• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1366-1372
• /
• 2019

In this paper, we designed a revised neural network to remove the Monte Carlo Rendering noise contained in the ray tracing graphics. The Monte Carlo Rendering is the best way to enhance the graphic's realism, but because of the need to calculate more than thousands of light effects per pixel, rendering processing time has increased rapidly, causing a major problem with real-time processing. To improve this problem, the number of light used in pixels is reduced, where rendering noise occurs and various studies have been conducted to eliminate this noise. In this paper, a deep learning is used to remove rendering noise, especially by separating the rendering image into diffuse and specular light, so that the structure of the dual neural network is designed. As a result, the dual neural network improved by an average of 0.58 db for 64 test images based on PSNR, and 99.22% less light compared to reference image, enabling real-time race-tracing rendering.

• Journal of Information Technology Services
• /
• v.16 no.4
• /
• pp.137-148
• /
• 2017

Researches on the Artificial Intelligence has been explosively activated in various fields since the advent of AlphaGo. Particularly, researchers on the application of multi-layer neural network such as deep learning, and various machine learning algorithms are being focused actively. In this paper, we described a development of an artificial intelligence Janggi game based on reinforcement learning algorithm and MCTS (Monte Carlo Tree Search) algorithm with accumulated game data. The previous artificial intelligence games are mostly developed based on mini-max algorithm, which depends only on the results of the tree search algorithms. They cannot use of the real data from the games experts, nor cannot enhance the performance by learning. In this paper, we suggest our approach to overcome those limitations as follows. First, we collects Janggi expert's game data, which can reflect abundant real game results. Second, we create a graph structure by using the game data, which can remove redundant movement. And third, we apply the reinforcement learning algorithm and MCTS algorithm to select the best next move. In addition, the learned graph is stored by object serialization method to provide continuity of the game. The experiment of this study is done with two different types as follows. First, our system is confronted with other AI based system that is currently being served on the internet. Second, our system confronted with some Janggi experts who have winning records of more than 50%. Experimental results show that the rate of our system is significantly higher.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.4 no.1
• /
• pp.119-124
• /
• 2004

Real data as web log file tend to be incomplete. But we have to find useful knowledge from these for optimal decision. In web log data, many useful things which are hyperlink information and web usages of connected users may be found. The size of web data is too huge to use for effective knowledge discovery. To make matters worse, they are very sparse. We overcome this sparse problem using Markov Chain Monte Carlo method as multiple imputations. This missing value imputation changes spare web data to complete. Our study may be a useful tool for discovering knowledge from data set with sparseness. The more sparseness of data in increased, the better performance of MCMC imputation is good. We verified our work by experiments using UCI machine learning repository data.

• Smart Structures and Systems
• /
• v.29 no.2
• /
• pp.321-336
• /
• 2022

Model uncertainty is a key factor that could influence the accuracy and reliability of numerical model-based analysis. It is necessary to acquire an appropriate updating approach which could search and determine the realistic model parameter values from measurements. In this paper, the Bayesian model updating theory combined with the transitional Markov chain Monte Carlo (TMCMC) method and K-means cluster analysis is utilized in the updating of the structural model parameters. Kriging and polynomial chaos expansion (PCE) are employed to generate surrogate models to reduce the computational burden in TMCMC. The selected updating approaches are applied to three structural examples with different complexity, including a two-storey frame, a ten-storey frame, and the national stadium model. These models stand for the low-dimensional linear model, the high-dimensional linear model, and the nonlinear model, respectively. The performances of updating in these three models are assessed in terms of the prediction uncertainty, numerical efforts, and prior information. This study also investigates the updating scenarios using the analytical approach and surrogate models. The uncertainty quantification in the Bayesian approach is further discussed to verify the validity and accuracy of the surrogate models. Finally, the advantages and limitations of the surrogate model-based updating approaches are discussed for different structural complexity. The possibility of utilizing the boosting algorithm as an ensemble learning method for improving the surrogate models is also presented.

• Structural Engineering and Mechanics
• /
• v.82 no.3
• /
• pp.271-282
• /
• 2022

The active learning surrogate model based on adaptive sampling strategy is increasingly popular in reliability analysis. However, most of the existing sampling strategies adopt the trial and error method to determine the size of the Monte Carlo (MC) candidate sample pool which satisfies the requirement of variation coefficient of failure probability. It will lead to a reduction in the calculation efficiency of reliability analysis. To avoid this defect, a new method for determining the optimal size of the MC candidate sample pool is proposed, and a new structural reliability analysis method combining polynomial chaos-based Kriging model (PC-Kriging) with adaptive sampling region is also proposed (PCK-ASR). Firstly, based on the lower limit of the confidence interval, a new method for estimating the optimal size of the MC candidate sample pool is proposed. Secondly, based on the upper limit of the confidence interval, an adaptive sampling region strategy similar to the radial centralized sampling method is developed. Then, the k-means++ clustering technique and the learning function LIF are used to complete the adaptive design of experiments (DoE). Finally, the effectiveness and accuracy of the PCK-ASR method are verified by three numerical examples and one practical engineering example.

• Journal of the Korea Society for Simulation
• /
• v.29 no.1
• /
• pp.47-55
• /
• 2020

This paper presents a real-time autonomous computation of shot numbers and aiming points against multiple soft targets on grounds by applying an unsupervised learning, k-mean clustering and Monte carlo simulation. For this computation, a 100 × 200 square meters size of virtual battlefield is created where an augmented enemy infantry platoon unit attacks, defences, and is scatted, and a virtual weapon with a lethal range of 15m is modeled. In order to determine damage types of the enemy unit: no damage, light wound, heavy wound and death, Monte carlo simulation is performed to apply the Carlton damage function for the damage effect of the soft targets. In addition, in order to achieve the damage effectiveness of the enemy units in line with the commander's intention, the optimal shot numbers and aiming point locations are calculated in less than 0.4 seconds by applying the k-mean clustering and repetitive Monte carlo simulation. It is hoped that this study will help to develop a system that reduces the decision time for 'detection-decision-shoot' process in battalion-scaled combat units operating Dronebot combat system.

• Journal of Environmental Health Sciences
• /
• v.46 no.6
• /
• pp.627-635
• /
• 2020

Objectives: Indoor air quality has become more important aspeople spend most of their times indoors. Since students spend most of their times at home or at school, they are more likely to be exposed to indoor air pollutants. Ventilation in school classrooms can affect health and learning performance. In this study, ventilation deficiency was evaluated in school classrooms using Monte Carlo simulation. Methods: This study used sensor-based monitoring for six months to measure carbon dioxide (CO2) concentrations in classrooms in elementary, middle, and high schools. The volume of the classroom and the number of students were investigated, and the students' body surface area was used to calculate the CO2 emission rate. The distribution of ventilation rates was estimated by measured CO2 concentration and a mass-balance model using Monte Carlo simulation. Results: In the elementary, middle, and high schools, the average CO2 concentrations exceeded 1000 ppm, indicating that the ventilation rates were insufficient. The ventilation rates were deficient from July to August and in December, but showed relatively high ventilation rates in October. Forty-three percent of elementary schools, 56% of middle schools, and 62% of high schools showed insufficient ventilation rates. Conclusions: The ventilation rates calculated in elementary, middle and high schools were found to be quite insufficient. Therefore, proper management is needed to overcome the lack of ventilation and improve air quality.

• Structural Engineering and Mechanics
• /
• v.66 no.6
• /
• pp.677-691
• /
• 2018

Reliability assessment of complex structures using simulation methods is time-consuming. Thus, surrogate models are usually employed to reduce computational cost. AK-MCS is a surrogate-based Active learning method combining Kriging and Monte-Carlo Simulation for structural reliability analysis. This paper proposes three modifications of the AK-MCS method to reduce the number of calls to the performance function. The first modification is related to the definition of an initial Design of Experiments (DoE). In the original AK-MCS method, an initial DoE is created by a random selection of samples among the Monte Carlo population. Therefore, samples in the failure region have fewer chances to be selected, because a small number of samples are usually located in the failure region compared to the safe region. The proposed method in this paper is based on a uniform selection of samples in the predefined domain, so more samples may be selected from the failure region. Another important parameter in the AK-MCS method is the size of the initial DoE. The algorithm may not predict the exact limit state surface with an insufficient number of initial samples. Thus, the second modification of the AK-MCS method is proposed to overcome this problem. The third modification is relevant to the type of regression trend in the AK-MCS method. The original AK-MCS method uses an ordinary Kriging model, so the regression part of Kriging model is an unknown constant value. In this paper, the effect of regression trend in the AK-MCS method is investigated for a benchmark problem, and it is shown that the appropriate choice of regression type could reduce the number of calls to the performance function. A stepwise approach is also presented to select a suitable trend of the Kriging model. The numerical results show the effectiveness of the proposed modifications.

• Nuclear Engineering and Technology
• /
• v.56 no.2
• /
• pp.715-727
• /
• 2024

During fast neutron imaging, besides the dark current noise and readout noise of the CCD camera, the main noise in fast neutron imaging comes from high-energy gamma rays generated by neutron nuclear reactions in and around the experimental setup. These high-energy gamma rays result in the presence of high-density gamma white spots (GWS) in the fast neutron image. Due to the microscopic quantum characteristics of the neutron beam itself and environmental scattering effects, fast neutron images typically exhibit a mixture of Gaussian noise. Existing denoising methods in neutron images are difficult to handle when dealing with a mixture of GWS and Gaussian noise. Herein we put forward a deep learning approach based on the Swin Transformer UNet (SUNet) model to remove high-density GWS-Gaussian mixture noise from fast neutron images. The improved denoising model utilizes a customized loss function for training, which combines perceptual loss and mean squared error loss to avoid grid-like artifacts caused by using a single perceptual loss. To address the high cost of acquiring real fast neutron images, this study introduces Monte Carlo method to simulate noise data with GWS characteristics by computing the interaction between gamma rays and sensors based on the principle of GWS generation. Ultimately, the experimental scenarios involving simulated neutron noise images and real fast neutron images demonstrate that the proposed method not only improves the quality and signal-to-noise ratio of fast neutron images but also preserves the details of the original images during denoising.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.3
• /
• pp.131-135
• /
• 2021

Numbers of studies related to optimization of design of organic light emitting diodes(OLED) through machine learning are increasing. We propose the generative method of the image to assess the performance of the device combining with machine learning technique. Principle parameter regarding dark spot growth mechanism of the OLED can be the key factor to determine the long-time performance. Captured images from actual device and randomly generated images at specific time and initial pinhole state are fed into the deep neural network system. The simulation reinforced by the machine learning technique can predict the device parameters accurately and faster. Similarly, the inverse design using multiple layer perceptron(MLP) system can infer the initial degradation factors at manufacturing with given device parameter to feedback the design of manufacturing process.