vertical line was perceived as repelled from the locus of attention. and a line segment appeared longer when attention was given to its vicinity. The effects decreased as the distance between the locus of attention or the time between the onset of attention and the stimulus presentation increased. The results imply that the space-enlargement hypothesis provides a better explanation for the attention-induced changes in perception than the receptive-field-recruitment hypothesis.

• 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.

• Korean Institute of Interior Design Journal
• /
• v.20 no.5
• /
• pp.51-58
• /
• 2011

As it gets nearer to the modern society, social and cultural situations are changing and the spatial form of public space is changing into the complex structure where it is interlinked with each other diversely. In particular, as the development of large-scale complex spreads nationwide, the form of complex commercial space assuming the nature of malls appears prominently. In such a large-scale complex commercial space, the diverse visual elements make the environment difficult to be perceived. Like this, the attention in the commercial space where a variety of visual stimuli are in the presence, is important element, so the plan of VP(visual presentation) is needed for effectively selecting or inducing the space. Thus, in this study, human visual and perception process will be reviewed and a method to evaluate the attention will be proposed. Also, the attention of each stores in the complex commercial spaces will be evaluated to propose the indicators for resonable spatial panning in the future.

• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.248-251
• /
• 2015

High injury and fatality rates remain a serious problem in the construction industry. Many construction injuries and fatalities can be prevented if workers can recognize potential hazards and take actions in time. Many efforts have been devoted in improving workers' ability of hazard recognition through various safety training and education methods. However, a reliable approach for evaluating this ability is missing. Previous studies in the field of human behavior and phycology indicate that the visual focus of attention (VFOA) is a good indicator of worker's actual focus. Towards this direction, this study introduces an automated approach for estimating the VFOA of equipment operators using a head orientation-based VFOA estimation method. The proposed method is validated in a virtual reality scenario using an immersive head mounted display. Results show that the proposed method can effectively estimate the VFOA of test subjects in different test scenarios. The findings in this study broaden the knowledge of detecting the visual focus and distraction of construction workers, and envision the future work in improving work's ability of hazard recognition.

• 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.

• The Journal of Pediatrics of Korean Medicine
• /
• v.20 no.2
• /
• pp.147-175
• /
• 2006

Objective : This study is to investigate the method for assesment and diagnosis of ADHD, especially focusing on behavior rating scales. Methods : We searched the recent date of the publication and paper in ADHD. Results : For Assesment and Diagnosis of ADHD, various method such as interview with parents, child and teacher, behavior observation, behavior rating scales and neuropsychological test are used. The structured interview consists of the restrictive questions and response, and then have diagnostic algorithm, consequently can be used by untrained clinicians. Of the structured interview, standardization of K-SADS in Korean version is finished. Behavior rating scales, the form of parent, teacher and self-report questionnaires, are used as diagnosis and treatment evaluation of ADHD. Behavior rating scales consist of both ADHD-specific scales and broad-band scales designed to screen for various symptoms (including ADHD symptoms). ADHD-specific scales are useful in differential diagnosis, discrimination of subtype, treatment evaluation, However, broad-band scales are useful in preliminary examination. The neuropsychological tests can evaluate attention deficit and effect of attention deficit on cognitive function and academic performance. The neuropsychological tests also used in diagnosis and treatment evaluation of ADHD. Conclusion : For Assesment and Diagnosis of ADHD, various method are used, especially behavior rating scales are both useful and simple tool for diagnosis and treatment evaluation.

• Journal of the Korea Convergence Society
• /
• v.12 no.12
• /
• pp.31-37
• /
• 2021

In this paper proposed a feature fusion and spatial attention-based modified YOLOv4S for small and occluded detection. Conventional YOLOv4S is a lightweight network and lacks feature extraction capability compared to the method of the deep network. The proposed method first combines feature maps of different scales with feature fusion to enhance semantic and low-level information. In addition expanding the receptive field with dilated convolution, the detection accuracy for small and occluded objects was improved. Second by improving the conventional spatial information with spatial attention, the detection accuracy of objects classified and occluded between objects was improved. PASCAL VOC and COCO datasets were used for quantitative evaluation of the proposed method. The proposed method improved mAP by 2.7% in the PASCAL VOC dataset and 1.8% in the COCO dataset compared to the Conventional YOLOv4S.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.4
• /
• pp.621-631
• /
• 2023

Adversarial training improves the robustness of deep neural networks for adversarial examples. However, the previous adversarial training method focuses only on the adversarial loss function, ignoring that even a small perturbation of the input layer causes a significant change in the hidden layer features. Consequently, the accuracy of a defended model is reduced for various untrained situations such as clean samples or other attack techniques. Therefore, an architectural perspective is necessary to improve feature representation power to solve this problem. In this paper, we apply an attention module that generates an attention map of an input image to a general model and performs PGD adversarial training upon the augmented model. In our experiments on the CIFAR-10 dataset, the attention augmented model showed higher accuracy than the general model regardless of the network structure. In particular, the robust accuracy of our approach was consistently higher for various attacks such as PGD, FGSM, and BIM and more powerful adversaries. By visualizing the attention map, we further confirmed that the attention module extracts features of the correct class even for adversarial examples.

• Journal of The Korean Association For Science Education
• /
• v.26 no.4
• /
• pp.510-517
• /
• 2006

This study investigated the influences of situational interest, attention, and cognitive effort on drawing as a method to assist students to connect and integrate multiple external representations provided in learning chemical concepts. Seventh graders (N=178) at two coed middle schools were taught about the "Boyle's Law" and the "Charles's Law" for two class hours through drawing. They observed macroscopic phenomena through demonstrations. After these observations, they drew their mental model from the external verbal representation, and then compared their drawings with external visual representation. The tests assessing situational interest, attention, cognitive effort, and conceptual understanding were administered as post-tests. Correlation and path analyses supported a causal model which situational interest had a positive direct effect on attention to the drawing. Attention led to conceptual understanding directly as well as through cognitive effort. These results suggest that situational interest may be induced by drawing first of all, and attention and cognitive effort may be direct causes of conceptual understanding in drawing. Educational implications are discussed.