• Journal of KIISE:Software and Applications
• /
• v.31 no.5
• /
• pp.595-604
• /
• 2004

Automatic analysis of concepts or semantic relations from text documents enables not only an efficient acquisition of relevant information, but also a comparison of documents in the concept level. We present a multiple cause model-based approach to text analysis, where latent topics are automatically extracted from document sets and similarity between documents is measured by semantic kernels constructed from the extracted topics. In our approach, a document is assumed to be generated by various combinations of underlying topics. A topic is defined by a set of words that are related to the same topic or cooccur frequently within a document. In a network representing a multiple-cause model, each topic is identified by a group of words having high connection weights from a latent node. In order to facilitate teaming and inferences in multiple-cause models, some approximation methods are required and we utilize an approximation by Helmholtz machines. In an experiment on TDT-2 data set, we extract sets of meaningful words where each set contains some theme-specific terms. Using semantic kernels constructed from latent topics extracted by multiple cause models, we also achieve significant improvements over the basic vector space model in terms of retrieval effectiveness.

• Journal of KIISE:Information Networking
• /
• v.37 no.5
• /
• pp.409-414
• /
• 2010

The applications based on geographical location are increasing rapidly in wireless sensor networks (WSN). Recently, various localization algorithms have been proposed but the majority of algorithms rely on the specific hardware to measure the distance from the signal sources. In this paper, we propose the Weighted Multiple Rings Localization(WMRL). We assume that each deployed anchor node may periodically emit the successive beacon signals of the different power level. Then, the beacon signals form the concentric rings depending on their emitted power level, theoretically. The proposed algorithm defines the different weighting factor based on the ratio of each radius of ring. Also, If a sensor node may listen, it can find the innermost ring of the propagated signal for each anchor node. Based on this information, the location of a sensor node is derived by a weighted sum of coordinates of the surrounding anchor nodes. Our proposed algorithm is fully distributed and does not require any additional hardwares and the unreliable distance indications such as RSSI and LQI. Nevertheless, the simulation results show that the WMRL with two rings twice outperforms centroid algorithm. In the case of WMRL with three rings, the accuracy is approximately equal to WCL(Weighted Centroid Localization).

• Journal of Korea Water Resources Association
• /
• v.43 no.8
• /
• pp.721-731
• /
• 2010

The rainfall-runoff relationship is very difficult to predict because it is complicate factor affected by many temporal and spatial parameters of the basin. In recent, models which is based on artificial intelligent such as neural network, genetic algorithm fuzzy etc., are frequently used to predict discharge while stochastic or deterministic or empirical models are used in the past. However, the discharge data which are generally used for prediction as training and validation set are often estimated from rating curve which has potential error in its estimation that makes a problem in reliability. Therefore, in this study, water stage is predicted from antecedent rainfall and water stage data for short term using three models of neural network which trained by error back propagation algorithm and optimized by genetic algorithm and training error back propagation after it is optimized by genetic algorithm respectively. As the result, the model optimized by Genetic Algorithm gives the best forecasting ability which is not much decreased as the forecasting time increase. Moreover, the models using stage data only as the input data give better results than the models using precipitation data with stage data.

• Journal of Wetlands Research
• /
• v.15 no.3
• /
• pp.367-380
• /
• 2013

In this study, sub-indicators, and thematic mid-indexes to evaluate the water use characteristics were selected through historical data analysis and factor analysis, and consisted of the subject approach framework. And the integrated index was developed to evaluate water use characteristics of the watershed. Using developed index, the water use characteristics were assessed for 812 standard basins with the exception for North Korea using data of 1990 to 2007 from the relevant agencies. A sensitivity analysis is conducted for this study to determine the proper way through various normalization and weighting methods. To increase the objectivity of developed index, the history of the damage indicators are excluded in the analysis. In addition, in order to ensure its reliability, results from index with and without consideration of the damage history were compared. Also, the index is also applied to real data for 2008 Gangwon region to verify its field applicability. Through the validation process this index confirmed the adequacy for the indicators selection and calculation method. The results of this study were analyzed based on the spatial and time vulnerability of the basin's water use, which can be applied to various parts such as priority decision-making for water business or policy, mitigations for the vulnerable components of the basin, and supporting measures to establishment by providing relevant information about it.

• Journal of The Geomorphological Association of Korea
• /
• v.20 no.1
• /
• pp.21-33
• /
• 2013

Weight of evidence model was applied for potential mapping of mountainous wetland to reduce the range of the field survey and to increase the efficiency of operations because the surveys of mountainous wetland need a lot of time and money owing to inaccessibility and extensiveness. The relationship between mountainous wetland location and related factors is expressed as a probability by Weight of evidence model. For this, the spatial database consist of slope map, curvature map, vegetation index map, wetness index map, soil drainage rating map was constructed in Yeongnam area, Korea, and weights of evidence based on the relationship between mountainous wetland location and each factor rating were calculated. As a result of correlation analysis between mountainous wetland location and each factors rating using likelihood ratio values, the probability of mountainous wetlands were increased at condition of lower slope, lower curvature, lower vegetation index value, lower wetness value, moderate soil drainage rating. Mountainous Wetland Potential Index(MWPI) was calculated by summation of the likelihood ratio and mountainous wetland potential map was constucted from GIS integration. The mountain wetland potential map was verified by comparison with the known mountainous wetland locations. The result showed the 75.48% in prediction accuracy.

• Journal of Broadcast Engineering
• /
• v.26 no.3
• /
• pp.283-295
• /
• 2021

This paper proposes a method for generating dense depth map using information of color images and depth map generated based on lidar based on self-organizing map. The proposed depth map upsampling method consists of an initial depth prediction step for an area that has not been acquired from LiDAR and an initial depth filtering step. In the initial depth prediction step, stereo matching is performed on two color images to predict an initial depth value. In the depth map filtering step, in order to reduce the error of the predicted initial depth value, a self-organizing map technique is performed on the predicted depth pixel by using the measured depth pixel around the predicted depth pixel. In the process of self-organization map, a weight is determined according to a difference between a distance between a predicted depth pixel and an measured depth pixel and a color value corresponding to each pixel. In this paper, we compared the proposed method with the bilateral filter and k-nearest neighbor widely used as a depth map upsampling method for performance comparison. Compared to the bilateral filter and the k-nearest neighbor, the proposed method reduced by about 6.4% and 8.6% in terms of MAE, and about 10.8% and 14.3% in terms of RMSE.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.5
• /
• pp.587-599
• /
• 2023

As climate change increasesthe frequency and risk of flooding in major cities around theworld, the importance ofsimulation technology that can quickly and accurately analyze high-resolution 2D flooding information in large-scale areasis emerging. The physically-based approaches based on the Shallow Water Equations (SWE) often requires huge computer resources hindering high-resolution flood prediction. This study investigated the theoretical background of Weighted Cellular Automata 2D (WCA2D), which simulates spatio-temporal changes offlooding using transition rules and weight-based system, and assessed feasibility to simulate pluvial flooding in the urbancatchment, theOncheon-cheon catchmentinBusan, SouthKorea.Inaddition,the computation performancewas compared by applying versions using OpenComputing Language (OpenCL) andOpenMulti-Processing (OpenMP) parallel computing techniques. Simulationresultsshowed that the maximuminundation depthmap by theWCA2Dmodel cansimilarly reproduce historical inundation maps. Also, it can precisely simulate spatio-temporal changes of flooding extent in the urban catchment with complex topographic characteristics. For computation efficiency, parallel computing schemes, theOpenCLandOpenMP, improved the computation by about 8~14 and 5~6 folds respectively, compared to the sequential computation.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.6
• /
• pp.793-799
• /
• 2023

This study classifies the types of urban railway stations that reflect the location characteristics of urban railway stations, the structure and form of station taxes, and the number of users, and the level of inconvenience in the transfer movement line for users by station type, the number and connectivity of transfer information, and the level of transfer convenience facilities. The number of installations, conflicts between users, and transfer information signs were analyzed. As a result of data analysis, it was found that the factors that cause the most inconvenience to urban rail users when transferring are the length and curvature of the transfer line, pedestrian density and number of passengers in the transfer passage, presence or absence of transportation convenience facilities, and the size and height of transfer information letters. These transfer inconveniences were objectified, quantified, and presented as evaluation indicators that can measure the transfer convenience of urban railway stations. Additionally, an evaluation scale was developed to measure the service level for each evaluation indicator. The evaluation scale for each indicator presented six levels by applying linear interpolation based on the maximum and minimum values of data derived through field surveys. However, it is judged that a comprehensive evaluation of transfer convenience that combines the importance and weight of each convenience evaluation indicator should be established through future research.

• Journal of the Korean Geotechnical Society
• /
• v.40 no.4
• /
• pp.49-60
• /
• 2024

Ground-penetrating radar (GPR) enables rapid data acquisition over extensive areas, but interpreting the obtained data requires specialized knowledge. Numerous studies have utilized numerical analysis methods to examine GPR signal characteristics under various conditions. To develop more realistic numerical models, the heterogeneous nature of the ground, which causes clutter, must be considered. Clutter refers to signals reflected by objects other than the target. The Peplinski material model and fractal techniques can simulate these heterogeneous characteristics, yet there is a shortage of research on the necessary input parameters. Moreover, methods for quantitatively evaluating the similarity between field and analytical data are not well established. In this study, we calculated the autocorrelation coefficient of field data and determined the correlation length using the autocorrelation function. The correlation length represented the temporal or spatial distance over which data exhibited similarity. By comparing the correlation length of field data with that of the numerical model incorporating fractal weights, we quantitatively evaluated a numerical model for heterogeneous ground. Consequently, the results of this study demonstrated a numerical modeling technique that reflected the clutter characteristics of the field through correlation length.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.46 no.3
• /
• pp.14-26
• /
• 2018

The Biotope Area Ratio (BAR) is a quantitative pre-planning index for sustainable development and an integrated indicator for the balanced development of buildings and outdoor spaces. However, it has been pointed out that there are problems in operations management: errors in area calculation, insufficiency in the underground soil condition and depth, reduction in biotope area after construction, and functional failure as a pre-planning index. To address these problems, this study proposes implementing LIM. Since the weights of the BAR are mainly decided by the underground soil condition and depth with land cover types, the study focused on the terrain and pavements. The model should conform to BIM guidelines and standards provided by government agencies and professional organizations. Thus, the scope and Level Of Detail (LOD) of the model were defined, and the method to build a model with BIM software was developed. An apartment complex on sloping ground was selected as a case study, a 3D terrain modeled, paving libraries created with property information on the BAR, and a LIM model completed for the site. Then the BAR was calculated and construction documents were created with the BAR table and pavement details. As results of the study, it was found that the application of the criteria on the BAR and calculation became accurate, and the efficiency of design tasks was improved by LIM. It also enabled the performance of evidence-based design on the terrain and underground structures. To adopt LIM, it is necessary to create and distribute LIM library manuals or templates, and build library content that comply with KBIMS standards. The government policy must also have practitioners submit BIM models in the certification system. Since it is expected that the criteria on planting types in the BAR will be expanded, further research is needed to build and utilize the information model for planting materials.