• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.1-9
• /
• 2022

Ship detection in synthetic aperture radar (SAR) images is an important application in marine monitoring for the military and civilian domains. Over the past decade, object detection has achieved significant progress with the development of convolutional neural networks (CNNs) and lot of labeled databases. However, due to difficulty in collecting and labeling SAR images, it is still a challenging task to solve SAR ship detection CNNs. To overcome the problem, some methods have employed conventional data augmentation techniques such as flipping, cropping, and affine transformation, but it is insufficient to achieve robust performance to handle a wide variety of types of ships. In this paper, we present a novel and effective approach for deep SAR ship detection, that exploits label-rich Electro-Optical (EO) images. The proposed method consists of two components: a data augmentation network and a ship detection network. First, we train the data augmentation network based on conditional generative adversarial network (cGAN), which aims to generate additional SAR images from EO images. Since it is trained using unpaired EO and SAR images, we impose the cycle-consistency loss to preserve the structural information while translating the characteristics of the images. After training the data augmentation network, we leverage the augmented dataset constituted with real and translated SAR images to train the ship detection network. The experimental results include qualitative evaluation of the translated SAR images and the comparison of detection performance of the networks, trained with non-augmented and augmented dataset, which demonstrates the effectiveness of the proposed framework.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1588-1594
• /
• 2020

In this paper, we discuss a data balancing method for learning a neural network that generates digital holograms using a deep neural network (DNN). Deep neural networks are based on deep learning (DL) technology and use a generative adversarial network (GAN) series. The fringe pattern, which is the basic unit of a hologram to be created through a deep neural network, has very different data types depending on the hologram plane and the position of the object. However, because the criteria for classifying the data are not clear, an imbalance in the training data may occur. The imbalance of learning data acts as a factor of instability in learning. Therefore, it presents a method for classifying and balancing data for which the classification criteria are not clear. And it shows that learning is stabilized through this.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.37-46
• /
• 2020

Recently, studies of facial attribute editing have obtained realistic results using generative adversarial net (GAN) and encoder-decoder structure. Spatial attention GAN (SaGAN), one of the latest researches, is the method that can change only desired attribute in a face image by spatial attention mechanism. However, sometimes unnatural results are obtained due to insufficient information on face areas. In this paper, we propose an improved SaGAN (MSaGAN) using a guide mask for learning and applying multitask learning approach to improve the limitations of the existing methods. Through extensive experiments, we evaluated the results of the facial attribute editing in therms of the mask loss function and the neural network structure. It has been shown that the proposed method can efficiently produce more natural results compared to the previous methods.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.6
• /
• pp.670-677
• /
• 2019

As the presence of background noise in acoustic signal degrades the performance of speech or acoustic event recognition, it is still challenging to extract noise-robust acoustic features from noisy signal. In this paper, we propose a combined structure of Wasserstein Generative Adversarial Network (WGAN) and MultiTask AutoEncoder (MTAE) as deep learning architecture that integrates the strength of MTAE and WGAN respectively such that it estimates not only noise but also speech features from noisy acoustic source. The proposed MTAE-WGAN structure is used to estimate speech signal and the residual noise by employing a gradient penalty and a weight initialization method for Leaky Rectified Linear Unit (LReLU) and Parametric ReLU (PReLU). The proposed MTAE-WGAN structure with the adopted gradient penalty loss function enhances the speech features and subsequently achieve substantial Phoneme Error Rate (PER) improvements over the stand-alone Deep Denoising Autoencoder (DDAE), MTAE, Redundant Convolutional Encoder-Decoder (R-CED) and Recurrent MTAE (RMTAE) models for robust speech recognition.

• Journal of Technologic Dentistry
• /
• v.46 no.2
• /
• pp.36-41
• /
• 2024

Purpose: This study aimed to generate virtual mandibular left first molar teeth using deep convolutional generative adversarial networks (DCGANs) and analyze their matching accuracy with actual tooth morphology to propose a new paradigm for using medical data. Methods: Occlusal surface images of the mandibular left first molar scanned using a dental model scanner were analyzed using DCGANs. Overall, 100 training sets comprising 50 original and 50 background-removed images were created, thus generating 1,000 virtual teeth. These virtual teeth were classified based on the number of cusps and occlusal surface ratio, and subsequently, were analyzed for consistency by expert dental technicians over three rounds of examination. Statistical analysis was conducted using IBM SPSS Statistics ver. 23.0 (IBM), including intraclass correlation coefficient for intrarater reliability, one-way ANOVA, and Tukey's post-hoc analysis. Results: Virtual mandibular left first molars exhibited high consistency in the occlusal surface ratio but varied in other criteria. Moreover, consistency was the highest in the occlusal buccal lingual criteria at 91.9%, whereas discrepancies were observed most in the occusal buccal cusp criteria at 85.5%. Significant differences were observed among all groups (p<0.05). Conclusion: Based on the classification of the virtually generated left mandibular first molar according to several criteria, DCGANs can generate virtual data highly similar to real data. Thus, subsequent research in the dental field, including the development of improved neural network structures, is necessary.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.653-655
• /
• 2022

Face aging aims to synthesize future face images by reflecting the age factor on given faces. In recent years, deep learning-based approaches have made outstanding progress in simulating the aging process of the human face. However, generating accurate and high-quality aging faces is still intrinsically difficult. We propose a new method that incorporates gender information into the model, which achieves comparable and stable performance. Experimental results demonstrate that our method can preserve the identity well and generate diverse aged faces.

• Journal of the Korean Society of Systems Engineering
• /
• v.19 no.2
• /
• pp.145-156
• /
• 2023

Trajectory of ballistic missile is defined by inherent flight dynamics, which decided range and maneuvering characteristics. It is crucial to predict range and maneuvering characteristics of ballistic missile in KAMD (Korea Air and Missile Defense) to minimize damage due to ballistic missile attacks, Nowadays, needs for applying AI(Artificial Intelligence) technologies are increasing due to rapid developments of DNN(Deep Neural Networks) technologies. To apply these DNN technologies amount of data are required for superviesed learning, but trajectory data of ballistic missiles is limited because of security issues. Trajectory data could be considered as multivariate time series including many variables. And augmentation in time series data is a developing area of research. In this paper, we tried to augment trajectory data of ballistic missiles using recently developed methods. We used TimeVAE(Time Variational AutoEncoder) method and TimeGAN(Time Generative Adversarial Networks) to synthesize missile trajectory data. We also compare the results of two methods and analyse for future works.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.2
• /
• pp.201-211
• /
• 2022

According to the recent change in the cybersecurity paradigm, research on anomaly detection methods using machine learning and deep learning techniques, which are AI implementation technologies, is increasing. In this study, a comparative study on data preprocessing techniques that can improve the anomaly detection performance of a GRU (Gated Recurrent Unit) neural network-based intrusion detection model using NGIDS-DS (Next Generation IDS Dataset), an open dataset, was conducted. In addition, in order to solve the class imbalance problem according to the ratio of normal data and attack data, the detection performance according to the oversampling ratio was compared and analyzed using the oversampling technique applied with DCGAN (Deep Convolutional Generative Adversarial Networks). As a result of the experiment, the method preprocessed using the Doc2Vec algorithm for system call feature and process execution path feature showed good performance, and in the case of oversampling performance, when DCGAN was used, improved detection performance was shown.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.19-26
• /
• 2021

Cultural assets excavated in historical areas have their own characteristics based on the background of the times, and it can be seen that their patterns and characteristics change little by little according to the history and the flow of the spreading area. Cultural properties excavated in some areas represent the culture of the time and some maintain their intact appearance, but most of them are damaged/lost or divided into parts, and many experts are mobilized to research the composition and repair the damaged parts. The purpose of this research is to learn patterns and characteristics of the past through artificial intelligence neural networks for such restoration research, and to restore the lost parts of the excavated cultural assets based on Generative Adversarial Network(GAN)[1]. The research is a process in which the rest of the damaged/lost parts are restored based on some of the cultural assets excavated based on the GAN. To recover some parts of dammed of cultural asset, through training with the 2D image of a complete cultural asset. This research is focused on how much recovered not only damaged parts but also reproduce colors and materials. Finally, through adopted this trained neural network to real damaged cultural, confirmed area of recovered area and limitation.

• Korean Chemical Engineering Research
• /
• v.61 no.1
• /
• pp.123-141
• /
• 2023

A sufficient amount of data with quality is needed for training artificial neural networks (ANNs). However, developing ANN models with a small amount of data often appears in engineering fields. This paper presented an ANN model to improve prediction performance of the ammonia emission amount with 83 data. The ammonia emission rate included eleven inputs and two outputs (maximum ammonia loss, N_max and time to reach half of N_max, K_m). Categorical input variables were transformed into multi-dimensional equal-distance variables, and 13 data were added into 66 training data using a generative adversarial network. Hyperparameters (number of layers, number of neurons, and activation function) of ANN were optimized using Gaussian process. Using 17 test data, the previous ANN model (Lim et al., 2007) showed the mean absolute error (MAE) of K_m and N_max to 0.0668 and 0.1860, respectively. The present ANN outperformed the previous model, reducing MAE by 38% and 56%.