• Journal of Environmental Health Sciences
• /
• v.48 no.3
• /
• pp.159-166
• /
• 2022

Background: A quantitative structure-activity relationship (QSAR) model was adopted in the Registration, Evaluation, Authorization, and Restriction of Chemicals (REACH, EU) regulations as well as the Act on Registration, Evaluation, etc. of Chemicals (AREC, Republic of Korea). It has been previously used in the registration of chemicals. Objectives: In this study, we investigated the correlation between the predicted data provided by three prediction programs using a QSAR model and actual experimental results (acute fish, daphnia magna toxicity). Through this approach, we aimed to effectively conjecture on the performance and determine the most applicable programs when designating toxic substances through the AREC. Methods: Chemicals that had been registered and evaluated in the Toxic Chemicals Control Act (TCCA, Republic of Korea) were selected for this study. Two prediction programs developed and operated by the U.S. EPA - the Ecological Structure-Activity Relationship (ECOSAR) and Toxicity Estimation Software Tool (T.E.S.T.) models - were utilized along with the TOPKAT (Toxicity Prediction by Komputer Assisted Technology) commercial program. The applicability of these three programs was evaluated according to three parameters: accuracy, sensitivity, and specificity. Results: The prediction analysis on fish and daphnia magna in the three programs showed that the TOPKAT program had better sensitivity than the others. Conclusions: Although the predictive performance of the TOPKAT program when using a single predictive program was found to perform well in toxic substance designation, using a single program involves many restrictions. It is necessary to validate the reliability of predictions by utilizing multiple methods when applying the prediction program to the regulation of chemicals.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.34 no.6
• /
• pp.315-324
• /
• 2022

The experimental data obtained in a wave flume were analyzed using machine learning techniques to establish a model that predicts the input wave height of the wavemaker based on the waves that have experienced wave shoaling and to verify the performance of the established model. For this purpose, artificial neural network (NN), the most representative machine learning technique, and Gaussian process regression (GPR), one of the non-parametric regression analysis methods, were applied respectively. Then, the predictive performance of the two models was compared. The analysis was performed independently for the case of using all the data at once and for the case by classifying the data with a criterion related to the occurrence of wave breaking. When the data were not classified, the error between the input wave height at the wavemaker and the measured value was relatively large for both the NN and GPR models. On the other hand, if the data were divided into non-breaking and breaking conditions, the accuracy of predicting the input wave height was greatly improved. Among the two models, the overall performance of the GPR model was better than that of the NN model.

• Journal of Korean Society on Water Environment
• /
• v.39 no.2
• /
• pp.162-174
• /
• 2023

In order to prevent water pollution caused by organic matter, Total Organic Carbon(TOC) has been adopted indicator and monitored. TOC can be divided into Dissolved Organic Carbon(DOC) and Particulate Organic Carbon(POC). POC is largely precipitated and removed during stream flow, which making DOC environmentally significant. However, there are lack of studies to define spatio-temporal distributions of DOC in stream affected by various land use. Therefore, it is necessary to estimate the past DOC concentration using other water quality indicators to evaluate status of watershed management. In this study, DOC was estimated by correlation and regression analysis using three different organic matter indicators monitored in mixed land-use watersheds. The results of correlation analysis showed that DOC has the highest correlation with TOC. Based on the results of the correlation analysis, the single- and multiple-regression models were developed using Biochemical Oxygen Demand(BOD), Chemical Oxygen Demand(COD), and TOC. The results of the prediction accuracy for three different regression models showed that the single-regression model with TOC was better than those of the other multiple-regression models. The trend analysis using extended average concentration DOC data shows that DOC tends to decrease reflecting watershed management. This study could contribute to assessment and management of organic water pollution in mixed land-use watershed by suggesting methods for assessment of unmeasured DOC concentration.

• Journal of Korean Society of Forest Science
• /
• v.112 no.3
• /
• pp.340-351
• /
• 2023

Landslides are major natural geological hazards that cause enormous property damage and human casualties annually. The vulnerability of mountainous areas to landslides is further exacerbated by the impacts of climate change. Soil depth is a crucial parameter in landslide and debris flow analysis, and plays an important role in the evaluation of watershed hydrological processes that affect slope stability. An accurate method of estimating soil depth is to directly investigate the soil strata in the field. However, this requires significant amounts of time and money; thus, numerous models for predicting soil depth have been proposed. However, they still have limitations in terms of practicality and accuracy. In this study, 71 seismic survey results were collected from domestic mountainous areas to estimate soil depth on hill slopes. Soil depth was estimated on the basis of a shear wave velocity of 700 m/s, and a database was established for slope angle, elevation, and soil depth. Consequently, the statistical characteristics of soil depth were analyzed, and the correlations between slope angle and soil depth, and between elevation and soil depth were investigated. Moreover, various soil depth prediction models based on slope angle were investigated, and corrected linear and exponential soil depth prediction models were proposed.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.1
• /
• pp.1-7
• /
• 2023

An artificial intelligence (AI) method based on image deep learning is proposed to predict the entire displacement shape of a structure using the feature of partial displacements. The performance of the method was investigated through a structural test of a steel frame. An image-to-image regression (I2IR) training method was developed based on the U-Net layer for image recognition. In the I2IR method, the U-Net is modified to generate images of entire displacement shapes when images of partial displacement shapes of structures are input to the AI network. Furthermore, the training of displacements combined with the location feature was developed so that nodal displacement values with corresponding nodal coordinates could be used in AI training. The proposed training methods can consider correlations between nodal displacements in 3D space, and the accuracy of displacement predictions is improved compared with artificial neural network training methods. Displacements of the steel frame were predicted during the structural tests using the proposed methods and compared with 3D scanning data of displacement shapes. The results show that the proposed AI prediction properly follows the measured displacements using 3D scanning.

• Journal of the Korean Geotechnical Society
• /
• v.24 no.12
• /
• pp.13-22
• /
• 2008

Fourteen calibration ehamber tests were performed using one cylindrical and two tapered piles with different taper angles to investigate the changes of the bearing capacity of tapered piles with soil state and taper angle of piles. The results of calibration chamber tests show that the ultimate base resistance of tapered piles increases with increasing mean stress and relative density of soil. It also increases with increasing taper angle for medium sand, but with decreasing taper angle for dense sand. The ultimate shaft resistance of tapered piles increases as vertical and horizontal stresses, relative density and taper angle increase. Based on the results of model pile load tests, a new design method with shape factors for estimation of the bearing capacity of tapered piles is proposed considering the effect of soil state and taper angle on bearing capacity of tapered piles. In order to check the accuracy of predictions calculated using the new method, middle-scale field pile load tests were also conducted on cylindrical and tapered drilled shafts in clayey sand. Comparison of calculated values with measured ones shows that the new design method produces satisfactory predictions tor tapered piles.

• Journal of the Korean Geotechnical Society
• /
• v.38 no.3
• /
• pp.35-42
• /
• 2022

The N-value from the Standard Penetration Test (SPT), which is one of the representative in-situ test, is an important index that provides basic geological information and the depth of the bearing layer for the design of geotechnical structures. In the aspect of time and cost-effectiveness, there is a need to carry out a representative sampling test. However, the various variability and uncertainty are existing in the soil layer, so it is difficult to grasp the characteristics of the entire field from the limited test results. Thus the spatial interpolation techniques such as Kriging and IDW (inverse distance weighted) have been used for predicting unknown point from existing data. Recently, in order to increase the accuracy of interpolation results, studies that combine the geotechnics and deep learning method have been conducted. In this study, based on the SPT results of about 22,000 holes of ground survey, a comparative study was conducted to predict the depth of the bearing layer using deep learning methods and IDW. The average error among the prediction results of the bearing layer of each analysis model was 3.01 m for IDW, 3.22 m and 2.46 m for fully connected network and PointNet, respectively. The standard deviation was 3.99 for IDW, 3.95 and 3.54 for fully connected network and PointNet. As a result, the point net deep learing algorithm showed improved results compared to IDW and other deep learning method.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.9
• /
• pp.265-273
• /
• 2018

In this paper, we propose an acoustic event detection method in tunnels using non-negative tensor factorization (NTF) and hidden Markov model (HMM) applied to multi-channel audio signals. Incidents in tunnel are inherent to the system and occur unavoidably with known probability. Incidents can easily happen minor accidents and extend right through to major disaster. Most incident detection systems deploy visual incident detection (VID) systems that often cause false alarms due to various constraints such as night obstacles and a limit of viewing angle. To this end, the proposed method first tries to separate and detect every acoustic event, which is assumed to be an in-tunnel incident, from noisy acoustic signals by using an NTF technique. Then, maximum likelihood estimation using Gaussian mixture model (GMM)-HMMs is carried out to verify whether or not each detected event is an actual incident. Performance evaluation shows that the proposed method operates in real time and achieves high detection accuracy under simulated tunnel conditions.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.6A
• /
• pp.789-798
• /
• 2008

The stiffness method provides a framework to calculate the structural deformations directly from solving the equilibrium state. However, to use the displacement shape functions leads to approximate estimation of stiffness matrix and resisting forces, and accordingly results in a low accuracy. The conventional flexibility method uses the relation between sectional forces and nodal forces in which the equilibrium is always satisfied over all sections along the element. However, the determination of the element resisting forces is not so straightforward. In this study, a new fiber finite element mixed method has been developed for nonlinear anaysis of steel-concrete composite structures in the context of a standard finite element analysis program. The proposed method applies the Newton method based on the load control and uses the incremental secant stiffness method which is computationally efficient and stable. Also, the method is employed to analyze the steel-concrete composite structures, and the analysis results are compared with those obtained by ABAQUS. The comparison shows that the proposed method consistently well predicts the nonlinear behavior of the composite structures, and gives good efficiency.

• Journal of the Korean Society of Food Culture
• /
• v.23 no.1
• /
• pp.33-40
• /
• 2008

Accuracy of dietary assessment depends on correct estimation of quantity as well as correct data on composition of the products. Milk and soymilk were considered quite homogeneous in items of package size and composition. One serving size of fluid milk and soymilk is considered 200 mL but there are products with different amounts on the market. This study was conducted to investigate variations of amounts and composition of fluid milk and soymilk products of one portion siz on Korean market. Twenty-nine milk products were purchased and categorized into 8 groups-regular, low-fat, skim, chocolate, strawberry-flavored, banana-flavored, and black soybean-added. Sixteen fluid soymilk products were purchased and categorized into 4 groups-regular, infant, black sesame or black soybean added and others. Actual volume of each product was measured by mass cylinder and compositions of major nutrients on the package were compared to the values in the most widely used nutrient DB in Korea. Amounts of milk specified on the package of purchased products were 182.3-318.5 ml, the largest being banana-flavored milk. Amounts of soy milk were 184.3-240.5 mL, the largest being regular soymilk. Measured amount of each products were close to the amount on the package (<5%). Contents of macronutrients on the package were different from the food composition table in several products. The amounts of calcium varied greatly among the products due to the popularity of adding calcium to milk and soymilk products recently. These variations in the amount and contents of major nutrients in milk and soymilk products can lead to considerable error to the results of dietary assessment unless the amount and the composition of each product are regularly updated in the food composition table whenever the new products are introduced in the market.