• 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.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.4
• /
• pp.169-178
• /
• 2022

Morphemes are most primitive units in a language that lose their original meaning when segmented into smaller parts. In Korean, a sentence is a sequence of eojeols (words) separated by spaces. Each eojeol comprises one or more morphemes. Korean morphological analysis (KMA) is to divide eojeols in a given Korean sentence into morpheme units. It also includes assigning appropriate part-of-speech(POS) tags to the resulting morphemes. KMA is one of the most important tasks in Korean natural language processing (NLP). Improving the performance of KMA is closely related to increasing performance of Korean NLP tasks. Recent research on KMA has begun to adopt the approach of machine translation (MT) models. MT is to convert a sequence (sentence) of units of one domain into a sequence (sentence) of units of another domain. Neural machine translation (NMT) stands for the approaches of MT that exploit neural network models. From a perspective of MT, KMA is to transform an input sequence of units belonging to the eojeol domain into a sequence of units in the morpheme domain. In this paper, we propose a deep learning model for KMA. The backbone of our model is based on the BERT-fused model which was shown to achieve high performance on NMT. The BERT-fused model utilizes Transformer, a representative model employed by NMT, and BERT which is a language representation model that has enabled a significant advance in NLP. The experimental results show that our model achieves 98.24 F1-Score.

• Journal of the Korean Society of Radiology
• /
• v.16 no.4
• /
• pp.411-417
• /
• 2022

This study aimed to learn and evaluate the effectiveness of VGGNet in the detection of pulmonary emphysema using low-dose chest computed tomography images. In total, 8000 images with normal findings and 3189 images showing pulmonary emphysema were used. Furthermore, 60%, 24%, and 16% of the normal and emphysema data were randomly assigned to training, validation, and test datasets, respectively, in model learning. VGG16 and VGG19 were used for learning, and the accuracy, loss, confusion matrix, precision, recall, specificity, and F1-score were evaluated. The accuracy and loss for pulmonary emphysema detection of the low-dose chest CT test dataset were 92.35% and 0.21% for VGG16 and 95.88% and 0.09% for VGG19, respectively. The precision, recall, and specificity were 91.60%, 98.36%, and 77.08% for VGG16 and 96.55%, 97.39%, and 92.72% for VGG19, respectively. The F1-scores were 94.86% and 96.97% for VGG16 and VGG19, respectively. Through the above evaluation index, VGG19 is judged to be more useful in detecting pulmonary emphysema. The findings of this study would be useful as basic data for the research on pulmonary emphysema detection models using VGGNet and artificial neural networks.

• 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.

• Journal of Internet Computing and Services
• /
• v.21 no.6
• /
• pp.23-31
• /
• 2020

This study was carried out to generate various images of railroad surfaces with random defects as training data to be better at the detection of defects. Defects on the surface of railroads are caused by various factors such as friction between track binding devices and adjacent tracks and can cause accidents such as broken rails, so railroad maintenance for defects is necessary. Therefore, various researches on defect detection and inspection using image processing or machine learning on railway surface images have been conducted to automate railroad inspection and to reduce railroad maintenance costs. In general, the performance of the image processing analysis method and machine learning technology is affected by the quantity and quality of data. For this reason, some researches require specific devices or vehicles to acquire images of the track surface at regular intervals to obtain a database of various railway surface images. On the contrary, in this study, in order to reduce and improve the operating cost of image acquisition, we constructed the 'Defective Railroad Surface Regeneration Model' by applying the methods presented in the related studies of the Generative Adversarial Network (GAN). Thus, we aimed to detect defects on railroad surface even without a dedicated database. This constructed model is designed to learn to generate the railroad surface combining the different railroad surface textures and the original surface, considering the ground truth of the railroad defects. The generated images of the railroad surface were used as training data in defect detection network, which is based on Fully Convolutional Network (FCN). To validate its performance, we clustered and divided the railroad data into three subsets, one subset as original railroad texture images and the remaining two subsets as another railroad surface texture images. In the first experiment, we used only original texture images for training sets in the defect detection model. And in the second experiment, we trained the generated images that were generated by combining the original images with a few railroad textures of the other images. Each defect detection model was evaluated in terms of 'intersection of union(IoU)' and F1-score measures with ground truths. As a result, the scores increased by about 10~15% when the generated images were used, compared to the case that only the original images were used. This proves that it is possible to detect defects by using the existing data and a few different texture images, even for the railroad surface images in which dedicated training database is not constructed.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.239-251
• /
• 2019

Statistical methods such as moving averages, Kalman filtering, exponential smoothing, regression analysis, and ARIMA (autoregressive integrated moving average) have been used for stock market predictions. However, these statistical methods have not produced superior performances. In recent years, machine learning techniques have been widely used in stock market predictions, including artificial neural network, SVM, and genetic algorithm. In particular, a case-based reasoning method, known as k-nearest neighbor is also widely used for stock price prediction. Case based reasoning retrieves several similar cases from previous cases when a new problem occurs, and combines the class labels of similar cases to create a classification for the new problem. However, case based reasoning has some problems. First, case based reasoning has a tendency to search for a fixed number of neighbors in the observation space and always selects the same number of neighbors rather than the best similar neighbors for the target case. So, case based reasoning may have to take into account more cases even when there are fewer cases applicable depending on the subject. Second, case based reasoning may select neighbors that are far away from the target case. Thus, case based reasoning does not guarantee an optimal pseudo-neighborhood for various target cases, and the predictability can be degraded due to a deviation from the desired similar neighbor. This paper examines how the size of learning data affects stock price predictability through k-nearest neighbor and compares the predictability of k-nearest neighbor with the random walk model according to the size of the learning data and the number of neighbors. In this study, Samsung electronics stock prices were predicted by dividing the learning dataset into two types. For the prediction of next day's closing price, we used four variables: opening value, daily high, daily low, and daily close. In the first experiment, data from January 1, 2000 to December 31, 2017 were used for the learning process. In the second experiment, data from January 1, 2015 to December 31, 2017 were used for the learning process. The test data is from January 1, 2018 to August 31, 2018 for both experiments. We compared the performance of k-NN with the random walk model using the two learning dataset. The mean absolute percentage error (MAPE) was 1.3497 for the random walk model and 1.3570 for the k-NN for the first experiment when the learning data was small. However, the mean absolute percentage error (MAPE) for the random walk model was 1.3497 and the k-NN was 1.2928 for the second experiment when the learning data was large. These results show that the prediction power when more learning data are used is higher than when less learning data are used. Also, this paper shows that k-NN generally produces a better predictive power than random walk model for larger learning datasets and does not when the learning dataset is relatively small. Future studies need to consider macroeconomic variables related to stock price forecasting including opening price, low price, high price, and closing price. Also, to produce better results, it is recommended that the k-nearest neighbor needs to find nearest neighbors using the second step filtering method considering fundamental economic variables as well as a sufficient amount of learning data.

• The Journal of the Acoustical Society of Korea
• /
• v.30 no.8
• /
• pp.446-460
• /
• 2011

The use of induction motors has been recently increasing with automation in aeronautical and automotive industries, and it playes a significant role. This has motivated that many researchers have studied on developing fault detection and classification systems of an induction motor in order to minimize economical damage caused by its fault. With this reason, this paper proposed feature vector extraction methods based on STE (short-time energy)+SVD (singular value decomposition) and DCT (discrete cosine transform)+SVD techniques to early detect and diagnose faults of induction motors, and classified faults of an induction motor into different types of them by using extracted features as inputs of BPNN (back propagation neural network) and multi-layer SVM (support vector machine). When BPNN and multi-lay SVM are used as classifiers for fault classification, there are many settings that affect classification performance: the number of input layers, the number of hidden layers and learning algorithms for BPNN, and standard deviation values of Gaussian radial basis function for multi-layer SVM. Therefore, this paper quantitatively simulated to find appropriate settings for those classifiers yielding higher classification performance than others.

• 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 the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.3 s.303
• /
• pp.47-52
• /
• 2005

Obstructive Sleep Apnea (OSA) is a representative symptom of sleep disorder caused by the obstruction of upper airway. Because OSA causes not only excessive daytime sleepiness and fatigue, hypertension and arrhythmia but also cardiac arrest and sudden death during sleep in the severe case, it is very important to detect the occurrence and the frequency of OSA. OSA is usually diagnosed through the laboratory-based Polysomnography (PSG) which is uncomfortable and expensive. Therefore researches to improve the disadvantages of PSG are needed and studies for the detection of OSA using only one or two parameters are being made as alternatives to PSG. In this paper, we developed an algorithm for the detection of OSA based on Heart Rate Variability (HRV). The proposed method is applied to the ECG data sets provided from PhysioNet which consist of learning set and training set. We extracted features for the detection of OSA such as average and standard deviation of 1 minute R-R interval, power spectrum of R-R interval and S-peak amplitude from data sets. These features are applied to the input of neural network. As a result, we obtained sensitivity of $89.66\%$ and specificity of $95.25\%$. It shows that the features suggested in this study are useful to detect OSA.

• Journal of Bio-Environment Control
• /
• v.26 no.4
• /
• pp.411-417
• /
• 2017

Environmental and growth factors such as light intensity, vapor pressure deficit, and leaf area index are important variables that can change the transpiration rate of plants. The objective of this study was to compare the transpiration rates estimated by modified Penman-Monteith model and artificial neural network. The transpiration rate of paprika (Capsicum annuum L. cv. Fiesta) was obtained by using the change in substrate weight measured by load cells. Radiation, temperature, relative humidity, and substrate weight were collected every min for 2 months. Since the transpiration rate cannot be accurately estimated with linear equations, a modified Penman-Monteith equation using compensated radiation (Shin et al., 2014) was used. On the other hand, ANN was applied to estimating the transpiration rate. For this purpose, an ANN composed of an input layer using radiation, temperature, relative humidity, leaf area index, and time as input factors and five hidden layers was constructed. The number of perceptons in each hidden layer was 512, which showed the highest accuracy. As a result of validation, $R^2$ values of the modified model and ANN were 0.82 and 0.94, respectively. Therefore, it is concluded that the ANN can estimate the transpiration rate more accurately than the modified model and can be applied to the efficient irrigation strategy in soilless cultures.