• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1604-1611
• /
• 2020

Light field image captured by a microlens array-based camera has many limitations in practical use due to its low spatial resolution and angular resolution. High spatial resolution images can be easily acquired with a single image super-resolution technique that has been studied a lot recently. But there is a problem in that high angular resolution images are distorted in the process of using disparity information inherent among images, and thus it is difficult to obtain a high-quality angular resolution image. In this paper, we propose light field angular super-resolution that extracts an initial feature map using an dilated convolutional neural network in order to effectively extract the view difference information inherent among images and generates target image using a residual neural network. The proposed network showed superior performance in PSNR and subjective image quality compared to existing angular super-resolution networks.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.130-138
• /
• 2021

This paper presents an effective structure by applying various normalization to Convolutional Neural Networks (CNN) for seismic event classification. Normalization techniques can not only improve the learning speed of neural networks, but also show robustness to noise. In this paper, we analyze the effect of input data normalization and hidden layer normalization on the deep learning model for seismic event classification. In addition an effective model is derived through various experiments according to the structure of the applied hidden layer. As a result of various experiments, the model that applied input data normalization and weight normalization to the first hidden layer showed the most stable performance improvement.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1259-1268
• /
• 2023

This study proposes a throttle and steering control technology using visual sensors based on deep learning's convolutional and recurrent neural networks. It collects camera image and control value data while driving a training track in clockwise and counterclockwise directions, and generates a model to predict throttle and steering through data sampling and preprocessing for efficient learning. Afterward, the model was validated on a test track in a different environment that was not used for training to find the optimal model and compare it with a CNN (Convolutional Neural Network). As a result, we found that the proposed deep learning model has excellent performance.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.63-65
• /
• 2023

본 논문에서는 FDG-PET 영상을 사용하는 딥러닝 네트워크를 이용하여 직장암 환자의 치료 후 완치를 예측하는 연구를 수행하였다. 직장암은 흔한 악성 종양 중 하나이지만 병리학적으로 완전하게 치료되는 가능성이 매우 낮아, 치료 후의 반응을 예측하고 적절한 치료 방법을 선택하는 것이 중요하다. 따라서 본 연구에서는 FDG-PET 영상에 합성곱 신경망(CNN)모델을 활용하여 딥러닝 네트워크를 구축하고 직장암 환자의 치료반응을 예측하는 연구를 진행하였다. 116명의 직장암 환자의 FDG-PET 영상을 획득하였다. 대상군은 2cm 이상의 종양 크기를 가지는 환자를 대상으로 하였으며 치료 후 완치된 환자는 21명이었다. FDG-PET 영상은 전신 영역과 종양 영역으로 나누어 평가하였다. 딥러닝 네트워크는 2차원 및 3차원 영상입력에 대한 CNN 모델로 구성되었다. 학습된 CNN 모델을 사용하여 직장암의 치료 후 완치를 예측하는 성능을 평가하였다. 학습 결과에서 평균 정확도와 정밀도는 각각 0.854와 0.905로 나타났으며, 모든 CNN 모델과 영상 영역에 따른 성능을 보였다. 테스트 결과에서는 3차원 CNN 모델과 종양 영역만을 이용한 네트워크에서 정확도가 높게 평가됨을 확인하였다. 본 연구에서는 CNN 모델의 입력 영상에 따른 차이와 영상 영역에 따른 딥러닝 네트워크의 성능을 평가하였으며 딥러닝 네트워크 모델을 통해 직장암 치료반응을 예측하고 적절한 치료 방향 결정에 도움이 될 것으로 기대한다.

• Journal of Convergence for Information Technology
• /
• v.10 no.8
• /
• pp.23-34
• /
• 2020

Recently, the artificial intelligence deep learning field has been hard to commercialize due to the high computing power and the price problem of computing resources. In this paper, we apply a double pruning techniques to evaluate the performance of the in-depth neural network and various datasets. Double pruning combines basic Network-slimming and Parameter-prunning. Our proposed technique has the advantage of reducing the parameters that are not important to the existing learning and improving the speed without compromising the learning accuracy. After training various datasets, the pruning ratio was increased to reduce the size of the model.We confirmed that MobileNet-V3 showed the highest performance as a result of NetScore performance analysis. We confirmed that the performance after pruning was the highest in MobileNet-V3 consisting of depthwise seperable convolution neural networks in the Cifar 10 dataset, and VGGNet and ResNet in traditional convolutional neural networks also increased significantly.

• Smart Media Journal
• /
• v.8 no.3
• /
• pp.62-69
• /
• 2019

Electrocardiogram (ECG) signals cannot be counterfeited and can easily acquire signals from both wrists. In this paper, we propose a method of generating a coupling image using direction information of ECG signals as well as its usage in a personal recognition method. The proposed coupling image is generated by using forward ECG signal and rotated inverse ECG signal based on R-peak, and the generated coupling image shows a unique pattern and brightness. In addition, R-peak data is increased through the ECG signal calculation of the same beat, and it is thus possible to improve the recognition performance of the individual. The generated coupling image extracts characteristics of pattern and brightness by using the proposed convolutional neural network and reduces data size by using multiple pooling layers to improve network speed. The experiment uses public ECG data of 47 people and conducts comparative experiments using five networks with top 5 performance data among the public and the proposed networks. Experimental results show that the recognition performance of the proposed network is the highest with 99.28%, confirming potential of the personal recognition.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.319-320
• /
• 2023

본 논문에서는 합성곱 신경망이 적용된 네트워크를 활용해 전이 학습의 과정을 거친 멸종위기종 철새들의 이미지를 분류하는 시스템의 설계과정과 결과를 제시한다. 연구 방법으로 한국 영랑호를 찾아오는 멸종위기종, 천연기념물인 철새들의 이미지를 학습시켜 "가창오리", "노랑부리백로", "물총새" 이 세 종의 철새들을 매우 정확하게 분류하는 것을 확인하였다. 데이터 예비학습과정에서 train data의 개수를 40개로 진행했을때 약 92%의 정확도를 확인 후, train data의 이미지 개수를 50장으로 늘려 더 높은 정확도를 얻을 수 있었다. 이 시스템은 한국을 방문하는 멸종위기종 철새들을 무분별하게 포획하지 않도록 철새 이미지 분류시 활용 가능하다고 사료된다.

• Journal of Aerospace System Engineering
• /
• v.16 no.4
• /
• pp.17-27
• /
• 2022

In this study, a deep learning-based network that can predict the aerodynamic characteristics of airfoils was designed, and the feasibility of the proposed network was confirmed by applying aerodynamic data generated by Xfoil. The prediction of aerodynamic characteristics according to the variation of airfoil thickness was performed. Considering the angle of attack, the coordinate data of an airfoil is converted into image data using signed distance function. Additionally, the distribution of the pressure coefficient on airfoil is expressed as reduced data via proper orthogonal decomposition, and it was used as the output of the proposed network. The test data were constructed to evaluate the interpolation and extrapolation performance of the proposed network. As a result, the coefficients of determination of the lift coefficient and moment coefficient were confirmed, and it was found that the proposed network shows benign performance for the interpolation test data, when compared to that of the extrapolation test data.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.865-868
• /
• 2017

일반적으로 비디오로부터 캡션을 생성하는 작업은 입력 비디오로부터 특징을 추출해내는 과정과 추출한 특징을 이용하여 캡션을 생성해내는 과정을 포함한다. 본 논문에서는 효과적인 비디오 캡션 생성을 위한 심층 신경망 모델과 그 학습 방법을 소개한다. 본 논문에서는 입력 비디오를 표현하는 시각 특징 외에, 비디오를 효과적으로 표현하는 동적 의미 특징과 정적 의미 특징을 입력 특징으로 이용한다. 본 논문에서 입력 비디오의 시각 특징들은 C3D, ResNet과 같은 합성곱 신경망을 이용하여 추출하지만, 의미 특징은 본 논문에서 제안하는 의미 특징 추출 네트워크를 활용하여 추출한다. 그리고 이러한 특징들을 기반으로 비디오 캡션을 효과적으로 생성하기 위하여 선택적 주의집중 캡션 생성 네트워크를 제안한다. Youtube 동영상으로부터 수집된 MSVD 데이터 집합을 이용한 다양한 실험을 통해, 본 논문에서 제안한 모델의 성능과 효과를 확인할 수 있었다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.3
• /
• pp.355-363
• /
• 2020

In this paper, we propose a deep learning training method for accurately classifying Kuzushiji-MNIST and Kuzushiji-49 datasets for ancient and medieval Japanese characters. We analyze the latest convolutional neural network networks through experiments to select the most suitable network, and then use the networks to select the number of training to classify Kuzushiji-MNIST and Kuzushiji-49 datasets. In addition, the training is conducted with high accuracy by applying learning methods such as Mixup and Random Erase. As a result of the training, the accuracy of the proposed method can be shown to be high by 99.75% for MNIST, 99.07% for Kuzushiji-MNIST, and 97.56% for Kuzushiji-49. Through this deep learning-based technology, it is thought to provide a good research base for various researchers who study East Asian and Western history, literature, and culture.