• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권9호
• /
• pp.375-384
• /
• 2021

딥러닝 기법은 영상 처리 분야에서 높은 성능을 입증 받아 다양한 분야에서 적용되고 있다. 이러한 딥러닝 모델의 검증에 가장 널리 사용되는 방법으로는 홀드아웃 검증 방법, k-겹 교차 검증 방법, 부트스트랩 방법 등이 있다. 이러한 기존의 기법들은 데이터 셋을 분할하는 과정에서 클래스 간의 비율에 대한 균형을 고려하지만, 같은 클래스 내에서도 존재하는 다양한 특징들의 비율은 고려하지 않고 있다. 이러한 특징들을 고려하지 않을 경우, 일부 특징에 편향된 검증 결과를 얻게 될 수 있다. 따라서 본 논문에서는 기존 검증 방법들을 개선하여 영상 분류를 위한 데이터 특징 커버리지 기반의 딥러닝 모델 검증 기법을 제안한다. 제안하는 기법은 딥러닝 모델의 학습과 검증을 위한 훈련 데이터 셋과 평가 데이터 셋이 전체 데이터 셋의 특징을 얼마나 반영하고 있는지 수치로 측정할 수 있는 데이터 특징 커버리지를 제안한다. 이러한 방식은 전체 데이터 셋의 특징을 모두 포함하도록 커버리지를 보장하여 데이터 셋을 분할할 수 있고, 모델의 평가 결과를 생성한 특징 군집 단위로 분석할 수 있다. 검증결과, 훈련 데이터 셋의 데이터 특징 커버리지가 낮아질 경우, 모델이 특정 특징에 편향되게 학습하여 모델의 성능이 낮아지며, Fashion-MNIST의 경우 정확도가 8.9%까지 차이나는 것을 확인하였다.

• 융합신호처리학회논문지
• /
• 제23권3호
• /
• pp.150-159
• /
• 2022

본 논문은 실시간 영상 분석을 통해서 산업현장에서 활동하는 여러 근로자의 영상 객체를 추출해 내고, 추출된 이미지로 부터 개별 영상 분석을 통해 헬멧의 착용 여부와 낙상 사고 여부를 확인하는 방법을 구현한다. 근로자의 영상 객체를 탐지하기 위해서 딥러닝 기반 컴퓨터 비전 모델인 YOLO를 사용하였으며, 추출된 이미지를 이용하여 헬멧의 착용여부를 판단하기 위해 따로 5,000장의 다양한 헬멧 학습 데이터 이미지를 만들어서 사용하였다. 또한, 낙상사고 여부를 판단하기 위해서 Mediapipe의 Pose 실시간 신체추적 알고리즘을 사용하여 머리의 위치를 확인하고 움직이는 속도를 계산하여 쓰러짐 여부를 판단하였다. 결과에 신뢰성을 주기위한 방법으로 YOLO의 바운딩 박스의 크기를 구하여 객체의 자세를 유추하는 방법을 추가하고 구현하였다. 최종적으로 관리자에게 알림 서비스를 위하여 텔레그램 API Bot과 Firebase DB 서버를 구현하였다.

• 천문학회보
• /
• 제44권1호
• /
• pp.81.2-81.2
• /
• 2019

We develop an image-to-image translation model, which is a popular deep learning method based on conditional Generative Adversarial Networks (cGANs), to generate solar magnetograms and EUV images from sunspot drawings. For this, we train the model using pairs of sunspot drawings from Mount Wilson Observatory (MWO) and their corresponding SDO/HMI magnetograms and SDO/AIA EUV images (512 by 512) from January 2012 to September 2014. We test the model by comparing pairs of actual SDO images (magnetogram and EUV images) and the corresponding AI-generated ones from October to December in 2014. Our results show that bipolar structures and coronal loop structures of AI-generated images are consistent with those of the original ones. We find that their unsigned magnetic fluxes well correlate with those of the original ones with a good correlation coefficient of 0.86. We also obtain pixel-to-pixel correlations EUV images and AI-generated ones. The average correlations of 92 test samples for several SDO lines are very good: 0.88 for AIA 211, 0.87 for AIA 1600 and 0.93 for AIA 1700. These facts imply that AI-generated EUV images quite similar to AIA ones. Applying this model to the Galileo sunspot drawings in 1612, we generate HMI-like magnetograms and AIA-like EUV images of the sunspots. This application will be used to generate solar images using historical sunspot drawings.

• 한국군사과학기술학회지
• /
• 제25권3호
• /
• pp.219-230
• /
• 2022

In implementing a robust automatic target recognition(ATR) system with synthetic aperture radar(SAR) imagery, one of the most important issues is accurate classification of target variants, which are the same targets with different serial numbers, configurations and versions, etc. In this paper, a deep learning network with channel attention modules is proposed to cope with the recognition problem for target variants based on the previous research findings that the channel attention mechanism selectively emphasizes the useful features for target recognition. Different from other existing attention methods, this paper employs the channel attention modules without dimensionality reduction along the channel direction from which direct correspondence between feature map channels can be preserved and the features valuable for recognizing SAR target variants can be effectively derived. Experiments with the public benchmark dataset demonstrate that the proposed scheme is superior to the network with other existing channel attention modules.

• 한국멀티미디어학회논문지
• /
• 제25권2호
• /
• pp.206-214
• /
• 2022

The way to measure the extent of damage from floods and droughts is to identify changes in the extent of water systems. In order to effectively grasp this at a glance, satellite images are used. KOMPSAT-5 uses Synthetic Aperture Radar (SAR) to capture images regardless of weather conditions such as clouds and rain. In this paper, various deep learning models are applied to perform semantic segmentation of the water system in this SAR image and the performance is compared. The models used are U-net, V-Net, U2-Net, UNet 3+, PSPNet, Deeplab-V3, Deeplab-V3+ and PAN. In addition, performance comparison was performed when the data was augmented by applying elastic deformation to the existing SAR image dataset. As a result, without data augmentation, U-Net was the best with IoU of 97.25% and pixel accuracy of 98.53%. In case of data augmentation, Deeplab-V3 showed IoU of 95.15% and V-Net showed the best pixel accuracy of 96.86%.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2022년도 학술발표회
• /
• pp.149-149
• /
• 2022

Accurate quantitative evaluation of baseflow contribution to streamflow is imperative to address seasonal drought vulnerability, flood occurrence and groundwater management concerns for efficient and sustainable water resources management in watersheds. Several baseflow separation algorithms using recursive filters, graphical method and tracer or chemical balance have been developed but resulting baseflow outputs always show wide variations, thereby making it hard to determine best separation technique. Therefore, the current global shift towards implementation of artificial intelligence (AI) in water resources is employed to compare the performance of deep learning models with conventional hydrograph separation techniques to quantify baseflow contribution to streamflow of Piney River watershed, Tennessee from 2001-2021. Streamflow values are obtained from the USGS station 03602500 and modeled to generate values of Baseflow Index (BI) using Web-based Hydrograph Analysis (WHAT) model. Annual and seasonal baseflow outputs from the traditional separation techniques are compared with results of Long Short Term Memory (LSTM) and simple Gated Recurrent Unit (GRU) models. The GRU model gave optimal BFI values during the four seasons with average NSE = 0.98, KGE = 0.97, r = 0.89 and future baseflow volumes are predicted. AI offers easier and more accurate approach to groundwater management and surface runoff modeling to create effective water policy frameworks for disaster management.

• Geomechanics and Engineering
• /
• 제37권1호
• /
• pp.49-64
• /
• 2024

Rocks undergoing repeated loading and unloading over an extended period, such as due to earthquakes, human excavation, and blasting, may result in the gradual accumulation of stress and deformation within the rock mass, eventually reaching an unstable state. In this study, a CNN-CCM is proposed to address the mechanical behavior. The structure and hyperparameters of CNN-CCM include Conv2D layers × 5; Max pooling2D layers × 4; Dense layers × 4; learning rate=0.001; Epoch=50; Batch size=64; Dropout=0.5. Training and validation data for deep learning include 71 rock samples and 122,152 data points. The AI Rock Constitutive Model learned by CNN-CCM can predict strain values(ε₁) using Mass (M), Axial stress (σ₁), Density (ρ), Cyclic number (N), Confining pressure (σ₃), and Young's modulus (E). Five evaluation indicators R², MAPE, RMSE, MSE, and MAE yield respective values of 0.929, 16.44%, 0.954, 0.913, and 0.542, illustrating good predictive performance and generalization ability of model. Finally, interpreting the AI Rock Constitutive Model using the SHAP explaining method reveals that feature importance follows the order N > M > σ₁ > E > ρ > σ₃.Positive SHAP values indicate positive effects on predicting strain ε₁ for N, M, σ₁, and σ₃, while negative SHAP values have negative effects. For E, a positive value has a negative effect on predicting strain ε₁, consistent with the influence patterns of conventional physical rock constitutive equations. The present study offers a novel approach to the investigation of the mechanical constitutive model of rocks under cyclic loading and unloading conditions.

• 문화기술의 융합
• /
• 제9권3호
• /
• pp.647-654
• /
• 2023

딥러닝은 이미지, 텍스트와 같이 복잡한 데이터를 분류 및 인식하는데 유용한 방법으로 딥러닝 기법의 정확도는 딥러닝이 인터넷상의 AI 기반의 서비스를 유용하게 하는데 기초가 되었다. 그러나 딥러닝에서 훈련에 사용되는 방대한 양의 사용자 데이터는 사생활 침해 문제를 야기하였고 사진이나 보이스와 같이 사용자이 개인적이고 민감한 데이터를 수집한 기업들이 데이터들을 무기한으로 소유한다. 사용자들은 자신의 데이터를 삭제할 수 없고 사용되는 목적도 제한할 수 없다. 예를 들면, 환자 진료기록에 대한 딥러닝 기술을 적용하기 원하는 의료기관들과 같은 데이터소유자들은 사생활과 기밀유지 문제로 환자의 데이터를 공유할 수 없고 딥러닝 기술의 혜택을 받기 어렵다. 우리는 멀티 파티 시스템에서 다수의 작업자들이 입력 데이터집합을 공유하지 않고 신경망 모델을 공동으로 사용할 수 있는 프라이버시 보존 기술을 적용한 딥러닝 방법을 설계한다. 변형된 확률적 경사 하강에 기초한 최적화 알고리즘을 이용하여 하위 집합을 선택적으로 공유할 수 있는 방법을 이용하였고 결과적으로 개인정보를 보호하면서 학습 정확도를 증가시킨 학습을 할 수 있도록 하였다.

• Journal of Positioning, Navigation, and Timing
• /
• 제10권1호
• /
• pp.49-54
• /
• 2021

Indoor positioning system becomes of increasing interests due to the demands for accurate indoor location information where Global Navigation Satellite System signal does not approach. Wi-Fi access points (APs) built in many construction in advance helps developing a Wi-Fi Received Signal Strength Indicator (RSSI) based indoor localization. This localization method first collects pairs of position and RSSI measurement set, which is called fingerprint database, and then estimates a user's position when given a query measurement set by comparing the fingerprint database. The challenge arises from nonlinearity and noise on Wi-Fi RSSI measurements and complexity of handling a large amount of the fingerprint data. In this paper, machine learning techniques have been applied to implement Wi-Fi based localization. However, most of existing indoor localizations focus on single position estimation. The main contribution of this paper is to develop multi-target localization by using deep neural, which is beneficial when a massive crowd requests positioning service. This paper evaluates the proposed multilocalization based on deep learning from a multi-story building, and analyses its learning effect as increasing number of target positions.

• Korean Journal of Radiology
• /
• 제23권3호
• /
• pp.343-354
• /
• 2022

Objective: To develop and evaluate a deep learning-based artificial intelligence (AI) model for detecting skull fractures on plain radiographs in children. Materials and Methods: This retrospective multi-center study consisted of a development dataset acquired from two hospitals (n = 149 and 264) and an external test set (n = 95) from a third hospital. Datasets included children with head trauma who underwent both skull radiography and cranial computed tomography (CT). The development dataset was split into training, tuning, and internal test sets in a ratio of 7:1:2. The reference standard for skull fracture was cranial CT. Two radiology residents, a pediatric radiologist, and two emergency physicians participated in a two-session observer study on an external test set with and without AI assistance. We obtained the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity along with their 95% confidence intervals (CIs). Results: The AI model showed an AUROC of 0.922 (95% CI, 0.842-0.969) in the internal test set and 0.870 (95% CI, 0.785-0.930) in the external test set. The model had a sensitivity of 81.1% (95% CI, 64.8%-92.0%) and specificity of 91.3% (95% CI, 79.2%-97.6%) for the internal test set and 78.9% (95% CI, 54.4%-93.9%) and 88.2% (95% CI, 78.7%-94.4%), respectively, for the external test set. With the model's assistance, significant AUROC improvement was observed in radiology residents (pooled results) and emergency physicians (pooled results) with the difference from reading without AI assistance of 0.094 (95% CI, 0.020-0.168; p = 0.012) and 0.069 (95% CI, 0.002-0.136; p = 0.043), respectively, but not in the pediatric radiologist with the difference of 0.008 (95% CI, -0.074-0.090; p = 0.850). Conclusion: A deep learning-based AI model improved the performance of inexperienced radiologists and emergency physicians in diagnosing pediatric skull fractures on plain radiographs.