• Journal of the Korean Geotechnical Society
• /
• v.23 no.8
• /
• pp.117-127
• /
• 2007

Slope stability analysis is a geotechnical engineering problem characterized by many sources of uncertainty. Some of them are connected to the uncertainties of soil properties involved in the analysis. In this paper, a numerical procedure for integrating commercial finite difference method into probabilistic analysis of slope stability is presented. Since the limit-state function cannot be expressed in an explicit form, the ANN-based response surface method is adopted to approximate the limit-state function and the first-, second-order reliability method and the Monte Carlo simulation technique are used to calculate the probability of failure. Probabilistic stability assessments for a hypothetical two-layer slope and the Sugar Creek embankment were performed to verify the application potential to the slope stability problems. The examples show the successful implementation and the possibility of the extension of the proposed procedure to the variety of geotechnical engineering problems.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.6
• /
• pp.218-226
• /
• 2020

An experimental study was conducted on baseline model updating and damage estimation techniques for the health monitoring of offshore wind turbine tripod substructures. First, a procedure for substructure health monitoring was proposed. An initial baseline model for a scaled model of a tripod substructure was established. A baseline model was updated based on the natural frequencies and the mode shapes measured in the healthy state. A training pattern was then generated using the updated baseline model, and the damage was estimated by inputting the modal parameters measured in the damaged state into the trained neural network. The baseline model could be updated reasonably using the effective fixity model. The damage tests were performed, and the damage locations could be estimated reasonably. In addition, the estimated damage severity also increased as the actual damage severity increased. On the other hand, when the damage severity was relatively small, the corresponding damage location was detected, but it was more difficult to identify than the other cases. Further studies on small damage estimation and stiffness reduction quantification will be needed before the presented method can be used effectively for the health monitoring of tripod substructures.

• Analytical Science and Technology
• /
• v.24 no.6
• /
• pp.533-543
• /
• 2011

The hERG (human ether-a-go-go related gene) ion channel is a main factor for cardiac repolarization, and the blockade of this channel could induce arrhythmia and sudden death. Therefore, potential hERG ion channel inhibitors are now a primary concern in the drug discovery process, and lots of efforts are focused on the minimizing the cardiotoxic side effect. In this study, $IC_{50}$ data of 202 organic compounds in HEK (human embryonic kidney) cell from literatures were used to develop predictive 2D-QSAR model. Multiple linear regression (MLR), Support Vector Machine (SVM), and artificial neural network (ANN) were utilized to predict inhibition concentration of hERG ion channel as machine learning methods. Population based-forward selection method with cross-validation procedure was combined with each learning method and used to select best subset descriptors for each learning algorithm. The best model was ANN model based on 14 descriptors ($R^2_{CV}$=0.617, RMSECV=0.762, MAECV=0.583) and the MLR model could describe the structural characteristics of inhibitors and interaction with hERG receptors. The validation of QSAR models was evaluated through the 5-fold cross-validation and Y-scrambling test.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.125-140
• /
• 2018

As one of the processes in the manufacturing industry, quality inspection inspects the intermediate products or final products to separate the good-quality goods that meet the quality management standard and the defective goods that do not. The manual inspection of quality in a mass production system may result in low consistency and efficiency. Therefore, the quality inspection of mass-produced products involves automatic checking and classifying by the machines in many processes. Although there are many preceding studies on improving or optimizing the process using the data generated in the production process, there have been many constraints with regard to actual implementation due to the technical limitations of processing a large volume of data in real time. The recent research studies on big data have improved the data processing technology and enabled collecting, processing, and analyzing process data in real time. This paper aims to propose the process and details of applying big data for quality inspection and examine the applicability of the proposed method to the dairy industry. We review the previous studies and propose a big data analysis procedure that is applicable to the manufacturing sector. To assess the feasibility of the proposed method, we applied two methods to one of the quality inspection processes in the dairy industry: convolutional neural network and random forest. We collected, processed, and analyzed the images of caps and straws in real time, and then determined whether the products were defective or not. The result confirmed that there was a drastic increase in classification accuracy compared to the quality inspection performed in the past.

• Journal of Internet Computing and Services
• /
• v.22 no.1
• /
• pp.23-30
• /
• 2021

This paper proposes a noise-tolerant image classification system using multiple autoencoders. The development of deep learning technology has dramatically improved the performance of image classifiers. However, if the images are contaminated by noise, the performance degrades rapidly. Noise added to the image is inevitably generated in the process of obtaining and transmitting the image. Therefore, in order to use the classifier in a real environment, we have to deal with the noise. On the other hand, the autoencoder is an artificial neural network model that is trained to have similar input and output values. If the input data is similar to the training data, the error between the input data and output data of the autoencoder will be small. However, if the input data is not similar to the training data, the error will be large. The proposed system uses the relationship between the input data and the output data of the autoencoder, and it has two phases to classify the images. In the first phase, the classes with the highest likelihood of classification are selected and subject to the procedure again in the second phase. For the performance analysis of the proposed system, classification accuracy was tested on a Gaussian noise-contaminated MNIST dataset. As a result of the experiment, it was confirmed that the proposed system in the noisy environment has higher accuracy than the CNN-based classification technique.

• Korean Chemical Engineering Research
• /
• v.53 no.2
• /
• pp.236-242
• /
• 2015

We present two data-driven modeling methods, partial least square (PLS) and artificial neural network (ANN), to predict the major operating and performance variables of a polymer electrolyte membrane (PEM) fuel cell stack. PLS and ANN models were constructed using the experimental data obtained from the testing of a 30 kW-class PEM fuel cell stack, and then were compared with each other in terms of their prediction and computational performances. To reduce the complexity of the models, we combined a variables importance on PLS projection (VIP) as a variable selection method into the modeling procedure in which the predictor variables are selected from a set of input operation variables. The modeling results showed that the ANN models outperformed the PLS models in predicting the average cell voltage and cathode outlet temperature of the fuel cell stack. However, the PLS models also offered satisfactory prediction performances although they can only capture linear correlations between the predictor and output variables. Depending on the degree of modeling accuracy and speed, both ANN and PLS models can be employed for performance predictions, offline and online optimizations, controls, and fault diagnoses in the field of PEM fuel cell designs and operations.

• Korean Journal of Construction Engineering and Management
• /
• v.21 no.6
• /
• pp.113-124
• /
• 2020

Social movements to improve the performance of buildings through remodeling of aging apartment houses are being captured. To this end, the remodeling construction cost analysis, structural analysis, and political institutional review have been conducted to suggest ways to activate the remodeling. However, although the method of analyzing construction cost for remodeling apartment houses is currently being proposed for research purposes, there are limitations in practical application possibilities. Specifically, In order to be used practically, it is applicable to cases that have already been completed or in progress, but cases that will occur in the future are also used for construction cost analysis, so the sustainability of the analysis method is lacking. For the purpose of this, we would like to suggest an automated estimating method. For the sustainability of construction cost estimates, Deep-Learning was introduced in the estimating procedure. Specifically, a method for automatically finding the relationship between design elements, work types, and cost increase factors that can occur in apartment remodeling was presented. In addition, Monte Carlo Simulation was included in the estimation procedure to compensate for the lack of uncertainty, which is the inherent limitation of the Deep Learning-based estimation. In order to present higher accuracy as cases are accumulated, a method of calculating higher accuracy by comparing the estimate result with the existing accumulated data was also suggested. In order to validate the sustainability of the automated estimates proposed in this study, 13 cases of learning procedures and an additional 2 cases of cumulative procedures were performed. As a result, a new construction cost estimating procedure was automatically presented that reflects the characteristics of the two additional projects. In this study, the method of estimate estimate was used using 15 cases, If the cases are accumulated and reflected, the effect of this study is expected to increase.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.11
• /
• pp.116-123
• /
• 1994

A novel opto-digital pattern recognition method which has shift, rotation, and scale invariant properties is proposed for recognizing two dimensional images having straight lines. The algorithm is composed of three stages. In the first stage the line features of the image are extracted. The second stage imposes the shift, rotation, and scale invariant properties on the extracted features through normalizing procedure. The required normalizing equations are analytically explained. In the last stage, the artificial feedforward neural network is trained with the extracted features. In order to evaluated the proposed algorithm, nine different edge enhnaced binary images composed of straight lines are tested. Thus the proposed algorithm can recognize the patterns event though they are shifted, rotated, and scaled.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.165-170
• /
• 2003

This paper presents an integrated approach to unconstrained face recognition in arbitrary scenes. The front end of the system comprises of a scale and pose tolerant face detector. Scale normalization is achieved through novel combination of a skin color segmentation and log-polar mapping procedure. Principal component analysis is used with the multi-view approach proposed in[10] to handle the pose variations. For a given color input image, the detector encloses a face in a complex scene within a circular boundary and indicates the position of the nose. Next, for recognition, a radial grid mapping centered on the nose yields a feature vector within the circular boundary. As the width of the color segmented region provides an estimated size for the face, the extracted feature vector is scale normalized by the estimated size. The feature vector is input to a trained neural network classifier for face identification. The system was evaluated using a database of 20 person's faces with varying scale and pose obtained on different complex backgrounds. The performance of the face recognizer was also quite good except for sensitivity to small scale face images. The integrated system achieved average recognition rates of 87% to 92%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.6
• /
• pp.1312-1317
• /
• 2003

This paper presents an integrated approach to unconstrained face recognition in arbitrary scenes. The front end of the system comprises of a scale and pose tolerant face detector. Scale normalization is achieved through novel combination of a skin color segmentation and log-polar mapping procedure. Principal component analysis is used with the multi-view approach proposed in[10] to handle the pose variations. For a given color input image, the detector encloses a face in a complex scene within a circular boundary and indicates the position of the nose. Next, for recognition, a radial grid mapping centered on the nose yields a feature vector within the circular boundary. As the width of the color segmented region provides an estimated size for the face, the extracted feature vector is scale normalized by the estimated size. The feature vector is input to a trained neural network classifier for face identification. The system was evaluated using a database of 20 person's faces with varying scale and pose obtained on different complex backgrounds. The performance of the face recognizer was also quite good except for sensitivity to small scale face images. The integrated system achieved average recognition rates of 87% to 92%.