• Journal of the Society of Disaster Information
• /
• v.18 no.4
• /
• pp.899-907
• /
• 2022

Purpose: Although many studies on seismic fragility analysis of general bridges have been conducted using machine learning methods, studies on curved bridge structures are insignificant. Therefore, the purpose of this study is to analyze the seismic fragility of bridges with I-shaped curved girders based on the machine learning method considering the material property and geometric uncertainties. Method: Material properties and pier height were considered as uncertainty parameters. Parameters were sampled using the Latin hypercube technique and time history analysis was performed considering the seismic uncertainty. Machine learning data was created by applying artificial neural network and response surface analysis method to the original data. Finally, earthquake fragility analysis was performed using original data and learning data. Result: Parameters were sampled using the Latin hypercube technique, and a total of 160 time history analyzes were performed considering the uncertainty of the earthquake. The analysis result and the predicted value obtained through machine learning were compared, and the coefficient of determination was compared to compare the similarity between the two values. The coefficient of determination of the response surface method was 0.737, which was relatively similar to the observed value. The seismic fragility curve also showed that the predicted value through the response surface method was similar to the observed value. Conclusion: In this study, when the observed value through the finite element analysis and the predicted value through the machine learning method were compared, it was found that the response surface method predicted a result similar to the observed value. However, both machine learning methods were found to underestimate the observed values.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.43 no.1
• /
• pp.1-10
• /
• 2023

This study aimed to confirm the importance ratio of climate and management variables on production of orchardgrass in Korea (1982-2014). For the climate, the mean temperature in January (MTJ, ℃), lowest temperature in January (LTJ, ℃), growing days 0 to 5 (GD 1, day), growing days 5 to 25 (GD 2, day), Summer depression days (SSD, day), rainfall days (RD, day), accumulated rainfall (AR, mm), and sunshine duration (SD, hr) were considered. For the management, the establishment period (EP, 0-6 years) and number of cutting (NC, 2nd-5th) were measured. The importance ratio on production of orchardgrass was estimated using the neural network model with the perceptron method. It was performed by SPSS 26.0 (IBM Corp., Chicago). As a result, EP was the most important variable (100%), followed by RD (82.0%), AR (79.1%), NC (69.2%), LTJ (66.2%), GD 2 (63.3%), GD 1 (61.6%), SD (58.1%), SSD (50.8%) and MTJ (41.8%). It implies that EP, RD, AR, and NC were more important than others. Since the annual rainfall in Korea is exceed the required amount for the growth and development of orchardgrass, the damage caused by heavy rainfall exceeding the appropriate level could be reduced through drainage management. It means that, when cultivating orchardgrass, factors that can be controlled were relatively important. Although it is difficult to interpret the specific effect of climates on production due to neural networking modeling, in the future, this study is expected to be useful in production prediction and damage estimation by climate change by selecting major factors.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.104-123
• /
• 2022

Style transfer based on neural network provides very high quality results by reflecting the high level structural characteristics of images, and thereby has recently attracted great attention. This paper deals with the problem of resolution limitation due to GPU memory in performing such neural style transfer. We can expect that the gradient operation for style transfer based on partial image, with the aid of the fixed size of receptive field, can produce the same result as the gradient operation using the entire image. Based on this idea, each component of the style transfer loss function is analyzed in this paper to obtain the necessary conditions for partitioning and padding, and to identify, among the information required for gradient calculation, the one that depends on the entire input. By structuring such information for using it as auxiliary constant input for partition-based gradient calculation, this paper develops a recursive algorithm for super high-resolution image style transfer. Since the proposed method performs style transfer by partitioning input image into the size that a GPU can handle, it can perform style transfer without the limit of the input image resolution accompanied by the GPU memory size. With the aid of such super high-resolution support, the proposed method can provide a unique style characteristics of detailed area which can only be appreciated in super high-resolution style transfer.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.3-12
• /
• 2022

Image deblurring aims to remove image blur, which can be generated while shooting the pictures by the movement of objects, camera shake, blurring of focus, and so forth. With the rise in popularity of smartphones, it is common to carry portable digital cameras daily, so image deblurring techniques have become more significant recently. Originally, image deblurring techniques have been studied using traditional optimization techniques. Then with the recent attention on deep learning, deblurring methods based on convolutional neural networks have been actively proposed. However, most of them have been developed while focusing on better performance. Therefore, it is not easy to use in real situations due to the speed of their algorithms. To tackle this problem, we propose a novel deep learning-based deblurring algorithm that can be operated in real-time on HD resolution. In addition, we improved the training and inference process and could increase the performance of our model without any significant effect on the speed and the speed without any significant effect on the performance. As a result, our algorithm achieves real-time performance by processing 33.74 frames per second at 1280×720 resolution. Furthermore, it shows excellent performance compared to its speed with a PSNR of 29.78 and SSIM of 0.9287 with the GoPro dataset.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.444-444
• /
• 2021

하천의 오염부하량 관리 계획은 지속적인 모니터링을 통한 자료 구축과 모형을 이용한 예측결과를 기반으로 수립된다. 하천의 모니터링과 예측 분석은 많은 예산과 인력 등이 필요하나, 정부의 담당 공무원 수는 극히 부족한 상황이 일반적이다. 이에 정부는 전문가에게 관련 용역을 의뢰하지만, 한국과 같이 지형이 복잡한 지역에서의 오염부하량 배출 특성은 각각 다르게 나타나기 때문에 많은 예산 소모가 발생 된다. 이를 개선하고자, 본 연구는 합성곱 신경망 (convolution neural network)과 수문학적 이미지 (hydrological image)를 이용하여 강우 발생시 BOD 및 총인의 부하량 예측 모형을 개발하였다. 합성곱 신경망의 입력자료는 일반적으로 RGB (red, green, bule) 사진을 이용하는데, 이를 그래도 오염부하량 예측에 활용하는 것은 경험적 모형의 전제(독립변수와 종속변수의 관계)를 무너뜨리는 결과를 초래할 수 있다. 이에, 본 연구에서는 오염부하량이 수문학적 조건과 토지이용 등의 변수에 의해 결정된다는 인과관계를 만족시키고자 수문학적 속성이 내재된 수문학적 이미지를 합성곱 신경망의 훈련자료로 사용하였다. 수문학적 이미지는 임의의 유역에 대해 2차원 공간에서 무차원의 수문학적 속성을 갖는 grid의 집합으로 정의되는데, 여기서 각 grid의 수문학적 속성은 SCS 토양보존국(soil conservation service, SCS)에서 발표한 수문학적 토양피복형수 (curve number, CN)를 이용하여 산출한다. 합성곱 신경망의 구조는 2개의 Convolution Layer와 1개의 Pulling Layer가 5회 반복하는 구조로 설정하고, 1개의 Flatten Layer, 3개의 Dense Layer, 1개의 Batch Normalization Layer를 배열하고, 마지막으로 1개의 Dense Layer가 연결되는 구조로 설계하였다. 이와 함께, 각 층의 활성화 함수는 정규화 선형함수 (ReLu)로, 마지막 Dense Layer의 활성화 함수는 연속변수가 도출될 수 있도록 회귀모형에서 자주 사용되는 Linear 함수로 설정하였다. 연구의 대상지역은 경기도 가평군 조종천 유역으로 선정하였고, 연구기간은 2010년 1월 1일부터 2019년 12월 31일까지로, 2010년부터 2016년까지의 자료는 모형의 학습에, 2017년부터 2019년까지의 자료는 모형의 성능평가에 활용하였다. 모형의 예측 성능은 모형효율계수 (NSE), 평균제곱근오차(RMSE) 및 평균절대백분율오차(MAPE)를 이용하여 평가하였다. 그 결과, BOD 부하량에 대한 NSE는 0.9, RMSE는 1031.1 kg/day, MAPE는 11.5%로 나타났으며, 총인 부하량에 대한 NSE는 0.9, RMSE는 53.6 kg/day, MAPE는 17.9%로 나타나 본 연구의 모형은 우수(good)한 것으로 판단하였다. 이에, 본 연구의 모형은 일반 ANN 모형을 이용한 선행연구와는 달리 2차원 공간정보를 반영하여 오염부하량 모의가 가능했으며, 제한적인 입력자료를 이용하여 간편한 모델링이 가능하다는 장점을 나타냈다. 이를 통해 정부의 물관리 정책을 위한 의사결정 및 부족한 물관리 분야의 행정력에 도움이 될 것으로 생각된다.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.9-16
• /
• 2023

Recently, a convolutional neural network (CNN) based system is being developed to overcome the limitations of human resources in the apple quality classification of farmhouse. However, since convolutional neural networks receive only images of the same size, preprocessing such as sampling may be required, and in the case of oversampling, information loss of the original image such as image quality degradation and blurring occurs. In this paper, in order to minimize the above problem, to generate a image patch based graph of an original image and propose a random walk-based positional encoding method to apply the graph transformer model. The above method continuously learns the position embedding information of patches which don't have a positional information based on the random walk algorithm, and finds the optimal graph structure by aggregating useful node information through the self-attention technique of graph transformer model. Therefore, it is robust and shows good performance even in a new graph structure of random node order and an arbitrary graph structure according to the location of an object in an image. As a result, when experimented with 5 apple quality datasets, the learning accuracy was higher than other GNN models by a minimum of 1.3% to a maximum of 4.7%, and the number of parameters was 3.59M, which was about 15% less than the 23.52M of the ResNet18 model. Therefore, it shows fast reasoning speed according to the reduction of the amount of computation and proves the effect.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.5A
• /
• pp.673-683
• /
• 2008

This study improved the existing method of using the longitudinal strain and concept of influence line to develop Bridge Weigh-in-Motion system without axle detector using the dynamic strain of the bridge girders and concrete slab. This paper first describes the considered algorithms of extracting passing vehicle information from the dynamic strain signal measured at the bridge slab, girders, and cross beams. Two different analysis methods of 1) influence line method, and 2) neural network method are considered, and parameter study of measurement locations is also performed. Then the procedures and the results of field tests are described. The field tests are performed to acquire training sets and test sets for neural networks, and also to verify and compare performances of the considered algorithms. Finally, comparison between the results of different algorithms and discussions are followed. For a PSC I-girder bridge, vehicle weight can be calculated within a reasonable error range using the dynamic strain gauge installed on the girders. The passing lane and passing speed of the vehicle can be accurately estimated using the strain signal from the concrete slab. The passing speed and peak duration were added to the input variables to reflect the influence of the dynamic interaction between the bridge and vehicles, and impact of the distance between axles, respectively; thus improving the accuracy of the weight calculation.

• Journal of Korea Water Resources Association
• /
• v.57 no.2
• /
• pp.73-85
• /
• 2024

Predicting water quality of rivers and reservoirs is necessary for the management of water resources. Artificial Neural Networks (ANNs) have been used in many studies to predict water quality with high accuracy. Previous studies have used Gradient Descent (GD)-based optimizers as an optimizer, an operator of ANN that searches parameters. However, GD-based optimizers have the disadvantages of the possibility of local optimal convergence and absence of a solution storage and comparison structure. This study developed improved optimizers to overcome the disadvantages of GD-based optimizers. Proposed optimizers are optimizers that combine adaptive moments (Adam) and Nesterov-accelerated adaptive moments (Nadam), which have low learning errors among GD-based optimizers, with Harmony Search (HS) or Novel Self-adaptive Harmony Search (NSHS). To evaluate the performance of Long Short-Term Memory (LSTM) using improved optimizers, the water quality data from the Dasan water quality monitoring station were used for training and prediction. Comparing the learning results, Mean Squared Error (MSE) of LSTM using Nadam combined with NSHS (NadamNSHS) was the lowest at 0.002921. In addition, the prediction rankings according to MSE and R² for the four water quality indices for each optimizer were compared. Comparing the average of ranking for each optimizer, it was confirmed that LSTM using NadamNSHS was the highest at 2.25.

• Resources Recycling
• /
• v.33 no.4
• /
• pp.3-14
• /
• 2024

The preheating and calcination processes in cement manufacturing, which are crucial for producing the cement intermediate product clinker, require a substantial quantity of fossil fuels to generate high-temperature thermal energy. However, owing to the ever-increasing severity of environmental pollution, considerable efforts are being made to reduce carbon emissions from fossil fuels in the cement industry. Several preliminary studies have focused on increasing the usage of alternative fuels like refuse-derived fuel (RDF). Alternative fuels offer several advantages, such as reduced carbon emissions, mitigated generation of nitrogen oxides, and incineration in preheaters and kilns instead of landfilling. However, owing to the diverse compositions of alternative fuels, estimating their calorific value is challenging. This makes it difficult to regulate the preheater stability, thereby limiting the usage of alternative fuels. Therefore, in this study, a model based on deep neural networks is developed to accurately predict the preheater temperature and propose optimal fuel input quantities using explainable artificial intelligence. Utilizing the proposed model in actual preheating process sites resulted in a 5% reduction in fossil fuel usage, 5%p increase in the substitution rate with alternative fuels, and 35% reduction in preheater temperature fluctuations.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.9
• /
• pp.1-7
• /
• 2024

In this paper, we proposes a Convolutional Neural Networks(CNN) equipped with Batch Normalization(BN) for handwritten digit recognition training the MNIST dataset. Aiming to surpass the performance of LeNet-5 by LeCun et al., a 6-layer neural network was designed. The proposed model processes 28×28 pixel images through convolution, Max Pooling, and Fully connected layers, with the batch normalization to improve learning stability and performance. The experiment utilized 60,000 training images and 10,000 test images, applying the Momentum optimization algorithm. The model configuration used 30 filters with a 5×5 filter size, padding 0, stride 1, and ReLU as activation function. The training process was set with a mini-batch size of 100, 20 epochs in total, and a learning rate of 0.1. As a result, the proposed model achieved a test accuracy of 99.22%, surpassing LeNet-5's 99.05%, and recorded an F1-score of 0.9919, demonstrating the model's performance. Moreover, the 6-layer model proposed in this paper emphasizes model efficiency with a simpler structure compared to LeCun et al.'s LeNet-5 (7-layer model) and the model proposed by Ji, Chun and Kim (10-layer model). The results of this study show potential for application in real industrial applications such as AI vision inspection systems. It is expected to be effectively applied in smart factories, particularly in determining the defective status of parts.