• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.1
• /
• pp.187-194
• /
• 1996

In this paper, we propose regression neural networks based on regression trees. We map regression trees into three layered feedforward networks. We put multi feature split functions in the first layer so that the networks have a better chance to get optimal partitions of input space. We suggest two supervised learning algorithms for the network training and test both in single feature split and multifeature split functions. In experiments, the proposed regression neural networks is proved to have the better learning performance than those of the single feature split regression trees and the single feature split regression networks. Furthermore, we shows that the proposed learning schemes have an effect to prune an over-grown tree without degrading the learning performance.

• Journal of Forest and Environmental Science
• /
• v.29 no.4
• /
• pp.307-313
• /
• 2013

Forest Survey consists of road survey, topographic survey, tree mapping survey, stream survey and also ridge survey. Information from forest survey is important and become essential in preparing base map to be used for forest harvesting planning and control. With the current technologies technique of data processing and mapping from traditionally hand drawn method had shifted to a computer system particularly the use of Computer Aided Design (CAD). This gives great advantages to the forest managers and logging operators. However data processing and mapping duration could be further reduced by integrating CAD with other established software such as Microsoft Excel. This time study to show that there is significance difference in term of duration for data processing and efficiency using AutoCAD in combination with Microsoft Excel program as compare to the use of AutoCAD program alone. From the study, it shows that the integration of AutoCAD and Microsoft Excel is able to reduce 70% of duration for data processing and mapping as compared to the use of AutoCAD program alone.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.32 no.2
• /
• pp.76-84
• /
• 2009

Since too much information has been generated, it became very difficult to find out valuable and necessary information. In order to deal with the problem of information overload, the taxonomy for information visualization techniques has been based upon visualized shapes such as tree map, fisheye view and parallel coordinates, so that it was difficult to choose the right representation technique by data characteristics. Therefore, this study was designed to introduce a new taxonomy for the information visualization by data characteristics which defined by space (3D vs. multi-dimensions), time (continuous vs. discrete), and relations of data (qualitative vs. quantitative). To verify the new taxonomy, forensic data which were generated to investigate the culprit of network security was used. The result showed that the new taxonomy was found to be very efficient and effective to choose the right visualized shape for forensic data for network security. In conclusion, the new taxonomy was proven to be very helpful to choose the right information visualization technique by data characteristics.

• Korean Journal of Environment and Ecology
• /
• v.29 no.1
• /
• pp.46-61
• /
• 2015

The purpose of this study is to investigate a vegetation structure around Tongdosa temple forest and provincial park and to provide preliminary data. In order to look over the vegetation status, an actual vegetation map was drawn around study area. Vegetation structure survey was carried out for 6 representative communities of actual vegetation which were Quercus variavilis community, Carpinus tschonoskii community, Pinus densiflora community, P. densiflora-Broadleaf deciduous Forest community, Q. mongolica community and Broadleaf deciduous Forest community. The area of the Tongdosa district measured $29,202,262m^2$. Actual vegetation type were divided into 35 types, and the ratio of Q. variavilis community was 32.35 % ($9,447,932m^2$). To investigate the structure of 6 representative communities, 58 plots were set up and unit area plots measured $100m^2$. The estimated age of the forest is 50~100-years-old and the oldest tree P. densiflora is 113-years-old.

• The KIPS Transactions:PartD
• /
• v.9D no.4
• /
• pp.579-586
• /
• 2002

This paper propose an efficient algorithm for mining association rules in the large main memory systems. To do this, the paper attempts firstly to extend the conventional algorithms such as DHP and Partition in order to be compatible to the large main memory systems and proposes secondly an algorithm to improve Partition algorithm by applying the techniques of the hash table and the bit map. The proposed algorithm is compared to the extended DHP within the experimental environments and the results show up to 65% performance improvement in comparison to the expanded DHP.

• The KIPS Transactions:PartB
• /
• v.12B no.2 s.98
• /
• pp.203-208
• /
• 2005

We propose an algorithmic approach for handling linguistic values defined in the same linguistic variable. Using the proposed approach, we can explicitly capture the differences of individuals' subjectivity with respect to linguistic values defined in the same linguistic variable. The proposed approach can be employed as a useful tool for discovering hidden relationship among linguistic values defined in the same linguistic variable. Consequently, it provides a basis for improving the precision of knowledge acquisition in the development of fuzzy systems including fuzzy expert systems, fuzzy decision tree, fuzzy cognitive map, ok. In this paper, we apply the proposed approach to a collective linguistic assessment among multiple experts.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.4
• /
• pp.1080-1099
• /
• 2023

Digital healthcare combined with telemedicine services in the form of convergence with digital technology and AI is developing rapidly. Digital healthcare research is being conducted on many conditions including shock. However, the causes of shock are diverse, and the treatment is very complicated, requiring a high level of medical knowledge. In this paper, we propose a shock detection method based on the correlation between shock and data extracted from hemodynamic monitoring equipment. From the various parameters expressed by this equipment, four parameters closely related to patient shock were used as the input data for a machine learning model in order to detect the shock. Using the four parameters as input data, that is, feature values, a random forest-based ensemble machine learning model was constructed. The value of the mean arterial pressure was used as the correct answer value, the so called label value, to detect the patient's shock state. The performance was then compared with the decision tree and logistic regression model using a confusion matrix. The average accuracy of the random forest model was 92.80%, which shows superior performance compared to other models. We look forward to our work playing a role in helping medical staff by making recommendations for the diagnosis and treatment of complex and difficult cases of shock.

• Korean Journal of Remote Sensing
• /
• v.40 no.2
• /
• pp.123-139
• /
• 2024

Forest vertical structure is vital for comprehending ecosystems and biodiversity, in addition to fundamental forest information. Currently, the forest vertical structure is predominantly assessed via an in-situ method, which is not only difficult to apply to inaccessible locations or large areas but also costly and requires substantial human resources. Therefore, mapping systems based on remote sensing data have been actively explored. Recently, research on analyzing and classifying images using machine learning techniques has been actively conducted and applied to map the vertical structure of forests accurately. In this study, Sentinel-2 and digital surface model images were obtained on two different dates separated by approximately one month, and the spectral index and tree height maps were generated separately. Furthermore, according to the acquisition time, the input data were separated into cases 1 and 2, which were then combined to generate case 3. Using these data, forest vetical structure mapping models based on random forest, support vector machine, and extreme gradient boost(XGBoost)were generated. Consequently, nine models were generated, with the XGBoost model in Case 3 performing the best, with an average precision of 0.99 and an F1 score of 0.91. We confirmed that generating a forest vertical structure mapping model utilizing bi-seasonal data and an appropriate model can result in an accuracy of 90% or higher.

• Journal of Korean Society of Forest Science
• /
• v.112 no.1
• /
• pp.40-56
• /
• 2023

Tree species within the Populus genus grow rapidly and have an excellent capacity to absorb carbon, conferring substantial ability to effective purify the environment. Poplar breeding can be achieved rapidly and efficiently if a genetic linkage map is constructed and quantitative trait loci (QTLs) are identified. Here, a high-density genetic linkage map was constructed for the control pollinated progeny using the genotyping-by-sequencing (GBS) technique, which is a next-generation sequencing method. A search was also performed for the genes associated with quantitative traits located in the genetic linkage map by examining the variables of height and diameter at root collar, and resilience to insect damage. The height and diameter at root collar were measured directly, while the ability to recover from insect damage was scored in a 4-year-old breeding population of aspen hybrids (Odae19 × Bonghyeon4 F1) established in the research forest of Seoul National University. After DNA extraction, paternity was confirmed using five microsatellite markers, and only the individuals for which paternity was confirmed were used for the analysis. The DNA was cut using restriction enzymes and the obtained DNA fragments were prepared using a GBS library and sequenced. The analyzed results were sorted using Populus trichocarpa as a reference genome. Overall, 58,040 aligned single-nucleotide polymorphism (SNP) markers were identified, 17,755 of which were used for mapping genetic linkages. The genetic linkage map was divided into 19 linkage groups, with a total length of 2,129.54 cM. The analysis failed to identify any growth-related QTLs, but a gene assumed to be related to recovery from insect damage was identified on linkage group (chromosome) 4 through genome-wide association study.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.1009-1029
• /
• 2023

Urban trees play a vital role in urban ecosystems,significantly reducing impervious surfaces and impacting carbon cycling within the city. Although previous research has demonstrated the efficacy of employing artificial intelligence in conjunction with airborne light detection and ranging (LiDAR) data to generate urban tree information, the availability and cost constraints associated with LiDAR data pose limitations. Consequently, this study employed freely accessible, high-resolution multispectral satellite imagery (i.e., Sentinel-2 data) to estimate fractional tree canopy cover (FTC) within the urban confines of Suwon, South Korea, employing machine learning techniques. This study leveraged a median composite image derived from a time series of Sentinel-2 images. In order to account for the diverse land cover found in urban areas, the model incorporated three types of input variables: average (mean) and standard deviation (std) values within a 30-meter grid from 10 m resolution of optical indices from Sentinel-2, and fractional coverage for distinct land cover classes within 30 m grids from the existing level 3 land cover map. Four schemes with different combinations of input variables were compared. Notably, when all three factors (i.e., mean, std, and fractional cover) were used to consider the variation of landcover in urban areas(Scheme 4, S4), the machine learning model exhibited improved performance compared to using only the mean of optical indices (Scheme 1). Of the various models proposed, the random forest (RF) model with S4 demonstrated the most remarkable performance, achieving R² of 0.8196, and mean absolute error (MAE) of 0.0749, and a root mean squared error (RMSE) of 0.1022. The std variable exhibited the highest impact on model outputs within the heterogeneous land covers based on the variable importance analysis. This trained RF model with S4 was then applied to the entire Suwon region, consistently delivering robust results with an R² of 0.8702, MAE of 0.0873, and RMSE of 0.1335. The FTC estimation method developed in this study is expected to offer advantages for application in various regions, providing fundamental data for a better understanding of carbon dynamics in urban ecosystems in the future.