• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.614-630
• /
• 2023

Dead trees significantly impact forest production and the ecological environment and pose constraints to the sustainable development of forests. A lightweight YOLOv4 dead tree detection algorithm based on unmanned aerial vehicle images is proposed to address current limitations in dead tree detection that rely mainly on inefficient, unsafe and easy-to-miss manual inspections. An improved logarithmic transformation method was developed in data pre-processing to display tree features in the shadows. For the model structure, the original CSPDarkNet-53 backbone feature extraction network was replaced by MobileNetV3. Some of the standard convolutional blocks in the original extraction network were replaced by depthwise separable convolution blocks. The new ReLU6 activation function replaced the original LeakyReLU activation function to make the network more robust for low-precision computations. The K-means++ clustering method was also integrated to generate anchor boxes that are more suitable for the dataset. The experimental results show that the improved algorithm achieved an accuracy of 97.33%, higher than other methods. The detection speed of the proposed approach is higher than that of YOLOv4, improving the efficiency and accuracy of the detection process.

• Journal of the Korean Wood Science and Technology
• /
• v.43 no.6
• /
• pp.826-837
• /
• 2015

In this study, we produced bioethanol from the original hydrolysate obtained during oxalic acid pretreatment of lignocellulosic biomass. The bioethanol was separated and concentrated by pervaporation and the residue after pervaporation was evaluated for its antioxidant activity. Xylose ($37.28g/{\ell}$) was the major product in the original hydrolysate. The original hydrolysate contained acetic acid, furfural and total phenolic compounds (TPC) as fermentation inhibitors. Acetic acid was removed by electrodialysis (ED), and $12.21g/{\ell}$ of bioethanol was produced from ED-treated hydrolysate. The TPC of ethyl acetate extracts from the residue obtained (OA-E) during pervaporation was 86.81 mg/100 g (extract). The $IC_{50}$ values of DPPH and ABTS radical scavenging activities, and reducing power of OA-E were $0.87mg/m{\ell}$, $0.85mg/m{\ell}$, and $0.59mg/m{\ell}$, respectively. Sugar degradation products and the phenolic compounds in OA-E were determined by GC-MS.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.179-179
• /
• 2023

This study suggests a new approach of water level forecasting for extended lead times using original data preprocessing with variational mode decomposition (VMD). Here, two machine learning algorithms including light gradient boosting machine (LGBM) and random forest (RF) were considered to incorporate extended lead times (i.e., 5, 10, 15, 20, 25, 30, 40, and 50 days) forecasting of water levels. At first, the original data at two water level stations (i.e., SW173 and SW269 in Bangladesh) and their decomposed data from VMD were prepared on antecedent lag times to analyze in the datasets of different lead times. Mean absolute error (MAE), root mean squared error (RMSE), and mean squared error (MSE) were used to evaluate the performance of the machine learning models in water level forecasting. As results, it represents that the errors were minimized when the decomposed datasets were considered to predict water levels, rather than the use of original data standalone. It was also noted that LGBM produced lower MAE, RMSE, and MSE values than RF, indicating better performance. For instance, at the SW173 station, LGBM outperformed RF in both decomposed and original data with MAE values of 0.511 and 1.566, compared to RF's MAE values of 0.719 and 1.644, respectively, in a 30-day lead time. The models' performance decreased with increasing lead time, as per the study findings. In summary, preprocessing original data and utilizing machine learning models with decomposed techniques have shown promising results for water level forecasting in higher lead times. It is expected that the approach of this study can assist water management authorities in taking precautionary measures based on forecasted water levels, which is crucial for sustainable water resource utilization.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.2 no.3
• /
• pp.75-79
• /
• 2000

Calibrations of fast-response krypton hygrometers were carried out using a dew-point hygrometer to investigate the changes in their absorption coefficients due to long-term field operation. Absorption coefficients changed proportionally with the number of hours of field operation. The increase in absorption coefficient indicates that the water vapor flux, calculated with the original absorption coefficient, would underestimate the true flux in the field. To minimize the uncertainty in quantifying evapotranspiration and surface energy budget studies, frequent calibrations (for example, every 1500 hours of field operation) of krypton hygrometer are recommended.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.8 no.2
• /
• pp.81-94
• /
• 2005

The purpose of this study is to test the applicability of landscape metrics for quantifying and monitoring the landscape structure in the Geumho River watershed, which has undergone heavy environmental disturbances. Landscape metrics were computed from land cover maps(1985, 1999) for the forest patches. The number of variables were reduced from 12 metrics to 3 factors through factor analysis. These factors accounted for above 91% of the variation in the original metrics. We also determined the relative effects of land development on the changes of forest landscape structure using multiple linear regression analysis. At the forest patches, the conversion of forest to urban areas and agriculture resulted in increased fragmentation. Patch area and patch size decreased. and patch density increased as a result of the conversion of forest to agriculture($R^2=0.696$, p<0.01). The heterogeneity of patch size and complexity of patch shape mainly decreased as a result of the conversion of forest to urban areas($R^2=0.405$, p<0.01). The density of core area and edge showed the tendency increase, but there was no relationship with the conversion of forest to urban area and agriculture The future research will be needed to analyze correlations between landscape structures and specific environmental and socioeconomic landscape functions.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.7 no.5
• /
• pp.26-37
• /
• 2004

Most domestic small rivers and streams due to industrialization and urbanization have managed by concrete structures. The environmental functions of the river and stream are disappearing and urban streams play only the role of drainage systems. Also, the researches to restore natural streams are something yet to develop and not established the restoration for ecological functions of a small stream. Therefore the researches are required to develop ecological engineering system for watershed management system to handle various pollutants with restoration for ecological functions of a small stream. To develop this, the ecological engineering system for watershed management system could be developed with ecological conservation. In addition, ecological engineering system for watershed management system should be prior to conserve the habitat of biological resources and water conservation and applied to the original shape of streams. Also, it should be designed to restore the micro-topography of stream, the habitat of plant population in watershed. It is needed to develop the integrated researches to restore a small stream ecosystem.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.25 no.3
• /
• pp.222-233
• /
• 1997

Riparian zone occupies not more than 5% of the total watershed area and can be considered in between the terrestrial and aquatic ecology as that does not fall under both of them. Unlike to common terrestrial plant that can e seen on other land, the riparian vegetation that exist in riparian zone can be classified into various groups because of their peculiar living form. The recognition of importance of terrestrial environment has considered the importance of natural river due to which even today, the movement throughout the world to retrograde the river development is taking place customarily. In this research, noticing the actual condition of the river management reality, the original capacity of river landscaping of Han river has been quantified grasping the actual condition of riparian vegetation from distribution area surveying and analysis. The objective of the research is to find out the river retrogression and maintenance methods based on the ecological environmental quality around the river by maintaining the river plants having high natural capacity and river planning method based on the harmony between conservation of river environment and use of riparian zone.

• Journal of Korean Society of Forest Science
• /
• v.90 no.6
• /
• pp.788-791
• /
• 2001

An improved double-cylinder hammer-driven sampling device was designed to extract undisturbed soil cores. The improvements consist of 1) separation of hammer from the driving head, 2) a split inside cylinder, and 3) a plastic sample holder. Pushing the sampler deep into the soil before hammering would result in less compression of the sample. Core samples should be taken in soils of medium moisture content. The improved soil core sampler provides sufficiently accurate volumetric soil samples with original soil layers and soil cores of 40cm in length and 5cm in diameter.

• The Journal of Information Systems
• /
• v.33 no.3
• /
• pp.175-185
• /
• 2024

Purpose This study aims to analyze the relationship between consumption patterns and default risk among financially vulnerable households in a rapidly changing economic environment. Financially vulnerable households are more susceptible to economic shocks, and their consumption patterns can significantly contribute to an increased risk of default. Therefore, this study seeks to provide a systematic approach to predict and manage these risks in advance. Design/methodology/approach The study utilizes data from the Korea Welfare Panel Study (KOWEPS) to analyze the consumption patterns and default status of financially vulnerable households. To address the issue of data imbalance, sampling techniques such as SMOTE, SMOTE-ENN, and SMOTE-Tomek Links were applied. Various machine learning algorithms, including Logistic Regression, Decision Tree, Random Forest, and Support Vector Machine (SVM), were employed to develop the prediction model. The performance of the models was evaluated using Confusion Matrix and F1-score. Findings The findings reveal that when using the original imbalanced data, the prediction performance for the minority class (default) was poor. However, after applying imbalance handling techniques such as SMOTE, the predictive performance for the minority class improved significantly. In particular, the Random Forest model, when combined with the SMOTE-Tomek Links technique, showed the highest predictive performance, making it the most suitable model for default prediction. These results suggest that effectively addressing data imbalance is crucial in developing accurate default prediction models, and the appropriate use of sampling techniques can greatly enhance predictive performance.

• Journal of Plant Biology
• /
• v.5 no.3
• /
• pp.37-38
• /
• 1962

The original plant for a medicine, Forsythia collected from Wui-Sung country, Kyungsangpuk-do, Korea, was identified as Forsythia viridissima by its characteristic greenish bark and clearly square stem as observed from the culture works at the Forest Experiment Station of Sung Kyung Kwan University. F. viridissima, an indigenic plant of China, is believed to be introduced to Korea as a nursary stock or brought by seeds sometime in the past. In Korea at present two other species of Forsythia, namely, F. suspensaa and F. japonica have also been cultured besides F. viridissima as an ornamental.