• Journal of Korean Society of Forest Science
• /
• v.112 no.2
• /
• pp.173-187
• /
• 2023

The forest protection policies implemented in South Korea have resulted in the significant accumulation of forest. Moreover, the associated public interest has also been closely evaluated. As forests mature, there arises a need for forest management (FM) practices, such as thinning and harvesting. It is therefore essential to perform a scientific analysis of the long-term effects of FM. In this study, conducted in Mt. Gariwang, the effect of FM on forest succession and wood production (WP) were evaluated based on changes in aboveground biomass (AGB) using the LANDIS-II model. The FM consists of three scenarios (Selection, Shelterwood, and Two-stories), characterized based on the harvest intensity, frequency, and period. The model was applied to changes in the forest over 200 years. All scenarios show that the total AGB decreased immediately after thinning and harvesting. However, AGB recovery time differed among scenarios, with recovery to preharvest level occurring from 15 to 50 years after harvest; further, after 200 years, harvested forests had a greater total AGB than forests without FMs In particular, the changes in AGB of each species was different depending on its shade tolerance. The AGB of currently dominant shade-intolerant and mid-tolerant species decreased dramatically after harvesting. However, shade-tolerant species, dominant in the understory, continued to grow but were not harvested due to their small size. The cumulative WP for each scenario was estimated at 545.6, 141.6, and 299.9 tons/ha in Selection, Shelterwood, and Two-stories, respectively. The composition of WP differed according to harvest intensity and period. Most WP originated from shade-intolerant and mid-tolerant species in the early period. Later, most WP was from shade-tolerant species, which became dominant. The modeling approach used in this study is capable of analyzing the long-term effects of FM on changes in forests and WP. This study can contribute to decision making to guide FM methods for a variety of purposes, including WP and controlling forest composition and structure.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.2
• /
• pp.90-95
• /
• 2012

Remotely sensed data provide valuable information on land monitoring due to multi-temporal observation over large areas. Especially, high resolution imagery with 0.6~1.0 m spatial resolutions contain a wealth of information and therefore are very useful for thematic mapping and monitoring change in urban areas. Recently, remote sensing technology has been successfully utilized for natural disaster monitoring such as forest fire, earthquake, and floods. In this paper, an efficient change detection method based on texture differences observed from high resolution multi-temporal data sets is proposed for mapping disaster damage and extracting damage information. It is composed of two parts: feature extraction and detection process. Timely and accurate information on disaster damage can provide an effective decision making and response related to damage.

• Journal of Korea Technical Association of The Pulp and Paper Industry
• /
• v.34 no.5
• /
• pp.63-69
• /
• 2002

A new concept of stock preparation for the increase of bending stiffness in paper and board was proposed. The "stiff" fibers, which were mechanically not treated or treated slightly to remove fiber curls, were combined with extensively refined fibers (ERF) to produce higher stiffness papers than those where the whole fibers were refined. The combination of "stiff" fibers and extensively refined fibers produced higher stiffness at the same tensile strength than the control furnish, in which all the fibers are refined together. In this concept, the fibers from recycled papers could be as much useful as the virgin fibers as long as they are stiff enough or they can produce highly bondable fiber fractions by extensive refining. Use of the concept in real paper mill needs considerations such as increase of refining energy, slower drainage, and added drying burden, but savings of wood fibers, utilization of more recycled fibers, and increase of physical properties may offset the negative concerns. The success of this concept implementation in mills, therefore, depends on the wood fiber market around the mills and the proper decision making for the papermakers about how to apply this concept. apply this concept.

• Steel and Composite Structures
• /
• v.53 no.4
• /
• pp.377-399
• /
• 2024

Accurately predicting the bearing capacity of steel and concrete piles is a critical factor in the design and safety of deep foundations. This study presents a novel application of hybrid machine learning models, specifically Invasive Weed Optimization with Multilayer Perceptron (IWOMLP) and Harris Hawks Optimization with Multilayer Perceptron (HHOMLP), for enhancing the prediction of pile bearing capacity. These hybrid models integrate evolutionary optimization algorithms with neural networks, aiming to improve prediction accuracy by addressing the nonlinearities and complexities in pile-soil interaction. The study compares the performance of IWOMLP and HHOMLP against conventional machine learning methods such as Simple Linear Regression, Gaussian Processes, Random Forest, and others. The training and testing phases evaluate the models based on various error metrics, including R², RMSE, MAE, and additional advanced metrics. The key innovation in this research lies in combining optimization techniques with neural networks, which significantly enhances the model's ability to predict complex geotechnical properties. The primary goal of this work is to develop a reliable, data-driven approach for accurate pile capacity prediction, providing a more precise tool for geotechnical engineers to improve decision-making in foundation design. Results indicate that the hybrid models, particularly IWOMLP, outperform traditional approaches, achieving higher R² and lower RMSE values. This research demonstrates the potential of hybrid models to advance geotechnical engineering practices by delivering more accurate and reliable predictions.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.18 no.1
• /
• pp.1-12
• /
• 2015

Beginning of the human ecology in 1920s, the efforts for applying the environmental values to a policy have been embodied by the enactments of international agreement and relevant laws. The government has been struggling to adopt the environmental values for the policy by enacting the relevant laws and establishing the environmental value evaluation information (environmental conservation value assessment map, eco-natural map, biotope map). In spite of the efforts to apply the environmental value assessment information for the habitat potential of wildlife, the application is being challenged by the discrepancy in methods and criteria. Thus this study intends to measure the potential of wildlife habitat and apply it to the spatial value classification for the application plan of wildlife habitat potential in policy. Maxent was used for the habitat potential and the land types were classified depending on the surface and land use pattern of cadastral map. As a result, the policy matrix including conservation strategy(CS), restoration strategy(RS), practical use strategy(PS) and development strategy(DS) has been deduced as CS $13.05km^2$(2.38%), RS $1.64km^2$(0.30%), PS $162.42km^2$(29.57%) and DS $8.56km^2$(1.56%). CS was emerged mostly on forest valleys and farmlands, and RS was appeared in the road area near the conservation strategy areas. Boryung downtown and Daecheon Beach were the center of DS, while the forest and farmlands were presented as PS. It is significant that this study suggest the new approaching method by comparing the wildlife habitat potential with the land type. Since this study evaluated the environmental value by one species of leopard cat (Prionailurusbengalensis) with Maxent model, it is necessary to apply the habitat potential measuring method for various target species as further research.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.9
• /
• pp.1153-1158
• /
• 2018

Online customer evaluations and social media information among a variety of information sources are critical for businesses as it influences the customer's decision making. There are limitations on the time and money that the survey will ask to identify a variety of customers' needs and complaints. The customer review data at online shopping malls provide the ideal data sources for analyzing customer sentiment about their products. In this study, we collected product reviews data on the smartphone of Samsung and Apple from Amazon. We applied five classification algorithms which are used as representative sentiment analysis techniques in previous studies. The five algorithms are based on support vector machines, bagging, random forest, classification or regression tree and maximum entropy. In this study, we proposed entropy score which can comprehensively evaluate the performance of classification algorithm. As a result of evaluating five algorithms using an entropy score, the SVMs algorithm's entropy score was ranked highest.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.6 no.1
• /
• pp.61-69
• /
• 2004

A long-term growth simulation was performed at 99 land units in Yeoncheon county to test the potential adaptability of each land unit for growing soybean cultivars. The land units for soybean cultivation(CZU), each represented by a geographically referenced land patch, were selected based on land use, soil characteristics, and minimum arable land area. Monthly climatic normals for daily maximum and minimum temperature, precipitation, number of rain days and solar radiation were extracted for each CZU from digital climate models(DCM). The DCM grid cells falling within a same CZU were aggregated to make spatially explicit climatic normals relevant to the CZU. A daily weather dataset for 30 years was randomly generated from the monthly climatic normals of each CZU. Growth and development parameters of CROPGRO-soybean model suitable for 2 domestic soybean cultivars were derived from long-term field observations. Three foreign cultivars with well established parameters were also added to this study, representing maturity groups 3, 4, and 5. Each treatment was simulated with the randomly generated 30 years' daily weather data(from planting to physiological maturity) for 99 land units in Yeoncheon to simulate the growth and yield responses to the inter-annual climate variation. The same model was run with input data from the Crop Experiment Station in Suwon to obtain a 30 year normal performance of each cultivar, which was used as a "reference" for evaluation. Results were analyzed with respect to spatial and temporal variation in yield and maturity, and used to evaluate the suitability of each land unit for growing a specific cultivar. A computer program(MAPSOY) was written to help utilize the results in a decision-making procedure for agrotechnology transfer. transfer.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.4 no.3
• /
• pp.133-140
• /
• 2002

Site-specific minimum temperature forecasts are critical in a short-term decision making procedure for preventive measures as well as a long-term strategy such as site selection in fruits industry. Nocturnal cold air pools frequently termed in mountainous areas under anticyclonic systems are very dangerous to the flowering buds in spring over Korea, but the spatial resolution to detect them exceeds the current weather forecast scale. To supplement the insufficient spatial resolution of official forecasts, we developed a GIS - assisted frost risk assesment scheme for using in mountainous areas. Daily minimum temperature data were obtained from 6 sites located in a 2.1 by 2.1 km area with complex topography near the southern edge of Sobaek mountains during radiative cooling nights in spring 2001. A digital elevation model with a 10 m spatial resolution was prepared for the entire study area and the cold air inflow was simulated for each grid cell by counting the number of surrounding cells coming into the processing cell. Primitive temperature surfaces were prepared for the corresponding dates by interpolating the Korea Meteorological Administration's automated observational data with the lapse rate correction. The cell temperature values corresponding to the 6 observation sites were extracted from the primitive temperature surface, and subtracted from the observed values to obtain the estimation error. The errors were regressed to the flow accumulation at the corresponding cells, delineating a statistically significant relationship. When we applied this relationship to the primitive temperature surfaces of frost nights during April 2002, there was a good agreement with the observations, showing a feasibility of site-specific frost warning system development in mountainous areas.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.37-43
• /
• 2021

This study proposed an effective automatic classification technique to identify dropout patterns of university students, and based on this, an intelligent recommender system to prevent dropouts. To this end, 1) a data processing method to improve the performance of machine learning was proposed based on actual enrollment/dropout data of university students, and 2) performance comparison experiments were conducted using five types of machine learning algorithms. 3) As a result of the experiment, the proposed method showed superior performance in all algorithms compared to the baseline method. The precision rate of discrimination of enrolled students was measured to be up to 95.6% when using a Random Forest(RF), and the recall rate of dropout students was measured to be up to 80.0% when using Naive Bayes(NB). 4) Finally, based on the experimental results, a method for using a counseling recommender system to give priority to students who are likely to drop out was suggested. It was confirmed that reasonable decision-making can be conducted through convergence research that utilizes technologies in the IT field to solve the educational issues, and we plan to apply various artificial intelligence technologies through continuous research in the future.

• Journal of Environmental Science International
• /
• v.32 no.12
• /
• pp.933-941
• /
• 2023

Since the Industrial Age, economic activities have raised environmental concerns, emphasizing the importance of biodiversity conservation areas. However, a fundamental contradiction exists between conservation and utilization, leading to conflicting interests. In light of these issues, the aim of this study was to propose efficient operational strategies for future urban biodiversity conservation areas, while also promoting local community economic development. Accordingly, the focus was the Gwangneung Forest Biosphere Reserve as a case study. The findings reveal the following. First, all local residents recognize the importance of the biosphere reserve and hold a high regard for its direct role in conservation. Second, developing and promoting brands appears to have a more positive impact on local economic activation than activating projects linked to the biosphere reserve. Simultaneously, local residents have expressed negative evaluations of indiscriminate facility development, fearing reckless expansion. Third, if governance is promoted in the future, community participation will likely increase, leading to a strengthening of conservation awareness and the establishment of a framework among local residents and those in adjacent areas. Findings of this study are expected to serve as fundamental data for establishing effective communication among local residents in protected areas facing similar challenges, thus facilitating efficient decision-making processes.