• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.2
• /
• pp.19-28
• /
• 2019

The purpose of this study is to examine the trends on machine learning and deep learning research in the published journals from the Web of Science Database. To achieve the study purpose, we used the abstracts of 20,664 articles published between 1990 and 2017, which include the word 'machine learning', 'deep learning', and 'artificial neural network' in their titles. Twenty major research topics were identified from topic modeling analysis and they were inclusive of classification accuracy, machine learning, optimization problem, time series model, temperature flow, engine variable, neuron layer, spectrum sample, image feature, strength property, extreme machine learning, control system, energy power, cancer patient, descriptor compound, fault diagnosis, soil map, concentration removal, protein gene, and job problem. The analysis of the time-series linear regression showed that all identified topics in machine learning research were 'hot' ones.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.7
• /
• pp.4508-4515
• /
• 2014

Real-time body detection has been researched actively. On the other hand, the detection rate of color distorted images is low because most existing detection methods use static skin color model. Therefore, this paper proposes a new method for detecting the skin color region using a gradient map and saturation features. The basic procedure of the proposed method sequentially consists of creating a gradient map, extracting a gradient feature of skin regions, noise removal using the saturation features of skin, creating a cluster for extraction regions, detecting skin regions using cluster information, and verifying the results. This method uses features other than the color to strengthen skin detection not affected by light, race, age, individual features, etc. The results of the detection rate showed that the proposed method is 10% or more higher than the traditional methods.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.6
• /
• pp.545-554
• /
• 2018

As the map paradigm shifts from analog to digital, the LOD (Level Of Detail) of spatial information needs to be redefined. In this study, we propose 4- dimensional indoor LOD model which can be used in digital map environment. For this purpose, the limitation of the previous research is derived through study of related works, and based on this, four different LODs are defined such PLOD (Position accuracy LOD) based on position accuracy, GLOD (Geometric LOD) based on shape representation, CLOD (Complete LOD) based on generalization, and SLOD (Semantic LOD) based on theme accuracy. In addition, we describe the relationships among the four different LODs, and explain how to express the indoor LOD using the four different LODs and show examples. In the future, the case studies of indoor LOD adoption for various indoor services and the study of method for applying CLOD and SLOD to each feature should be performed to verify the feasibility and validity of proposed indoor LOD.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.8
• /
• pp.1187-1193
• /
• 2013

In this paper, we present realistic 3D head modeling and facial expression systems. For 3D head modeling, we perform generic model fitting to make individual head shape and texture mapping. To calculate the deformation function in the generic model fitting, we determine correspondence between individual heads and the generic model. Then, we reconstruct the feature points to 3D with simultaneously captured images from calibrated stereo camera. For texture mapping, we project the fitted generic model to image and map the texture in the predefined triangle mesh to generic model. To prevent extracting the wrong texture, we propose a simple method using a modified interpolation function. For generating 3D facial expression, we use the vector muscle based algorithm. For more realistic facial expression, we add the deformation of the skin according to the jaw rotation to basic vector muscle model and apply mass spring model. Finally, several 3D facial expression results are shown at the end of the paper.

• The Journal of Engineering Geology
• /
• v.33 no.4
• /
• pp.673-687
• /
• 2023

Exploratory data analysis is the process of observing and understanding data collected from various sources to identify their distributions and correlations through their structures and characterization. This process can be used to identify correlations among conditioning factors and select the most effective factors for analysis. This can help the assessment of landslide susceptibility, because landslides are usually triggered by multiple factors, and the impacts of these factors vary by region. This study compared two stages of exploratory data analysis to examine the impact of the data exploration procedure on the landslide prediction model's performance with respect to factor selection. Deep-learning-based landslide susceptibility analysis used either a combinations of selected factors or all 23 factors. During the data exploration phase, we used a Pearson correlation coefficient heat map and a histogram of random forest feature importance. We then assessed the accuracy of our deep-learning-based analysis of landslide susceptibility using a confusion matrix. Finally, a landslide susceptibility map was generated using the landslide susceptibility index derived from the proposed analysis. The analysis revealed that using all 23 factors resulted in low accuracy (55.90%), but using the 13 factors selected in one step of exploration improved the accuracy to 81.25%. This was further improved to 92.80% using only the nine conditioning factors selected during both steps of the data exploration. Therefore, exploratory data analysis selected the conditioning factors most suitable for landslide susceptibility analysis and thereby improving the performance of the analysis.

• Journal of Korea Water Resources Association
• /
• v.39 no.3 s.164
• /
• pp.215-226
• /
• 2006

In this study, we performed verification of VSRF (Very Short Range Forecast of precipitation) model and application of NWSPC (National Weather Service PC) rainfall-runoff model in Kyoungan-chun basin. We used two methods for verification of VSRF model. The first method is a meteorological verification that evaluates the special quality feature for rain amount between AWS and VSRF model over Kyoungan-chun basin, while second method is a hydrological verification that compares the calculated Mean Area Precipitation (MAP) between AWS and VSRF Quantitatively. This study examines the usefulness of VSRF precipitation forecasting model data in NWSPC hydrological model. As a result, correlation coefficient is over 0.6 within 3 hour lead time. It represents that the forecast results from VSRF are useful for water resources application.

• Journal of Korean Society for Geospatial Information Science
• /
• v.11 no.1 s.24
• /
• pp.51-59
• /
• 2003

This study intended to extract the spatial data and attribute data from the images of terrestrial and aerial photographs and to compile the digital map from the images using various kinds of photogrammetric analysis. The Three Dimensional Frame Model (3DFM) was produced from multiple images of terrestial photographs, and the Three Dimensional Photo Image Model (3DPIM) was made using 3DFM and image patches of terrestrial photo, which is useful for identifying the feature and characteristics of the object. In addition, the spatial data base for the buildings, roads and supplementary facilities in the objective area was updated by the vectorizing procedures with small scale areal photos.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.2
• /
• pp.430-435
• /
• 2007

In this paper, we propose an intelligent deployment of sensor network for reliable communication. The proposed method determines optimal transmission range based on the wireless channel characteristics, and searches the optimal number of sensor nodes, and optimal locations with SOFM. We calculate PRR against a distance uses the log-normal path loss model, and decide the communication range of sensor node from PRR. In order to verify the effectiveness of the proposed method, we performed simulations on the searching for intelligent deployment and checking for link condition of sensor network.

• Journal of The Geomorphological Association of Korea
• /
• v.23 no.3
• /
• pp.67-78
• /
• 2016

Soil carbon(C) is an essential property for characterizing soil quality. Understanding spatial patterns of soil C is particularly limited for mountain areas. This study aims to predict the spatial pattern of soil C using terrain analysis in a steep mountainous area. Specifically, model performances and prediction uncertainties were investigated based on the number of resampling repetitions. Further, important predictors for soil C were also identified. Finally, the spatial distribution of uncertainty was analyzed. A total of 91 soil samples were collected via conditioned latin hypercube sampling and a digital soil C map was developed using support vector regression which is one of the powerful machine learning methods. Results showed that there were no distinct differences of model performances depending on the number of repetitions except for 10-fold cross validation. For soil C, elevation and surface curvature were selected as important predictors by recursive feature elimination. Soil C showed higher values in higher elevation and concave slopes. The spatial pattern of soil C might possibly reflect lateral movement of water and materials along the surface configuration of the study area. The higher values of uncertainty in higher elevation and concave slopes might be related to geomorphological characteristics of the research area and the sampling design. This study is believed to provide a better understanding of the relationship between geomorphology and soil C in the mountainous ecosystem.

• Journal of Multimedia Information System
• /
• v.8 no.2
• /
• pp.101-110
• /
• 2021

In computer vision, single-image super resolution has been an area of research for a significant period. Traditional techniques involve interpolation-based methods such as Nearest-neighbor, Bilinear, and Bicubic for image restoration. Although implementations of convolutional neural networks have provided outstanding results in recent years, efficiency and single model multi-scalability have been its challenges. Furthermore, previous works haven't placed enough emphasis on real-number scalability. Interpolation-based techniques, however, have no limit in terms of scalability as they are able to upscale images to any desired size. In this paper, we propose a convolutional neural network possessing the advantages of the interpolation-based techniques, which is also efficient, deeming it suitable in practical implementations. It consists of convolutional layers applied on the low-resolution space, post-up-sampling along the end hidden layers, and additional layers on high-resolution space. Up-sampling is applied on a multiple channeled feature map via bicubic interpolation using a single model. Experiments on architectural structure, layer reduction, and real-number scale training are executed with results proving efficient amongst multi-scale learning (including scale multi-path-learning) based models.