• Journal of Soil and Groundwater Environment
• /
• v.26 no.6
• /
• pp.47-64
• /
• 2021

In this study, the annual and monthly groundwater recharge for the Sapgyo-cheon upstream basin in Chungnam Province was evaluated by water balance analysis utilizing WetSpass-M model. The modeling input data such as topography, climate parameters, LAI (Leaf Area Index), land use, and soil characteristics were established using ArcGIS, QGIS, and Python programs. The results showed that the annual average groundwater recharge in 2001 - 2020 was 251 mm, while the monthly groundwater recharge significantly varied over time, fluctuating between 1 and 47 mm. The variation was high in summer, and relatively low in winter. Variation in groundwater recharge was the largest in July in which precipitation was heavily concentrated, and the variation was closely associated with several factors including the total amount of precipitation, the number of days of the precipitation, and the daily average precipitation. This suggests the extent of groundwater recharge is greatly influenced not only by quantity of precipitation but also the precipitation pattern. Since climate condition has a profound effect on the monthly groundwater recharge, evaluation of monthly groundwater recharge need to be carried out by considering both seasonal and regional variability for better groundwater usage and management. In addition, the mathematical tools for groundwater recharge analysis need to be improved for more accurate prediction of groundwater recharge.

• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1464-1479
• /
• 2018

In face recognition, sometimes the number of available training samples for single category is insufficient. Therefore, the performances of models trained by convolutional neural network are not ideal. The small sample face recognition algorithm based on novel Siamese network is proposed in this paper, which doesn't need rich samples for training. The algorithm designs and realizes a new Siamese network model, SiameseFacel, which uses pairs of face images as inputs and maps them to target space so that the $L_2$ norm distance in target space can represent the semantic distance in input space. The mapping is represented by the neural network in supervised learning. Moreover, a more lightweight Siamese network model, SiameseFace2, is designed to reduce the network parameters without losing accuracy. We also present a new method to generate training data and expand the number of training samples for single category in AR and labeled faces in the wild (LFW) datasets, which improves the recognition accuracy of the models. Four loss functions are adopted to carry out experiments on AR and LFW datasets. The results show that the contrastive loss function combined with new Siamese network model in this paper can effectively improve the accuracy of face recognition.

• Smart Structures and Systems
• /
• v.23 no.6
• /
• pp.565-577
• /
• 2019

One of the most effective countermeasures for mitigating cable vibration is to install mechanical dampers near the anchorage of the cable. Most of the dampers used in the field are so-called passive dampers where their parameters cannot be changed once designed. The parameters of passive dampers are usually determined based on the optimal damper force obtained from the universal design curve for linear dampers, which will provide a maximum additional damping for the cable. As the optimal damper force is chosen based on a predetermined principal vibration mode, passive dampers will be most effective if cable undergoes single-mode vibration where the vibration mode is the same as the principal mode used in the design. However, in the actual engineering practice, multi-mode vibrations are often observed for cables. Therefore, it is desirable to have dampers that can suppress different modes of cable vibrations simultaneously. In this paper, MR dampers are proposed for controlling multi-mode cable vibrations, because of its ability to change parameters and its adaptability of active control without inquiring large power resources. Although the highly nonlinear feature of the MR material leads to a relatively complex representation of its mathematical model, effective control strategies can still be derived for suppressing multi-mode cable vibrations based on nonlinear modelling, as proposed in this paper. Firstly, the nonlinear Bouc-wen model is employed to accurately portray the salient characteristics of the MR damper. Then, the desired optimal damper force is determined from the universal design curve of friction dampers. Finally, the input voltage (current) of MR damper corresponding to the desired optimal damper force is calculated from the nonlinear Bouc-wen model of the damper using a piecewise linear interpolation scheme. Numerical simulations are carried out to validate the effectiveness of the proposed control algorithm for mitigating multi-mode cable vibrations induced by different external excitations.

• Geomechanics and Engineering
• /
• v.27 no.6
• /
• pp.551-560
• /
• 2021

Due to the low strength and high compressibility characteristics, the loess deposits tunnels are prone to large deformations and collapse. An accurate stability evaluation for loess deposits is of considerable significance in deformation control and safety work during tunnel construction. 37 groups of representative data based on real loess deposits cases were adopted to establish the stability evaluation model for the tunnel project in Yan'an, China. Physical and mechanical indices, including water content, cohesion, internal friction angle, elastic modulus, and poisson ratio are selected as index system on the stability level of loess. The data set is randomly divided into 80% as the training set and 20% as the test set. Firstly, principal component analysis (PCA) is used to convert the five index system to three linearly independent principal components X1, X2 and X3. Then, the principal components were used as input vectors for probabilistic neural network (PNN) to map the nonlinear relationship between the index system and stability level of loess. Furthermore, Leave-One-Out cross validation was applied for the training set to find the suitable smoothing factor. At last, the established model with the target smoothing factor 0.04 was applied for the test set, and a 100% prediction accuracy rate was obtained. This intelligent classification method for loess deposits can be easily conducted, which has wide potential applications in evaluating loess deposits.

• Journal of Environmental Science International
• /
• v.31 no.8
• /
• pp.691-706
• /
• 2022

Magnetic activated carbon was prepared by adding a magnetic material to activated carbon that had been prepared from waste citrus peel in Jeju. The adsorption characteristics of an aqueous solution of the antibiotic trimethoprim (TMP) were investigated using the magnetic activated carbon, as an adsorbent, and response surface methodology (RSM). Batch experiments were carried out according to a four-factor Box-Behnken experimental design affecting TMP adsorption with their input parameters (TMP concentration: 50~150 mg/L; pH: 4~10; temperature: 293~323 K; adsorbent dose: 0.05~0.15 g). The significance of the independent variables and their interaction was assessed by ANOVA and t-test statistical techniques. Statistical results showed that TMP concentration was the most effective parameter, compared with others. The adsorption process can be well described by the pseudo-second-order kinetic model. The experimental isotherm data followed the Langmuir isotherm model. The maximum adsorption capacities of TMP, estimated with the Langmuir isotherm model were 115.9-130.5 mg/g at 293-323 K. Also, both the thermodynamic parameters, ΔH and ΔG, have both positive values, indicating that the adsorption of TMP by the magnetic activated carbon is an endothermic reaction and proceeds via an involuntary process.

• Composites Research
• /
• v.21 no.5
• /
• pp.15-22
• /
• 2008

This paper describes the results of structural integrity and crashworthiness of Automatic Guideway Transit(AGT) vehicle made of sandwich composites. The applied sandwich composite of vehicle structure was composed of aluminum honeycomb core and WR580/NF4000 glass fabric/epoxy laminate composite facesheet. Material testing was conducted to determine the input parameters for the composite facesheet model, and the effective equivalent damage model fer the orthotropic honeycomb core material. The finite element analysis using ANSYS v11.0 was dont to evaluate structural integrity of AGT vehicle according to JIS E 7105 and ASCE 21-98. Crashworthiness analysis was carried out using explicit finite element code LS-DYNA3D with the lapse of time. The crash condition was frontal accident with speed of 10km/h at rigid wall. The results showed that the structural integrity and crashworthiness of AGT vehicle were proven under the specified loading and crash conditions. Also, the modified Chang-Chang failure criterion was recommended to evaluate the failure modes of composite structures after crashworthiness event.

• Composites Research
• /
• v.21 no.1
• /
• pp.22-29
• /
• 2008

This paper presents the evaluation of crashworthiness and rollover characteristics of low-floor bus vehicles made of aluminum honeycomb sandwich composites with glass-fabric epoxy laminate facesheets. Crashworthiness and rollover analysis of low-floor bus was carried out using explicit finite element analysis code LS-DYNA3D with the lapse of time. Material testing was conducted to determine the input parameters for the composite laminate facesheet model, and the effective equivalent damage model for the orthotropic honeycomb core material. The crash conditions of low-floor bus were frontal accident with speed of 60km/h. Rollover analysis were conducted according to the safety rules of European standard (ECE-R66). The results showed that the survival space for driver and passengers was secured against frontal crashworthiness and rollover of low-floor bus. Also, The modified Chang-Chang failure criterion is recommended to predict the failure mode of composite structures for crashworthiness and rollover analysis.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.39-55
• /
• 2019

Recently banks and large financial institutions have introduced lots of Robo-Advisor products. Robo-Advisor is a Robot to produce the optimal asset allocation portfolio for investors by using the financial engineering algorithms without any human intervention. Since the first introduction in Wall Street in 2008, the market size has grown to 60 billion dollars and is expected to expand to 2,000 billion dollars by 2020. Since Robo-Advisor algorithms suggest asset allocation output to investors, mathematical or statistical asset allocation strategies are applied. Mean variance optimization model developed by Markowitz is the typical asset allocation model. The model is a simple but quite intuitive portfolio strategy. For example, assets are allocated in order to minimize the risk on the portfolio while maximizing the expected return on the portfolio using optimization techniques. Despite its theoretical background, both academics and practitioners find that the standard mean variance optimization portfolio is very sensitive to the expected returns calculated by past price data. Corner solutions are often found to be allocated only to a few assets. The Black-Litterman Optimization model overcomes these problems by choosing a neutral Capital Asset Pricing Model equilibrium point. Implied equilibrium returns of each asset are derived from equilibrium market portfolio through reverse optimization. The Black-Litterman model uses a Bayesian approach to combine the subjective views on the price forecast of one or more assets with implied equilibrium returns, resulting a new estimates of risk and expected returns. These new estimates can produce optimal portfolio by the well-known Markowitz mean-variance optimization algorithm. If the investor does not have any views on his asset classes, the Black-Litterman optimization model produce the same portfolio as the market portfolio. What if the subjective views are incorrect? A survey on reports of stocks performance recommended by securities analysts show very poor results. Therefore the incorrect views combined with implied equilibrium returns may produce very poor portfolio output to the Black-Litterman model users. This paper suggests an objective investor views model based on Support Vector Machines(SVM), which have showed good performance results in stock price forecasting. SVM is a discriminative classifier defined by a separating hyper plane. The linear, radial basis and polynomial kernel functions are used to learn the hyper planes. Input variables for the SVM are returns, standard deviations, Stochastics %K and price parity degree for each asset class. SVM output returns expected stock price movements and their probabilities, which are used as input variables in the intelligent views model. The stock price movements are categorized by three phases; down, neutral and up. The expected stock returns make P matrix and their probability results are used in Q matrix. Implied equilibrium returns vector is combined with the intelligent views matrix, resulting the Black-Litterman optimal portfolio. For comparisons, Markowitz mean-variance optimization model and risk parity model are used. The value weighted market portfolio and equal weighted market portfolio are used as benchmark indexes. We collect the 8 KOSPI 200 sector indexes from January 2008 to December 2018 including 132 monthly index values. Training period is from 2008 to 2015 and testing period is from 2016 to 2018. Our suggested intelligent view model combined with implied equilibrium returns produced the optimal Black-Litterman portfolio. The out of sample period portfolio showed better performance compared with the well-known Markowitz mean-variance optimization portfolio, risk parity portfolio and market portfolio. The total return from 3 year-period Black-Litterman portfolio records 6.4%, which is the highest value. The maximum draw down is -20.8%, which is also the lowest value. Sharpe Ratio shows the highest value, 0.17. It measures the return to risk ratio. Overall, our suggested view model shows the possibility of replacing subjective analysts's views with objective view model for practitioners to apply the Robo-Advisor asset allocation algorithms in the real trading fields.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_3
• /
• pp.1273-1283
• /
• 2019

This paper proposes an advanced crop classification model that combines a procedure for weighted combination of spatial features extracted from multi-scale input images with a conventional convolutional neural network (CNN) structure. The proposed model first extracts spatial features from patches with different sizes in convolution layers, and then assigns different weights to the extracted spatial features by considering feature-specific importance using squeeze-and-excitation block sets. The novelty of the model lies in its ability to extract spatial features useful for classification and account for their relative importance. A case study of crop classification with multi-temporal Landsat-8 OLI images in Illinois, USA was carried out to evaluate the classification performance of the proposed model. The impact of patch sizes on crop classification was first assessed in a single-patch model to find useful patch sizes. The classification performance of the proposed model was then compared with those of conventional two CNN models including the single-patch model and a multi-patch model without considering feature-specific weights. From the results of comparison experiments, the proposed model could alleviate misclassification patterns by considering the spatial characteristics of different crops in the study area, achieving the best classification accuracy compared to the other models. Based on the case study results, the proposed model, which can account for the relative importance of spatial features, would be effectively applied to classification of objects with different spatial characteristics, as well as crops.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.1
• /
• pp.51-59
• /
• 1999

In this paper we propose the technique for tracking players and a ball and for obtaining players' ground traces using image mosaic in general soccer sequences. Here, general soccer sequences mean the case that there is no extreme zoom-in or zoom-out of TV camera. Obtaining player's ground traces requires that the following three main problems be solved. There main problems: (1) ground field extraction (2) player and ball tracking and team indentification (3) player positioning. The region of ground field is extracted on the basis of color information. Players are tracked by template matching and Kalman filtering. Occlusion reasoning between overlapped players in done by color histogram back-projection. To find the location of a player, a ground model is constructed and transformation between the input images and the field model is computed using four or more feature points. But, when feature points extracted are insufficient, image-based mosaic technique is applied. By this image-to-model transformation, the traces of players on the ground model can be determined. We tested our method on real TV soccer sequence and the experimental results are given.