• 한국HCI학회논문지
• /
• 제10권2호
• /
• pp.27-33
• /
• 2015

증강현실 기술은 현실 공간의 객체에 가상 정보를 연계 하고 공간적으로 정합 하여 보여 준다. 이러한 정보 가시화 형식은 그만의 특별한 유용성과 한계를 가지고 있고 또한 증강현실 기술에 따른 여러 가지 특별한 요구사항을 가질 수 있다. 본 논문에서는 증강현실이 가지는 고유의 특성에 따라 효과적인 증강정보가 가져야 할 세 가지 덕목, 즉 "자연스러움," "가시성," "지속성"을 제시 하고, 이들을 중심으로 기존의 증강정보 가시화 방법들을 살펴보고, 이 분야에서의 앞으로 나아가야 할 방향을 모색 해 본다.

• 한국정보통신학회논문지
• /
• 제25권9호
• /
• pp.1271-1274
• /
• 2021

RF fingerprinting based on deep learning (DL) has gained interests as a means to improve the security of near field communication (NFC) by allowing identification of NFC tags based on unique physical characteristics. To achieve high accuracy in the identification of NFC tags, it is crucial to utilize a large number of training data, however it is hard to collect such dataset in practice. In this study, we have provided new methodology to generate RF waveform from NFC tags, i.e., data augmentation, based on a conditional generative adversarial network (CGAN). By using the RF waveform of NFC tags which is collected from the testbed with software defined radio (SDR), we have confirmed that the realistic RF waveform can be generated through our proposed scheme.

• 전기전자학회논문지
• /
• 제27권1호
• /
• pp.59-64
• /
• 2023

딥러닝은 다양한 컴퓨터 비전 문제를 해결할 수 있지만, 대량의 데이터셋이 필요하다. 본 논문에서는 대형 이미지 데이터셋을 구축하기 위해 이미지 이진화 기반 데이터 증강 기법을 제안한다. 이미지 이진화를 사용하여 특성을 추출하고 추출된 나머지 픽셀을 랜덤하게 배치하여 새로운 이미지를 생성한다. 생성된 이미지는 원본 이미지와 유사한 품질을 보여주며, 딥러닝 모델에서도 뛰어난 성능을 보였다.

• Investigative Magnetic Resonance Imaging
• /
• 제26권1호
• /
• pp.76-81
• /
• 2022

The number of women undergoing breast augmentation surgery with a prosthesis for cosmetic purposes or reconstruction after a mastectomy is steadily increasing. Hematoma is one of complications associated with breast augmentation surgery. It usually occurs early in the postoperative period. It rarely occurs late (after six months). However, chronic hematomas after prosthesis removal have not yet been reported in the radiological literature. We present a case of unilateral chronic organizing hematoma that developed late and grew persistently over long period after breast explantation, mimicking a soft tissue tumor of the chest wall clinically. Meanwhile, characteristic magnetic resonance imaging features of heterogeneous signal intensities on T1-weighted and T2-weighted images and dark signal intensity with a persistent enhancement of the peripheral wall of the lesion were found. These can be used for a differential diagnosis.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2020년도 추계학술대회
• /
• pp.244-247
• /
• 2020

Data augmentation has been helpful in improving the performance in deep learning, when we have a limited data and random erasing is one of the augmentations that have shown impressive performance in deep learning in multiple domains. But the main issue is that sometime it loses good features when randomly selected region is erased by some random values, that does not improve performance as it should. We target that problem in way that good features should not be lost and also want random erasing at the same time. For that purpose, we introduce new augmentation technique named Intra-Class Random Erasing (ICRE) that focuses on data to learn robust features of the same class samples by randomly exchanging randomly selected region. We perform multiple experiments by using different models including resnet18, VGG16 over variety of the datasets including ESC10, UrbanSound8K. Our approach has shown effectiveness over others methods including random erasing.

• 시스템엔지니어링학술지
• /
• 제19권2호
• /
• 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.

• Korean Journal of Radiology
• /
• 제22권7호
• /
• pp.1005-1020
• /
• 2021

Breast augmentation is becoming more common, be it for cosmetic reasons or post-mastectomy. Multiple articles in the literature describe the imaging findings of various types of cosmetic breast augmentation. Some articles describe imaging findings for different types of post-mastectomy reconstructions. This essay aims to serve as a comprehensive reference for the multimodality imaging of various types of breast augmentations in native breast and post-mastectomy reconstructions. Familiarity with these findings will facilitate the detection of complications and new or recurrent breast malignancies in patients. With the extensive illustrations provided in this essay on normal and abnormal imaging findings of augmented breasts, readers will receive exposure that will facilitate effective practice.

• Journal of Positioning, Navigation, and Timing
• /
• 제13권2호
• /
• pp.207-213
• /
• 2024

This paper examines the frame boundary detection performance for a satellite navigation augmentation signal orthogonally modulated with Hadamard code to determine the number of message preamble bits. Simulation results show that, even in weak signal environments, designing the message preamble with 32 bits is recommended for achieving stable frame boundary detection.

• 한국빅데이터학회지
• /
• 제4권2호
• /
• pp.1-12
• /
• 2019

인공지능 기술이 발전하면서 이미지, 음성, 텍스트 등 다양한 분야에 적용되고 있으며, 데이터가 충분한 경우 기존 기법들에 비해 좋은 결과를 보인다. 주식시장은 경제, 정치와 같은 많은 변수에 의해 영향을 받기 때문에, 주식 가격의 움직임 예측은 어려운 과제로 알려져 있다. 다양한 기계학습 기법과 인공지능 기법을 이용하여 주가 패턴을 연구하여 주가의 등락을 예측하려는 시도가 있어왔다. 본 연구는 딥러닝 기법 중 컨볼루셔널 뉴럴 네트워크(CNN)를 기반으로 주가 패턴 예측률 향상을 위한 데이터 증강 방안을 제안한다. CNN은 컨볼루셔널 계층을 통해 이미지에서 특징을 추출하여 뉴럴 네트워크를 이용하여 이미지를 분류한다. 따라서, 본 연구는 주식 데이터를 캔들스틱 차트 이미지로 만들어 CNN을 통해 패턴을 예측하고 분류하고자 한다. 딥러닝은 다량의 데이터가 필요하기에, 주식 차트 이미지에 다양한 데이터 증강(Data Augmentation) 방안을 적용하여 분류 정확도를 향상 시키는 방법을 제안한다. 데이터 증강 방안으로는 차트를 랜덤하게 변경하는 방안과 차트에 가우시안 노이즈를 적용하여 추가 데이터를 생성하였으며, 추가 생성된 데이터를 활용하여 학습하고 테스트 집합에 대한 분류 정확도를 비교하였다. 랜덤하게 차트를 변경하여 데이터를 증강시킨 경우의 분류 정확도는 79.92%였고, 가우시안 노이즈를 적용하여 생성된 데이터를 가지고 학습한 경우의 분류 정확도는 80.98%이었다. 주가의 다음날 상승/하락으로 분류하는 경우에는 60분 단위 캔들 차트가 82.60%의 정확도를 기록하였다.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• 제30권3호
• /
• pp.283-291
• /
• 2008

The malar mound defines the contour of the lateral face between the inferior orbital rim and the mandible, and hypoplasia or asymmetry of this region is readily noticeable. A flat, hypoplastic malar eminence can make the face blunt and wearisome, which contributes to a premature aged appearance. Patients with congenital or traumatic flattening of the malar eminence can obtain esthetic improvement with implants. Indications for placement of malar implants to improve the appearance of subtle flattening or to enhance the esthetic harmony of a patient's face have been suggested in several studies. Many augmentation materials, such as silicone, proplast, polyamide, and porous polyethylene implants have been used. Many methods of localization have been described, the key to proper placement of the implants lies in a through understanding of the esthetics of the malar mound. From August 2001 to June 2007, 12 patients with malar depression who visited the Department of Oral and Maxillofacial Surgery, Chonnam National University Hospital were treated by augmentation malarplasty with Porous polyethylene. The location and amount of augmentation are determined by preoperative interview, physical examinations, facial models and radiographic findings. 12 patients were satisfied with the results of augmentation malarplasty and severe complications were not occurred.