• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1739-1748
• /
• 2021

Real estate prices affect countries, businesses, and households, and many studies have been conducted on the real estate bubble in recent soaring real estate prices. However, if the real estate bubble prediction simply compares the real estate price, or if it does not reflect key psychological variables in real estate sales, it can be judged that the accuracy of the bubble prediction model is poor. The purpose of this study is to design a predictive model that can explain the real estate bubble situation by region using the autoencoder technique. Existing real estate bubble analysis studies failed to set various types of variables that affect prices, and most of them were conducted based on linear models. Thus, this study suggests the possibility of introducing techniques and variables that have not been used in existing real estate bubble studies.

• Journal of Internet of Things and Convergence
• /
• v.8 no.1
• /
• pp.59-64
• /
• 2022

Existing edge discovery techniques only found edges of defined shapes based on precise definitions of edges. Therefore, there are many limitations in finding edges for images of complex and diverse shapes that exist in the real world. A method for solving these problems and discovering various types of edges is a cost minimization method. In this method, the cost function and cost factor are defined and used. This cost function calculates the cost of the candidate edge model generated according to the candidate edge generation strategy. If a satisfactory result is obtained, the corresponding candidate edge model becomes the edge for the image. In this study, a new candidate edge generation strategy was proposed to discover edges for images of more diverse shapes in order to improve the disadvantage of only finding edges of a defined shape, which is a problem of the cost minimization method. In addition, the contents of improvement were confirmed through a simple simulation that reflected these points.

• Coupled systems mechanics
• /
• v.11 no.6
• /
• pp.505-524
• /
• 2022

Floods represent extreme hydrological phenomena that affect populations, environment, social, political, and ecological systems. After the catastrophic floods that have hit Europe and the World in recent decades, the flood problem has become more current. At the EU level, a legal framework has been put in place with the entry into force of Directive 2007/60/EC on Flood Risk Assessment and Management (Flood Directive). Two years after the entry into force of the Floods Directive, Bosnia and Herzegovina (B&H), has adopted a Regulation on the types and content of water protection plans, which takes key steps and activities under the Floods Directive. The "Methodology for developing flood hazard and risk maps" (Methodology) was developed for the territory of Bosnia and Herzegovina, following the methodology used in the majority of EU member states, but with certain modifications to the country's characteristics. Accordingly, activities for the preparation of the Preliminary Flood Risk Assessment for each river basin district were completed in 2015 for the territory of Bosnia and Herzegovina. Activities on the production of hazard maps and flood risk maps are in progress. The results of probable climate change impact model forecasts should be included in the preparation of the Flood Risk Management Plans, which is the subsequent phase of implementing the Flood Directive. By the foregoing, the paper will give an example of the development of the hydrodynamic model of the Zujevina River, as well as the development of hazard and risk maps. Hazard and risk maps have been prepared for medium probability floods of 1/100 as well as for high probability floods of 1/20. The results of LiDAR (Light Detection and Ranging) recording were used to create a digital terrain model (DMR). It was noticed that there are big differences between the flood maps obtained by recording LiDAR techniques in relation to the previous flood maps obtained using georeferenced topographic maps. Particular attention is given to explaining the Methodology applied in Bosnia and Herzegovina.

• Imaging Science in Dentistry
• /
• v.52 no.4
• /
• pp.383-391
• /
• 2022

Purpose: Periodontitis, the most prevalent chronic inflammatory condition affecting teeth-supporting tissues, is diagnosed and classified through clinical and radiographic examinations. The staging of periodontitis using panoramic radiographs provides information for designing computer-assisted diagnostic systems. Performing image segmentation in periodontitis is required for image processing in diagnostic applications. This study evaluated image segmentation for periodontitis staging based on deep learning approaches. Materials and Methods: Multi-Label U-Net and Mask R-CNN models were compared for image segmentation to detect periodontitis using 100 digital panoramic radiographs. Normal conditions and 4 stages of periodontitis were annotated on these panoramic radiographs. A total of 1100 original and augmented images were then randomly divided into a training (75%) dataset to produce segmentation models and a testing (25%) dataset to determine the evaluation metrics of the segmentation models. Results: The performance of the segmentation models against the radiographic diagnosis of periodontitis conducted by a dentist was described by evaluation metrics(i.e., dice coefficient and intersection-over-union [IoU] score). MultiLabel U-Net achieved a dice coefficient of 0.96 and an IoU score of 0.97. Meanwhile, Mask R-CNN attained a dice coefficient of 0.87 and an IoU score of 0.74. U-Net showed the characteristic of semantic segmentation, and Mask R-CNN performed instance segmentation with accuracy, precision, recall, and F1-score values of 95%, 85.6%, 88.2%, and 86.6%, respectively. Conclusion: Multi-Label U-Net produced superior image segmentation to that of Mask R-CNN. The authors recommend integrating it with other techniques to develop hybrid models for automatic periodontitis detection.

• Journal of the Society of Disaster Information
• /
• v.19 no.3
• /
• pp.689-697
• /
• 2023

Purpose: The purpose of this study is to automatically extract information on underground facilities using a general-purpose smartphone in the process of applying the mini-trenching method. Method: Data sets for image learning were collected under various conditions such as day and night, height, and angle, and the object detection algorithm used the R-CNN algorithm. Result: As a result of the study, F1-Score was applied as a performance evaluation index that can consider the average of accurate predictions and reproduction rates at the same time, and F1-Score was 0.76. Conclusion: The results of this study showed that it was possible to extract information on underground buried materials based on smartphones, but it is necessary to improve the precision and accuracy of the algorithm through additional securing of learning data and on-site demonstration.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.158-158
• /
• 2023

Characterizing the performance of precipitation (hereafter PRE) products in estimating the uncertainties in daily PRE in the era of global warming is of great value to the ecosystem's sustainability and human survival. This study intercompares the performance of different PRE products (gauge-based, satellite and reanalysis) sourced from the Frequent Rainfall Observations on GridS (FROGS) database over diverse climate zones in Africa and identifies regions where they depict minimal uncertainties in order to build optimal maps as a guide for different climate users. This is achieved by utilizing various techniques, including the triple collection (TC) approach, to assess the capabilities and limitations of different PRE products over nine climatic zones over the continent. For daily scale analysis, the uncertainties in light PRE (0.1 5mm/day) are prevalent over most regions in Africa during the study duration (2001-2016). Estimating the occurrence of extreme PRE events based on daily PRE 90th percentile suggests that extreme PRE is mainly detected over central Africa (CAF) region and some coastal regions of west Africa (WAF) where the majority of uncorrected satellite products show good agreement. The detection of PRE days and non-PRE days based on categorical statistics suggests that a perfect POD/FAR score is unattainable irrespective of the product type. Daily PRE uncertainties determined based on quantitative metrics show that consistent, satisfactory performance is demonstrated by the IMERG products (uncorrected), ARCv2, CHIRPSv2, 3B42v7.0 and PERSIANN_CDRv1r1 (corrected), and GPCC, CPC_v1.0, and REGEN_ALL (gauge) during the study period. The optimal maps that show the classification of products in regions where they depict reliable performance can be recommended for various usage for different stakeholders.

• Journal of the Korea Society for Simulation
• /
• v.19 no.4
• /
• pp.235-247
• /
• 2010

An environmental factor is very important in a war game model supporting military training. Most war game models in Korean armed forces apply the same weather conditions to all operation areas. As a result, it fails to derive a high-fidelity simulation result. For this reason this study attempts to develop factor techniques for a high-fidelity war game that can apply distributed synthetic atmospheric environment modeling data to a military simulation. The major developed factor technology of this study applies regional distributed precipitation data to the 2D-GIS based Simplified Detection Probability Model(SDPM) that was developed for this study. By doing this, this study shows that diversely distributed local weather conditions can be applied to a military simulation depending on the model resolution from theater level to engineering level, on the use from training model to analytical model, and on the description level from corps level to battalion level.

• Journal of Korea Society of Industrial Information Systems
• /
• v.14 no.5
• /
• pp.139-148
• /
• 2009

In this paper, I propose an automatic analysis method of golf swine from single-camera video sequences. I define necessary swing features for automatic swing analysis in 2-dimensional environment and present efficient swing analysis methods using various image processing techniques including line and edge detection. The proposed method has two characteristics compared with previous swing analysis systems and related studies. First, the proposed method enables an automatic swing analysis in 2-dimension while previous systems require 3-dimensional environment which is relatively complex and expensive to run. Second, swing analysis is done automatically without human intervention while other 2-dimensional systems necessarily need analysis by a golf expert. I tested the method on 20 swing video sequences and found the proposed method works effective for automatic analysis of golf swing.

• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.85-92
• /
• 2023

Deep learning applications are increasingly being leveraged for disease detection tasks in medical imaging modalities such as X-ray, Computed Tomography (CT), and Magnetic Resonance Imaging (MRI). Most data-centric deep learning challenges necessitate the use of supervised learning methodologies to attain high accuracy and to facilitate performance evaluation through comparison with the ground truth. Supervised learning mandates a substantial amount of image and label sets, however, procuring an adequate volume of medical imaging data for training is a formidable task. Various data augmentation strategies can mitigate the underfitting issue inherent in supervised learning-based models that are trained on limited medical image and label sets. This research investigates the enhancement of a deep learning-based rib fracture segmentation model and the efficacy of data augmentation techniques such as left-right flipping, rotation, and scaling. Augmented dataset with L/R flipping and rotations(30°, 60°) increased model performance, however, dataset with rotation(90°) and ⨯0.5 rescaling decreased model performance. This indicates the usage of appropriate data augmentation methods depending on datasets and tasks.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.4
• /
• pp.601-608
• /
• 2023

Mobile robots are widely used in industries because mobile robots perform tasks in various environments. In order to carry out tasks, determining the precise location of the robot in real-time is important due to the need for path generation and obstacle detection. In particular, when mobile robots autonomously navigate in indoor environments and carry out assigned tasks within pre-determined areas, highly precise positioning performance is required. However, mobile robots frequently experience data missing in wireless communication environments. The robots need to rely on predictive techniques to autonomously determine the mobile robot positions and continue performing mobile robot tasks. In this paper, we propose an extended Kalman filter-based algorithm to enhance the accuracy of mobile robot localization and address the issue of data missing. Trilateration algorithm relies on measurements taken at that moment, resulting in inaccurate localization performance. In contrast, the proposed algorithm uses residual values of predicted measurements in data missing environments, making precise mobile robot position estimation. We conducted simulations in terms of data missing to verify the superior performance of the proposed algorithm.