• 문화기술의 융합
• /
• 제8권6호
• /
• pp.867-871
• /
• 2022

최근 빠른 유행의 변화 속에서 디자인의 변화는 패션기업의 매출에 큰 영향을 미치기 때문에 기업들은 신제품디자인 선택에 신중할 수밖에 없다. 최근 인공지능 분야의 발달에 따라 패션시장에서도 소비자들의 선호도를 높이기 위해 다양한 기계학습을 많이 활용하고 있다. 우리는 선호도와 같은 추상적인 개념을 수치화함으로써 신제품 개발에 신뢰성을 높이는 부분에 기여하고자 한다. 이를 위해 3가지 적대적 생성 신경망(Generative adversial netwrok, GAN)을 통하여 기존에 없는 새로운 이미지를 생성하고, 미리 훈련된 합성곱 신경망(Convolution neural networkm, CNN)을 이용하여 선호도라는 추상적인 개념을 수치화시켜 비교하였다. 심층 컨볼루션 적대적 생성 신경망(Deep convolutional generative adversial netwrok, DCGAN), 점진적 성장 적대적 생성 신경망(Progressive growing generative adversial netwrok, PGGAN), 이중 판별기 적대적 생성 신경망(Dual Discriminator generative adversial netwrok, D2GAN)의 3가지 방법을 통해 새로운 이미지를 생성하였고, 판매량이 높았던 제품으로 훈련된 합성곱 신경망으로 유사도를 비교, 측정하였다. 측정된 유사도의 정도를 선호도로 간주하였으며 실험 결과 D2GAN이 DCGAN, PGGAN에 비해 상대적으로 높은 유사도를 보여주었다.

• 문화기술의 융합
• /
• 제8권5호
• /
• pp.489-495
• /
• 2022

언어모델(Language Model)을 구축하기 위한 딥러닝 기법인 LSTM의 경우 학습에 사용되는 말뭉치의 전처리 방식에 따라 그 결과가 달라진다. 본 연구에서는 유명한 문학작품(기형도의 시집)을 말뭉치로 사용하여 LSTM 모델을 학습시켰다. 원문을 그대로 사용하는 경우와 조사/어미 등을 삭제한 경우에 따라 상이한 단어벡터 세트를 각각 얻을 수 있다. 이러한 전처리 방식에 따른 유사도/유추 연산 결과, 단어벡터의 평면상의 위치 및 언어모델의 텍스트생성 결과를 비교분석했다. 문학작품을 말뭉치로 사용하는 경우, 전처리 방식에 따라 연산된 단어는 달라지지만, 단어들의 유사도가 높고 유추관계의 상관도가 높다는 것을 알 수 있었다. 평면상의 단어 위치 역시 달라지지만 원래의 맥락과 어긋나지 않았고, 생성된 텍스트는 원래의 분위기와 비슷하면서도 이색적인 작품으로 감상할 수 있었다. 이러한 분석을 통해 문학작품을 객관적이고 다채롭게 향유할 수 있는 수단으로 딥러닝 기법의 언어모델을 활용할 수 있다고 판단된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권3호
• /
• pp.881-895
• /
• 2023

Modern image inpainting techniques based on deep learning have achieved remarkable performance, and more and more people are working on repairing more complex and larger missing areas, although this is still challenging, especially for facial image inpainting. For a face image with a huge missing area, there are very few valid pixels available; however, people have an ability to imagine the complete picture in their mind according to their subjective will. It is important to simulate this capability while maintaining the identity features of the face as much as possible. To achieve this goal, we propose a three-stage network model, which we refer to as the identity and structure feature refinement network (ISFRNet). ISFRNet is based on 1) a pre-trained pSp-styleGAN model that generates an extremely realistic face image with rich structural features; 2) a shallow structured network with a small receptive field; and 3) a modified U-net with two encoders and a decoder, which has a large receptive field. We choose structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), L1 Loss and learned perceptual image patch similarity (LPIPS) to evaluate our model. When the missing region is 20%-40%, the above four metric scores of our model are 28.12, 0.942, 0.015 and 0.090, respectively. When the lost area is between 40% and 60%, the metric scores are 23.31, 0.840, 0.053 and 0.177, respectively. Our inpainting network not only guarantees excellent face identity feature recovery but also exhibits state-of-the-art performance compared to other multi-stage refinement models.

• 한국지반공학회논문집
• /
• 제26권7호
• /
• pp.171-186
• /
• 2010

일반적으로 강성벽체에 비하여 연성벽체의 경우가 거동 mechanism이 상대적으로 복잡한 것으로 알려져 있으며 여기에다 버팀보 지지의 장지간인 경우 굴착단면 양쪽의 지반조건과 굴착공정의 차이가 부가되면 버팀보 축력변화 분석은 더욱 어렵게 된다. 시공과정에서 현장여건에 의한 과굴착이나 지보재의 설치지연, 지반조건의 변화 등이 발생 할 경우 특정 버팀보에 큰 축력이 발생하여 안전 시공을 위협하게 될 수 있다. 본 논문은 거의 유사한 지반조건, 굴착 및 지보조건을 갖는 동일현장의 약 50m 이격된 2개소의 버팀보 및 rock bolt 지지 장지간 연성벽체 깊은 굴착단면들의 시공과정에서 얻어진 계측결과인 지반변형 및 버팀보 축력변화 특성을 분석하고 2단면 계측결과의 유사성 및 차이점을 비교 고찰함으로써 향후 유사지반 및 동일공법 적용 project들의 설계, 시공과정에서 개선, 보완해야 할 사항 들을 제안하고자 한다.

• 한국재료학회지
• /
• 제32권8호
• /
• pp.345-353
• /
• 2022

In this study, using deep learning, super-resolution images of transmission electron microscope (TEM) images were generated for nanomaterial analysis. 1169 paired images with 256 × 256 pixels (high resolution: HR) from TEM measurements and 32 × 32 pixels (low resolution: LR) produced using the python module openCV were trained with deep learning models. The TEM images were related to DyVO₄ nanomaterials synthesized by hydrothermal methods. Mean-absolute-error (MAE), peak-signal-to-noise-ratio (PSNR), and structural similarity (SSIM) were used as metrics to evaluate the performance of the models. First, a super-resolution image (SR) was obtained using the traditional interpolation method used in computer vision. In the SR image at low magnification, the shape of the nanomaterial improved. However, the SR images at medium and high magnification failed to show the characteristics of the lattice of the nanomaterials. Second, to obtain a SR image, the deep learning model includes a residual network which reduces the loss of spatial information in the convolutional process of obtaining a feature map. In the process of optimizing the deep learning model, it was confirmed that the performance of the model improved as the number of data increased. In addition, by optimizing the deep learning model using the loss function, including MAE and SSIM at the same time, improved results of the nanomaterial lattice in SR images were achieved at medium and high magnifications. The final proposed deep learning model used four residual blocks to obtain the characteristic map of the low-resolution image, and the super-resolution image was completed using Upsampling2D and the residual block three times.

• 디지털산업정보학회논문지
• /
• 제14권4호
• /
• pp.69-77
• /
• 2018

The malignant melanoma accounts for about 1 to 3% of the total malignant tumor in the West, especially in the US, it is a disease that causes more than 9,000 deaths each year. Generally, skin lesions are difficult to detect the features through photography. In this paper, we propose a computer-aided diagnosis algorithm based on deep learning for classification of malignant melanoma and benign skin tumor in RGB channel skin images. The proposed deep learning model configures the tumor lesion segmentation model and a classification model of malignant melanoma. First, U-Net was used to segment a skin lesion area in the dermoscopic image. We could implement algorithms to classify malignant melanoma and benign tumor using skin lesion image and results of expert's labeling in ResNet. The U-Net model obtained a dice similarity coefficient of 83.45% compared with results of expert's labeling. The classification accuracy of malignant melanoma obtained the 83.06%. As the result, it is expected that the proposed artificial intelligence algorithm will utilize as a computer-aided diagnosis algorithm and help to detect malignant melanoma at an early stage.

• 문화기술의 융합
• /
• 제8권1호
• /
• pp.545-550
• /
• 2022

딥러닝은 많은 데이터를 필요로 한다는 것은 이미 널리 알려져있다. 이를 통해, 딥러닝에 쓰이는 신경망의 수없이 많은 parameter들을 학습시킨다. 학습과정에는 데이터뿐 아니라, 각 데이터별로 전문가가 입력한 label이 필요한 경우가 대부분인데, 이 label을 얻는 과정은 시간과 자원 소비가 심하다. 이 문제를 완화하기 위해, few-shot learning, self-supervised learning, weak-supervised learning등이 연구되어오고 있다. 본 논문에서는, label을 상대적으로 적은 노력으로 수행하기 위한 연구들의 동향을 살펴보고, 앞으로의 개선 방향을 제시하도록 한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권2호
• /
• pp.632-657
• /
• 2022

Detecting web attacks is a major challenge, and it is observed that the use of simple models leads to low sensitivity or high false positive problems. In this study, we aim to develop a robust two-stage deep learning based stacked ensemble web application firewall. Normal and abnormal classification is carried out in the first stage of the proposed WAF model. The classification process of the types of abnormal traffics is postponed to the second stage and carried out using an integrated stacked ensemble model. By this way, clients' requests can be served without time delay, and attack types can be detected with high sensitivity. In addition to the high accuracy of the proposed model, by using the statistical similarity and diversity analyses in the study, high generalization for the ensemble model is achieved. Within the study, a comprehensive, up-to-date, and robust multi-class web anomaly dataset named GAZI-HTTP is created in accordance with the real-world situations. The performance of the proposed WAF model is compared to state-of-the-art deep learning models and previous studies using the benchmark dataset. The proposed two-stage model achieved multi-class detection rates of 97.43% and 94.77% for GAZI-HTTP and ECML-PKDD, respectively.

• 한국군사과학기술학회지
• /
• 제27권2호
• /
• pp.256-264
• /
• 2024

In the last 10 years, AI has made rapid progress, and image classification, in particular, are showing excellent performance based on deep learning. Nevertheless, due to the nature of deep learning represented by a black box, it is difficult to actually use it in critical decision-making situations such as national defense, autonomous driving, medical care, and finance due to the lack of explainability of judgement results. In order to overcome these limitations, in this study, a model description algorithm capable of local interpretation was applied to the inception network-derived AI to analyze what grounds they made when classifying national defense data. Specifically, we conduct a comparative analysis of explainability based on confidence values by performing LIME analysis from the Inception v2_resnet model and verify the similarity between human interpretations and LIME explanations. Furthermore, by comparing the LIME explanation results through the Top1 output results for Inception v3, Inception v2_resnet, and Xception models, we confirm the feasibility of comparing the efficiency and availability of deep learning networks using XAI.

• Geomechanics and Engineering
• /
• 제25권3호
• /
• pp.179-194
• /
• 2021

In this paper, to study the stability of surrounding rock during roadway excavation in different rock mass structures, the physical model test for roadway excavation process in three types of intact rock mass, layered rock mass and massive rock mass were carried out by using the self-developed two-dimensional simulation testing system of complex underground engineering. Firstly, based on the engineering background of a deep mine in eastern China, the similar materials of the most appropriate ratio in line with the similarity theory were tested, compared and determined. Then, the physical models of four different schemes with 1000 mm (height) × 1000 mm (length) × 250 mm (width) were constructed. Finally, the roadway excavation was carried out after applying boundary conditions to the physical model by the simulation testing system. The results indicate that the supporting effect of rockbolts has a great influence on the shallow surrounding rock, and the rock mass structure can affect the overall stability of the surrounding rock. Furthermore, the failure mechanism and bearing capacity of surrounding rock were further discussed from the comparison of stress evolution characteristics, distribution of stress arch, and failure modes in different schemes.