• Journal of the Korea Convergence Society
• /
• v.8 no.6
• /
• pp.29-36
• /
• 2017

In this paper, we propose a method for generating improved saliency map by learning multiple features to improve the accuracy and reliability of saliency map which has similar result to human visual perception type. In order to overcome the inaccurate result of reverse selection or partial loss in color based salient area estimation in existing salience map generation, the proposed method generates multi feature data based on learning. The features to be considered in the image are analyzed through the process of distinguishing the color pattern and the region having the specificity in the original image, and the learning data is composed by the combination of the similar protrusion area definition and the specificity area using the LAB color space based color analysis. After combining the training data with the extrinsic information obtained from low level features such as frequency, color, and focus information, we reconstructed the final saliency map to minimize the inaccurate saliency area. For the experiment, we compared the ground truth image with the experimental results and obtained the precision-recall value.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.14 no.4
• /
• pp.741-749
• /
• 1994

The purpose of the present study is to propose a realistic method to analyze the prestressed concrete members subjected to long term torsional loading. The present study devises a method to realistically take into account the tensile stiffness of concrete after cracking. The effects of biaxial compressive and tensile loadings on the compressive and tensile strengths of concrete are also taken into account in the present model. The salient feature of the present study lies in the fact that the cracking, creep, and shrinkage behavior of concrete and the relaxation of steel have been realistically considered. The comparison of the present theory with experimental data indicates that the proposed model dipicts reasonably well the actual behavior of prestressed concrete members under long-term torsional loadings.

• The Journal of the Korea Contents Association
• /
• v.20 no.11
• /
• pp.378-390
• /
• 2020

English stress plays such a critical role in understanding spoken English words that its misplacement can lead to a breakdown of communication. Korean learners of English, whose native language is known to lack this feature, are expected to have some difficulty acquiring this English prosodic system. This study explored how Korean is different from English in manifesting prominence at the word level and how the interlanguage of Korean learners of English is dissimilar to both languages in that regard. Four polysyllabic English loanwords in Korean and their English source words were used as stimuli. Ten native English speakers read the English source words while ten Korean learners of English read the English loan words first and then the English source words. The analysis of 120 speech samples revealed that Korean words did not have any salient syllable realized by all stress features: duration, amplitude, and F0. On the contrary, English words had syllables with relative prominence, which was consistently manifested by all the features. Interestingly, in realizing English stress, the interlanguage of the Korean English learners bore more resemblance to that of English than that of their native language.

• Journal of the Korean Society of Costume
• /
• v.50 no.5
• /
• pp.117-130
• /
• 2000

The purpose of this thesis is to offer basic data for clothing design which is intended to apply appropriate shape and capacity to clothes. The following are the analyzed results of an investigation which was conducted to characterize the upper half of the female body of 193 women whose ages are 18 to 25, taking part in this investigation. According to the results of analyzing young women's bust, I came to find a large individual difference of the wide varying factor numbers at the items of the side feature, the body stance, and the dart quantity. For the analysis of the female's upper body, 11 factors are used. The are as follows: Factor 1. width of the bust Factor 2. height of the bust and length of the arm Factor 3. side thickness of the bust and the upside type Factor 4. length of the bust on the front Factor 5. length of the bust on the back Factor 6. salient ratio of the breast Factor 7. width of the neck. the armhole, and measurement of the droop Factor 8. length of the shoulder Factor 9. flat ratio of the bust Factor 10. inclination of the shoulder factor 11. form of the back The shape of young women's upper bodies can be divided into four groups. The character ization of each group are as follows : Group 1 . 28.5% of the women who take part in this investigation belong to Group 1 These women have the shortest body, with a longer length of the front than the back and more thickness on the front than the back. Group 2. 21.1% of the women who take part in this investigation belong to this group. They show a longer length of the back and more thickness of the back than the front. In addition, this group is bent forward. Group 3. This group is the mast common type, showing the shortest and thickest character. 37.8% of the women who take part in this investigation have this bust character Group 4. 12.4% of the women belong to Group 4. They possess the highest and fattest character, skewing smaller necks, armholes, and waists than the other groups. This group also shows the drooping shoulders.

• The Mathematical Education
• /
• v.56 no.3
• /
• pp.281-300
• /
• 2017

This study analyzed the difficulties of middle school students in computer simulation of the law of large numbers through eye movement analysis. Some students did not attend to the simulation results and could not make meaningful inferences. It is observed that students keep the existing concept even though they observe the simulation results which are inconsistent with the misconceptions they have. Since probabilistic intuition influence student's thinking very strongly, it is necessary to design a task that allows students to clearly recognize the difference between their erroneous intuitions and simulation results. In addition, we could confirm through eye movements analysis that students could not make meaningful observations and inferences if too much reasoning was needed even though the simulation included a rich context. It is necessary to use visual representations such as graphs to provide immediate feedback to students, to encourage students to attend to the results in a certain intentional way to discover the underlying mathematical structure rather than simply presenting experimental data. Some students focused their attention on the visually salient feature of the experimental results and have made incorrect conclusion. The simulation should be designed so that the patterns of the experimental results that the student must discover are not visually distorted and allow the students to perform a sufficient number of simulations. Based on the results of this study, we suggested that cumulative relative frequency graph showing multiple results at the same time, and the term 'generally tends to get closer' should be used in learning of the law of large numbers. In addition, it was confirmed that eye-tracking method is a useful tool for analyzing interaction in technology-based probabilistic learning.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.155-160
• /
• 2003

This paper presents a multiple face detector based on a robust pupil detection technique. The pupil detector uses active illumination that exploits the retro-reflectivity property of eyes to facilitate detection. The detection range of this method is appropriate for interactive desktop and kiosk applications. Once the location of the pupil candidates are computed, the candidates are filtered and grouped into pairs that correspond to faces using heuristic rules. To demonstrate the robustness of the face detection technique, a dual mode face tracker was developed, which is initialized with the most salient detected face. Recursive estimators are used to guarantee the stability of the process and combine the measurements from the multi-face detector and a feature correlation tracker. The estimated position of the face is used to control a pan-tilt servo mechanism in real-time, that moves the camera to keep the tracked face always centered in the image.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.45 no.11
• /
• pp.951-966
• /
• 2017

In this work, numerical analyses are carried out and the behaviors are investigated for three types of double-acting oleo-pneumatic shock absorbers along with the mathematical models proposed in the part I of this work. After presenting each numerical algorithm corresponding to each model, the numerical algorithms are implemented as user-subroutines in MSC/ADAMS commercial multi-body dynamic software. By using the developed user-subroutines, numerical studies are carried out for compression/stretch test as well as drop test. From the comparative studies, we investigated the salient feature of each double-acting oleo-pneumatic shock absorber. Results identifies that it is possible to increase the absorbing efficiency in accordance with the requirements for aircraft landing conditions.

• The KIPS Transactions:PartB
• /
• v.17B no.4
• /
• pp.263-274
• /
• 2010

To provide context-aware music recommendation service, first of all, we need to catch music mood that a user prefers depending on his situation or context. Among various music characteristics, music mood has a close relation with people‘s emotion. Based on this relationship, some researchers have studied on music mood detection, where they manually select a representative segment of music and classify its mood. Although such approaches show good performance on music mood classification, it's difficult to apply them to new music due to the manual intervention. Moreover, it is more difficult to detect music mood because the mood usually varies with time. To cope with these problems, this paper presents an automatic method to classify the music mood. First, a whole music is segmented into several groups that have similar characteristics by structural information. Then, the mood of each segments is detected, where each individual's preference on mood is modelled by regression based on Thayer's two-dimensional mood model. Experimental results show that the proposed method achieves 80% or higher accuracy.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.9-18
• /
• 2004

This paper proposes a new and simple stereo matching algorithm using the disparity space image (DSI) technique. First of all, we detect some salient feature points on each scan-line of the image pair and set the matching area using those points and define a simple cost matrix. And we take advantage of matching by pixel-by-pixel instead of using the matching window. While the pixel-by-pixel method boost up the speed of matching, because of no using neighbor information, the correctness of the matching may not be better. To cover this point, we expand the matching path using character of disparity-space-image for using neighbor information. In addition, we devise the compensated matching module using the volume of the disparity space image in order to improve the accuracy of the match. Consequently, we can reduce mismatches at the disparity discontinuities and can obtain the more detailed and correct disparity map.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.6
• /
• pp.50-59
• /
• 2014

In mobile healthcare service, the accurate detection and the notification of the emergency situation are important to chronic patients' life. In the existing healthcare service, the medical staff or medical service provider always judges patients' health status by monitoring from the measured from bio-data. However, it is difficult to monitor many patients in real-time simultaneously, because the medical staff should monitor the health status continuously. Furthermore, an emergency condition diagnosis based solely on the statistical level of the bio-data may be difficult, since the emergency judgment of the bio-data might differ depending on the health characteristics of each person such as age, history of disease, gender, etc. In order to solve this problem, this article presents an mobile healthcare system for emergency bio-data management using a personalized emergency policy. The salient feature of the proposed mobile healthcare system is that the characteristics of the health status of an unique patient is defined to the policy, which is used to judge the emergency condition of the bio-data measured from the patient. The prototype of proposed mobile healthcare system has been built to demonstrate the design concept.