• Journal of the Korea Society of Computer and Information
• /
• v.28 no.9
• /
• pp.17-25
• /
• 2023

In this paper, we propose a model that can perform human pose estimation through a MobileViT-based model with fewer parameters and faster estimation. The based model demonstrates lightweight performance through a structure that combines features of convolutional neural networks with features of Vision Transformer. Transformer, which is a major mechanism in this study, has become more influential as its based models perform better than convolutional neural network-based models in the field of computer vision. Similarly, in the field of human pose estimation, Vision Transformer-based ViTPose maintains the best performance in all human pose estimation benchmarks such as COCO, OCHuman, and MPII. However, because Vision Transformer has a heavy model structure with a large number of parameters and requires a relatively large amount of computation, it costs users a lot to train the model. Accordingly, the based model overcame the insufficient Inductive Bias calculation problem, which requires a large amount of computation by Vision Transformer, with Local Representation through a convolutional neural network structure. Finally, the proposed model obtained a mean average precision of 0.694 on the MS COCO benchmark with 3.28 GFLOPs and 9.72 million parameters, which are 1/5 and 1/9 the number compared to ViTPose, respectively.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.5
• /
• pp.833-842
• /
• 2017

In this study, the design methodology of radial basis function neural networks based on incremental K-means clustering is introduced for learning and processing the big data. If there is a lot of dataset to be trained, general clustering may not learn dataset due to the lack of memory capacity. However, the on-line processing of big data could be effectively realized through the parameters operation of recursive least square estimation as well as the sequential operation of incremental clustering algorithm. Radial basis function neural networks consist of condition part, conclusion part and aggregation part. In the condition part, incremental K-means clustering algorithms is used tweights of the conclusion part are given as linear function and parameters are calculated using recursive least squareo get the center points of data and find the fitness using gaussian function as the activation function. Connection s estimation. In the aggregation part, a final output is obtained by center of gravity method. Using machine learning data, performance index are shown and compared with other models. Also, the performance of the incremental K-means clustering based-RBFNNs is carried out by using PSO. This study demonstrates that the proposed model shows the superiority of algorithmic design from the viewpoint of on-line processing for big data.

• Korean journal of psychology:General
• /
• v.36 no.2
• /
• pp.241-270
• /
• 2017

In this study we investigated the structural relationship between the Big Five personality traits which is a pretrauma characteristic, posttraumatic cognition, rumination, posttraumatic growth(PTG), and posttraumatic stress disorder(PTSD) symptoms. The participants were 1,000 adults who experienced traumatic event. For statistical analysis we set the research model with the Big Five personality traits affecting deliberate rumination through posttraumatic cognition and intrusive rumination. Competing model was set without the path from intrusive rumination to deliberate rumination. The results indicated that rumination and posttraumatic cognition did not mediate the relationship between extraversion, agreeableness, conscientiousness and PTG, PTSD symptoms. Second, there was a mediating effect of intrusive rumination between openness to experience and PTSD symptoms. Moreover, the pathway to intrusive rumination, deliberate rumination, and PTG from openness to experience was also significant. Third, the pathway to posttraumatic cognition, event-related rumination, and both PTSD symptoms and PTG from neuroticism was significant. These results support the cognitive process of PTG model In the end we discussed the implication and limitations of the study.

• The Journal of the Korea Contents Association
• /
• v.17 no.10
• /
• pp.307-321
• /
• 2017

This study examined the developmental changes of adolescent personality regarding personality traits of Big 5 model in 2,260 middle and high school students. We found that there was a difference in the developmental change of personality 5 factor according to sex and grade. In addition, we investigated the timing and characteristics of adolescent problem behavior by analyzing the sub - factors of neurosis. Analysis was used for One-Way ANOVA. if there is significant differences we proceeded post hoc tests. The results of this study are as follows; first, The five personality traits of the adolescents showed differences according to gender. The girls were higher than boys in the Openness, Conscientiousness and Extraversion. In contrast, the boys were higher than girls in the Neuroticism. Second, There was a difference in the characteristics of five personality traits of adolescents according to grade. Third, Gender-specific developmental grade tendency characteristics of adolescent personality trait shows a different pattern in gender. Especially, in the analysis by gender and grade boys showed that personality traits prominent in the middle school Grade 2. likewise, girls showed that personality traits prominent in the high school Grade 3. Then, associated with Neuroticism the Externalizing behavior problems was found to be expressed in the middle school Grade 1 and 2. likewise, the Internalizing behavior problems was found to be expressed in high school Grade 3. Therefore, this study was able to determine the current developmental change in personality traits adolescence of our country. Also it found that mental health problems can be a different expression depending on gender and grade.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.5
• /
• pp.693-701
• /
• 2018

Transfer types at the Seoul Metropolitan Urban Railway Stations can be classified into transfer between lines and station transfer. Station transfer is defined as occurring when either 1) the operating line that operates the tag-in card-reader and that operating the first train boarded by the passenger are different; or 2) the line operating the final alighted train and that operating the tag-out card-reader are different. In existing research, transportation card data is used to estimate transfer volume between lines, but excludes station transfer volume which leads to underestimation of volume through transfer passages. This research applies transportation card data to a method for station transfer volume estimation. To achieve this, the passenger path choice model is made appropriate for station transfer estimation using a modified big-node based network construction and data structure method. Case study analysis is performed using about 8 million daily data inputs from the metropolitan urban railway.

• Journal of Environmental Health Sciences
• /
• v.47 no.5
• /
• pp.462-471
• /
• 2021

Background: The number of synthesized chemicals has rapidly increased over the past decade. For many chemicals, there is a lack of information on toxicity. With the current movement toward reducing animal testing, the use of toxicity big data and deep learning could be a promising tool to screen potential toxicants. Objectives: This study identified potential chemicals related to reproductive and estrogen receptor (ER)-mediated toxicities for 1135 cleaning products and 886 laundry products. Methods: We listed chemicals contained in cleaning and laundry products from a publicly available database. Then, chemicals that potentially exhibited reproductive and ER-mediated toxicities were identified using the European Union Classification, Labeling and Packaging classification and ToxCast database, respectively. For chemicals absent from the ToxCast database, ER activity was predicted using deep learning models. Results: Among the 783 listed chemicals, there were 53 with potential reproductive toxicity and 310 with potential ER-mediated toxicity. Among the 473 chemicals not tested with ToxCast assays, deep learning models indicated that 42 chemicals exhibited ER-mediated toxicity. A total of 13 chemicals were identified as causing reproductive toxicity by reacting with the ER. Conclusions: We demonstrated a screening method to identify potential chemicals related to reproductive and ER-mediated toxicities utilizing chemical toxicity big data and deep learning. Integrating toxicity data from in vivo, in vitro, and deep learning models may contribute to screening chemicals in consumer products.

• Knowledge Management Research
• /
• v.24 no.4
• /
• pp.63-85
• /
• 2023

This study aims to identify the primary user group in the growing metaverse space based on the increased interest during the COVID-19 era. It also aims to explore the predictive factors for metaverse adoption. To predict online activities, the study examined user purposes, motivations, and relevant demographic factors as predictive variables through model analysis. The data from the Korean Media Panel Survey were used, and a two-stage analysis with the Heckman two-stage sample selection model was conducted to predict metaverse users. The analysis revealed that the key factors influencing metaverse adoption were offline activities, openness, OTT usage, and purchasing of paid content. Moreover, in the second stage model, openness, gender, and paid content purchases were identified as significant variables for increasing metaverse usage time. These results indicate that understanding metaverse users is essential in the context of the rising interest in online activities during the COVID-19 era and can provide valuable insights for metaverse platform-related companies and developers.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.2B
• /
• pp.168-175
• /
• 2011

In modem society, human relationships has been received much attention as important element to judge the success as well as the social life of the individual. To respond to these changing times has been used various ways to maintain an appropriate relationship that each other's character can be predicted. In this paper, we should be carried out a study on correlation analysis and features of five-character types to extract shape of philtrum, mouth, ears in facial image of Men in the 20's for Interview system application. From this, we extracted to area of philtrum, mouth, ears by Visual C++ to face and side image. Then we performed analysis, comparison a group of S-character types to find a result according to philtrum rate, mouth size, shape of ears. As a result, we drew a significance through morphological results by philtrum rate, mouth size, shape of ears as five-character types.

• The Bulletin of The Korean Astronomical Society
• /
• v.36 no.2
• /
• pp.88.2-88.2
• /
• 2011

Fast Imaging Solar Spectrograph (FISS) is an instrument developed by Seoul National University and Korea Astronomy and Space Science Institute and installed at the 1.6 meter New Solar Telescope of Big Bear Solar Observatory. Using this instrument, we observed solar filaments and analyzed the data focusing on determining the temperature and non-thermal velocity. We inferred the Doppler absorption widths of $H{\alpha}$ and Ca II 8542$\bar{A}$ lines from the line profiles using the cloud model. From these values, we separately determined temperature and non-thermal velocity. Our first result came from a solar filament observed on 2010 July 29th. Temperature inside a small selected region of this ranges from 4500K to 12000K and non-thermal velocity, from 3.5km/s to 7km/s. We also found temperature varied a lot with time. For example temperature at a fixed point varied from 8000K to 18000K for 40 minutes, displaying an oscillating pattern with a period of about 8 minutes and amplitude of about 2000K. We will also present new results from filaments observed in 2011 summer.

• Journal of Gifted/Talented Education
• /
• v.27 no.1
• /
• pp.1-16
• /
• 2017

This study aimed to analyze the relationships between Big five personality (openness to experience, conscientiousness, extraversion, agreeableness, neuroticism), self-regulation learning, and achievement in children in a gifted education program. 95 students in a gifted education program participated in this study. A hypothetical model proposed openness to experience, conscientiousness, extraversion, agreeableness, neuroticism as independent variables, and self-regulation learning and achievement with gifted education as dependent variables. Stepwise regression analysis indicated that openness to experience, conscientiousness, and agreeableness significantly predicted self-regulation learning. Also, neuroticism, selfregulation learning, and extraversion significantly impacted achievement with gifted education. openness to experience, conscientiousness, and agreeableness showed that complete mediating effects through self-regulation learning to achievement. A foundation for improving learning strategies in a successful gifted education program can be constructed on the basis of the results of this study.