• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.33 no.4
• /
• pp.271-277
• /
• 2020

There are increasing cases of monitoring the structural response of structures using multiple sensors. However, owing to cost and management problems, limited sensors are installed in the structure. Thus, few structural responses are collected, which hinders analyzing the behavior of the structure. Therefore, a technique to predict responses at a location where sensors are not installed to a reliable level using limited sensors is necessary. In this study, a numerical study is conducted to predict the seismic response of low-rise buildings using limited information. It is assumed that the available response information is only the acceleration responses of the first and top floors. Using both information, the first natural frequency of the structure can be obtained. The acceleration information on the first floor is used as the ground motion information. To minimize the error on the acceleration history response of the top floor and the first natural frequency error of the target structure, the method for predicting the mass and stiffness information of a structure using the genetic algorithm is presented. However, the constraints are not considered. To determine the range of design variables that mean the search space, the parameter prediction method based on artificial neural networks is proposed. To verify the proposed method, a five-story structure is used as an example.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.21 no.5
• /
• pp.510-517
• /
• 2001

This paper describes an initial study for the application of eddy current pattern recognition approaches to more realistic flaw characterization in steam generator tubes. For this purpose, finite-element model-based theoretical eddy current testing (ECT) signals are simulated from 5 types of OD flaws with the variation in flaw size parameters and testing frequency. In addition, three kinds of software are developed for the convenience in the application of steps in pattern recognition approaches such as feature extraction feature selection and classification by probabilistic neural networks (PNNs). The cross point of the ECT signals simulated from flaws with non-symmetric cross-sections shows the deviation from the origin of the impedance plane. New features taking advantages of this phenomenon are added to complete the feature set with a total of 18 features. Then, classification with PNNs are performed based on this feature set. The PNN classifiers show high performance for the identification of symmetry in the cross-section of a flaw. However, they show very limited success in the interrogation of the sharpness of flaw tips.

• Journal of Korean Society of Transportation
• /
• v.22 no.3 s.74
• /
• pp.109-125
• /
• 2004

In recent decades, microscopic simulation models have become powerful tools to analyze traffic flow on highways and to assist the investigation of level of service. The existing microscopic simulation models simulate an individual vehicle's speed based on a constant free-flow speed dominantly specified by users and driver's behavior models reflecting vehicle interactions, such as car following and lane changing. They set a single free-flow speed for a single vehicle on a given link and neglect to consider the effects of highway design elements to it in their internal simulation. Due to this, the existing models are limitted to provide with identical simulation results on both curved and tangent sections of highways. This paper presents a model developed to estimate the change of free-flow speeds based on highway design elements. Nine neural network models were trained based on the field data collected from seven different freeway curve sections and three different locations at each section to capture the percent changes of free-flow speeds: 100 m upstream of the point of curve (PC) and the middle of the curve. The model employing seven highway design elements as its input variables was selected as the best : radius of curve, length of curve, superelevation, the number of lanes, grade variations, and the approaching free-flow speed on 100 m upstream of PC. Tests showed that the free-flow speeds estimated by the proposed model were statistically identical to the ones from the field at 95% confidence level at each three different locations described above. The root mean square errors at the starting and the middle of curve section were 6.68 and 10.06, and the R-squares at these points were 0.77 and 0.65, respectively. It was concluded from the study that the proposed model would be one of the potential tools introducing the effects of highway design elements to free-flow speeds in simulation.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.48 no.10
• /
• pp.773-782
• /
• 2020

The development of joint FE models for deep learning neural network (DLNN)-based hybrid FEA is presented. Material models of bolts and bearings in the front axle of tractor, showing complex behavior induced by various tightening conditions, were replaced with DLNN models. Bolts are modeled as one-dimensional Timoshenko beam elements with six degrees of freedom, and bearings as three-dimensional solid elements. Stress-strain data were extracted from all elements after finite element analysis subjected to various load conditions, and DLNN for bolts and bearing were trained with Tensorflow. The DLNN-based joint models were implemented in the ABAQUS user subroutines where stresses from the next increment are updated and the algorithmic tangent stiffness matrix is calculated. Generalization of the trained DLNN in the FE model was verified by subjecting it to a new loading condition. Finally, the DLNN-based FEA for the front axle of the tractor was conducted and the feasibility was verified by comparing with results of a static structural experiment of the actual tractor.

• Journal of Broadcast Engineering
• /
• v.22 no.3
• /
• pp.282-294
• /
• 2017

In this paper, we propose a novel intelligent headlight control (IHC) system which is durable to various road lights and camera movement caused by vehicle driving. For detecting candidate light blobs, the region of interest (ROI) is decided as front ROI (FROI) and back ROI (BROI) by considering the camera geometry based on perspective range estimation model. Then, light blobs such as headlights, taillights of vehicles, reflection light as well as the surrounding road lighting are segmented using two different adaptive thresholding. From the number of segmented blobs, taillights are first detected using the redness checking and random forest classifier based on Haar-like feature. For the headlight and taillight classification, we use the random forest instead of popular support vector machine or convolutional neural networks for supporting fast learning and testing in real-life applications. Pairing is performed by using the predefined geometric rules, such as vertical coordinate similarity and association check between blobs. The proposed algorithm was successfully applied to various driving sequences in night-time, and the results show that the performance of the proposed algorithms is better than that of recent related works.

• Korean Journal of Acupuncture
• /
• v.30 no.3
• /
• pp.161-170
• /
• 2013

Objectives : Our study aimed to investigate the sustained effects of sham (SHAM) and verum acupuncture (ACUP) into the post-stimulus resting state. Methods : In contrast to previous studies, in order to define the changes in resting state induced by acupuncture, changes were evaluated with a multi-method approach by using regional homogeneity (ReHo) and amplitude of low frequency fluctuation (ALFF). Twelve healthy participants received SHAM and ACUP stimulation right GB34 (Yanglingquan) and the neural changes between post- and pre-stimulation were detected. Results : The following results were found; in both ReHo and ALFF, the significant foci of; left and right middle frontal gyrus, left medial frontal gyrus, left superior frontal gyrus, and right posterior cingulate cortex, areas that are known as a default mode network, showed increased connectivity. In addition, in ReHo, but not in ALFF, brain activation changes in the insula, anterior cingulate cortex, and the thalamus, which are associated with acupuncture pain modulation, were found. Conclusions : In this study, results obtained by using ReHo and ALFF, showed that acupuncture can modulate the post-stimulus resting state and that ReHo, but not ALFF, can also detect the neural changes that were induced by the acupuncture stimulations. Although more future studies with ReHo and ALFF will be needed before any firm conclusions can be drawn, our study shows that particularly ReHo could be an interesting method for future clinical neuroimaging studies on acupuncture.

• The Journal of Society for e-Business Studies
• /
• v.25 no.4
• /
• pp.61-75
• /
• 2020

The scope of data for understanding or predicting stock prices has been continuously widened from traditional structured format data to unstructured data. This study investigates whether commentary data collected from SNS may affect future stock prices. From "Stock Discussion Room" in Naver, we collect 20 stocks' commentary data for six months, and test whether this data have prediction power with respect to one-hour ahead price direction and price range. Deep neural network such as LSTM and CNN methods are employed to model the predictive relationship. Among the 20 stocks, we find that future price direction can be predicted with higher than the accuracy of 50% in 13 stocks. Also, the future price range can be predicted with higher than the accuracy of 50% in 16 stocks. This study validate that the investors' sentiment reflected in SNS community such as Naver's "Stock Discussion Room" may affect the demand and supply of stocks, thus driving the stock prices.

• Journal of Wetlands Research
• /
• v.17 no.4
• /
• pp.348-358
• /
• 2015

Impacts of climate change are being observed in the globe as well as the Korean peninsula. In the past 100 years, the average temperature of the earth rose about 0.75 degree in celsius, while that of Korean peninsula rose about 1.5 degree in celsius. The fifth Assessment Report of IPCC(Intergovermental Panel on Climate Change) predicts that the water pollution will be aggravated by change of hydrologic extremes such as floods and droughts and increase of water temperature (KMA and MOLIT, 2009). In this study, future runoff was calculated by applying climate change scenario to analyze the future water quality for each targe period (Obs : 2001 ~ 2010, Target I : 2011 ~ 2040, Target II : 2041 ~ 2070, Target III : 2071 ~ 2100) in Hongcheon river basin, Korea. In addition, The future water quality was analyzed by using multiple linear regression analysis and artificial neural networks after flow-duration curve analysis. As the results of future water quality prediction in Hongcheon river basin, we have known that BOD, COD and SS will be increased at the end of 21 century. Therefore, we need consider long-term water and water quality management planning and monitoring for the improvement of water quality in the future. For the prediction of more reliable future water quality, we may need consider various social factors with climate components.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.14 no.5
• /
• pp.179-186
• /
• 2010

When a structure is damaged, its dynamic responses (natural frequency, acceleration, strain) are found to be changed. The ANN(Artificial Neural Network) damage-assesment method is that some measured dynamic signals from the structural changing dynamic responses are applied to ANN to assess the structural damage. Although there have been some studies on a certain typical cases so far, it is rare to find studies about the characteristics of the ANN damage-assesment method or about its applicability, its strength and weakness. So this study researches on the characteristics of ANN damage assesment method and on a problem in application of the various dynamic responses to ANN. What the ANN damage assessment method usually does in past researches is to teach an ANN by using some response signals obtained from damaged structures under one kind of excitations and to identify the locations and the extents of damage of same structures under the same excitations. However, the excitations inflicted on the structures are not always the same. Thus this study experiments whether a ANN which is trained using the same excitations is able to identify the damage when different excitations inflict. All response signals are obtained from experimental models.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.409-418
• /
• 2021

Conformal coating is a technology that protects PCB(Printed Circuit Board) and minimizes PCB failures. Since the defects in the coating are linked to failure of the PCB, the coating surface is examined for air bubbles to satisfy the successful conditions of the conformal coating. In this paper, we propose an algorithm for detecting problematic bubbles in high-risk groups by applying image signal processing. The algorithm consists of finding candidates for problematic bubbles and verifying candidates. Bubbles do not appear in visible light images, but can be visually distinguished from UV(Ultra Violet) light sources. In particular the center of the problematic bubble is dark in brightness and the border is high in brightness. In the paper, these brightness characteristics are called valley and mountain features, and the areas where both characteristics appear at the same time are candidates for problematic bubbles. However, it is necessary to verify candidates because there may be candidates who are not bubbles. In the candidate verification phase, we used convolutional neural network models, and ResNet performed best compared to other models. The algorithms presented in this paper showed the performance of precision 0.805, recall 0.763, and f1-score 0.767, and these results show sufficient potential for bubble test automation.