• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.27-35
• /
• 2023

In this paper, we propose a process of increasing productivity by applying a deep learning-based defect detection and classification system to the prepreg fiber manufacturing process, which is in high demand in the field of producing composite materials. In order to apply it to toe prepreg manufacturing equipment that requires a solution due to the occurrence of a large amount of defects in various conditions, the optimal environment was first established by selecting cameras and lights necessary for defect detection and classification model production. In addition, data necessary for the production of multiple classification models were collected and labeled according to normal and defective conditions. The multi-classification model is made based on CNN and applies pre-learning models such as VGGNet, MobileNet, ResNet, etc. to compare performance and identify improvement directions with accuracy and loss graphs. Data augmentation and dropout techniques were applied to identify and improve overfitting problems as major problems. In order to evaluate the performance of the model, a performance evaluation was conducted using the confusion matrix as a performance indicator, and the performance of more than 99% was confirmed. In addition, it checks the classification results for images acquired in real time by applying them to the actual process to check whether the discrimination values are accurately derived.

• Journal of Intelligence and Information Systems
• /
• v.9 no.3
• /
• pp.117-135
• /
• 2003

This study is to propose a procedure solving scale problem of traditional collaborative filtering (CF) approach. The CF approach generally uses some similarity measures like correlation coefficient. So, as the user of the Website increases, the complexity of computation increases exponentially. To solve the scale problem, this study suggests a clustering model-based approach using Self-Organizing Map (SOM) and RFM (Recency, Frequency, Momentary) method. SOM clusters users into some user groups. The preference score of each item in a group is computed using RFM method. The items are sorted and stored in their preference score order. If an active user logins in the system, SOM determines a user group according to the user's characteristics. And the system recommends items to the user using the stored information for the group. If the user evaluates the recommended items, the system determines whether it will be updated or not. Experimental results applied to MovieLens dataset show that the proposed method outperforms than the traditional CF method comparatively in the recommendation performance and the computation complexity.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.2
• /
• pp.509-514
• /
• 2020

The conventional TTS system consists of several modules, including text preprocessing, parsing analysis, grapheme-to-phoneme conversion, boundary analysis, prosody control, acoustic feature generation by acoustic model, and synthesized speech generation. But TTS system with deep learning is composed of Text2Mel process that generates spectrogram from text, and vocoder that synthesizes speech signals from spectrogram. In this paper, for the optimal Korean TTS system construction we apply Tacotron2 to Tex2Mel process, and as a vocoder we introduce the methods such as WaveNet, WaveRNN, and WaveGlow, and implement them to verify and compare their performance. Experimental results show that WaveNet has the highest MOS and the trained model is hundreds of megabytes in size, but the synthesis time is about 50 times the real time. WaveRNN shows MOS performance similar to that of WaveNet and the model size is several tens of megabytes, but this method also cannot be processed in real time. WaveGlow can handle real-time processing, but the model is several GB in size and MOS is the worst of the three vocoders. From the results of this study, the reference criteria for selecting the appropriate method according to the hardware environment in the field of applying the TTS system are presented in this paper.

• Journal of the Korea Convergence Society
• /
• v.11 no.5
• /
• pp.1-8
• /
• 2020

Machine translation refers to a system where a computer translates a source sentence into a target sentence. There are various subfields of machine translation. APE (Automatic Post Editing) is a subfield of machine translation that produces better translations by editing the output of machine translation systems. In other words, it means the process of correcting errors included in the translations generated by the machine translation system to make proofreading. Rather than changing the machine translation model, this is a research field to improve the translation quality by correcting the result sentence of the machine translation system. Since 2015, APE has been selected for the WMT Shaed Task. and the performance evaluation uses TER (Translation Error Rate). Due to this, various studies on the APE model have been published recently, and this paper deals with the latest research trends in the field of APE.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.363-363
• /
• 2019

활성화 함수(activation function)는 기계학습(machine learning)의 학습과정에 비선형성을 도입하여 심층적인 학습을 용이하게 하고 예측의 정확도를 높이는 중요한 요소 중 하나이다(Roy et al., 2019). 일반적으로 기계학습에서 사용되고 있는 활성화 함수의 종류에는 계단 함수(step function), 시그모이드 함수(sigmoid 함수), 쌍곡 탄젠트 함수(hyperbolic tangent function), ReLU 함수(Rectified Linear Unit function) 등이 있으며, 예측의 정확도 향상을 위하여 다양한 형태의 활성화 함수가 제시되고 있다. 본 연구에서는 기계학습을 통하여 수위예측 시 정확도 향상을 위하여 Hybrid 활성화 함수를 제안하였다. 연구대상지는 조수간만의 영향을 받는 한강을 대상으로 선정하였으며, 2009년 ~ 2018년까지 10년간의 수문자료를 활용하였다. 수위예측 알고리즘은 Python 내 Tensorflow의 RNN (Recurrent Neural Networks) 모델을 이용하였으며, 강수량, 수위, 조위, 댐 방류량, 하천 유량의 수문자료를 학습시켜 3시간 및 6시간 후의 수위를 예측하였다. 예측정확도 향상을 위하여 입력 데이터는 정규화(Normalization)를 시켰으며, 민감도 분석을 통하여 신경망모델의 은닉층 개수, 학습률의 최적 값을 도출하였다. Hybrid 활성화 함수는 쌍곡 탄젠트 함수와 ReLU 함수를 혼합한 형태로 각각의 가중치($w_1,w_2,w_1+w_2=1$)를 변경하여 정확도를 평가하였다. 그 결과 가중치의 비($w_1/w_2$)에 따라서 예측 결과의 RMSE(Roote Mean Square Error)가 최소가 되고 NSE (Nash-Sutcliffe model Efficiency coefficient)가 최대가 되는 지점과 Peak 수위의 예측정확도가 최대가 되는 지점을 확인할 수 있었다. 본 연구는 현재 Data modeling을 통한 수위예측의 정확도 향상을 위해 기초가 되는 연구이나, 향후 다양한 형태의 활성화 함수를 제안하여 정확도를 향상시킨다면 예측 결과를 통하여 침수예보에 대한 의사결정이 가능할 것으로 기대된다.

• Journal of the Korea Computer Graphics Society
• /
• v.24 no.2
• /
• pp.1-9
• /
• 2018

In this paper, we propose a method to restore corrupted black and white facial images to color. Previous studies have shown that when coloring damaged black and white photographs, such as old ID photographs, the area around the damaged area is often incorrectly colored. To solve this problem, this paper proposes a method of restoring the damaged area of input photo first and then performing colorization based on the result. The proposed method consists of two steps: BEGAN (Boundary Equivalent Generative Adversarial Networks) model based restoration and CNN (Convolutional Neural Network) based coloring. Our method uses the BEGAN model, which enables a clearer and higher resolution image restoration than the existing methods using the DCGAN (Deep Convolutional Generative Adversarial Networks) model for image restoration, and performs colorization based on the restored black and white image. Finally, we confirmed that the experimental results of various types of facial images and masks can show realistic color restoration results in many cases compared with the previous studies.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.155-170
• /
• 2018

Predicting a company's financial bankruptcy is traditionally one of the most crucial forecasting problems in business analytics. In previous studies, prediction models have been proposed by applying or combining statistical and machine learning-based techniques. In this paper, we propose a novel intelligent prediction model based on the simulated annealing which is one of the well-known optimization techniques. The simulated annealing is known to have comparable optimization performance to the genetic algorithms. Nevertheless, since there has been little research on the prediction and classification of business decision-making problems using the simulated annealing, it is meaningful to confirm the usefulness of the proposed model in business analytics. In this study, we use the combined model of simulated annealing and machine learning to select the input features of the bankruptcy prediction model. Typical types of combining optimization and machine learning techniques are feature selection, feature weighting, and instance selection. This study proposes a combining model for feature selection, which has been studied the most. In order to confirm the superiority of the proposed model in this study, we apply the real-world financial data of the Korean companies and analyze the results. The results show that the predictive accuracy of the proposed model is better than that of the naïve model. Notably, the performance is significantly improved as compared with the traditional decision tree, random forests, artificial neural network, SVM, and logistic regression analysis.

• Information Systems Review
• /
• v.18 no.2
• /
• pp.173-198
• /
• 2016

Financial distress can damage stakeholders and even lead to significant social costs. Thus, financial distress prediction is an important issue in macroeconomics. However, most existing studies on building a financial distress prediction model have only considered idiosyncratic risk factors without considering systematic risk factors. In this study, we propose a prediction model that considers both the idiosyncratic risk based on a financial ratio and the systematic risk based on a business cycle. Ultimately, we build several IT artifacts associated with financial ratio and add them to the idiosyncratic risk factors as well as address the imbalanced data problem by using an oversampling technique and synthetic minority oversampling technique (SMOTE) to ensure good performance. When considering systematic risk, our study ensures that each data set consists of both financially distressed companies and financially sound companies in each business cycle phase. We conducted several experiments that change the initial imbalanced sample ratio between the two company groups into a 1:1 sample ratio using SMOTE and compared the prediction results from the individual data set. We also predicted data sets from the subsequent business cycle phase as a test set through a built prediction model that used business contraction phase data sets, and then we compared previous prediction performance and subsequent prediction performance. Thus, our findings can provide insights into making rational decisions for stakeholders that are experiencing an economic crisis.

• Journal of the Korean Geotechnical Society
• /
• v.15 no.1
• /
• pp.99-112
• /
• 1999

By using 92 values of lateral earth pressure coefficient(K) measured in Korea, the tendency of K with varying depth is analyzed and compared with the range of K defined by Hoek and Brown. The horizontal stress is generally larger than the vertical stress in Korea : About 84 % of K values are above 1. In this study, the theory of elasto-plasticity is applied to analyze the variation of K values, and the results are compared with those of numerical analysis. This reveals that the erosion, sedimentation and weathering of earth crust are important factors in the determination of K values. Surface erosion, large lateral pressure and good rock mass increase the K values, but sedimentation decreases the K values. This study enable us to analyze the effects of geological processes on the K values, especially at shallow depth where underground excavation takes place. A neural network expert system using multi-layer back-propagation algorithm is developed to predict the K values. The neural network model has a correlation coefficient above 0.996 when it is compared with measured data. The comparison with 9 measured data which are not included in the back-propagation learning has shown an average inference error of 20% and the correlation coefficient above 0.95. The expert system developed in this study can be used for reliable determination of K values.

• The KIPS Transactions:PartD
• /
• v.16D no.6
• /
• pp.851-858
• /
• 2009

Mobbing is not restricted to problem of young people but the bigger recent problem occurs in workspaces. According to reports of ILO and domestic case mobbing in the workplace is increasing more and more numerically from 9.1%('03) to 30.7%('08). These mobbing brings personal and social losses. The proposed algorithm makes it possible to grasp not only current mobbing victims but also potential mobbing victims through user profile and contribute to efficient personnel management. This paper extracts user profile related to mobbing, in a way of selecting seven factors and fifty attributes that are related to this matter. Next, expressing extracting factors as '1' if they are related me or not '0'. And apply similarity function to attributes summation included in factors to calculate similarity between the users. Third, calculate optimizing weight choosing factors included attributes by applying neural network algorithm of SPSS Clementine and through this summation Mobbing-Value(MV) can be calculated . Finally by mapping MV of online social network users to G2 mobbing propensity classification model(4 Groups; Ideal Group of the online social network, Bullies, Aggressive victims, Victims) which is designed in this paper, can grasp mobbing propensity of users, which will contribute to efficient personnel management.