• Science of Emotion and Sensibility
• /
• v.20 no.3
• /
• pp.13-22
• /
• 2017

Emotion has a direct influence such as decision-making, perception, etc. and plays an important role in human life. For the convenient and accurate recognition of high-arousal negative emotion, the purpose of this paper is to design an algorithm for analysis using the bio-signal. In this study, after two emotional induction using the 'normal' / 'fear' emotion types of videos, we measured the Galvanic Skin Response (GSR) signal which is the simple of bio-signals. Then, by decomposing Tonic component and Phasic component in the measured GSR and decomposing Skin Conductance Very Slow Response (SCVSR) and Skin Conductance Slow Response (SCSR) in the Phasic component associated with emotional stimulation, extracting the major features of the components for an accurate analysis, we used a discrete wavelet transform with excellent time-frequency localization characteristics, not the method used previously. The extracted features are maximum value of Phasic component, amplitude of Phasic component, zero crossing rate of SCVSR and zero crossing rate of SCSR for distinguishing high-arousal negative emotion. As results, the case of high-arousal negative emotion exhibited higher value than the case of low-arousal normal emotion in all 4 of the features, and the more significant difference between the two emotion was found statistically than the previous analysis method. Accordingly, the results of this study indicate that the GSR may be a useful indicator for a high-arousal negative emotion measurement and contribute to the development of the emotional real-time rating system using the GSR.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.35 no.6
• /
• pp.1321-1328
• /
• 2015

The automobiles in Korea have approximately 60 years of history and this is relatively short compared to advanced countries. However, considering the traffic accident rate or severity related to automobiles, various efforts are required to reduce traffic accidents. Various problems caused by traffic accidents are not only related to individual damages but also have become social problems. In order to resolve this, it is important to analyze the cause of traffic accidents. This study aims to suggest methods to reduce traffic accidents by analyzing driving behavior, which is one of the reasons for a number of traffic accidents that were collected through traffic accident videos reported using DVRs (Driving Video Recorder) and were aired to the public via a SBS TV program for the past two years and four months. In particular, unlike other existing studies that aim at analyzing the causes of traffic accidents simply using data, this study constructed a database by analyzing every single DVR that stores the situation before and after the accident using relatively high-resolution video information to provide practical plans to reduce traffic accidents through statistical analysis.

• Journal of Broadcast Engineering
• /
• v.11 no.3 s.32
• /
• pp.336-348
• /
• 2006

The recent advances in multimedia signal coding and transmission technologies allow lots of users to watch videos on small LCD displays. In this paper, we briefly describe an intelligent display technique to provide small-display-viewers with comfortable experiences, and study the minimum image size tolerated and utility of displaying region of interest (ROI) only when needed. The study, with 111 participants, examines minimum image size to ensure viewers pleasant viewing experiences, and evaluates the degree of satisfaction when they are viewed with region of interest (ROI) only. The experimental results show that the ROI display enhances the viewers' satisfaction when the image size becomes less than $320{\times}240$, and thus it is useful to provide the intelligent display, if necessary, which can extract and display ROI only.

• Journal of The Korean Association of Information Education
• /
• v.19 no.1
• /
• pp.113-126
• /
• 2015

This study intends to investigate the features and the difference between traditional instruction and flipped learning through a comparative analysis of verbal interaction on those learning method. The videos of traditional instruction and flipped learning of 5th graders social class were recorded and transcribed, which were analyzed in Flanders verbal interaction model. The results were as follows: First, the flipped learning is composed of students' learning activity and a teacher's statement properly, while the traditional instruction consists of a teacher's statement mostly. Second, the traditional instruction tends to be directive classes that full of dominant, despotic, restrictive communication of teacher oriented. In contrast, the flipped learning is inclined to be nondirective with integrated, democratic, comprehensive, permissive communication of students oriented. Third, the flipped learning emphasizes students' activities and statement and reduces delivery of knowledge, meanwhile, the traditional instruction stresses delivery of content that the teacher centrally located. Lastly, the type of verbal interaction in traditional instruction is a one-way communication, students responding simply in teacher's lectures and questions. On the other hand, in flipped learning lessons, more interactive communication occurs, teachers complimenting students and accepting their comments.

• Journal of the HCI Society of Korea
• /
• v.10 no.1
• /
• pp.29-41
• /
• 2015

Technologies for video reality (e.g., 3D displays, vibration, surround sound, etc.) utilize various sensory input and many of them are now commercialized. However, when it comes to the use of olfaction for video reality, there has not been much progress in both practical and academic respects. Because olfactory sense is tightly associated with human emotion, proper use of this sense is expected to help to achieve a high degree of video reality. This research tested the effects of a video's color-temperature related scent on reality improvement when the video does not have apparent object (e.g., coffee, flower, etc.) which suggest specific smell. To this end, we had participants to rate 48 scents based on a color-temperature scale of 1,500K (warm)-15,000K (cold) and chose 8 scents (4 warm scents, 4 cold scents) which showed clear correspondence with warm or cold color-temperatures (Expt. 1). And then after applying warm (3,000K), neutral (6,500K), or cold (14,000K) color-temperatures to images or videos, we presented warm or cold scents to participants while they rate reality improvement on a 7-point scale depending on relatedness of scent vs. color-temperature (related, unrelated, neutral) (Expts. 2-3). The results showed that participants experienced greater reality when scent and color-temperature was related than when they were unrelated or neutral. This research has important practical implications in demonstrating the possibility that provision of color-temperature related scent improves video reality even when there are no concrete objects that suggest specific olfactory information.

• Journal of Korean Home Economics Education Association
• /
• v.30 no.4
• /
• pp.127-139
• /
• 2018

The purpose of this study was to develop and examine the effect of flipped learning in hand sewing practice. The flipped learning class was designed to three steps(pre-class, in-class, after-class). Pre-class: Students learned kinds of hand sewing by watching video and ppt. In-class: Students were evaluated for their prior learning through the quiz. After the quiz, instructor had a brief hand sewing demonstration. Then basic hand sewing practice was progressed. After that advanced project(making things using more than 3 kinds of hand sewing methods) was progressed. After-class: Students were evaluated each other through project exhibition. The effectiveness of flipped learning was measured based on the students' self-reflective journals and class awareness surveys. As the results, students were actively participated in flipped learning and satisfied with the overall quality of the flipped learning class. They said that videos, project & feedback were helpful in understanding hand sewing. Flipped learning applied to hand sewing practice showed more positive learning effect than the general practice class.

• Journal of Broadcast Engineering
• /
• v.19 no.6
• /
• pp.798-809
• /
• 2014

Video stabilization is performed to remove unexpected shaky and irregular motion from a video. It is often used as preprocessing for robust feature tracking and matching in video. Typical video stabilization algorithms are developed to compensate motion from surveillance video or outdoor recordings that are captured by a hand-help camera. However, since the vehicle video contains rapid change of motion and local features, typical video stabilization algorithms are hard to be applied as it is. In this paper, we propose a novel approach to compensate shaky and irregular motion in vehicle video using linear regression model and vertical projection histogram matching. Towards this goal, we perform vertical projection histogram matching at each sub region of an input frame, and then we generate linear regression model to extract vertical translation and rotation parameters with estimated regional vertical movement vector. Multiple binarization with sub-region analysis for generating the linear regression model is effective to typical recording environments where occur rapid change of motion and local features. We demonstrated the effectiveness of our approach on blackbox videos and showed that employing the linear regression model achieved robust estimation of motion parameters and generated stabilized video in full automatic manner.

• Research in Community and Public Health Nursing
• /
• v.14 no.2
• /
• pp.200-210
• /
• 2003

Purpose: This quasi-experimental study was performed to investigate the effects of a health promotion program(HPP) on self-efficacy, healthy lifestyle and blood lipid profile in employees with hyperlipidemia. Methods: The subjects were forty-three employees who were diagnosed as having hyperlipidemia during routine health examination at two worksites in Seoul in 2001. Of the forty-three subjects, thirty were allocated to the experimental group and the remaining thirteen were allocated to the control group. Data were collected from September 24, 2001 to March 16, 2002. The HPP was applied to the experimental group for 11 weeks and included health education, diet counseling, watching videos, conference, and so on. The health education included information about exercise, smoking cessation, and abstinence from drinking alcohol and seven sessions of hyperlipidemia education. The experimental group was requested to keep a daily health promotion lifestyle diary. This diary was analyzed by a dietician and subjects were instructed based on the results. As for data analyses, wilcoxon signed rank test and wilcoxon rank sum test and x2-test were carried out using SAS program. Results: 1. Self-efficacy scores of the experimental group were significantly more increased than those of the control group (experimental: 5.86 10.80, control: -4.04 11.91, p=0.018). 2. Healthy lifestyle scores of the experimental group were significantly more increased than those of the control group (experimental: 0.19 0.26, control: -0.05 0.29, p=0.024). 3. Blood total cholesterol values of the experimental group were significantly more decreased than those of the control group (experimental: -13.07 30.10mg/dl, control: 10.00 26.57mg/dl, p=0.033). 4. Blood triglyceride values of the experimental group were significantly more decreased than those of the control group (experimental: -29.17 192.40mg/dl, control: 63.31 107.53mg/dl, p=0.050). Conclusion: These findings indicate that the HHP could be effective in improving self-efficacy, healthy lifestyle and blood HDL cholesterol and decreasing blood total cholesterol in employees with hyperlipidemia. Therefore, the HHP could be suggested as an effective nursing intervention for employees in the worksite by ultimately preventing cerebral and cardiac vessel complications related to hyperlipidemia.

• Journal of Broadcast Engineering
• /
• v.21 no.6
• /
• pp.957-964
• /
• 2016

Acquisition of reliable depth maps is a critical requirement in many applications such as 3D videos and free-viewpoint TV. Depth information can be obtained from the object directly using physical sensors, such as infrared ray (IR) sensors. Recently, Time-of-Flight (ToF) range camera including KINECT depth camera became popular alternatives for dense depth sensing. Although ToF cameras can capture depth information for object in real time, but are noisy and subject to low resolutions. Recently, filter-based depth up-sampling algorithms such as joint bilateral upsampling (JBU) and noise-aware filter for depth up-sampling (NAFDU) have been proposed to get high quality depth information. However, these methods often lead to texture copying in the upsampled depth map. To overcome this limitation, we formulate a convex optimization problem using higher order regularization for depth map upsampling. We decrease the texture copying problem of the upsampled depth map by using edge weighting term that chosen by the edge information. Experimental results have shown that our scheme produced more reliable depth maps compared with previous methods.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.351-360
• /
• 2018

Human emotion recognition is a research topic that is receiving continuous attention in computer vision and artificial intelligence domains. This paper proposes a method for classifying human emotions through multiple neural networks based on multi-modal signals which consist of image, landmark, and audio in a wild environment. The proposed method has the following features. First, the learning performance of the image-based network is greatly improved by employing both multi-task learning and semi-supervised learning using the spatio-temporal characteristic of videos. Second, a model for converting 1-dimensional (1D) landmark information of face into two-dimensional (2D) images, is newly proposed, and a CNN-LSTM network based on the model is proposed for better emotion recognition. Third, based on an observation that audio signals are often very effective for specific emotions, we propose an audio deep learning mechanism robust to the specific emotions. Finally, so-called emotion adaptive fusion is applied to enable synergy of multiple networks. The proposed network improves emotion classification performance by appropriately integrating existing supervised learning and semi-supervised learning networks. In the fifth attempt on the given test set in the EmotiW2017 challenge, the proposed method achieved a classification accuracy of 57.12%.