• Korean Journal of Radiology
• /
• v.22 no.12
• /
• pp.2073-2081
• /
• 2021

Deep learning-based applications have great potential to enhance the quality of medical services. The power of deep learning depends on open databases and innovation. Radiologists can act as important mediators between deep learning and medicine by simultaneously playing pioneering and gatekeeping roles. The application of deep learning technology in medicine is sometimes restricted by ethical or legal issues, including patient privacy and confidentiality, data ownership, and limitations in patient agreement. In this paper, we present an open platform, MI2RLNet, for sharing source code and various pre-trained weights for models to use in downstream tasks, including education, application, and transfer learning, to encourage deep learning research in radiology. In addition, we describe how to use this open platform in the GitHub environment. Our source code and models may contribute to further deep learning research in radiology, which may facilitate applications in medicine and healthcare, especially in medical imaging, in the near future. All code is available at https://github.com/mi2rl/MI2RLNet.

• Geomechanics and Engineering
• /
• v.38 no.1
• /
• pp.29-44
• /
• 2024

This research investigates the effectiveness of data augmentation techniques in the automated analysis of B-scan images from ground-penetrating radar (GPR) using deep learning. In spite of the growing interest in automating GPR data analysis and advancements in deep learning for image classification and object detection, many deep learning-based GPR data analysis studies have been limited by the availability of large, diverse GPR datasets. Data augmentation techniques are widely used in deep learning to improve model performance. In this study, we applied four data augmentation techniques (geometric transformation, color-space transformation, noise injection, and applying kernel filter) to the GPR datasets obtained from a testbed. A deep learning model for GPR data analysis was developed using three models (Faster R-CNN ResNet, SSD ResNet, and EfficientDet) based on transfer learning. It was found that data augmentation significantly enhances model performance across all cases, with the mAP and AR for the Faster R-CNN ResNet model increasing by approximately 4%, achieving a maximum mAP (Intersection over Union = 0.5:1.0) of 87.5% and maximum AR of 90.5%. These results highlight the importance of data augmentation in improving the robustness and accuracy of deep learning models for GPR B-scan analysis. The enhanced detection capabilities achieved through these techniques contribute to more reliable subsurface investigations in geotechnical engineering.

• International journal of advanced smart convergence
• /
• v.9 no.2
• /
• pp.90-104
• /
• 2020

It is difficult for non-experts to build machine learning (ML) models at the level that satisfies their needs. Deep learning models are even more challenging because it is unclear how to improve the model, and a trial-and-error approach is not feasible since training these models are time-consuming. To assist these novice users, we examined how interactive and explainable feedback while training a deep learning network can contribute to model performance and users' satisfaction, focusing on the data preparation process. We conducted a user study with 31 participants without expertise, where they were asked to improve the accuracy of a deep learning model, varying feedback conditions. While no significant performance gain was observed, we identified potential barriers during the process and found that interactive and explainable feedback provide complementary benefits for improving users' understanding of ML. We conclude with implications for designing an interface for building ML models for novice users.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.3
• /
• pp.346-354
• /
• 2024

Deep learning models require high computing power due to a substantial amount of computation. It is difficult to use them in devices with limited computing environments, such as coastal surveillance equipments. In this study, a lightweight model is constructed by analyzing the weight changes of the convolutional layers during the training process based on MobileNet and then pruning the layers that affects the model less. The performance comparison results show that the lightweight model maintains performance while reducing computational load, parameters, model size, and data processing speed. As a result of this study, an effective pruning method for constructing lightweight deep learning models and the possibility of using equipment resources efficiently through lightweight models in limited computing environments such as coastal surveillance equipments are presented.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.4_2
• /
• pp.1001-1007
• /
• 2024

Recent deep learning algorithms for object detection in real-time play a crucial role in various applications such as autonomous driving, traffic monitoring, health care, and water quality monitoring. The size of small objects, in particular, significantly impacts the accuracy of detection models. However, data containing small objects can lead to underfitting issues in models. Therefore, this study developed a deep learning model capable of quickly detecting small objects to provide more accurate predictions. The RE-SOD (Residual block based Small Object Detector) developed in this research enhances the detection performance for small objects by using RGB separation preprocessing and residual blocks. The model achieved an accuracy of 1.0 in image classification and an mAP50-95 score of 0.944 in object detection. The performance of this model was validated by comparing it with real-time detection models such as YOLOv5, YOLOv7, and YOLOv8.

• Electronics and Telecommunications Trends
• /
• v.33 no.4
• /
• pp.1-13
• /
• 2018

Deep learning (DL) models have been widely applied to AI applications such image recognition and language translation with big data. Recently, DL models have becomes larger and more complicated, and have merged together. For the accelerated training of a large-scale deep learning model, model parallelism that partitions the model parameters for non-shared parallel access and updates across multiple machines was provided by a few distributed deep learning frameworks. Model parallelism as a training acceleration method, however, is not as commonly used as data parallelism owing to the difficulty of efficient model parallelism. This paper provides a comprehensive survey of the state of the art in model parallelism by comparing the implementation technologies in several deep learning frameworks that support model parallelism, and suggests a future research directions for improving model parallelism technology.

• Journal of Korean Society of Water and Wastewater
• /
• v.34 no.6
• /
• pp.481-493
• /
• 2020

Deep learning models, which imitate the function of human brain, have drawn attention from many engineering fields (mechanical, agricultural, and computer engineering etc). The major advantages of deep learning in engineering fields can be summarized by objects detection, classification, and time-series prediction. As well, it has been applied into environmental science and engineering fields. Here, we compiled our previous attempts to apply deep learning models in water-environment field and presented the future opportunities.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.2
• /
• pp.46.2-46.2
• /
• 2021

We present solar event auto detection using deep-learning-based object detection algorithms and DeepSDO event dataset. DeepSDO event dataset is a new detection dataset with bounding boxed as ground-truth for three solar event (coronal holes, sunspots and prominences) features using Solar Dynamics Observatory data. To access the reliability of DeepSDO event dataset, we compared to HEK data. We train two representative object detection models, the Single Shot MultiBox Detector (SSD) and the Faster Region-based Convolutional Neural Network (R-CNN) with DeepSDO event dataset. We compared the performance of the two models for three solar events and this study demonstrates that deep learning-based object detection can successfully detect multiple types of solar events. In addition, we provide DeepSDO event dataset for further achievements event detection in solar physics.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.17-25
• /
• 2023

In this paper, we propose a lightweight deep learning architecture tailored for efficient text detection in fashion design sketch images. Given the increasing prominence of Digital Transformation in the fashion industry, there is a growing emphasis on harnessing digital tools for creating fashion design sketches. As digitization becomes more pervasive in the fashion design process, the initial stages of text detection and recognition take on pivotal roles. In this study, a lightweight network was designed by building upon existing text detection deep learning models, taking into consideration the unique characteristics of apparel design drawings. Additionally, a separately collected dataset of apparel design drawings was added to train the deep learning model. Experimental results underscore the superior performance of our proposed deep learning model, outperforming existing text detection models by approximately 20% when applied to fashion design sketch images. As a result, this paper is expected to contribute to the Digital Transformation in the field of clothing design by means of research on optimizing deep learning models and detecting specialized text information.

• Journal of information and communication convergence engineering
• /
• v.21 no.1
• /
• pp.9-16
• /
• 2023

The natural language on social network platforms has a certain front-to-back dependency in structure, and the direct conversion of Chinese text into a vector makes the dimensionality very high, thereby resulting in the low accuracy of existing text classification methods. To this end, this study establishes a deep learning model that combines a big data ultra-deep convolutional neural network (UDCNN) and long short-term memory network (LSTM). The deep structure of UDCNN is used to extract the features of text vector classification. The LSTM stores historical information to extract the context dependency of long texts, and word embedding is introduced to convert the text into low-dimensional vectors. Experiments are conducted on the social network platforms Sogou corpus and the University HowNet Chinese corpus. The research results show that compared with CNN + rand, LSTM, and other models, the neural network deep learning hybrid model can effectively improve the accuracy of text classification.