• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.141-143
• /
• 2021

본 논문에서는 목조 문화재의 변위량을 감지할 수 있는 앙상블 딥러닝 모델 모델을 제안한다. 우선 총 2개의 서로 다른 사전 학습된 합성 곱 신경망을 사용하여 입력 영상에 대한 심층 특징들을 추출한다. 그 이후 2개의 서로 다른 심층 특징들을 결합하여 하나의 특징 벡터를 생성한다. 그 이후 합쳐진 특징 벡터는 완전 연결 계층의 입력 값으로 들어와서 최종적으로 변위의 심각 단계에 대한 예측을 수행하게 된다. 데이터 셋으로는 충주시 근처의 문화재에 방문해서 수집한 목조 문화재 이미지를 가지고 정상 및 비정상으로 구분한 데이터 셋을 사용하였다. 실험 결과 앙상블 딥러닝 기법을 사용한 모델이 앙상블 기법을 사용하지 않는 모델보다 더 좋은 성능을 나타냄을 확인하였다. 이러한 결과로부터 우리가 제안한 방법이 목재 문화재의 변위량 예측에 있어서 매우 적합함을 보여준다.

• Transactions of the Korean hydrogen and new energy society
• /
• v.31 no.5
• /
• pp.436-443
• /
• 2020

The performance prediction model of a solid oxide fuel cell stack has been developed using deep neural network technique, one of the machine learning methods. The machine learning has been received much interest in various fields, including energy system mo- deling. Using machine learning technique can save time and cost requried in developing an energy system model being compared to the conventional method, that is a combination of a mathematical modeling and an experimental validation. Results reveal that the mean average percent error, root mean square error, and coefficient of determination (R2) range 1.7515, 0.1342, 0.8597, repectively, in maximum. To improve the predictability of the model, the pre-processing is effective and interpolative machine learning and application is more accurate than the extrapolative cases.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.4
• /
• pp.625-632
• /
• 2021

This paper studies the effect of the number of filters in the CNN (Convolutional Neural Network) layer on the performance of a noise attenuator. Speech is estimated from a noised speech signal using a 64-neuron, 16-kernel CNN filter and an error back-propagation algorithm. In this study, in order to verify the performance of the noise attenuator with respect to the number of filters, a program using Keras library was written and simulation was performed. As a result of simulation, it can be seen that this system has the smallest MSE (Mean Squared Error) and MAE (Mean Absolute Error) values when the number of filters is 16, and the performance is the lowest when there are 4 filters. And when there are more than 8 filters, it was shown that the MSE and MAE values do not differ significantly depending on the number of filters. From these results, it can be seen that about 8 or more filters must be used to express the characteristics of the speech signal.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.10
• /
• pp.1435-1440
• /
• 2021

With the advent of the low interest rate era, many investors are flocking to the stock market. In the past stock market, people invested in stocks labor-intensively through company analysis and their own investment techniques. However, in recent years, stock investment using artificial intelligence and data has been widely used. The success rate of stock prediction through artificial intelligence is currently not high, so various artificial intelligence models are trying to increase the stock prediction rate. In this study, we will look at various artificial intelligence models and examine the pros and cons and prediction rates between each model. This study investigated as stock prediction programs using artificial intelligence artificial neural network (ANN), deep learning or hierarchical learning (DNN), k-nearest neighbor algorithm(k-NN), convolutional neural network (CNN), recurrent neural network (RNN), and LSTMs.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.351-360
• /
• 2022

Image blurring is a phenomenon that occurs due to factors such as movement of a subject and shaking of a camera. Recently, the research for image deblurring has been actively conducted based on convolution neural networks. In particular, the method of guiding the restoration process via the difference between blur and sharp images has shown the promising performance. This paper proposes a novel method for improving the deblurring performance based on the distortion information. To this end, the transformer-based neural network module is designed to guide the restoration process. The proposed method efficiently reflects the distorted region, which is predicted through the global inference during the deblurring process. We demonstrate the efficiency and robustness of the proposed module based on experimental results with various deblurring architectures and benchmark datasets.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.7
• /
• pp.37-44
• /
• 2021

Automatic classification of brain MRI images play an important role in early diagnosis of brain tumors. In this work, we present a deep learning-based brain tumor classification model in MRI images using ensemble of deep features. In our proposed framework, three different deep features from brain MR image are extracted using three different pre-trained models. After that, the extracted deep features are fed to the classification module. In the classification module, the three different deep features are first fed into the fully-connected layers individually to reduce the dimension of the features. After that, the output features from the fully-connected layers are concatenated and fed into the fully-connected layer to predict the final output. To evaluate our proposed model, we use openly accessible brain MRI dataset from web. Experimental results show that our proposed model outperforms other machine learning-based models.

• Journal of Convergence for Information Technology
• /
• v.12 no.4
• /
• pp.260-269
• /
• 2022

In this paper, We propose an anomaly detection model using deep neural network to automate the identification of outliers of the national air pollution measurement network data that is previously performed by experts. We generated training data by analyzing missing values and outliers of weather data provided by the Institute of Environmental Research and based on the BeatGAN model of the unsupervised learning method, we propose a new model by changing the kernel structure, adding the convolutional filter layer and the transposed convolutional filter layer to improve anomaly detection performance. In addition, by utilizing the generative features of the proposed model to implement and apply a retraining algorithm that generates new data and uses it for training, it was confirmed that the proposed model had the highest performance compared to the original BeatGAN models and other unsupervised learning model like Iforest and One Class SVM. Through this study, it was possible to suggest a method to improve the anomaly detection performance of proposed model while avoiding overfitting without additional cost in situations where training data are insufficient due to various factors such as sensor abnormalities and inspections in actual industrial sites.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.319-325
• /
• 2022

The variation of utterance lengths is a representative factor that can degrade the performance of speaker verification systems. To handle this issue, previous studies had attempted to extract speaker features from various branches or to use convolution layers with different receptive fields. Combining the advantages of the previous two approaches for variable-length input, this paper proposes integrated receptive field diversification that extracts speaker features through more diverse receptive field. The proposed method processes the input features by convolutional layers with different receptive fields at multiple time-axis branches, and extracts speaker embedding by dynamically aggregating the processed features according to the lengths of input utterances. The deep neural networks in this study were trained on the VoxCeleb2 dataset and tested on the VoxCeleb1 evaluation dataset that divided into 1 s, 2 s, 5 s, and full-length. Experimental results demonstrated that the proposed method reduces the equal error rate by 19.7 % compared to the baseline.

• Journal of the Korean Society of Visualization
• /
• v.20 no.3
• /
• pp.109-116
• /
• 2022

The optimized design of airfoils is essential to increase the performance and efficiency of wind turbines. The aerodynamic characteristics of airfoils near the stall show large deviation from experiments and numerical simulations. Hence, it is needed to perform repetitive analysis of various shapes near the stall. To overcome this, the artificial intelligence is used and combined with numerical simulations. In this study, three types of airfoils are chosen, which are S809, S822 and SD7062 used in wind turbines. A convolutional neural network model is proposed in the combination of VGG16 and U-Net. Learning data are constructed by extracting pressure fields and aerodynamic characteristics through numerical analysis of 2D shape. Based on these data, the pressure field and lift coefficient of untrained airfoils are predicted. As a result, even in untrained airfoils, the pressure field is accurately predicted with an error of within 0.04%.

• Journal of the Korean Society of Visualization
• /
• v.21 no.1
• /
• pp.103-109
• /
• 2023

This research developed a measurement technique that can measure the oxygen temperature inside a high temperature furnace. Instead of measuring only changes in frequency components within a small range used in the existing variable laser absorption spectroscopy, laser spectroscopy technology was used to spread out wavelength of the light source passing through the gas Based on a total of 20,000 image data, research was conducted to predict the temperature of a high-temperature furnace using CNN with black and white images in the form of spectral bands by temperature of 25 to 800 degrees. The optimal model was found through Hyper parameter optimization, R2 score is 0.89, and the accuracy of the test data is 88.73%. Based on this research, it is expected that concentration measurement and air-fuel ratio control technology can be applied.