• Smart Media Journal
• /
• v.10 no.4
• /
• pp.45-54
• /
• 2021

The skin is the body's first line of defense against external infection. When a skin disease strikes, the skin's protective role is compromised, necessitating quick diagnosis and treatment. Recently, as artificial intelligence has advanced, research for technical applications has been done in a variety of sectors, including dermatology, to reduce the rate of misdiagnosis and obtain quick treatment using artificial intelligence. Although previous studies have diagnosed skin diseases with low incidence, this paper proposes a method to classify common illnesses such as warts and corns using a convolutional neural network. The data set used consists of 3 classes and 2,515 images, but there is a problem of lack of training data and class imbalance. We analyzed the performance using a deep metric loss function and a cross-entropy loss function to train the model. When comparing that in terms of accuracy, recall, F1 score, and accuracy, the former performed better.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.725-737
• /
• 2021

Although the performance of cameras is gradually improving now, there are noise in the acquired digital images from the camera, which acts as an obstacle to obtaining high-resolution images. Traditionally, a filtering method has been used for denoising, and a convolutional neural network (CNN), one of the deep learning techniques, has been showing better performance than traditional methods in the field of image denoising, but the details in images could be lost during the learning process. In this paper, we present a CNN for image denoising, which improves image details by learning the details of the image based on wavelet transform. The proposed network uses two subnetworks for detail enhancement and noise extraction. The experiment was conducted through Gaussian noise and real-world noise, we confirmed that our proposed method was able to solve the detail loss problem more effectively than conventional algorithms, and we verified that both objective quality evaluation and subjective quality comparison showed excellent results.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.29-37
• /
• 2021

In this paper, we propose a deep learning-based retinal vessel segmentation model for handling multi-scale information of fundus images. we integrate the selective kernel convolution into U-Net-based convolutional neural network. The proposed model extracts and segment features information with various shapes and sizes of retinal blood vessels, which is important information for diagnosing eye-related diseases from fundus images. The proposed model consists of standard convolutions and selective kernel convolutions. While the standard convolutional layer extracts information through the same size kernel size, The selective kernel convolution extracts information from branches with various kernel sizes and combines them by adaptively adjusting them through split-attention. To evaluate the performance of the proposed model, we used the DRIVE and CHASE DB1 datasets and the proposed model showed F1 score of 82.91% and 81.71% on both datasets respectively, confirming that the proposed model is effective in segmenting retinal blood vessels.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.3
• /
• pp.115-122
• /
• 2019

For Korean phoneme recognition, Hidden Markov-Gaussian Mixture model(HMM-GMM) or hybrid models which combine artificial neural network with HMM have been mainly used. However, current approach has limitations in that such models require force-aligned corpus training data that is manually annotated by experts. Recently, researchers used neural network based phoneme recognition model which combines recurrent neural network(RNN)-based structure with connectionist temporal classification(CTC) algorithm to overcome the problem of obtaining manually annotated training data. Yet, in terms of implementation, these RNN-based models have another difficulty in that the amount of data gets larger as the structure gets more sophisticated. This problem of large data size is particularly problematic in the Korean language, which lacks refined corpora. In this study, we introduce CTC algorithm that does not require force-alignment to create a Korean phoneme recognition model. Specifically, the phoneme recognition model is based on convolutional neural network(CNN) which requires relatively small amount of data and can be trained faster when compared to RNN based models. We present the results from two different experiments and a resulting best performing phoneme recognition model which distinguishes 49 Korean phonemes. The best performing phoneme recognition model combines CNN with 3hop Bidirectional LSTM with the final Phoneme Error Rate(PER) at 3.26. The PER is a considerable improvement compared to existing Korean phoneme recognition models that report PER ranging from 10 to 12.

• Journal of Korea Water Resources Association
• /
• v.54 no.5
• /
• pp.301-309
• /
• 2021

In this study, we tried to improve the performance of the existing U-net-based deep learning rainfall prediction model, which can weaken the meaning of time series order. For this, ConvLSTM2D U-Net structure model considering temporal consistency of data was applied, and we evaluated accuracy of the ConvLSTM2D U-Net model using a RainNet model and an extrapolation-based advection model. In addition, we tried to improve the uncertainty in the model training process by performing learning not only with a single model but also with 10 ensemble models. The trained neural network rainfall prediction model was optimized to generate 10-minute advance prediction data using four consecutive data of the past 30 minutes from the present. The results of deep learning rainfall prediction models are difficult to identify schematically distinct differences, but with ConvLSTM2D U-Net, the magnitude of the prediction error is the smallest and the location of rainfall is relatively accurate. In particular, the ensemble ConvLSTM2D U-Net showed high CSI, low MAE, and a narrow error range, and predicted rainfall more accurately and stable prediction performance than other models. However, the prediction performance for a specific point was very low compared to the prediction performance for the entire area, and the deep learning rainfall prediction model also had limitations. Through this study, it was confirmed that the ConvLSTM2D U-Net neural network structure to account for the change of time could increase the prediction accuracy, but there is still a limitation of the convolution deep neural network model due to spatial smoothing in the strong rainfall region or detailed rainfall prediction.

• Journal of Internet Computing and Services
• /
• v.23 no.4
• /
• pp.21-33
• /
• 2022

Recently, the recommender system has been widely used in various fields such as movies, music, online shopping, and social media, and in the meantime, the recommender model has been developed from correlation analysis through the Apriori model, which can be said to be the first-generation model in the recommender system field. In 2005, many models have been proposed, including deep learning-based models, which are receiving a lot of attention within the recommender model. The recommender model can be classified into a collaborative filtering method, a content-based method, and a hybrid method that uses these two methods integrally. However, these basic methods are gradually losing their status as methodologies in the field as they fail to adapt to internal and external changing factors such as the rapidly changing user-item interaction and the development of big data. On the other hand, the importance of deep learning methodologies in recommender systems is increasing because of its advantages such as nonlinear transformation, representation learning, sequence modeling, and flexibility. In this paper, among deep learning methodologies, RNN, CNN, and GAN-based models suitable for sequential modeling that can accurately and flexibly analyze user-item interactions are classified, compared, and analyzed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.338-339
• /
• 2018

본 논문은 스피커 임베딩을 이용한 다화자 음성 합성 시스템을 제안한다. 이 모델은 인공신경망을 기반으로 하는 당일화자 음성 합성 시스템인 타코트론을 기초로 구성된다. [1]. 제안 된 모델은 입력 데이터에 화자 임베딩을 추가 데이터로 항께 넣어주는 간단한 방식으로 구현되며 당일화자 모델에 비해 큰 성능 저하 없이 성공적으로 음성을 생성한다.

• Composites Research
• /
• v.36 no.1
• /
• pp.48-52
• /
• 2023

Fiber-reinforced composites have anisotropic material properties, so the mechanical properties of composite structures can vary depending on the stacking sequence. Therefore, it is essential to design the proper stacking sequence of composite structures according to the functional requirements. However, depending on the manufacturing condition or the shape of the structure, there are many cases where the designed stacking angle is out of range, which can affect structural performance. Accordingly, it is important to analyze the stacking angle in order to confirm that the composite structure is correctly fabricated as designed. In this study, the stacking angle was predicted from real cross-sectional images of fiber-reinforced composites using convolutional neural network (CNN)-based deep learning. Carbon fiber-reinforced composite specimens with several stacking angles were fabricated and their cross-sections were photographed on a micro-scale using an optical microscope. The training was performed for a CNN-based deep learning model using the cross-sectional image data of the composite specimens. As a result, the stacking angle can be predicted from the actual cross-sectional image of the fiber-reinforced composite with high accuracy.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.4
• /
• pp.457-466
• /
• 2005

In this paper, we propose a wavelet neural network(WNN) based predictive control method for path tracking of mobile robots with multi-input and multi-output. In our control method, we use a WNN as a state predictor which combines the capability of artificial neural networks in learning processes and the capability of wavelet decomposition. A WNN predictor is tuned to minimize errors between the WNN outputs and the states of mobile robot using the gradient descent rule. And control signals, linear velocity and angular velocity, are calculated to minimize the predefined cost function using errors between the reference states and the predicted states. Through a computer simulation for the tracking performance according to varied track, we demonstrate the efficiency and the feasibility of our predictive control system.

• Journal of Korea Game Society
• /
• v.18 no.2
• /
• pp.89-98
• /
• 2018

The recent Neural Network technique has shown good performance in content generation such as image generation in addition to the conventional classification problem and clustering problem solving. In this study, we propose an image generation method using artificial neural network as a next generation content creation technique. The proposed artificial neural network model receives two images and combines them into a new image by taking color from one image and shape from the other image. This model is made up of Convolutional Neural Network, which has two encoders for extracting color and shape from images, and a decoder for taking all the values of each encoder and generating a combination image. The result of this work can be applied to various 2D image generation and modification works in game development process at low cost.