• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.4
• /
• pp.44-57
• /
• 2019

Various studies have been conducted to solve traffic congestions in many metropolitan cities through accurate traffic flow prediction. Most studies are based on the assumption that past traffic patterns repeat in the future. Models based on such an assumption fall short in case irregular traffic patterns abruptly occur. Instead, the approaches such as predicting traffic pattern through big data analytics and artificial intelligence have emerged. Specifically, deep learning algorithms such as RNN have been prevalent for tackling the problems of predicting temporal traffic flow as a time series. However, these algorithms do not perform well in terms of long-term prediction. In this paper, we take into account various external factors that may affect the traffic flows. We model the correlation between the multi-dimensional context information with temporal traffic speed pattern using deep neural networks. Our model trained with the traffic data from TOPIS system by Seoul, Korea can predict traffic speed on a specific date with the accuracy reaching nearly 90%. We expect that the accuracy can be improved further by taking into account additional factors such as accidents and constructions for the prediction.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.32 no.6
• /
• pp.446-457
• /
• 2020

Crescentic sand bar in the coastal zone of eastern Korea is a common morphological feature and the rhythmic patterns exist constantly except for high wave energy events. However, four consecutive typhoons that directly and indirectly affected the East Sea of Korea from September to October in 2019 impacted the formation of longshore uniform sand bar and overall shoreline retreats (approx. 2 m) although repetitive erosion and accretion patterns exist near the shoreline. Widely used XBeach to predict storm erosions in the beach is utilized to investigate the morphological response to a series of storms and each storm impact (NE-E wave incidence). Several calibration processes for improved XBeach modeling are conducted by recently reported calibration methods and the optimal calibration set obtained is applied to the numerical simulation. Using observed wave, tide, and pre & post-storm bathymetries data with optimal calibration set for XBeach input, XBeach successfully reproduces erosion and accretion patterns near MSL (BSS = 0.77 (Erosion profile), 0.87 (Accretion profile)) and observed the formation of the longshore uniform sandbar. As a result of analysis of simulated total sediment transport vectors and bed level changes at each storm peak Hs, the incident wave direction contributes considerable impact to the behavior of crescentic sandbar. Moreover, not only the wave height but also storm duration affects the magnitude of the sediment transport. However, model results suggest that additional calibration processes are needed to predict the exact crest position of bar and bed level changes across the inner surfzone.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.17 no.1
• /
• pp.129-143
• /
• 2014

The purpose of this study is to evaluate the availability of dual-polarization radar rain for flood routing in Chungju Dam watershed($6,625.8km^2$) using KIMSTORM (Grid-based KIneMatic wave STOrm Runoff Model). The Sobaek dual-polarization radar data for 1 heavy rain and 3 typhoon(Khanun, Bolaven, and Sanba) events in 2012 were obtained from Han River Flood Control Office. The spatio-temporal patterns between the two data were similar showing the ratio of radar rain to ground rain with 0.97. The KIMSTORM was set to $500{\times}500m$ resolution and a total of 45,738 cells(198 rows${\times}$231 columns) for the watershed. For radar rain and 41 ground rains, the model was independently calibrated using discharge data at 3 streamflow gauging stations(YW1, YC, and CJD) with coefficient of determination($R^2$), Nash and Sutcliffe Model Efficiency(ME), and Volume Conservation Index(VCI). The $R^2$, ME, and VCI 0.80, 0.62 and 1.08 for radar rain and 0.83, 0.68 and 1.10 for ground rain respectively.

• Science of Emotion and Sensibility
• /
• v.9 no.spc3
• /
• pp.209-224
• /
• 2006

Hierarchy which is often named as the tree-structure is used to reduce complexity and show primitive structures of complicated information. This paper aims at explaining information-visualization methods using hierarchies in multimedia domains and prospecting the possible applications by examining how they affect the user's tasks involved in information-seeking activities. As a result, four types of information visualization methods named Treemap, Hyperbolic, Cone Tree and DOI Tree employed in multimedia domain, are presented and pros and cons of each method are explained in this paper. Another important part is defining the core tasks and other related-tasks in information-seeking activities, such as, overview, zoom, filter, details-on-demand, relate, history, and extract. Followings are major findings. Treemap uses 'overview' as the core task, which makes user to gain a overall meaning of the whole information cluster. Hyperbolic and DOI Tree apply 'Boom' task through the function of focus+context or by the function of meaningful scaling to magnify or downsize each node. Cone Tree, also, makes the information organizer to classify the patterns of information acquired in the process of users' information-seeking activities by using 'extract' task. Through this study, it is finally found out that the information-visualization methods using hierarchies in multimedia domains should incorporate the wide variety of functional needs related to users' information-seeking behaviors beyond the visual representation of information.

• Korean Journal of Applied Biomechanics
• /
• v.19 no.1
• /
• pp.159-166
• /
• 2009

The purpose of this study was to develop and automatic gait event detection algorithm using single accelerometer which is attached at the top of the shoe. The sinal vector magnitude and anterior-posterior(x-axis) directional component of accelerometer were used to detect heel strike(HS) and toe off(TO), respectively. To evaluate proposed algorithm, gait event timing was compared with that by force plate and kinematic data. In experiment, 7 subjects performed 10 trials level walking with 3 different walking conditions such as fast, preferred & slow walking. An accelerometer, force plate and 3D motion capture system were used during experiment. Gait event by force plate was used as reference timing. Results showed that gait event by accelerometer is similar to that by force plate. The distribution of differences were spread about $22.33{\pm}17.45m$ for HS and $26.82{\pm}14.78m$ for To and most error was existed consistently prior to 20ms. The difference between gait event by kinematic data and developed algorithm was small. Thus it can be concluded that developed algorithm can be used during outdoor walking experiment. Further study is necessary to extract gait spatial variables by removing gravity factor.

• Journal of KIISE:Software and Applications
• /
• v.35 no.2
• /
• pp.70-80
• /
• 2008

Today, businesses have to respond with flexibility and speed to ever-changing customer demand and market opportunities. Service-oriented architecture (SOA) is the best methodology for minimizing the complexity and the cost of enterprise-level infrastructure and for maximizing the productivity and the flexibility of an enterprise. Most of the enterprise-level SOA delivery strategies deal with the top-down approach, which organization has to define the business processes, to model business services, and to find the required services or to develop new services. However, a lot of peoples want to maximally reuse legacy component-based systems as well as to deliver SOA into their organizations. In this paper, we propose a bottom-up approach for identifying business services with proper granularity. It can improve the reusability and maintenance of services by considering not data I/O of components of legacy applications but GUI event patterns. Our proposed method is applied to MIS with 129 GUIs and 13 components. As a result, the valiance of the coupling value of components is increased five times and three business services are distinctly exposed. It also provides a 49% improvement in reducing the relationship problems between services over a service identification method using only partitioning information of components.

• Journal of the HCI Society of Korea
• /
• v.5 no.1
• /
• pp.37-43
• /
• 2010

Twitter has been continuously growing since October, 2006. Especially, not only the users and the number of messages have been increasing but also a new concept in social networking called 'micro blogging' has diffused. Within Korea, service such as 'me2day' has already been introduced and the improvement of internet accessibility within mobile devices is expected to expand the 'micro blogs'. In this point, this research is executed to study the new medium, 'micro blog'. To do so, we collected and analyzed Twitter logs of Korean users. Especially, we were curious about the extreme heavy users using Twitter, despite of the linguistic and cultural barrier of the foreign service. Who they are, why and how they use the 'micro blog'. First, we reviewed the general aspect of followers and messages by collecting a certain number of random samples. Using the Lorenz curve we found out that there was the imbalance within the users and based on this phenomenon we deducted an extreme heavy user group. In order to perform further analysis, log analysis was performed on the extreme heavy users. As the result, the users used multiple mobile and desktop 'Twitter' clients. The usage pattern was similar to that of internet usage time but was used during their "micro" time. The users using 'Twitter' not only to spread messages about important information, special events and emotions, but also as a habitual 'chatting tool' to express ordinary personal chats similar to SMS and IM services. In this research, it is proved that 68% of the total messages were ordinary personal chats. Also, with 24% of the total messages were retweets, we were able to find out that virtually connected 'people' and 'relationships' acted as the dominant trigger of their articulation.

• Journal of Korean Society of Disaster and Security
• /
• v.14 no.4
• /
• pp.17-27
• /
• 2021

Streamflow prediction is a very vital disaster mitigation approach for effective flood management and water resources planning. Lately, torrential rainfall caused by climate change has been reported to have increased globally, thereby causing enormous infrastructural loss, properties and lives. This study evaluates the contribution of rainfall to streamflow prediction in normal and peak rainfall scenarios, typical of the recent flood at Piney Resort in Vernon, Hickman County, Tennessee, United States. Daily streamflow, water level, and rainfall data for 20 years (2000-2019) from two USGS gage stations (03602500 upstream and 03599500 downstream) of the Piney River watershed were obtained, preprocesssed and fitted with Long short term memory (LSTM) model. Tensorflow and Keras machine learning frameworks were used with Python to predict streamflow values with a sequence size of 14 days, to determine whether the model could have predicted the flooding event in August 21, 2021. Model skill analysis showed that LSTM model with full data (water level, streamflow and rainfall) performed better than the Naive Model except some rainfall models, indicating that only rainfall is insufficient for streamflow prediction. The final LSTM model recorded optimal NSE and RMSE values of 0.68 and 13.84 m³/s and predicted peak flow with the lowest prediction error of 11.6%, indicating that the final model could have predicted the flood on August 24, 2021 given a peak rainfall scenario. Adequate knowledge of rainfall patterns will guide hydrologists and disaster prevention managers in designing efficient early warning systems and policies aimed at mitigating flood risks.