• Annual Conference on Human and Language Technology
• /
• 2016.10a
• /
• pp.176-180
• /
• 2016

대화형 시스템이 사람의 경청 기술을 모방할 수 있다면 대화 상대방과 더 효과적으로 상호작용 할 수 있을 것이다. 본 논문에서는 시스템이 경청 기술을 모방할 수 있도록 사용자의 발화를 기반으로 질문을 생성하는 것에 대해 연구하였다. 그리고 이러한 연구를 위해 필요한 데이터를 Image captioning과 Visual QA 데이터를 기반으로 생성하고 활용하는 방안에 대해 제안한다. 또한 이러한 데이터를 Attention 메커니즘을 적용한 Sequence to sequence 모델에 적용하여 질문을 생성하고, 생성된 질문의 질문 유형을 분석하였다. 마지막으로 사람이 작성한 질문과 모델의 질문 생성 결과 비교를 BLEU 점수를 이용하여 수행하였다.

• Proceedings of the KIEE Conference
• /
• 1994.11a
• /
• pp.299-301
• /
• 1994

Visual feedback has traditionally been used in robot manipulator control to a limited extent. However in varying environment, visual data is needed to control the manipulator to complete the desired task. In this paper we present a method of manipulator control scheme called image-based visual servo. In this scheme we use image data as feedback to control robot manipulator. And we also show the experimental results with an industrial robot manipulator.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.1
• /
• pp.1-8
• /
• 2002

This study is discussed research on management of items in PC's GUI(Graphical User Interface) environment. A items are general knowledge data like books, musical CD, English CD, and game CD, which are the time when we don't seek the right items in the case of re-reading and re-listening the items. In this paper, We propose an example designed to be used in the management of a items. The proposed example is implemented by educational VC＋＋(Visual C＋＋) programming language. This program and discussions for management of a items will understand the development procedure of searching and storing data, which will provide some basics into designing large database systems.

• KIEAE Journal
• /
• v.6 no.2
• /
• pp.3-10
• /
• 2006

This study assessed the visual performance of luminous environment by the lightshelf. The subject survey method was used and results are presented and analyzed. The lightshelf daylighting system was developed by LAEL at KH University and was applied on the window of a mock-up office. The questionnaire for assessing visual performance contains 9 questions with 7 grade bipolar scales. The experiment was conducted during the bright part of the day from noon to one thirty on June 7, 2006. The questionnaire for assessing visual performance contains 9 questions with 7 grade bipolar scales. During the experiment was carrying out, the work plane illuminance and luminous distribution at surrounding the windows was measured. The semantic differential rating data of experiment were analyzed by t-test and factor analysis using SPSS 12.0 statistics package. The visual performance of the lightshelf was more positive. The factors affecting the visual performance are task performance and visual comfort. The subjects were more comfortable in a room installed with lightshelves on both the task performance and the visual comfort aspect. Therefore, the application of sloped lightshelf daylighting system improves visual performance of luminous environment.

• Journal of Korean Public Health Nursing
• /
• v.35 no.1
• /
• pp.149-164
• /
• 2021

Purpose: To identify the factors associated with poor self-rated health in individuals with acquired visual impairment through classification of such individuals into severe and mild visual impairment groups. Methods: This descriptive, cross-sectional, survey-based study analyzed data from 563 individuals with visual impairment due to acquired causes who had been recruited in the 2017 Korean National Survey on Persons with Disabilities. Results: Individuals with severe visual impairment reported poorer self-rated health. Mild depression (p=.003), and low smartphone use (p=.045) were associated with poorer self-rated health in those with severe visual impairment. The factors associated with poor self-rated health in those with mild visual impairment were comorbidities, low smartphone use (p=.006), needed health information (p=.020), unbalanced diet (p<.001), low weight (p=.024), and lack of health checkups (p=.001). Conclusion: Depression was found to be a predictor of poor self-rated health in individuals with severe visual impairment, which highlights the need for nursing and related healthcare intervention to lower depression in this specific population. Further, promoting social network building and providing health information using smartphones may serve to encourage appropriate health behavior in people with severe visual impairment who have reduced mobility and health literacy.

• Proceedings of the Optical Society of Korea Conference
• /
• 2001.08a
• /
• pp.164-165
• /
• 2001

No Abstract.See Full-text

• Korean Journal of Radiology
• /
• v.24 no.4
• /
• pp.284-293
• /
• 2023

Objective: To validate a simplified ordinal scoring method, referred to as modified length-based grading, for assessing coronary artery calcium (CAC) severity on non-electrocardiogram (ECG)-gated chest computed tomography (CT). Materials and Methods: This retrospective study enrolled 120 patients (mean age ± standard deviation [SD], 63.1 ± 14.5 years; male, 64) who underwent both non-ECG-gated chest CT and ECG-gated cardiac CT between January 2011 and December 2021. Six radiologists independently assessed CAC severity on chest CT using two scoring methods (visual assessment and modified length-based grading) and categorized the results as none, mild, moderate, or severe. The CAC category on cardiac CT assessed using the Agatston score was used as the reference standard. Agreement among the six observers for CAC category classification was assessed using Fleiss kappa statistics. Agreement between CAC categories on chest CT obtained using either method and the Agatston score categories on cardiac CT was assessed using Cohen's kappa. The time taken to evaluate CAC grading was compared between the observers and two grading methods. Results: For differentiation of the four CAC categories, interobserver agreement was moderate for visual assessment (Fleiss kappa, 0.553 [95% confidence interval {CI}: 0.496-0.610]) and good for modified length-based grading (Fleiss kappa, 0.695 [95% CI: 0.636-0.754]). The modified length-based grading demonstrated better agreement with the reference standard categorization with cardiac CT than visual assessment (Cohen's kappa, 0.565 [95% CI: 0.511-0.619 for visual assessment vs. 0.695 [95% CI: 0.638-0.752] for modified length-based grading). The overall time for evaluating CAC grading was slightly shorter in visual assessment (mean ± SD, 41.8 ± 38.9 s) than in modified length-based grading (43.5 ± 33.2 s) (P < 0.001). Conclusion: The modified length-based grading worked well for evaluating CAC on non-ECG-gated chest CT with better interobserver agreement and agreement with cardiac CT than visual assessment.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.2
• /
• pp.447-456
• /
• 2007

Recently, the multivariate statistical analysis has been used to analyze meaningful information for various data. In this paper, we develope the multivariate statistical analysis system combined with Fisher discriminant analysis, logistic regression, neural network, and decision tree using visual basic 6.0.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1831-1834
• /
• 2003

Due to the increasing of multimedia data quantity, database searching based on image becomes important. For this scheme, MPEG-7 gives a good solution to efficient data searching. MPEG-7 uses Descriptors which are color, texture, and shape to extract features from images. It is obvious that using more than one Descriptor causes more accurate data searching result than using just one. In this paper, selecting a composite of MPEG-7 visual Descriptor using KL-Expansion is proposed.

• Journal of Fashion Business
• /
• v.11 no.4
• /
• pp.82-91
• /
• 2007

The purpose of this study is to evaluate the differences of visual effects by variations in the shoulder length and puff volume of the puff sleeve blouse. The stimuli are 21 samples: 3 variations of the shoulder length and 7 variations of the puff volume. The data has been obtained from 40 fashion design majors. The data has analyzed by Frequency, Factor Analysis, ANOVA, Scheffe's test and MCA method. The result of the study are as follows. The visual effects by the shoulder length and puff volume are composed of 4 factors : the width of the upper body, the shape of the breast part, the shape of the neck part and the shape of the upper arm. In these factors, the width of the upper body is estimated by most important factor. In view of the visual effects by variation of the shoulder length, the shorter shoulder length goes, the more positive visual image comes in the shape of the breast part. In comparison of the differences of visual effects by the 7 variations of puff volume, the arm looks thin and long when the puff volume goes enough and the breast part has a better visual assesment in case the puff volume goes poor. In the interaction effects between the shoulder length and puff volume, the shoulder length have significant differences in the shape of the breast part, the shape of the neck part and the shape of the upper arm and puff volume has significant difference in the width of the upper body.