• Proceedings of The Korean Society of Agricultural and Forest Meteorology Conference
• /
• 2019.08a
• /
• pp.157-158
• /
• 2019

• Journal of Korean Society of Forest Science
• /
• v.65 no.1
• /
• pp.68-73
• /
• 1984

The purpose of this paper was to figure out the efficiencies of two sampling techniques, a simple random sampling and a two-stage P.P.S. (probability proportional to size) sampling, in estimating the volume of the mature coniferous stands near Salzburg, Austria. With black-and-white infrared photographs at a scale 1:10,000, the following four classes were considered; non-forest, young stands less than 40 years, mature beech and mature coniferous stands. After the classification, a field survey was carried out using a relascope with a BAF (basal area factor) 4. For the simple random sampling, 99 points were sampled, while for the P.P.S. sampling, 75 points were sampled in the mature coniferous stands. The following results were obtained. 1) The mean standing coniferous volume estimate was $422.0m^3/ha$ for the simple random sampling and $433.5m^3/ha$ for the P.P.S. sampling method. However, the difference was not statistically significant. 2) The required number of sampling points for a 5% sampling error were 170 for the two stage P.P.S. sampling, but 237 for the simple random sampling. 3) The two stage P.P.S. method reduced field survey time by 17% as compared to the simple random sampling.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.1
• /
• pp.1-9
• /
• 2013

This paper propose a human action recognition method that uses bag-of-features (BoF) based on CS-LBP (center-symmetric local binary pattern) and a spatial pyramid in addition to the random forest classifier. To construct the BoF, an image divided into dense regular grids and extract from each patch. A code word which is a visual vocabulary, is formed by k-means clustering of a random subset of patches. For enhanced action discrimination, local BoF histogram from three subdivided levels of a spatial pyramid is estimated, and a weighted BoF histogram is generated by concatenating the local histograms. For action classification, a random forest, which is an ensemble of decision trees, is built to model the distribution of each action class. The random forest combined with the weighted BoF histogram is successfully applied to Standford Action 40 including various human action images, and its classification performance is better than that of other methods. Furthermore, the proposed method allows action recognition to be performed in near real-time.

• Journal of Information Processing Systems
• /
• v.17 no.1
• /
• pp.75-88
• /
• 2021

Automobile credit business has developed rapidly in recent years, and corresponding default phenomena occur frequently. Credit default will bring great losses to automobile financial institutions. Therefore, the successful prediction of automobile credit default is of great significance. Firstly, the missing values are deleted, then the random forest is used for feature selection, and then the sample data are randomly grouped. Finally, six prediction models of support vector machine (SVM), random forest and k-nearest neighbor (KNN), logistic, decision tree, and artificial neural network (ANN) are constructed. The results show that these six machine learning models can be used to predict the default of automobile credit. Among these six models, the accuracy of decision tree is 0.79, which is the highest, but the comprehensive performance of SVM is the best. And random grouping can improve the efficiency of model operation to a certain extent, especially SVM.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.5
• /
• pp.358-365
• /
• 2016

We propose a novel application of random forest, a machine learning-based general classification algorithm, to analyze the influence of design attributes on the silicon-to-SPICE (S2S) gap. To improve modeling accuracy, we introduce magnification of learning data as well as randomization for the counting of design attributes to be used for each tree in the forest. From the automatically generated decision trees, we can extract the so-called importance and impact indices, which identify the most significant design attributes determining the S2S gap. We apply the proposed method to actual silicon data, and observe that the identified design attributes show a clear trend in the S2S gap. We finally unveil 10nm key fin-shaped field effect transistor (FinFET) structures that result in a large S2S gap using the measurement data from 10nm test vehicles specialized for model-hardware correlation.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.660-661
• /
• 2020

본 논문에서는 기존 인공 신경망 기반 시계열 학습 기법인 Recurrent Neural Network (RNN)의 많은 연산량 및 고 사양 시스템 요구를 개선하기 위해 랜덤 포레스트 (Random Forest)기반의 새로운 시계열 학습 기법을 제안한다. 기존의 RNN 기반 방법들은 복잡한 연산을 통해 높은 성능을 달성하는 데 집중하고 있다. 이러한 방법들은 학습에 많은 파라미터가 필요할 뿐만 아니라 대규모의 연산을 요구하므로 실시간 시스템에 적용하는데 어려움이 있다. 따라서 본 논문에서는, 효율적이면서 빠르게 동작할 수 있는 시계열 다층 랜덤 포레스트(Time series Multilayered Random Forest)를 제안하고 산불 조기 탐지에 적용해 기존 RNN 계열의 방법들과 성능을 비교하였다. 다양한 산불화재 실험데이터에 알고리즘을 적용해본 결과 GPU 상에서 방대한 연산을 수행하는 RNN 기반 방법들과 비교해 성능적인 한계가 존재했지만 CPU 에서도 빠르게 동작 가능하므로 성능의 개선을 통해 다양한 임베디드 시스템에 적용 가능하다.

• Journal of Korean Society of Forest Science
• /
• v.95 no.4
• /
• pp.388-392
• /
• 2006

To investigate physiological characteristics and genetic diversity of Rhizina undulata isolates distributed in Korea, cultural characteristics and random amplified polymorphic DNA (RAPD) of 13 Rhizina undulata isolates from Pinus densiflora and P. thunbergi stands were analyzed. There were no correlations between the host species of R. undulata isolates and the mycelial growth of R. undulata isolates on culture media supplemented with water-soluble extract from the two different host species, i.e., Pinus densiflora and P. thunbergi. Genetic diversity of genomic DNA from 13 R. undulata isolates was analyzed by RAPD using 12 random primers. There was no differentiation in RAPD profiles among the isolates from Korea. But, there was some differentiation in RAPD profiles between Korean isolates and Japanese isolates, with 88% homology by phylogenetic tree analysis.

• The Journal of Engineering Geology
• /
• v.34 no.1
• /
• pp.107-115
• /
• 2024

This study assesses forest fire susceptibility in Gangwon-do, South Korea, which hosts the largest forested area in the nation and constitutes ~21% of the country's forested land. With 81% of its terrain forested, Gangwon-do is particularly susceptible to wildfires, as evidenced by the fact that seven out of the ten most extensive wildfires in Korea have occurred in this region, with significant ecological and economic implications. Here, we analyze 480 historical wildfire occurrences in Gangwon-do between 2003 and 2019 using 17 predictor variables of wildfire occurrence. We utilized three machine learning algorithms—random forest, logistic regression, and support vector machine—to construct wildfire susceptibility prediction models and identify the best-performing model for Gangwon-do. Forest and soil map data were integrated as important indicators of wildfire susceptibility and enhanced the precision of the three models in identifying areas at high risk of wildfires. Of the three models examined, the random forest model showed the best predictive performance, with an area-under-the-curve value of 0.936. The findings of this study, especially the maps generated by the models, are expected to offer important guidance to local governments in formulating effective management and conservation strategies. These strategies aim to ensure the sustainable preservation of forest resources and to enhance the well-being of communities situated in areas adjacent to forests. Furthermore, the outcomes of this study are anticipated to contribute to the safeguarding of forest resources and biodiversity and to the development of comprehensive plans for forest resource protection, biodiversity conservation, and environmental management.

• The KIPS Transactions:PartB
• /
• v.18B no.6
• /
• pp.341-348
• /
• 2011

ECG(Electrocardiogram), a field of Bio-signal, is generally experimented with classification algorithms most of which are SVM(Support Vector Machine), MLP(Multilayer Perceptron). But this study modified the Random Forest Algorithm along the basis of signal characteristics and comparatively analyzed the accuracies of modified algorithm with those of SVM and MLP to prove the ability of modified algorithm. The R-R interval extracted from ECG is used in this study and the results of established researches which experimented co-equal data are also comparatively analyzed. As a result, modified RF Classifier showed better consequences than SVM classifier, MLP classifier and other researches' results in accuracy category. The Band-pass filter is used to extract R-R interval in pre-processing stage. However, the Wavelet transform, median filter, and finite impulse response filter in addition to Band-pass filter are often used in experiment of ECG. After this study, selection of the filters efficiently deleting the baseline wandering in pre-processing stage and study of the methods correctly extracting the R-R interval are needed.

• Journal of Cadastre & Land InformatiX
• /
• v.50 no.1
• /
• pp.181-200
• /
• 2020

This study used the OLS model to estimate the determinants affecting the tenure of a home and then compared the predictive power of each model with SVM, Decision Tree, Random Forest, Gradient Boosting, XGBooest and LightGBM. There is a difference from the preceding study in that the Stacking model, one of the ensemble models, can be used as a base model to establish a more predictable model to identify the volume of housing transactions in the housing market. OLS analysis showed that sales profits, housing prices, the number of household members, and the type of residential housing (detached housing, apartments) affected the period of housing ownership, and compared the predictability of the machine learning model with RMSE, the results showed that the machine learning model had higher predictability. Afterwards, the predictive power was compared by applying each machine learning after rebuilding the data with the influencing variables, and the analysis showed the best predictive power of Random Forest. In addition, the most predictable Random Forest, Decision Tree, Gradient Boosting, and XGBooost models were applied as individual models, and the Stacking model was constructed using Linear, Ridge, and Lasso models as meta models. As a result of the analysis, the RMSE value in the Ridge model was the lowest at 0.5181, thus building the highest predictive model.