• 대한임베디드공학회논문지
• /
• 제17권3호
• /
• pp.129-138
• /
• 2022

Collecting and labeling sufficient training data, which is essential to deep learning-based visual inspection, is difficult for manufacturers to perform because it is very expensive. This paper presents a steel plate surface defect detection system with industrial-grade detection performance by training a small amount of steel plate surface images consisting of labeled and non-labeled data. To overcome the problem of lack of training data, we propose two data augmentation techniques: program-based augmentation, which generates defect images in a geometric way, and generative model-based augmentation, which learns the distribution of labeled data. We also propose a 4-step semi-supervised learning using pseudo labels and consistency training with fixed-size augmentation in order to utilize unlabeled data for training. The proposed technique obtained about 99% defect detection performance for four defect types by using 100 real images including labeled and unlabeled data.

• 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.

• 한국정보통신학회논문지
• /
• 제26권4호
• /
• pp.591-597
• /
• 2022

최근 데이터셋을 효율적으로 구축하는 방법으로 데이터 증강 기법과 관련하여 많은 연구가 이루어지고 있다. 이 중 대표적인 데이터 증강 기법은 생성적 적대 신경망(Generative Adversarial Network:GAN)을 활용하는 방법이며, 이는 생성자와 판별자를 서로 경쟁 학습시킴으로써 진짜 데이터와 유사한 데이터를 생성해내는 기법이다. 그러나, GAN을 학습할 때 환경 및 진행 정도에 따라 생성되는 유사 데이터 중에서 픽셀이 깨지는 파손 영상이 발생하는 경우가 있으며, 이러한 영상은 데이터셋으로 활용할 수 없고 학습 시간을 증가시키는 원인이 된다. 본 논문에서는 GAN 학습 과정에서 생성되는 영상 데이터의 히스토그램을 분석하여 이러한 파손 영상을 선별해내는 알고리즘을 개발하였으며, 기존 GAN에서 생성되는 영상과 비교해 본 결과 파손 영상의 비율을 33.3배(3,330%) 감소시켰다.

• 방송공학회논문지
• /
• 제28권3호
• /
• pp.275-284
• /
• 2023

유전자 발현 데이터는 질병의 예후 예측, 약물 반응성 예측 등 질병에 대한 이해와 정밀 의료 실현을 위한 연구들에 활용될 수 있지만 충분한 양의 데이터를 수집하는 데 많은 비용적 문제가 있다. 본 논문에서는 Conditional VAE에 기반한 유전자 발현 데이터 생성 모델을 제안하였다. 이전 연구인 WGAN-GP기반의 유전자 발현 생성 모델과 정형 데이터 생성 모델인 CTGAN, TVAE와 비교하여 본 논문의 Conditional VAE기반 모델이 생물학적, 통계학적으로 더 유의미한 합성 데이터를 생성할 수 있음을 보였다.

• Journal of Information Processing Systems
• /
• 제19권1호
• /
• pp.67-79
• /
• 2023

In the image field, data augmentation refers to increasing the amount of data through an editing method such as rotating or cropping a photo. In this study, a generative adversarial network (GAN) image was created using CycleGAN, and various colors of dogs were reflected through data augmentation. In particular, dog data from the Stanford Dogs Dataset and Oxford-IIIT Pet Dataset were used, and 10 breeds of dog, corresponding to 300 images each, were selected. Subsequently, a GAN image was generated using CycleGAN, and four learning groups were established: 2,000 original photos (group I); 2,000 original photos + 1,000 GAN images (group II); 3,000 original photos (group III); and 3,000 original photos + 1,000 GAN images (group IV). The amount of data in each learning group was augmented using existing data augmentation methods such as rotating, cropping, erasing, and distorting. The augmented photo data were used to train the MobileNet_v3_Large, ResNet-152, InceptionResNet_v2, and NASNet_Large frameworks to evaluate the classification accuracy and loss. The top-3 accuracy for each deep neural network model was as follows: MobileNet_v3_Large of 86.4% (group I), 85.4% (group II), 90.4% (group III), and 89.2% (group IV); ResNet-152 of 82.4% (group I), 83.7% (group II), 84.7% (group III), and 84.9% (group IV); InceptionResNet_v2 of 90.7% (group I), 88.4% (group II), 93.3% (group III), and 93.1% (group IV); and NASNet_Large of 85% (group I), 88.1% (group II), 91.8% (group III), and 92% (group IV). The InceptionResNet_v2 model exhibited the highest image classification accuracy, and the NASNet_Large model exhibited the highest increase in the accuracy owing to data augmentation.

• 품질경영학회지
• /
• 제51권1호
• /
• pp.119-129
• /
• 2023

Purpose: This study proposes a classification model for implementing condition-based maintenance (CBM) by monitoring the real-time status of a machine using acceleration sensor data collected from a vehicle. Methods: The classification model's performance was improved by applying Fourier transform to convert the acceleration sensor data from the time domain to the frequency domain. Additionally, the Generative Adversarial Network (GAN) algorithm was used to augment images and further enhance the classification model's performance. Results: Experimental results demonstrate that the GAN algorithm can effectively serve as an image augmentation technique to enhance the performance of the classification model. Consequently, the proposed approach yielded a significant improvement in the classification model's accuracy. Conclusion: While this study focused on the effectiveness of the GAN algorithm as an image augmentation method, further research is necessary to compare its performance with other image augmentation techniques. Additionally, it is essential to consider the potential for performance degradation due to class imbalance and conduct follow-up studies to address this issue.

• KEPCO Journal on Electric Power and Energy
• /
• 제8권2호
• /
• pp.137-141
• /
• 2022

To inspect the power facility faults using artificial intelligence, it need that improve the accuracy of the diagnostic model are required. Data augmentation skill using generative adversarial network (GAN) is one of the best ways to improve deep learning performance. GAN model can create realistic-looking fake images using two competitive learning networks such as discriminator and generator. In this study, we intend to verify the effectiveness of virtual data generation technology by including the fake image of power facility generated through GAN in the deep learning training set. The GAN-based fake image was created for damage of LP insulator, and ResNet based normal and defect classification model was developed to verify the effect. Through this, we analyzed the model accuracy according to the ratio of normal and defective training data.

• 동의생리병리학회지
• /
• 제38권2호
• /
• pp.49-58
• /
• 2024

The rapid advancement of generative large language models has revolutionized various real-life domains, emphasizing the importance of exploring their applications in healthcare. This study aims to examine how generative large language models are implemented in the medical domain, with the specific objective of searching for the possibility and potential of integration between generative large language models and East Asian medicine. Through a comprehensive current state analysis, we identified limitations in the deployment of generative large language models within East Asian medicine and proposed directions for future research. Our findings highlight the essential need for accumulating and generating structured data to improve the capabilities of generative large language models in East Asian medicine. Additionally, we tackle the issue of hallucination and the necessity for a robust model evaluation framework. Despite these challenges, the application of generative large language models in East Asian medicine has demonstrated promising results. Techniques such as model augmentation, multimodal structures, and knowledge distillation have the potential to significantly enhance accuracy, efficiency, and accessibility. In conclusion, we expect generative large language models to play a pivotal role in facilitating precise diagnostics, personalized treatment in clinical fields, and fostering innovation in education and research within East Asian medicine.

• 대한영상의학회지
• /
• 제81권6호
• /
• pp.1290-1304
• /
• 2020

영상처리 기반으로 의료영상을 분석하는 기법은 정상 환자와 비정상 환자를 분류, 병변 검출 및 장기나 병변의 분할 등에 사용되고 있다. 최근 인공지능 기술의 비약적 발전으로 의료영상 분석 연구들이 딥러닝 기술을 활용하여 시도되고 있다. 의료영상은 학습에 필요한 데이터를 충분히 모으기 어렵고 클래스별 데이터 수의 차이 때문에, 딥러닝 모델의 성능을 올리는데 어려움이 있다. 이러한 문제를 해결하기 위해 다양한 연구가 시도되고 있으며, 이 중 하나가 학습 데이터를 증강하는 것이다. 본 종설에서는 회전, 역상, 밝기 변화 등과 같은 영상처리 기반의 데이터 증강, 적대적생성네트워크를 활용한 데이터 증강, 그리고 기존 영상의 속성들을 섞는 등의 최신 데이터 증강 기법을 알아보고, 의료영상 연구에 적용된 사례들과 그 결과를 조사해 보고자 한다. 끝으로 데이터 증강의 필요성을 고찰하고 앞으로의 방향을 짚어본다.

• 한국컴퓨터정보학회논문지
• /
• 제26권1호
• /
• pp.57-67
• /
• 2021

최근 딥 러닝(Deep Learning) 분석에 이질적인 데이터를 함께 사용하는 멀티모달(Multi-modal) 딥러닝 기술이 많이 활용되고 있으며, 특히 텍스트로부터 자동으로 이미지를 생성해내는 Text to Image 합성에 관한 연구가 활발하게 수행되고 있다. 이미지 합성을 위한 딥러닝 학습은 방대한 양의 이미지와 이미지를 설명하는 텍스트의 쌍으로 구성된 데이터를 필요로 하므로, 소량의 데이터로부터 다량의 데이터를 생성하기 위한 데이터 증강 기법이 고안되어 왔다. 텍스트 데이터 증강의 경우 유의어 대체에 기반을 둔 기법들이 다수 사용되고 있지만, 이들 기법은 명사 단어의 유의어 대체 시 이미지의 내용과 상이한 텍스트를 생성할 가능성이 있다는 한계를 갖는다. 따라서 본 연구에서는 단어가 갖는 품사별 특징을 활용하는 텍스트 데이터 증강 방안, 즉 일부 품사에 대해 단어 계층 정보를 활용하여 단어를 대체하는 방안을 제시하였다. 또한 제안 방법론의 성능을 평가하기 위해 MSCOCO 데이터를 사용하여 실험을 수행하여 결과를 제시하였다.