• Journal of Computing Science and Engineering
• /
• v.7 no.2
• /
• pp.99-111
• /
• 2013

Approximating a divergence between two probability distributions from their samples is a fundamental challenge in statistics, information theory, and machine learning. A divergence approximator can be used for various purposes, such as two-sample homogeneity testing, change-point detection, and class-balance estimation. Furthermore, an approximator of a divergence between the joint distribution and the product of marginals can be used for independence testing, which has a wide range of applications, including feature selection and extraction, clustering, object matching, independent component analysis, and causal direction estimation. In this paper, we review recent advances in divergence approximation. Our emphasis is that directly approximating the divergence without estimating probability distributions is more sensible than a naive two-step approach of first estimating probability distributions and then approximating the divergence. Furthermore, despite the overwhelming popularity of the Kullback-Leibler divergence as a divergence measure, we argue that alternatives such as the Pearson divergence, the relative Pearson divergence, and the $L^2$-distance are more useful in practice because of their computationally efficient approximability, high numerical stability, and superior robustness against outliers.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.14 no.5
• /
• pp.1320-1329
• /
• 1990

A static performance tester for a torque rod assembly was developed to evaluate the three characteristics of the rod rubber bushing : radial spring characteristic, thrust spring characteristic, and rotational torque characteristic. Among the various schemes considered in the conceptual design stage, the final versatile type was determined to perform three different tests in one machine. The performance testing machine carried out radial spring test, thrust spring test, and torque test of the torque rod assembly. Static performance of the torque rod assembly was evaluated with the tester developed and fatigue strength of the assembly was also tested with the servo-hydraulic structural fatigue testing machine. The life of the component was found to be related with the rubber quality and adhesionability between the rubber and the steel rod. The optimum rubber hardness was experimentally found by changing the chemical compositions of rubber, and the adhesion was improved by optimizing the shape of the outer section of a the rubber, this study ensured the development of a reliable torque rod assembly.

• Journal of Korean Society of Forest Science
• /
• v.104 no.2
• /
• pp.198-205
• /
• 2015

The aim of this study was to provide the basic design parameters for developing logging residue compression machines by investigating compressive deformation characteristics of different types of logging residues. To achieve these objectives, Pinus rigida, Pinus koraensis and Quercus mongolica were selected as specimens, and compression-deformation tests by UTM(universial testing machine) were conducted. The experimental dataset were used to set up the model based on the compression-deformation ratio in the form of exponential function. The results showed that stress coefficient in terms of mechanical properties of logging residues was decreased, whereas strain coefficient tended to be increased as the number of compression increased at target density of $350kg/m^3$ and $400kg/m^3$. The model presented that the required stress was decreased as the number of compression increased, and the stress growth rate was swelled compared to the change of the deformation rate. Therefore, it showed that proper initial compression force was a significant variable in order to achieve the target density of logging residue.

• Journal of Power System Engineering
• /
• v.17 no.6
• /
• pp.130-135
• /
• 2013

It is a research about the change in reduction efficiency and performance resulting from installation of the EGR cooler, which is the core technology reducing NOx in response to standards been tightened of exhaust controls for off-road vehicle. It can reduce NOx by altering combustion temperature and oxygen concentration by recycling high-temperature exhaust gas. The target engine was large diesel engine for construction machine through by which we were able to verify a rate of change in output and capabilities for a heat-exchange within cooler itself depending on the existence of EGR cooler system. We have acquired a emission reduction technology for a construction machine by testing the reduction performance and rate of change in output.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.57 no.6
• /
• pp.131-140
• /
• 2015

This paper presents overall procedure by experimental study in order to deriving design factors of snow removal machine on roof of multi-span greenhouse. For the purpose of the testing, the scale model of the machine was made in the form to drive above the monorail. The test was performed in order to calculating friction coefficient of the machine and shear coefficient between sliced horizontal section of snow at constant temperature and humidity room in National Academic of Agricultural Science. As a result of the laboratory test, shear coefficient between sliced horizontal section of snow were calculated 1.60~2.37. Further investigation, we will study to derive the relationship between the real and scaled model through the field test.

• Nuclear Engineering and Technology
• /
• v.53 no.12
• /
• pp.4072-4079
• /
• 2021

This article presents a study on the state-of-the-art methods for automated radioactive material detection and identification, using gamma-ray spectra and modern machine learning methods. The recent developments inspired this in deep learning algorithms, and the proposed method provided better performance than the current state-of-the-art models. Machine learning models such as: fully connected, recurrent, convolutional, and gradient boosted decision trees, are applied under a wide variety of testing conditions, and their advantage and disadvantage are discussed. Furthermore, a hybrid model is developed by combining the fully-connected and convolutional neural network, which shows the best performance among the different machine learning models. These improvements are represented by the model's test performance metric (i.e., F1 score) of 93.33% with an improvement of 2%-12% than the state-of-the-art model at various conditions. The experimental results show that fusion of classical neural networks and modern deep learning architecture is a suitable choice for interpreting gamma spectra data where real-time and remote detection is necessary.

• Korean Journal of Remote Sensing
• /
• v.35 no.1
• /
• pp.93-115
• /
• 2019

The availability of high-resolution laser scanning data and advanced machine learning algorithms has enabled an accurate potential rockfall source identification. However, the presence of other mass movements, such as landslides within the same region of interest, poses additional challenges to this task. Thus, this research presents a method based on an integration of Gaussian mixture model (GMM) and ensemble artificial neural network (bagging ANN [BANN]) for automatic detection of potential rockfall sources at Kinta Valley area, Malaysia. The GMM was utilised to determine slope angle thresholds of various geomorphological units. Different algorithms(ANN, support vector machine [SVM] and k nearest neighbour [kNN]) were individually tested with various ensemble models (bagging, voting and boosting). Grid search method was adopted to optimise the hyperparameters of the investigated base models. The proposed model achieves excellent results with success and prediction accuracies at 95% and 94%, respectively. In addition, this technique has achieved excellent accuracies (ROC = 95%) over other methods used. Moreover, the proposed model has achieved the optimal prediction accuracies (92%) on the basis of testing data, thereby indicating that the model can be generalised and replicated in different regions, and the proposed method can be applied to various landslide studies.

• Computers and Concrete
• /
• v.30 no.3
• /
• pp.225-236
• /
• 2022

In this article, Multi-Gene Genetic Programming (MGGP) is proposed for the estimation of the compressive strength of concrete. MGGP is known to be a powerful algorithm able to find a relationship between certain input space features and a desired output vector. With respect to most conventional machine learning algorithms, which are often used as "black boxes" that do not provide a mathematical formulation of the output-input relationship, MGGP is able to identify a closed-form formula for the input-output relationship. In the study presented in this article, MGPP was used to predict the compressive strength of plain concrete, concrete with fly ash, and concrete with furnace slag. A formula was extracted for each mixture and the performance and the accuracy of the predictions were compared to the results of Artificial Neural Network (ANN) and Extreme Learning Machine (ELM) algorithms, which are conventional and well-established machine learning techniques. The results of the study showed that MGGP can achieve a desirable performance, as the coefficients of determination for plain concrete, concrete with ash, and concrete with slag from the testing phase were equal to 0.928, 0.906, 0.890, respectively. In addition, it was found that MGGP outperforms ELM in all cases and its' accuracy is slightly less than ANN's accuracy. However, MGGP models are practical and easy-to-use since they extract closed-form formulas that may be implemented and used for the prediction of compressive strength.

• Nuclear Engineering and Technology
• /
• v.55 no.5
• /
• pp.1708-1717
• /
• 2023

The grade analysis of lead-zinc ore is the basis for the optimal development and utilization of deposits. In this study, a method combining Prompt Gamma Neutron Activation Analysis (PGNAA) technology and machine learning is proposed for lead-zinc mine borehole logging, which can identify lead-zinc ores of different grades and gangue in the formation, providing real-time grade information qualitatively and semi-quantitatively. Firstly, Monte Carlo simulation is used to obtain a gamma-ray spectrum data set for training and testing machine learning classification algorithms. These spectra are broadened, normalized and separated into inelastic scattering and capture spectra, and then used to fit different classifier models. When the comprehensive grade boundary of high- and low-grade ores is set to 5%, the evaluation metrics calculated by the 5-fold cross-validation show that the SVM (Support Vector Machine), KNN (K-Nearest Neighbor), GNB (Gaussian Naive Bayes) and RF (Random Forest) models can effectively distinguish lead-zinc ore from gangue. At the same time, the GNB model has achieved the optimal accuracy of 91.45% when identifying high- and low-grade ores, and the F₁ score for both types of ores is greater than 0.9.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.467-468
• /
• 2021

In order to improve the performance of the indoor positioning system using BLE beacons, a receiver that measures the angle of arrival among the direction finding technologies supported by BLE5.1 was manufactured and analyzed by machine learning to measure the optimal position. For the creation and testing of machine learning models, k-nearest neighbor classification and regression, logistic regression, support vector machines, decision tree artificial neural networks, and deep neural networks were used to learn and test. As a result, when the test set 4 produced in the study was used, the accuracy was up to 99%.