• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.12
• /
• pp.2779-2784
• /
• 2015

The prediction of the accurate traffic information can provide an optimal route from the place of departure to a destination, therefore, this makes it possible to obtain a saving of time and money. To predict traffic information, we use a Bayesian network method based on probability model in this paper. Existing researches predicting the traffic information based on a Bayesian network generally used to study the data for all time. In this paper, however, only data corresponding to same time and day of the week to predict selectively will be used for learning. In fact, the experiment was carried out for 14 links zone in Seoul, also, the accuracy of the prediction results of the two different methods should be tested with MAPE (Mean Absolute Percentage Error) which is commonly used. In view of MAPE, experimental results show that the proposed method may calculate traffic prediction value with a higher accuracy than the method used to learn the data for all time zones.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.26 no.7
• /
• pp.892-903
• /
• 2020

The rapid and accurate prediction of storm-surge height during typhoon attacks is essential in responding to coastal disasters. Most methods used for predicting typhoon data are based on numerical modeling, but numerical modeling takes significant computing resources and time. Recently, various studies on the expeditious production of predictive data based on artificial intelligence have been conducted, and in this study, artificial intelligence-based storm-surge height prediction was performed. Several learning data were needed for artificial intelligence training. Because the number of previous typhoons was limited, many synthesized typhoons were created using the tropical cyclone risk model, and the storm-surge height was also generated using the storm surge model. The comparison of the storm-surge height predicted using artificial intelligence with the actual typhoon, showed that the root-mean-square error was 0.09 ~ 0.30 m, the correlation coefficient was 0.65 ~ 0.94, and the absolute relative error of the maximum height was 1.0 ~ 52.5%. Although errors appeared to be somewhat large at certain typhoons and points, future studies are expected to improve accuracy through learning-data optimization.

• Computers and Concrete
• /
• v.13 no.1
• /
• pp.17-30
• /
• 2014

This research presents the effect of various ground pozzolanic materials in blended cement concrete on the strength and chloride penetration resistance. An experimental investigation dealing with concrete incorporating ground fly ash (GFA), ground bottom ash (GBA) and ground rice husk ash (GRHA). The concretes were mixed by replacing each pozzolan to Ordinary Portland cement at levels of 0%, 10%, 20% and 40% by weight of binder. Three different water to cement ratios (0.35, 0.48 and 0.62) were used and type F superplasticizer was added to keep the required slump. Compressive strength and chloride permeability were determined at the ages of 28, 60, and 90 days. Furthermore, using this experimental database, linear and nonlinear multiple regression techniques were developed to construct a mathematical model of chloride permeability in concretes. Experimental results indicated that the incorporation of GFA, GBA and GRHA as a partial cement replacement significantly improved compressive strength and chloride penetration resistance. The chloride penetration of blended concrete continuously decreases with an increase in pozzolan content up to 40% of cement replacement and yields the highest reduction in the chloride permeability. Compressive strength of concretes incorporating with these pozzolans was obviously higher than those of the control concretes at all ages. In addition, the nonlinear technique gives a higher degree of accuracy than the linear regression based on statistical parameters and provides fairly reasonable absolute fraction of variance ($R^2$) of 0.974 and 0.960 for the charge passed and chloride penetration depth, respectively.

• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.247-249
• /
• 2006

The objective of this study is to detect a inter-tidal topographic change in a decade. Waterline extraction is a one of widely used method to generate digital elevation model (DEM) of tidal flat using multi-temporal optical data. This method has been well known that it is possible to construct detailed topographic relief of tidal flat using waterlines In this study, we generated two sets of tidal flat DEM for the southern Ganghwado. The DEMs showed that the Yeongjongdo northern tidal flat is relatively high elevation with steep gradients. The Ganghwado southern tidal flat is relatively low elevation and gentle gradients. To detect the morphologic change of tidal flat during a decade, we compared between early 1990's DEM and early 2000's DEM. Erosion during a decade is dominant at the west of southern Ganghwado tidal flat, while sedimentation is dominant at the wide channel between the southern Ganghwado and Yeongjongdo tidal flats. This area has been commonly affected by high current and sedimentation energy. Although we are not able to verify the accuracy of the changes in topography and absolute volume of sediments, this result shows that DEM using waterline extraction method is an effective tool for long term topographic change estimation.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.4
• /
• pp.621-628
• /
• 2017

This paper presents an artificial neural network (ANN) based model with a back-propagation algorithm for short-term load forecasting in microgrid power systems. Owing to the significant weather factors for such purpose, relevant input variables were selected in order to improve the forecasting accuracy. As remarked above, forecasting is more complex in a microgrid because of the increased variability of disaggregated load curves. Accurate forecasting in a microgrid will depend on the variables employed and the way they are presented to the ANN. This study also shows numerically that there is a close relationship between forecast errors and the number of training patterns used, and so it is necessary to carefully select the training data to be employed with the system. Finally, this work demonstrates that the concept of load forecasting and the ANN tools employed are also applicable to the microgrid domain with very good results, showing that small errors of Mean Absolute Percentage Error (MAPE) around 3% are achievable.

• Asian-Australasian Journal of Animal Sciences
• /
• v.27 no.12
• /
• pp.1678-1683
• /
• 2014

This study considers a problem of genomic selection (GS) for adjacent genetic markers of Yorkshire pigs which are typically correlated. The GS has been widely used to efficiently estimate target variables such as molecular breeding values using markers across the entire genome. Recently, GS has been applied to animals as well as plants, especially to pigs. For efficient selection of variables with specific traits in pig breeding, it is required that any such variable selection retains some properties: i) it produces a simple model by identifying insignificant variables; ii) it improves the accuracy of the prediction of future data; and iii) it is feasible to handle high-dimensional data in which the number of variables is larger than the number of observations. In this paper, we applied several variable selection methods including least absolute shrinkage and selection operator (LASSO), fused LASSO and elastic net to data with 47K single nucleotide polymorphisms and litter size for 519 observed sows. Based on experiments, we observed that the fused LASSO outperforms other approaches.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.11 no.4
• /
• pp.565-574
• /
• 2000

A new ground penetrating radar imaging method for the estimation of buried artificial structures location and their approximate shapes in dispersive lossy ground is investigated. Fundamental idea is based on estimating delayed time and amplitude retrieval coefficients from scattered signals by buried scatterers. Using absolute value integration of each scanning site not only improve the accuracy of measured scattered signal, but also offers convenient ways to extract the image of buried structures. Multi-term Debye model was employed to describe a dispersive and lossy ground medium. We used the finite difference time domain method to discretize the wave equation in continuous form into the machine suitable form. This imaging method uses a new wave path tracing technique in time domain, which is helpful to identify the exact position of buried structures against the ground surface fluctuations.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.4
• /
• pp.65-71
• /
• 2020

In order to accurately track the trajectory of the smartphone indoors and outdoors, the WiFi Fingerprint method and the Pedestrian Dead Reckoning method are fused. The former can estimate the absolute position, but an error occurs randomly from the actual position, and the latter continuously estimates the position, but there are accumulated errors as it moves. In this paper, the model and Kalman Filter equation to fuse the estimated position data of the two methods were established, and optimal system parameters were derived. According to covariance value of the system noise and measurement noise the estimation accuracy is analyzed. Using the measured data and simulation, it was confirmed that the improved performance was obtained by complementing the two methods.

• Korean Journal of Geomatics
• /
• v.4 no.2
• /
• pp.39-45
• /
• 2004

Building reconstruction attempts to generate geometric and radiometric models of existing buildings usually from sensory data, which have been traditionally aerial or satellite images, more recently airborne LIDAR data, or the combination of these data. Extensive studies on building reconstruction from these data have developed some competitive algorithms with reasonable performance and some degree of automation. Nevertheless, the level of details and completeness of the reconstructed building models often cannot reach the high standards that is now or will be required by various applications in future. Hence, the use of terrestrial sensory data that can provide higher resolution and more complete coverage has been intensively emphasized. We developed a fusion framework for building reconstruction from terrestrial sensory data, that is, points from a laser scanner, images from digital camera, and absolute coordinates from a total station. The proposed approach was then applied to reconstructing a building model from real data sets acquired from a large complex existing building. Based on the experimental results, we assured that the proposed approach cam achieve high resolution and accuracy in building reconstruction. The proposed approach can effectively contribute in developing an operational system producing large urban models for 3D GIS with reasonable resources.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.26 no.6
• /
• pp.611-616
• /
• 2008

When extracting geo-referenced 3D data from cameras mounted on Mobile Mapping Systems, one of important properties for accuracy of extracted data is the alignment of the relative translation(lever-arm) and rotation(bore-sight) between the coordinate systems of Inertial Measurement Unit(IMU)/Ground Positioning System(GPS) and cameras. Since the conventional method calculates absolute camera orientation using ground control points (GCP), the alignment is determined in one Coordinated System (GPS Coordinated System). It basically require GCP. We proposed a mathematical model for the alignment using the initially uncoupled data of cameras and IMU/GPS without GCPs.