• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.433-439
• /
• 1998

In this paper, we present an approach to the structure identification based on the input space partition methods and to the parameter identification by hybrid learning method in neuro-fuzzy system. The structure identification can automatically estimate the number of membership function and fuzzy rule using grid partition, tree partition, scatter partition from numerical input-output data. And then the parameter identification is carried out by the hybrid learning scheme using back-propagation and least squares estimate. Finally, we sill show its usefulness for neuro-fuzzy modeling to truck backer-upper control.

• Journal of the Korean Society of Safety
• /
• v.36 no.5
• /
• pp.52-60
• /
• 2021

As the prevention of fatal accidents is considered an essential part of social responsibilities, both government and individual have devoted efforts to mitigate the unsafe conditions and behaviors that facilitate accidents. Several studies have analyzed the factors that cause fatal accidents and compared them to those of non-fatal accidents. However, studies on mathematical and systematic analysis techniques for identifying the features of fatal accidents are rare. Recently, various industrial fields have employed machine learning algorithms. This study aimed to apply machine learning algorithms for the classification of fatal and non-fatal accidents based on the features of each accident. These features were obtained by text mining literature on accidents. The classification was performed using four machine learning algorithms, which are widely used in industrial fields, including logistic regression, decision tree, neural network, and support vector machine algorithms. The results revealed that the machine learning algorithms exhibited a high accuracy for the classification of accidents into the two categories. In addition, the importance of comparing similar cases between fatal and non-fatal accidents was discussed. This study presented a method for classifying accidents using machine learning algorithms based on the reports on previous studies on accidents.

• The Journal of the Korea Contents Association
• /
• v.22 no.2
• /
• pp.545-558
• /
• 2022

The purpose of this study is to explore a prediction model for accurately predicting Financial Difficulties of Chinese Cultural Industry Enterprises through Traditional Statistics and Machine Learning. To construct the prediction model, the data of 128 listed Cultural Industry Enterprises in China are used. On the basis of data groups composed of 25 explanatory variables, prediction models using Traditional Statistical such as Discriminant Analysis and logistic as well as Machine Learning such as SVM, Decision Tree and Random Forest were constructed, and Python software was used to evaluate the performance of each model. The results show that the Random Forest model has the best prediction performance, with an accuracy of 95%. The SVM model was followed with 93% accuracy. The Decision Tree model was followed with 92% accuracy.The Discriminant Analysis model was followed with 89% accuracy. The model with the lowest prediction effect was the Logistic model with an accuracy of 88%. This shows that Machine Learning model can achieve better prediction effect than Traditional Statistical model when predicting financial distress of Chinese cultural industry enterprises.

• KIISE Transactions on Computing Practices
• /
• v.21 no.3
• /
• pp.167-172
• /
• 2015

Machine learning is a technique for training computers to be used in classification or forecasting. Among the various types, support vector machine (SVM) is a fast and reliable machine learning mechanism. In this paper, we evaluate the stock price predictability of SVM based on financial statements, through a fundamental analysis predicting the stock price from the corporate intrinsic values. Corporate financial statements were used as the input for SVM. Based on the results, the rise or drop of the stock was predicted. The SVM results were compared with the forecasts of experts, as well as other machine learning methods such as ANN, decision tree and AdaBoost. SVM showed good predictive power while requiring less execution time than the other machine learning schemes.

• 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.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_4
• /
• pp.1145-1153
• /
• 2023

Urban trees play an important role in absorbing carbon dioxide from the atmosphere, improving air quality, mitigating the urban heat island effect, and providing ecosystem services. To effectively manage and conserve urban trees, accurate spatial information on their location, condition, species, and population is needed. In this study, we propose an algorithm that uses a high-resolution urban tree cover map constructed from deep learning approach to separate trees from the urban land surface and accurately detect tree locations through local maximum filtering. Instead of using a uniform filter size, we improved the tree detection performance by selecting the appropriate filter size according to the tree height in consideration of various urban growth environments. The research output, the location and height of individual trees in human settlement over Suwon, will serve as a basis for sustainable management of urban ecosystems and carbon reduction measures.

• Structural Engineering and Mechanics
• /
• v.89 no.3
• /
• pp.283-300
• /
• 2024

Machine learning (ML) models based on artificial neural network (ANN) and decision tree (DT) were developed for estimation of axial capacity of concrete columns reinforced with fiber reinforced polymer (FRP) bars. Between the design codes, the Canadian code provides better formulation compared to the Australian or American code. For empirical models based on elastic modulus of FRP, Hadhood et al. (2017) model performed best. Whereas for empirical models based on tensile strength of FRP, as well as all empirical models, Raza et al. (2021) was adjudged superior. However, compared to the empirical models, all ML models exhibited superior performance according to all five performance metrics considered. The performance of ANN and DT models were comparable in general. Under the present setup, inclusion of the transverse reinforcement information did not improve the accuracy of estimation with either ANN or DT. With selective use of inputs, and a much simpler ANN architecture (4-3-1) compared to that reported in literature (Raza et al. 2020: 6-11-11-1), marginal improvement in correlation could be achieved. The metrics for the best model from the study was a correlation of 0.94, absolute errors between 420 kN to 530 kN, and the range being 0.39 to 0.51 for relative errors. Though much superior performance could be obtained using ANN/DT models over empirical models, further work towards improving accuracy of the estimation is indicated before design of FRP reinforced concrete columns using ML may be considered for design codes.

• Journal of Korean Society of Water and Wastewater
• /
• v.35 no.4
• /
• pp.259-275
• /
• 2021

This study explored the usefulness and implications of the Bayesian hyperparameter optimization in developing species distribution models (SDMs). A variety of machine learning (ML) algorithms, namely, support vector machine (SVM), random forest (RF), boosted regression tree (BRT), XGBoost (XGB), and Multilayer perceptron (MLP) were used for predicting the occurrence of four benthic macroinvertebrate species. The Bayesian optimization method successfully tuned model hyperparameters, with all ML models resulting an area under the curve (AUC) > 0.7. Also, hyperparameter search ranges that generally clustered around the optimal values suggest the efficiency of the Bayesian optimization in finding optimal sets of hyperparameters. Tree based ensemble algorithms (BRT, RF, and XGB) tended to show higher performances than SVM and MLP. Important hyperparameters and optimal values differed by species and ML model, indicating the necessity of hyperparameter tuning for improving individual model performances. The optimization results demonstrate that for all macroinvertebrate species SVM and RF required fewer numbers of trials until obtaining optimal hyperparameter sets, leading to reduced computational cost compared to other ML algorithms. The results of this study suggest that the Bayesian optimization is an efficient method for hyperparameter optimization of machine learning algorithms.

• Journal of KIBIM
• /
• v.9 no.1
• /
• pp.22-31
• /
• 2019

In this paper, we construct a prototype model for city data prediction by using time series data of floating population, and use machine learning to analyze urban data of complex structure. A correlation prediction model was constructed using three of the 10 data (total flow population, male flow population, and Monday flow population), and the result was compared with the actual data. The results of the accuracy were evaluated. The results of this study show that the predicted model of the floating population predicts the correlation between the predicted floating population and the current state of commerce. It is expected that it will help efficient and objective design in the planning stages of architecture, landscape, and urban areas such as tree environment design and layout of trails. Also, it is expected that the dynamic population prediction using multivariate time series data and collected location data will be able to perform integrated simulation with time series data of various fields.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1407-1422
• /
• 2022

This study was conducted to classify tree species and assess the classification accuracy, using SE-Inception, a classification-based deep learning model. The input images of the dataset used Worldview-3 and GeoEye-1 images, and the size of the input images was divided into 10 × 10 m, 30 × 30 m, and 50 × 50 m to compare and evaluate the accuracy of classification of tree species. The label data was divided into five tree species (Pinus densiflora, Pinus koraiensis, Larix kaempferi, Abies holophylla Maxim. and Quercus) by visually interpreting the divided image, and then labeling was performed manually. The dataset constructed a total of 2,429 images, of which about 85% was used as learning data and about 15% as verification data. As a result of classification using the deep learning model, the overall accuracy of up to 78% was achieved when using the Worldview-3 image, the accuracy of up to 84% when using the GeoEye-1 image, and the classification accuracy was high performance. In particular, Quercus showed high accuracy of more than 85% in F₁ regardless of the input image size, but trees with similar spectral characteristics such as Pinus densiflora and Pinus koraiensis had many errors. Therefore, there may be limitations in extracting feature amount only with spectral information of satellite images, and classification accuracy may be improved by using images containing various pattern information such as vegetation index and Gray-Level Co-occurrence Matrix (GLCM).