• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.2
• /
• pp.91-108
• /
• 2022

In most cases, optical images have been used as training data of DL (Deep Learning) models for object detection, recognition, identification, classification, semantic segmentation, and instance segmentation. However, properties of 3D objects in the real-world could not be fully explored with 2D images. One of the major sources of the 3D geospatial information is DSM (Digital Surface Model). In this matter, characteristic information derived from DSM would be effective to analyze 3D terrain features. Especially, man-made objects such as buildings having geometrically unique shape could be described by geometric elements that are obtained from 3D geospatial data. The background and motivation of this paper were drawn from concept of the intrinsic image that is involved in high-level visual information processing. This paper aims to extract buildings after classifying terrain features by training DL model with DSM-derived information including slope, aspect, and SRI (Shaded Relief Image). The experiments were carried out using DSM and label dataset provided by ISPRS (International Society for Photogrammetry and Remote Sensing) for CNN-based SegNet model. In particular, experiments focus on combining multi-source information to improve training performance and synergistic effect of the DL model. The results demonstrate that buildings were effectively classified and extracted by the proposed approach.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.1
• /
• pp.38-44
• /
• 2022

Speech enhancement is performed to improve intelligibility and quality of the noise-corrupted speech. In this paper, speech enhancement performance was compared using different loss functions in time and frequency domains. This study proposes a combination of loss functions to utilize advantage of each domain by considering both the details of spectrum and the speech waveform. In our study, Scale Invariant-Source to Noise Ratio (SI-SNR) is used for the time domain loss function, and Mean Squared Error (MSE) is used for the frequency domain, which is calculated over the complex-valued spectrum and magnitude spectrum. The phase loss is obtained using the sin function. Speech enhancement result is evaluated using Source-to-Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short-Time Objective Intelligibility (STOI). In order to confirm the result of speech enhancement, resulting spectrograms are also compared. The experimental results over the TIMIT database show the highest performance when using combination of SI-SNR and magnitude loss functions.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.51-58
• /
• 2022

Drivable area detection, one of the main functions of advanced driver assistance systems, means detecting an area where a vehicle can safely drive. The drivable area detection is closely related to the safety of the driver and it requires high accuracy with real-time operation. To satisfy these conditions, V-disparity-based method is widely used to detect a drivable area by calculating the road disparity value in each row of an image. However, the V-disparity-based method can falsely detect a non-road area as a road when the disparity value is not accurate or the disparity value of the object is equal to the disparity value of the road. In a road environment including vegetation, such as a highway and a country road, the vegetation area may be falsely detected as the drivable area because the disparity characteristics of the vegetation are similar to those of the road. Therefore, this paper proposes a drivable area detection method and hardware architecture with a high accuracy in road environments including vegetation areas by reducing the number of false detections caused by V-disparity characteristic. When 289 images provided by KITTI road dataset are used to evaluate the road detection performance of the proposed method, it shows an accuracy of 90.12% and a recall of 97.96%. In addition, when the proposed hardware architecture is implemented on the FPGA platform, it uses 8925 slice registers and 7066 slice LUTs.

• Journal of the Korean Wood Science and Technology
• /
• v.30 no.4
• /
• pp.80-86
• /
• 2002

Volatile compounds in three different kinds of crude vinegars obtained from oak (Quercus serrata), bamboo (phyllostachys) and pine (Pinus densiflora) species were analyzed by the solid-phase microextraction (SPME) method. A total of 264 peaks were detected on the chromatograms obtained from the polar (CBP 20) and the nonpolar (CBP 1) columns, which were used for analyzing the volatile compounds in these vinegars. The major volatile compounds identified by using the polar column were 2-butanone, acetic acid, guaiacol, phenol, cresols, 4-ethyl guaiacol, 4-ethyl phenol, and syringol. Using the nonpolar column, seven compounds could be identified: 1,2-dimethoxybenzyl alcohol, 1-hydroxy-2-butanone, 1-(2-furanyl)-1-propane, ethisolide, furfuryl acetate, 1,2-dimethoxybenzene, phenyl acetate. The volatile compounds were classified into five groups: phenols, neutral compounds, organic acids, esters and others. The phenols were the main component and comprised 49~65% of the volatile compounds of these vinegars. In the case of bamboo vinegar, the proportion of the phenols in the volatile compounds was lower than that of the two wood vinegars. However, the proportions of the neutral compounds and the organic acids were higher than those of the wood vinegars. Therefore, it seems that these differences of the proportions of the volatile compounds would make a certain difference of a smoke flavor between the bamboo vinegar and the wood vinegars.

• Journal of Soil and Groundwater Environment
• /
• v.27 no.2
• /
• pp.50-60
• /
• 2022

The concentration levels and distribution characteristics of 16 polycyclic aromatic hydrocarbons (PAHs) were investigated and evaluated for total 100 soil samples as a part of the survey on soil contamination in Gwangju. The results (median and range) of T-PAHs (sum of 16 PAH concentrations), C-PAHs (sum of carcinogenic PAH concentrations) and T-TEQs (sum of 16 TEQ concentrations) were 20.8 (7.6~1158.1), 2.2 (N.D~509.6), and 0.3 (N.D~424.6) ㎍/kg, respectively. There was a positive correlation between C-PAHs/T-PAHs and T-TEQs/T-PAHs except one point where the concentration of benzo(a)pyrene was high. The ratios of the C-PAHs/T-PAHs were 31.7% for low molecular weight-PAHs and 68.3% for high molecular weight-PAHs, suggesting that PAHs generation mainly arose from combustion sources. The ratio of isomers of individual PAHs, Phe/Ant, Flu/Pyr, Ant/(Ant+Phe), Flu/(Flu+Pyr), and BaA/(BaA+Chr), also confirmed the predominance of PAHs from combustion activities. Statistical tracing of the source of PAHs through principal component analysis indicated that the main sources of combustion were automobile fuel and coal. The overall results of this study suggested HMW-PAHs, T-PAHs, C-PAHs and T-TEQs should be separately evaluated to better assess the toxicity and environmental behavior of individual PAHs.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.1-10
• /
• 2022

Deep neural networks are widely used to solve various problems. In a fully connected neural network, the nonlinear activation function is a function that nonlinearly transforms the input value and outputs it. The nonlinear activation function plays an important role in solving the nonlinear problem, and various nonlinear activation functions have been studied. In this study, we propose a combined parametric activation function that can improve the performance of a fully connected neural network. Combined parametric activation functions can be created by simply adding parametric activation functions. The parametric activation function is a function that can be optimized in the direction of minimizing the loss function by applying a parameter that converts the scale and location of the activation function according to the input data. By combining the parametric activation functions, more diverse nonlinear intervals can be created, and the parameters of the parametric activation functions can be optimized in the direction of minimizing the loss function. The performance of the combined parametric activation function was tested through the MNIST classification problem and the Fashion MNIST classification problem, and as a result, it was confirmed that it has better performance than the existing nonlinear activation function and parametric activation function.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.1
• /
• pp.127-134
• /
• 2022

Recently, policies and research to prevent increasing construction accidents have been actively conducted in the domestic construction industry. In previous studies, the prediction model developed to prevent construction accidents mainly used only structured data, so various characteristics of construction sites are not sufficiently considered. Therefore, in this study, we developed a machine learning-based construction accident prediction model that enables the characteristics of construction sites to be considered sufficiently by using both structured and text-type unstructured data. In this study, 6,826 cases of construction accident data were collected from the Construction Safety Management Integrated Information (CSI) for machine learning. The Decision forest algorithm and the BERT language model were used to train structured and unstructured data respectively. As a result of analysis using both types of data, it was confirmed that the prediction accuracy was 95.41 %, which is improved by about 20 % compared to the case of using only structured data. Conclusively, the performance of the predictive model was effectively improved by using the unstructured data together, and construction accidents can be expected to be reduced through more accurate prediction.

• Journal of Naturopathy
• /
• v.10 no.1
• /
• pp.1-9
• /
• 2021

Purpose: This study has proved the intervention effects of the proposed logotherapy-based music imagery (LBMI) program on the self-worth of the personal assistants for the disabled. The program, in the image activities and at the stage of postlude after listening to music, unites logodrama of logotherapy, paradoxical intention and dereflected techniques. The intervention effects of the LBMI program were tested for the 28 personal assistants for the disabled who found themselves without the value and meaning of life and were randomly equally divided into the experimental and control groups. This intervention was carried out for the six different terms, each of which was alloted 60 minutes. To evaluate the intervention effects, the self-worth scale were examined before and after the intervention for both experimental and control group. The result shows that the self-worth improved significantly in the experimental group(p < 0.001), whereas it remained unchanged in the control group(p > 0.459). This finding proves that the proposed LBMI program ameliorates the self-worth of the personal assistants for the disabled.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.714-724
• /
• 2021

The point cloud content is immersive content recorded by acquiring points and colors corresponding to the real environment and objects having three-dimensional location information. When a point cloud content consisting of three-dimensional points having position and color information is enlarged and rendered, the gap between the points widens and an empty hole occurs. In this paper, we propose a method for improving the quality of point cloud contents through inverse transformation-based interpolation using depth information for holes by finding holes that occur due to the gap between points when expanding the point cloud. The points on the back are rendered between the holes created by the gap between the points, acting as a hindrance to applying the interpolation method. To solve this, remove the points corresponding to the back side of the point cloud. Next, a depth map at the point in time when an empty hole is generated is extracted. Finally, inverse transform is performed to extract pixels from the original data. As a result of rendering content by the proposed method, the rendering quality improved by 1.2 dB in terms of average PSNR compared to the conventional method of increasing the size to fill the blank area.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.23 no.6
• /
• pp.559-575
• /
• 2021

Due to the increase in ground excavation work, the possibility of ground subsidence accidents is increasing. And it is very difficult to prevent these risk fundamentally through institutional reinforcement such as the special law for underground safety management. As for the various cases of urban ground excavation practice, the ground subsidence behavior characteristics which is predicted using various information before excavation showed a considerable difference that could not be ignored compared to the results real construction data. Changes in site conditions such as seasonal differences in design and construction period, changes in construction methods depending on the site conditions and long-term construction suspension due to various reasons could be considered as the main causes. As the countermeasures, the safety management system through various construction information is introduced, but there is still no suitable system which can predict the effect of excavation and risk assessment. In this study, a web-based system was developed in order to predict the degree of impact on the ground subsidence and surrounding structures in advance before ground excavation and evaluate the risk in the design and construction of urban ground excavation projects. A system was built using time series analysis technique that can predict the current and future behavior characteristics such as ground water level and settlement based on past field construction records with field monitoring data. It was presented as a geotechnical data visualization (GDV) technology for risk reduction and disaster management based on web-based system, Using this newly developed web-based assessment system, it is possible to predict ground excavation impact prediction and risk assessment.