• Korean Journal of Agricultural and Forest Meteorology
• /
• v.26 no.1
• /
• pp.31-52
• /
• 2024

Considering the significant relationship between a tree's branch structure and physiology, understanding the detailed branch structure is crucial for fields such as species classification, and 3D tree modelling. Recently, terrestrial laser scanning (TLS) and quantitative structure model (QSM) have enhanced the understanding of branch structures by capturing the radius, length, and branching angle of branches. Previous studies examining branch structure with TL S and QSM often relied on mean or median of branch structure parameters, such as the radius ratio and length ratio in parent-child relationships, as representative values. Additionally, these studies have typically focused on the relationship between trunk and the first order branches. This study aims to explore the distribution of branch structure parameters up to the third order in Aesculus hippocastanum, Ginkgo biloba, and Prunus yedoensis. The gamma distribution best represented the distributions of branch structure parameters, as evidenced by the average of Kolmogorov-Smirnov statistics (radius = 0.048; length = 0.061; angle = 0.050). Comparisons of the mode, mean, and median were conducted to determine the most representative measure indicating the central tendency of branch structure parameters. The estimated distributions showed differences between the mode and mean (average of normalized differences for radius ratio = 11.2%; length ratio = 17.0%; branching angle = 8.2%), and between the mode and median (radius ratio = 7.5%; length ratio = 11.5%; branching angle = 5.5%). Comparisons of the estimated distributions across branch orders and species were conducted, showing variations across branch orders and species. This study suggests that examining the estimated distribution of the branch structure parameter offers a more detailed description of branch structure, capturing the central tendencies of branch structure parameters. We also emphasize the importance of examining higher branch orders to gain a comprehensive understanding of branch structure, highlighting the differences across branch orders.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.139-156
• /
• 2021

The biggest reason for using a deep learning model in image classification is that it is possible to consider the relationship between each region by extracting each region's features from the overall information of the image. However, the CNN model may not be suitable for emotional image data without the image's regional features. To solve the difficulty of classifying emotion images, many researchers each year propose a CNN-based architecture suitable for emotion images. Studies on the relationship between color and human emotion were also conducted, and results were derived that different emotions are induced according to color. In studies using deep learning, there have been studies that apply color information to image subtraction classification. The case where the image's color information is additionally used than the case where the classification model is trained with only the image improves the accuracy of classifying image emotions. This study proposes two ways to increase the accuracy by incorporating the result value after the model classifies an image's emotion. Both methods improve accuracy by modifying the result value based on statistics using the color of the picture. When performing the test by finding the two-color combinations most distributed for all training data, the two-color combinations most distributed for each test data image were found. The result values were corrected according to the color combination distribution. This method weights the result value obtained after the model classifies an image's emotion by creating an expression based on the log function and the exponential function. Emotion6, classified into six emotions, and Artphoto classified into eight categories were used for the image data. Densenet169, Mnasnet, Resnet101, Resnet152, and Vgg19 architectures were used for the CNN model, and the performance evaluation was compared before and after applying the two-stage learning to the CNN model. Inspired by color psychology, which deals with the relationship between colors and emotions, when creating a model that classifies an image's sentiment, we studied how to improve accuracy by modifying the result values based on color. Sixteen colors were used: red, orange, yellow, green, blue, indigo, purple, turquoise, pink, magenta, brown, gray, silver, gold, white, and black. It has meaning. Using Scikit-learn's Clustering, the seven colors that are primarily distributed in the image are checked. Then, the RGB coordinate values of the colors from the image are compared with the RGB coordinate values of the 16 colors presented in the above data. That is, it was converted to the closest color. Suppose three or more color combinations are selected. In that case, too many color combinations occur, resulting in a problem in which the distribution is scattered, so a situation fewer influences the result value. Therefore, to solve this problem, two-color combinations were found and weighted to the model. Before training, the most distributed color combinations were found for all training data images. The distribution of color combinations for each class was stored in a Python dictionary format to be used during testing. During the test, the two-color combinations that are most distributed for each test data image are found. After that, we checked how the color combinations were distributed in the training data and corrected the result. We devised several equations to weight the result value from the model based on the extracted color as described above. The data set was randomly divided by 80:20, and the model was verified using 20% of the data as a test set. After splitting the remaining 80% of the data into five divisions to perform 5-fold cross-validation, the model was trained five times using different verification datasets. Finally, the performance was checked using the test dataset that was previously separated. Adam was used as the activation function, and the learning rate was set to 0.01. The training was performed as much as 20 epochs, and if the validation loss value did not decrease during five epochs of learning, the experiment was stopped. Early tapping was set to load the model with the best validation loss value. The classification accuracy was better when the extracted information using color properties was used together than the case using only the CNN architecture.

• Journal of Technology Innovation
• /
• v.18 no.2
• /
• pp.253-288
• /
• 2010

Production innovation capabilities are critical to the survival and growth of firms. This paper investigates industrial dynamics and dynamic capabilities of firms by looking at how an industry evolution process influences firms' product innovation strategy and how dynamic capabilities affect firms' product innovation process. Korea Wireless Internet industry shows a full cycle of industry evolution process including introduction phase, growth phase, maturity phase, and decline phase using by dynamic technological and market changes. 7 listed companies in Korea Wireless Internet industry were selected. We have conducted multiple case studies based upon in depth interviews. Empirical results show that different phases of industry evolution influence firms' strategy of product innovation. Dynamic capabilities are also appears to be very important to the survival and growth of a firm.

• The Journal of Society for e-Business Studies
• /
• v.23 no.1
• /
• pp.47-63
• /
• 2018

This study suggested quantitative models to calculate a royalty rate as an important input factor of the relief from royalty method which has the characteristics of income approach method and market approach method that are generally used in the valuation of intangible assets. This study built a royalty rate regression model by referring to the patent infringement damages cases based on royalties, i.e., by using the royalty rates as a dependent variable and the patent indexes of the corresponding patent right as independent variables. Then, a logistic regression model was constructed by referring to inter-partes review cases of patent rights, i.e. by using not-unpatentable results as a dependent variable and the patent indexes of the corresponding patent right as independent variables. A final royalty rate was calculated by matching the royalty rate from the royalty rate regression model with a not-unpatentable probability from the logistic regression model. The suggested royalty rate was compared with the royalty rate obtained by the traditional methods to check its reliability.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.5
• /
• pp.671-683
• /
• 2018

The flood damage caused by heavy rains in urban watershed is increasing, and, as evidenced by many previous studies, urban flooding usually exceeds the water capacity of drainage networks. The flood on the area which considerably urbanized and densely populated cause serious social and economic damage. To solve this problem, deterministic and probabilistic studies have been conducted for the prediction flooding in urban areas. However, it is insufficient to obtain lead times and to derive the prediction results for the flood volume in a short period of time. In this study, IDNN, TDNN and NARX were compared for real-time flood prediction based on urban runoff analysis to present the optimal real-time urban flood prediction technique. As a result of the flood prediction with rainfall event of 2010 and 2011 in Gangnam area, the Nash efficiency coefficient of the input delay artificial neural network, the time delay neural network and nonlinear autoregressive network with exogenous inputs are 0.86, 0.92, 0.99 and 0.53, 0.41, 0.98 respectively. Comparing with the result of the error analysis on the predicted result, it is revealed that the use of nonlinear autoregressive network with exogenous inputs must be appropriate for the establishment of urban flood response system in the future.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.10
• /
• pp.1422-1432
• /
• 1993

Nonlinear mapping function of the HCNN( Hidden Control Neural Network ) can change over time to model the temporal variability of a speech signal by combining the nonlinear prediction of conventional neural networks with the segmentation capability of HMM. We have two things in this paper. first, we showed that the performance of the HCNN is better than that of HMM. Second, the HCNN with its prediction error measure given by weighted distance is proposed to use suitable distance measure for the HCNN, and then we showed that the superiority of the proposed system for speaker-independent speech recognition tasks. Weighted distance considers the differences between the variances of each component of the feature vector extraced from the speech data. Speaker-independent Korean digit recognition experiment showed that the recognition rate of 95%was obtained for the HCNN with Euclidean distance. This result is 1.28% higher than HMM, and shows that the HCNN which models the dynamical system is superior to HMM which is based on the statistical restrictions. And we obtained 97.35% for the HCNN with weighted distance, which is 2.35% better than the HCNN with Euclidean distance. The reason why the HCNN with weighted distance shows better performance is as follows : it reduces the variations of the recognition error rate over different speakers by increasing the recognition rate for the speakers who have many misclassified utterances. So we can conclude that the HCNN with weighted distance is more suit-able for speaker-independent speech recognition tasks.

• Journal of Korea Water Resources Association
• /
• v.50 no.11
• /
• pp.745-758
• /
• 2017

The copula-based models have been successfully applied to hydrological modeling including drought frequency analysis and time series modeling. However, uncertainty estimation associated with the parameters of these model is not often properly addressed. In these context, the main purposes of this study are to develop the Bayesian inference scheme for bivariate copula functions. The main applications considered are two-fold: First, this study developed and tested an approach to copula model parameter estimation within a Bayesian framework for drought frequency analysis. The proposed modeling scheme was shown to correctly estimate model parameters and detect the underlying dependence structure of the assumed copula functions in the synthetic dataset. The model was then used to estimate the joint return period of the recent 2013~2015 drought events in the Han River watershed. The joint return period of the drought duration and drought severity was above 100 years for many of stations. The results obtained in the validation process showed that the proposed model could effectively reproduce the underlying distribution of observed extreme rainfalls as well as explicitly account for parameter uncertainty in the bivariate drought frequency analysis.

• Journal of Korea Water Resources Association
• /
• v.55 no.12
• /
• pp.1137-1147
• /
• 2022

River and groundwater stages are the main elements in the hydrologic cycle. They are spatially correlated and can be used to evaluate hydrological and agricultural drought. Stochastic simulation is often performed independently on hydrological variables that are spatiotemporally correlated. In this setting, interdependency across mutual variables may not be maintained. This study proposes the Bayesian vector autoregression model (VAR) to capture the interdependency between multiple variables over time. VAR models systematically consider the lagged stages of each variable and the lagged values of the other variables. Further, an autoregressive model (AR) was built and compared with the VAR model. It was confirmed that the VAR model was more effective in reproducing observed interdependency (or cross-correlation) between river and ground stages, while the AR generally underestimated that of the observed.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.4
• /
• pp.366-373
• /
• 2021

This study attempted to establish a field data-based write analysis standard by analyzing field observation data, which is non-linear data of southern garlic. Five regions, including Goheung, Namhae, Sinan, Changnyeong, and Haenam, were selected for analysis. Observation values for each observation station were extracted from the temperature data of farmland in the region through inverse distance weighted. Southern-type garlic production and temperature data were collected for 10 years, from 2010 to 2019. Local regression analysis (Kernel) of the obtained data was performed, and growth temperatures were analyzed, such as 0.8 (18.781℃), 0.9 (18.930℃), 1.0 (19.542℃), 1.1 (20.165℃), and 1.2 (21.042℃) depending on the bandwidth. The analyzed optimum temperature and the grown temperature (4℃/25℃) were applied to extract the growth temperature for each temperature by using the temperature response model analysis. Regression analysis and correlation analysis were performed between the analyzed growth temperature and production data. The coefficient of determination(R²) was analyzed as 0.325 to 0.438, and in the correlation analysis, the correlation coefficient of 0.57 to 0.66 was analyzed at the significance probability 0.001 level. Overall, as the bandwidth increased, the coefficient of determination was higher. However, in all analyses except bandwidth 1.0, it was analyzed that all variables were not used due to bias. The purpose of this study is to accommodate all data through non-linear data. It was analyzed that bandwidth 1.0 with a high coefficient of determination while accepting modeling as a whole is the most suitable.

• Journal of Environmental Impact Assessment
• /
• v.27 no.2
• /
• pp.203-214
• /
• 2018

The purpose of this study is to estimate the concentrated distribution area of nutria (Myocastor coypus) and potential suitable habitat and to provide useful data for the effective management direction setting. Based on the nationwide distribution data of nutria, the cross-validation value was applied to analyze the distribution density. As a result, the concentrated distribution areas thatrequired preferential elimination is found in 14 administrative areas including Busan Metropolitan City, Daegu Metropolitan City, 11 cities and counties in Gyeongsangnam-do and 1 county in Gyeongsangbuk-do. In the potential suitable habitat estimation using a MaxEnt (Maximum Entropy) model, the possibility of emergency was found in the Nakdong River middle and lower stream area and the Seomjin riverlower stream area and Gahwacheon River area. As for the contribution by variables of a model, it showed DEM, precipitation of driest month, min temperature of coldest month and distance from river had contribution from the highest order. In terms of the relation with the probability of appearance, the probability of emergence was higher than the threshold value in areas with less than 34m of altitude, with $-5.7^{\circ}C{\sim}-0.6^{\circ}C$ of min temperature of the coldest month, with 15-30mm of precipitation of the driest month and with less than 1,373m away from the river. Variables that Altitude, existence of water and wintertemperature affected settlement and expansion of nutria, considering the research results and the physiological and ecological characteristics of nutria. Therefore, it is necessary to reflect them as important variables in the future habitable area detection and expansion estimation modeling. It must be essential to distinguish the concentrated distribution area and the management area of invasive alien species such as nutria and to establish and apply a suitable management strategy to the management site for the permanent control. The results in this study can be used as useful data for a strategic management such as rapid management on the preferential management area and preemptive and preventive management on the possible spreading area.