• Journal of Wetlands Research
• /
• v.16 no.3
• /
• pp.393-401
• /
• 2014

The purpose of this study was to investigate the objective impact in accuracy and reliability with tendency depend on training samples by using the high-resolution images. Supervised classification was performed based on multi-spectral images which made by each satellite and aerial images for considering all of bands' characteristics. The highest accuracy was 84.7% with satellite image(3*3) and 83% with aerial image(5*5) at the accuracy verification phase. Also, the overall accuracy with the consideration of Kappa coefficient were 0.84 for satellite images and 0.82 for aerial images. In all of the images, the smaller training sample was, the higher accuracy showed. Therefore, tree species classification accuracy was tended to rely on training sample size.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.1
• /
• pp.13-20
• /
• 2001

Adaptive digital filters with long impulse response such as acoustic echo canceller and active noise controller suffer from slow convergence and computational burden. Subband techniques and multirate signal processing have been recently developed to improve the problem of computational complexity and slow convergence in conventional adaptive filter. Any FIR transfer function can be realized as a serial connection of interpolators followed by subfilters with a sparse impulse response. In this case, each interpolator which is related to the column vector of Hadamard matrix has band-pass magnitude response characteristics shifted uniformly. Subband technique using Hadamard transform and decimation of subband signal to reduce sampling rate are adapted to system modeling and acoustic noise cancellation In this paper, delayless subband structure with nonuniform bandwidth has been proposed to improve the performance of the convergence speed without aliasing due to decimation, where input signal is split into subband one using tree-structured filter bank, and the subband signal is decimated by a decimator to reduce the sampling rate in each channel, then subfilter with sparse impulse response is transformed to full band adaptive filter coefficient using Hadamard transform. It is shown by computer simulations that the proposed method can be adapted to general adaptive filtering.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.1
• /
• pp.393-401
• /
• 2013

Most traditional databases exploit record-oriented storage model where the attributes of a record are placed contiguously in hard disk to achieve high performance writes. However, for search-mostly datawarehouse systems, column-oriented storage has become a proper model because of its superior read performance. Today, flash memory is largely recognized as the preferred storage media for high-speed database systems. In this paper, we introduce fast column-oriented database model and then propose a new column-aware index management scheme for the high-speed column-oriented datawarehouse system. Our index management scheme which is based on enhanced $B^+$-Tree achieves high search performance by embedded flash index and unused space compression in internal and leaf nodes. Based on the results of the performance evaluation, we conclude that our index management scheme outperforms the traditional scheme in the respect of the search throughput and response time.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.12
• /
• pp.3559-3568
• /
• 1999

The information overload with many information resources is an inevitable problem in modern electronic life. It is more difficult to search some information with user's information needs from an uncontrolled flood of many digital information resources, such as the internet which has been rapidly increased. So, many information retrieval systems have been researched and appeared. In text retrieval systems, they have met with user's information needs. While, in image retrieval systems, they have not properly dealt with user's information needs. In this paper, for resolving this problem, we proposed the intelligent user interface for image retrieval. It is based on HCOS(Human-Computer Symmetry) model which is a layed interaction model between a human and computer. Its' methodology is employed to reduce user's information overhead and semantic gap between user and systems. It is implemented with machine learning algorithms, decision tree and backpropagation neural network, for user adaptation capabilities of intelligent image retrieval system(IIRS).

• Korean Journal of Remote Sensing
• /
• v.19 no.2
• /
• pp.135-147
• /
• 2003

This study used the multistage hierarchical clustering image classification to analyze the satellite images for the land-cover types of an area in the Korean peninsula. The multistage algorithm consists of two stages. The first stage performs region-growing segmentation by employing a hierarchical clustering procedure with the restriction that pixels in a cluster must be spatially contiguous, and finally the whole image space is segmented into sub-regions where adjacent regions have different physical properties. Without spatial constraints for merging, the second stage clusters the segments resulting from the previous stage. The image classification of hierarchical clustering, which merges step-by step two small groups into one large one based on the hierarchical structure of digital imagery, generates a hierarchical tree of the relation between the classified regions. The experimental results show that the hierarchical tree has the detailed information on the hierarchical structure of land-use and more detailed spectral information is required for the correct analysis of land-cover types.

• Journal of the Korean Society for information Management
• /
• v.36 no.2
• /
• pp.57-77
• /
• 2019

Random Forest (RF), a representative ensemble technique, was applied to automatic classification of journal articles in the field of library and information science. Especially, I performed various experiments on the main factors such as tree number, feature selection, and learning set size in terms of classification performance that automatically assigns class labels to domestic journals. Through this, I explored ways to optimize the performance of random forests (RF) for imbalanced datasets in real environments. Consequently, for the automatic classification of domestic journal articles, Random Forest (RF) can be expected to have the best classification performance when using tree number interval 100~1000(C), small feature set (10%) based on chi-square statistic (CHI), and most learning sets (9-10 years).

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.12
• /
• pp.445-452
• /
• 2022

Class distribution of unbalanced data is an important part of the digital world and is a significant part of cybersecurity. Abnormal activity of unbalanced data should be found and problems solved. Although a system capable of tracking patterns in all transactions is needed, machine learning with disproportionate data, which typically has abnormal patterns, can ignore and degrade performance for minority layers, and predictive models can be inaccurately biased. In this paper, we predict target variables and improve accuracy by combining estimates using Synthetic Minority Oversampling Technique (SMOTE) and Light GBM algorithms as an approach to address unbalanced datasets. Experimental results were compared with logistic regression, decision tree, KNN, Random Forest, and XGBoost algorithms. The performance was similar in accuracy and reproduction rate, but in precision, two algorithms performed at Random Forest 80.76% and Light GBM 97.16%, and in F1-score, Random Forest 84.67% and Light GBM 91.96%. As a result of this experiment, it was confirmed that Light GBM's performance was similar without deviation or improved by up to 16% compared to five algorithms.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.5
• /
• pp.325-330
• /
• 2023

This paper proposes to apply machine learning to the process of predicting the slab thickness based on the structural analysis results or experience and subjectivity of engineers in the design of bridge data construction to enable digital-based decision-making. This study aims to build a reliable design environment by utilizing machine learning techniques to provide guide values to engineers in addition to structural analysis for slab thickness selection. Based on girder bridges, which account for the largest proportion of bridge data, a prediction model process for predicting slab thickness among superstructures was defined. Various machine learning models (Linear Regress, Decision Tree, Random Forest, and Muliti-layer Perceptron) were competed for each process to produce the prediction value for each process, and the optimal model was derived. Through this study, the applicability of machine learning techniques was confirmed in areas where slab thickness was predicted only through existing structural analysis, and an accuracy of 95.4% was also obtained. models can be utilized in a more reliable construction environment if the accuracy of the prediction model is improved by expanding the process

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.7 no.2
• /
• pp.132-140
• /
• 2005

This study was conducted to develop regional site index equations for main tree species in Gangwon, Gyunggi-Chungcheong, Gyungsang, and Jeolla area of Korea, using environmental and soil factors obtained from a digital forest site map. Using the large data set obtained from the digital forest map, a total of 28 environmental and soil factors were regressed on site index by tree species for developing the best site index equations for each of the regions. The selected main tree species were Larix 1eptolepis, Pinus koraiensis, Pinus densiflora, Pinus thunbergii, and Quercus acutissima. Finally, four to five environmental and soil factors by species were chosen as independent variables in defining the best regional site index equations with the highest coefficients of determination $(R^2)$. For those site index equations, three evaluation statistics such as mean difference, standard deviation of difference and standard error of difference were applied to the data sets independently collected from fields within the region. According to the evaluation statistics, it was found that the regional site index equations by species developed in this study conformed well to the independent data set, having relatively low bias and variation. It was concluded that the regional site index equations by species had sufficient capability for the estimation of site productivity.

• Journal of Digital Convergence
• /
• v.13 no.8
• /
• pp.375-385
• /
• 2015

This study aims to identify geographical variations and factors that affect smoking rates. The data are collected from the Community Health Survey conducted between 2009 and 2011 by Korea Centers for Disease Control and Prevention and other government organizations. Correlation and multiple regression analysis were used to examine the factors influencing smoking rates. For the purpose of investigating regional variations, we employed a decision tree model. The study has found that the significant factors associated with geographical variations in the smoking rates were the rate of hazardous drinking, the completion rate of hypertension education, the experience rate of anti-smoking campaigns, stress awareness rate, hypertension prevalence, health insurance cost, diabetes prevalence, obesity rate, and strength training rate. Convergence-based analysis on geographical variations of the smoking rates is highly important when the regionally customized healthcare programs is implemented. In the future, it is necessary to develop effective program and customized approach for the regions of high smoking rates. Our study is expected to be used as meaningful data for the design of effective health care programs and assessments to lead effective non-smoking program.