• The Journal of the Korea Contents Association
• /
• v.11 no.12
• /
• pp.28-39
• /
• 2011

While the broadband multimedia technologies have been developing, the commercial market of digital contents has also been widely spreading. Most of all, digital cartoon market like internet cartoon has been rapidly large so video cartooning continuously has been researched because of lack and variety of cartoon. Until now, video cartooning system has been focused in non-photorealistic rendering and word balloon. But the meaningful frame extraction must take priority for cartooning system when applying in service. In this paper, we propose new automatic frame extraction method for video cartooning system. At frist, we separate video and audio from movie and extract features parameter like MFCC and ZCR from audio data. Audio signal is classified to speech, music and speech+music comparing with already trained audio data using GMM distributor. So we can set speech area. In the video case, we extract frame using general scene change detection method like histogram method and extract meaningful frames in the cartoon using face detection among the already extracted frames. After that, first of all existent face within speech area image transition frame extract automatically. Suitable frame about movie cartooning automatically extract that extraction image transition frame at continuable period of time domain.

• Journal of Korean Society for Atmospheric Environment
• /
• v.25 no.6
• /
• pp.550-561
• /
• 2009

This study is to investigate the air pollution characteristics of an industrialized midsize west-coastal city by comparing air quality to a neighboring inland city. The hourly averaged data of $O_3$, $SO_2$, $NO_2$, CO, and $PM_{10}$ measured from continuous air quality monitoring sites in Gunsan (coastal) and Jeonju (inland) were analyzed. The data set covers the period from 2004 to 2006. The annual average concentrations of the air pollutants in two cities were compared in their abundances and temporal trends as well. $O_3$ and $SO_2$ in Gunsan were relatively higher than those in Jeonju, while vice versa in case of $NO_2$ and $PM_{10}$. It seems that heavy automobile emissions from Jeonju mainly bring on higher $NO_2$ and $PM_{10}$ than those in Gunsan on annual base. $NO_2$ concentrations in both cities showed bimodal diurnal variations with peaks in the morning and in the late evening. These peaks correspond to the coupled effects of rush hour traffic and meteorological conditions (i.e., variation of mixing height and dispersion conditions). Maximum hourly averages of $NO_2$ ranged from 18 ppb to 28 ppb at Jeonju, and from 12 ppb to 20 ppb at Gunsan. $O_3$ showed typical diurnal variation with a maximum in the afternoon between 14:00 and 16:00 LST. Diurnal variations of CO and $PM_{10}$ were similar to $NO_2$ while $SO_2$ was similar to $O_3$. Seasonal variations of $PM_{10}$ in both cities indicated that their concentrations during spring season were significantly high. Asian dust storms occur frequently during spring and seem to affect increase in $PM_{10}$. High $O_3$ and $PM_{10}$ days were selected from both cities. The analyses based on the HYSPLIT trajectory model during the high $O_3$ and $PM_{10}$ showed these episodes (six cases) were mostly coincident with Asian dust storm originated from northern China and Mongolia. However, these high air pollution episodes in the west coastal cities may not only be caused by the Asian dust but also affected by other air pollutants transported from China accompanying the Asian dust.

• Journal of The Korean Association For Science Education
• /
• v.38 no.2
• /
• pp.219-234
• /
• 2018

In this study, we explored the possibility of automating the process of analyzing elements of scientific argument in the context of a Korean classroom. To gather training data, we collected 990 sentences from science education journals that illustrate the results of coding elements of argumentation according to Toulmin's argumentation structure framework. We extracted 483 sentences as a test data set from the transcription of students' discourse in scientific argumentation activities. The words and morphemes of each argument were analyzed using the Python 'KoNLPy' package and the 'Kkma' module for Korean Natural Language Processing. After constructing the 'argument-morpheme:class' matrix for 1,473 sentences, five machine learning techniques were applied to generate predictive models relating each sentences to the element of argument with which it corresponded. The accuracy of the predictive models was investigated by comparing them with the results of pre-coding by researchers and confirming the degree of agreement. The predictive model generated by the k-nearest neighbor algorithm (KNN) demonstrated the highest degree of agreement [54.04% (${\kappa}=0.22$)] when machine learning was performed with the consideration of morpheme of each sentence. The predictive model generated by the KNN exhibited higher agreement [55.07% (${\kappa}=0.24$)] when the coding results of the previous sentence were added to the prediction process. In addition, the results indicated importance of considering context of discourse by reflecting the codes of previous sentences to the analysis. The results have significance in that, it showed the possibility of automating the analysis of students' argumentation activities in Korean language by applying machine learning.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.3
• /
• pp.1215-1224
• /
• 2013

Great efforts have been made worldwide to reduce the Green House Gas (GHG) emission following the "Kyoto Protocol" declared during the United Nations Framework Convention on Climate Change in 1997. Many industries have restructured to meet the standard set by the Protocol. However, no clear guidance has been established for the purpose of reducing the GHG emission in construction industry. In addition, no significant effort has been made to conserve the energy during construction activities. For more effective energy saving in construction industry, it is essential to collect data about energy consumption, quantity of environmental emissions and costs. However, most studies on sustainable construction have been concentrated on the use of equipment, maintenance and repair works during construction due to the difficulties of collecting such data. This study suggests a method to select the most environmentally friendly equipment combination for earthwork with comparing environmental loads and costs using the database of Life Cycle Inventory in the Ministry of Knowledge Economy and Ministry of Environment of Korea.

• Journal of Educational Research in Mathematics
• /
• v.20 no.4
• /
• pp.459-476
• /
• 2010

The purpose of this study is to suggest a new direction in using LOGO as a gifted education program and to seek an effective approach for LOGO teaching and learning, by analyzing the strategic thinking of mathematically gifted elementary students. This research is exploratory and inquisitive qualitative inquiry, involving observations and analyses of the LOGO Project learning process. Four elementary students were selected and over 12 periods utilizing LOGO programming, data were collected, including screen captures from real learning situations, audio recordings, observation data from lessons involving experiments, and interviews with students. The findings from this research are as follows: First, in LOGO Project Learning, the mathematically gifted elementary students were found to utilize such strategic ways of thinking as inferential thinking in use of prior knowledge and thinking procedures, generalization in use of variables, integrated thinking in use of the integration of various commands, critical thinking involving evaluation of prior commands for problem-solving, progressive thinking involving understanding, and applying the current situation with new viewpoints, and flexible thinking involving the devising of various problem solving skills. Second, the students' debugging in LOGO programming included comparing and constrasting grammatical information of commands, graphic and procedures according to programming types and students' abilities, analytical thinking by breaking down procedures, geometry-analysis reasoning involving analyzing diagrams with errors, visualizing diagrams drawn following procedures, and the empirical reasoning on the relationships between the whole and specifics. In conclusion, the LOGO Project Learning was found to be a program for gifted students set apart from other programs, and an effective way to promote gifted students' higher-level thinking abilities.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.40 no.2
• /
• pp.78-91
• /
• 2017

In this study, we conducted a comparative study on user's perception and behavior on public system service (PSS) using institutionalism theory and MGA (multi-group analysis) methodology. In particular, this study focuses on how institutional isomorphism is applied to public system services and how MGA can be implemented correctly in a variance based SEM (structural equation model) such as PLS (partial least square). A data set of 496 effective responses was collected from pubic system users and an empirical research was conducted using three segmented models categorized by public proximity theory (public firms = 113, government contractors = 210, private contractors = 173). For rigorous group comparisons, each model was estimated by the same indicators and approaches. PLS-SEM was used in testing research hypotheses, followed by parametric and non-parametric PLS-MGA procedures in testing categorical moderation effects. This study applied novel procedures for testing composite measurement invariance prior to multi-group comparisons. The following main results and implications are drawn : 1) Partial measurement invariance was established. Multi-group analysis can be done by decomposed models although data can not be pooled for one integrated model. 2) Multi-group analysis using various approaches showed that proximity to public sphere moderated some hypothesized paths from quality dimensions to user satisfaction, which means that categorical moderating effects were partially supported. 3) Careful attention should be given to the selection of statistical test methods and the interpretation of the results of multi-group analysis, taking into account the different outcomes of the PLS-MGA test methods and the low statistical power of the moderating effect. It is necessary to use various methods such as comparing the difference in the path coefficient significance and the significance of the path coefficient difference between the groups. 4) Substantial differences in the perceptions and behaviors of PSS users existed according to proximity to public sphere, including the significance of path coefficients, mediation and categorical moderation effects. 5) The paper also provides detailed analysis and implication from a new institutional perspective. This study using a novel and appropriate methodology for performing group comparisons would be useful for researchers interested in comparative studies employing institutionalism theory and PLS-SEM multi-group analysis technique.

• Journal of Korea Water Resources Association
• /
• v.38 no.11
• /
• pp.937-946
• /
• 2005

The objective of the study is to develop a reservoir optimal operation model and to suggest the appropriate amount of additional water supply and optimal operation rule. The model uses multiple objective function and a global search method, SCE-UA method. The objective function is set up to maintain the storage at target level, to satisfy the water demand, and to maximize the hydropower product. To evaluate the model's applicability, the model was applied for allocating the optimal water depending on storage level changes of Seomjin dam. The results comparing optimal operation and historical data showed that hydropower product increased from $-2.29\%$ to $14.51\%$, $-5.94\%$ to $3.98\%$, and $-0.43\%$ to $6.35\%$ with varying target levels in wet, dry, and normal period, respectively. Also, The model was applied for assessing water supply capacity of Seomjin dam to satisfy increasing water demand. The dam was operated by the model on consideration of downstream flow as 0.17, 0.50, 0.70, 1.0, 1.5, and $3.0\;m^3/sec$. The results showed that in case of operating the dam with downstream flow less than $0.70\;m^3/sec$ and with target water level lower than 194.0 m, hydropower product was more than the historical operation data and existing amount of water supply was less influenced.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.6
• /
• pp.609-616
• /
• 2017

In this paper, we propose an algorithm to obtain more stable and high recognition rate by using left and right rotation information of input image in order to obtain a stable recognition rate in face recognition. The proposed algorithm uses the facial image as the input information in the web camera environment to reduce the size of the image and normalize the information about the brightness and color to obtain the improved recognition rate. We apply Principal Component Analysis (PCA) to the detected candidate regions to obtain feature vectors and classify faces. Also, In order to reduce the error rate range of the recognition rate, a set of data with the left and right $45^{\circ}$ rotation information is constructed considering the directionality of the input face image, and each feature vector is obtained with PCA. In order to obtain a stable recognition rate with the obtained feature vector, it is after scattered in the eigenspace and the final face is recognized by comparing euclidean distant distances to each feature. The PCA-based feature vector is low-dimensional data, but there is no problem in expressing the face, and the recognition speed can be fast because of the small amount of calculation. The method proposed in this paper can improve the safety and accuracy of recognition and recognition rate faster than other algorithms, and can be used for real-time recognition system.

• Korean Journal of Applied Biomechanics
• /
• v.26 no.4
• /
• pp.343-351
• /
• 2016

Objective: The purpose of this study was to help improve game performance and provide preliminary data to enhance the efficiency of the kick and stability of the support foot by comparing the kinematic characteristics of the repeated side kick (geodeupyeopchagi) in poomsaeKoryo between expert and non-expert groups. Method: The subjects were divided into 2 groups according to proficiency in Taekwondo, an expert group and a non-expert group (n = 7 in each group), to observe the repeated side-kick technique. Four video cameras were set at a speed of 60 frames/sec and exposure time of 1/500 sec to measure the kinematic factors of the 2 groups. The Kwon3D XPprogramas used to collect and analyze three-dimensional spatial coordinates. Ground reaction force data were obtained through a force plate with a 1.200-Hz frequency. An independent samplesttest was performed, and statistical significance was defined as .05. The SPSS 18.0 software was used to calculate the mean and standard deviation of the kinematic factors and to identify the difference between the experts and non-experts. Results: The angular displacement of the hip joint in both the expert and non-expert groups showed statistical significance on E1 and E4 of the left support foot and E5 of the right foot (p<.05). The angle displacement of the knee joint in both groups showed statistical significance on E4 of the left support foot, and E1 and E2 of the right foot (p<.05). The angular velocity of the lower leg in both groups showed no statistical significance on the left support foot but showed statistical significance on E2 and E6 of the right foot (p<.05). The angular velocity of the foot in both groups showed no statistical significance on the left support foot but showed statistical significance on E2 of the right foot (p<.05). The vertical ground reaction force in both groups showed statistical significance on E2 (p<.05). The center of pressure in all directions in both groups showed statistical significance (p<.5). Conclusion: While performing the repeated side kick (geodeupyeopchagi), the experts maintainedconsistency and stability of the angle of the support leg while the kick foot moved high and fast. On the other hand, the angle of the support foot of non-experts appeared inconsistent, and the kick foot was raised, relying on the support leg, resulting in unstable and inaccurate movement.

• Journal of the Korea Institute of Building Construction
• /
• v.22 no.6
• /
• pp.619-630
• /
• 2022

The concrete mix design and compressive strength evaluation are used as basic data for the durability of sustainable structures. However, the recent diversification of mixing factors has created difficulties in calculating the correct mixing factor or setting the reference value concrete mixing design. The purpose of this study is to design a predictive model of bidirectional analysis that calculates the mixing elements of ternary concrete using deep learning, one of the artificial intelligence techniques. For the DNN-based predictive model for calculating the concrete mixing factor, performance evaluation and comparison were performed using a total of 8 models with the number of layers and the number of hidden neurons as variables. The combination calculation result was output. As a result of the model's performance evaluation, an average error rate of about 1.423% for the concrete compressive strength factor was achieved. and an average MAPE error of 8.22% for the prediction of the ternary concrete mixing factor was satisfied. Through comparing the performance evaluation for each structure of the DNN model, the DNN5L-2048 model showed the highest performance for all compounding factors. Using the learned DNN model, the prediction of the ternary concrete formulation table with the required compressive strength of 30 and 50 MPa was carried out. The verification process through the expansion of the data set for learning and a comparison between the actual concrete mix table and the DNN model output concrete mix table is necessary.