• Smart Media Journal
• /
• v.13 no.3
• /
• pp.27-35
• /
• 2024

This study deals with a method of combining image generation using Semi Supervised Learning based on GAN (Generative Adversarial Network) and image classification using ResNet50. Through this, a new approach was proposed to obtain more accurate and diverse results by integrating image generation and classification. The generator and discriminator are trained to distinguish generated images from actual images, and image classification is performed using ResNet50. In the experimental results, it was confirmed that the quality of the generated images changes depending on the epoch, and through this, we aim to improve the accuracy of industrial accident prediction. In addition, we would like to present an efficient method to improve the quality of image generation and increase the accuracy of image classification through the combination of GAN and ResNet50.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1000-1011
• /
• 2021

In recent years, using Deep Learning methods to apply for medical and biomedical image analysis has seen many advancements. In clinical, using Deep Learning-based approaches for cancer image analysis is one of the key applications for cancer detection and treatment. However, the scarcity and shortage of labeling images make the task of cancer detection and analysis difficult to reach high accuracy. In 2015, the Unet model was introduced and gained much attention from researchers in the field. The success of Unet model is the ability to produce high accuracy with very few input images. Since the development of Unet, there are many variants and modifications of Unet related architecture. This paper proposes a new approach of using Unet++ with pretrained EfficientNet as backbone architecture for breast tumor cell nuclei segmentation and uses the multi-organ transfer learning approach to segment nuclei of breast tumor cells. We attempt to experiment and evaluate the performance of the network on the MonuSeg training dataset and Triple Negative Breast Cancer (TNBC) testing dataset, both are Hematoxylin and Eosin (H & E)-stained images. The results have shown that EfficientUnet++ architecture and the multi-organ transfer learning approach had outperformed other techniques and produced notable accuracy for breast tumor cell nuclei segmentation.

• Journal of KIISE:Software and Applications
• /
• v.28 no.10
• /
• pp.773-784
• /
• 2001

Since documents on the Web are naturally partitioned into may document database, the efficient information retrieval process requires identifying the document database that are most likely to provide relevant documents to the query and then querying the identified document database. We propose a neural net agent approach to such an efficient information retrieval. First, we present a neural net agent that learns about underlying document database using the relevance feedbacks obtained from many retrieval experiences. For a given query, the neural net agent, which is sufficiently trained on the basis of the BPN learning mechanism, discovers the document database associated with the relevant documents and retrieves those documents effectively. In the experiment, we introduce a neural net agent based information retrieval system and evaluate its performance by comparing experimental results to those of the conventional well-known approaches.

• Proceedings of the Korea Contents Association Conference
• /
• 2005.05a
• /
• pp.475-479
• /
• 2005

In this paper we constructed semantic net that can efficiently conform retrieval and reuse of object-oriented source code. In odor that initial relevance of semantic net was constructed using thesaurus to represent concept of object-oriented inheritance between each node. Also we made up for the weak points in spreading activation method that use to activate node and line of semantic net and to impulse activation value. Therefore we proposed the method to enhance retrieval time and to keep the quality of spreading activation.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.398-400
• /
• 2019

Faced with the increasing demand for image recognition on mobile devices, how to run convolutional neural network (CNN) models on mobile devices with limited computing power and limited storage resources encourages people to study efficient model design. In recent years, many effective architectures have been proposed, such as mobilenet_v1, mobilenet_v2 and PeleeNet. However, in the process of feature selection, all these models neglect some information of shallow features, which reduces the capture of shallow feature location and semantics. In this study, we propose an effective framework based on Feature Pyramid Networks to improve the recognition accuracy of deep and shallow images while guaranteeing the recognition speed of PeleeNet structured images. Compared with PeleeNet, the accuracy of structure recognition on CIFA-10 data set increased by 4.0%.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.448-450
• /
• 2023

본 논문에서는 복부 CT 의료영상에서 근감소증 진단을 위한 지표로 활용하는 요추 3번 슬라이스를 분류하기 위해서 CNN 기반의 EfficientNetV2를 사용하여 자동분류모델을 개발하였다. 이를 위해 먼저 전체 복부 CT 의료영상에서 Thoracic, L1, L2, L3, L4, L5, Sacral 7개의 슬라이스를 검출하도록 하였다. 자동분류모델의 정확성을 측정하기 위해서 Test 데이터셋을 사용하여 Confusion Matrix 결과를 통해 개발된 모델의 성능을 검증한 결과를 보였다. 본 연구결과는 복부 CT 영상에서 기존 L3 레벨의 특정 단면에서 근육량을 측정하는 것에서 다양한 부위에서 측정할 수 있는 장점을 갖게 된다. 그리고 의료영상기반의 근감소증 진단 연구에 도움을 줄 것으로 기대하고 있다.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2003.05a
• /
• pp.254-256
• /
• 2003

This paper presents the result if a study m the development of a net type wave absorber with air pumping. The authors already show the usefulness of net type wave absorber in the previous study. However, when it comes to the long waves, it was not easy to maintain the same efficiency with net type wave absorber only. The authors tried to overcome this difficulty by adding air bubbles to the water. The results show that combining the net type wave absorber and the air bubble is more efficient than single adoptation of the wave absorber or a net type wave absorber.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.334-335
• /
• 2023

본 논문에서는 이미지 데이터와 각종 텍스트 기반의 데이터를 적절히 결합하여 유용한 데이터를 만들어 내는 방법을 제안한다. 그 사례로 편의점 상품 이미지와 편의점 프로모션 데이터, 사용자 위치정보 데이터를 적절히 결합하여 사용자가 편의점 상품 전면 이미지를 제공했을 때, 해당 상품이 어떤 편의점 브랜드에서 어떤 프로모션을 진행하고 있는지, 그리고 현재 위치에서 가까운 점포가 어디인지를 사용자에게 제공하는 시스템을 구현한다. 이미지를 어떤 데이터와 결합하는지에 따라 다양한 요구사항에 대응할 수 있다.

• ETRI Journal
• /
• v.46 no.2
• /
• pp.263-276
• /
• 2024

Different diseases occur in the brain. For instance, hereditary and progressive diseases affect and degenerate the white matter. Although addressing, diagnosing, and treating complex abnormalities in the brain is challenging, different strategies have been presented with significant advances in medical research. With state-of-art developments in artificial intelligence, new techniques are being applied to brain magnetic resonance images. Deep learning has been recently used for the segmentation and classification of brain images. In this study, we classified normal and pathological brain images using pretrained deep models through transfer learning. The EfficientNet-B5 model reached the highest accuracy of 98.39% on real data, 91.96% on augmented data, and 100% on pathological data. To verify the reliability of the model, fivefold cross-validation and a two-tier cross-test were applied. The results suggest that the proposed method performs reasonably on the classification of brain magnetic resonance images.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.29-30
• /
• 2021

본 논문에서는 이미지 분류에 쓰이는 최신 모델로 CNN과 ImageNet을 기반으로 한 EfficientNet을 활용해서 Square, Oval, Oblong, Round, Heart 총 다섯 가지의 얼굴 모양으로 분류하는 task에 두 가지 데이터로 실험해보고 추가적으로 Image Augmentation 기법을 활용해 성능향상을 보였다.