• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.3
• /
• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.6
• /
• pp.1545-1559
• /
• 2023

In the cloud environment, microservices are implemented through Kubernetes, and these services can be expanded or reduced through the autoscaling function under Kubernetes, depending on the service request or resource usage. However, the increase in the number of nodes or distributed microservices in Kubernetes and the unpredictable autoscaling function make it very difficult for system administrators to conduct operations. Artificial Intelligence for IT Operations (AIOps) supports resource management for cloud services through AI and has attracted attention as a solution to these problems. For example, after the AI model learns the metric or log data collected in the microservice units, failures can be inferred by predicting the resources in future data. However, it is difficult to construct data sets for generating learning models because many microservices used for autoscaling generate different metrics or logs in the same timestamp. In this study, we propose a cloud data refining module and structure that collects metric or log data in a microservice environment implemented by Kubernetes; and arranges it into computing resources corresponding to each service so that AI models can learn and analogize service-specific failures. We obtained Kubernetes-based AIOps learning data through this module, and after learning the built dataset through the AI model, we verified the prediction result through the differences between the obtained and actual data.

• International Journal of Computer Science & Network Security
• /
• v.24 no.7
• /
• pp.170-176
• /
• 2024

Since the World Health Organization (WHO) has declared COVID-19 as pandemic, many researchers have started working on developing vaccine and developing AI systems to detect COVID-19 patient using Chest X-ray images. The purpose of this work is to improve the performance of pre-trained Deep convolution neural nets (DCNNs) on Chest X-ray images dataset specially COVID-19 which is developed by collecting from different sources such as GitHub, Kaggle. To improve the performance of Deep CNNs, data augmentation is used in this study. The COVID-19 dataset collected from GitHub was containing 257 images while the other two classes normal and pneumonia were having more than 500 images each class. There were two issues whike training DCNN model on this dataset, one is unbalanced and second is the data is very less. In order to handle these both issues, we performed data augmentation such as rotation, flipping to increase and balance the dataset. After data augmentation each class contains 510 images. Results show that augmentation on Chest X-ray images helps in improving accuracy. The accuracy before and after augmentation produced by our proposed architecture is 96.8% and 98.4% respectively.

• ETRI Journal
• /
• v.42 no.6
• /
• pp.815-826
• /
• 2020

We propose a two-dimensional (2D) scattering-center-extraction (SCE) method using sparse recovery based on the compressive-sensing theory, even with data missing from the received radar cross-section (RCS) dataset. First, using the proposed method, we generate a 2D grid via adaptive discretization that has a considerably smaller size than a fully sampled fine grid. Subsequently, the coarse estimation of 2D scattering centers is performed using both the method of iteratively reweighted least square and a general peak-finding algorithm. Finally, the fine estimation of 2D scattering centers is performed using the orthogonal matching pursuit (OMP) procedure from an adaptively sampled Fourier dictionary. The measured RCS data, as well as simulation data using the point-scatterer model, are used to evaluate the 2D SCE accuracy of the proposed method. The results indicate that the proposed method can achieve higher SCE accuracy for an incomplete RCS dataset with missing data than that achieved by the conventional OMP, basis pursuit, smoothed L0, and existing discrete spectral estimation techniques.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.4
• /
• pp.381-389
• /
• 2022

Detecting partially occluded objects is difficult due to the appearances and shapes of occluders are highly variable. These variabilities lead to challenges of localizing accurate bounding box or classifying objects with visible object parts. To address these problems, we propose a two-stage part-based attention approach for robust object detection under partial occlusion. First, our part attention network(PAN) captures the important object parts and then it is used to generate weighted object features. Based on the weighted features, the re-weighted object features are produced by our reinforced PAN(RPAN). Experiments are performed on our collected military vehicle dataset and synthetic occlusion dataset. Our method outperforms the baselines and demonstrates the robustness of detecting objects under partial occlusion.

• The Journal of Korea Robotics Society
• /
• v.18 no.1
• /
• pp.122-126
• /
• 2023

An unexpected occlusion in a real life, not in a laboratory, can be more fatal to neural networks than expected. In addition, it is virtually impossible to create a network that learns all the environmental changes as well as occlusions. Therefore, we propose an alternative approach in which the architecture and number of parameters remain unchanged while adapting to occlusion circumstances. Learning method with the term Conversion Learning classifies them more robustly by converting the weights from various occlusion situations. The experiments on MNIST dataset showed a 3.07 [%p] performance improvement over the baseline CNN model in a situation where most objects are occluded and unknowing what occlusion will appear in advance. The experimental results suggest that Conversion Learning is an efficient method to respond to environmental changes such as occluded images.

• Korean Journal of Radiology
• /
• v.23 no.3
• /
• 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.

• Journal of Internet Computing and Services
• /
• v.25 no.1
• /
• pp.189-198
• /
• 2024

AI is accepted not only in the private sector but also in the defense sector as a cutting-edge technology that must be introduced for the development of national defense. In particular, artificial intelligence has been selected as a key task in defense science and technology innovation, and the importance of data is increasing. As the national defense department shifts from a closed data policy to data sharing and activation, efforts are being made to secure high-quality data necessary for the development of national defense. In particular, we are promoting a review of the business budget system to secure data so that related procedures can be improved to reflect the unique characteristics of AI and big data, and research and development can begin with sufficient large quantities and high-quality data. However, there is a need to establish standardization and quality standards for structured data and unstructured data at the national defense level, but the defense department is still proposing standardization and quality standards for structured data, so this needs to be supplemented. In this paper, we propose an unstructured data set standard format for defense unstructured data sets, which are most needed in defense artificial intelligence, and based on this, we propose a standardization method for defense unstructured data sets.

• Korean Journal of Remote Sensing
• /
• v.38 no.4
• /
• pp.395-409
• /
• 2022

The purpose of this study is to evaluate the classification performance and applicability when land cover datasets constructed for AI training are cross validation to other areas. For study areas, Gyeongsang-do and Jeolla-do in South Korea were selected as cross validation areas, and training datasets were obtained from AI-Hub. The obtained datasets were applied to the U-Net algorithm, a semantic segmentation algorithm, for each region, and the accuracy was evaluated by applying them to the same and other test areas. There was a difference of about 13-15% in overall classification accuracy between the same and other areas. For rice field, fields and buildings, higher accuracy was shown in the Jeolla-do test areas. For roads, higher accuracy was shown in the Gyeongsang-do test areas. In terms of the difference in accuracy by weight, the result of applying the weights of Gyeongsang-do showed high accuracy for forests, while that of applying the weights of Jeolla-do showed high accuracy for dry fields. The result of land cover classification, it was found that there is a difference in classification performance of existing datasets depending on area. When constructing land cover map for AI training, it is expected that higher quality datasets can be constructed by reflecting the characteristics of various areas. This study is highly scalable from two perspectives. First, it is to apply satellite images to AI study and to the field of land cover. Second, it is expanded based on satellite images and it is possible to use a large scale area and difficult to access.

• Journal of Veterinary Science
• /
• v.23 no.1
• /
• pp.17.1-17.10
• /
• 2022

Background: Inspection of livestock farms using surveillance cameras is emerging as a means of early detection of transboundary animal disease such as African swine fever (ASF). Object tracking, a developing technology derived from object detection aims to the consistent identification of individual objects in farms. Objectives: This study was conducted as a preliminary investigation for practical application to livestock farms. With the use of a high-performance artificial intelligence (AI)-based 3D depth camera, the aim is to establish a pathway for utilizing AI models to perform advanced object tracking. Methods: Multiple crossovers by two humans will be simulated to investigate the potential of object tracking. Inspection of consistent identification will be the evidence of object tracking after crossing over. Two AI models, a fast model and an accurate model, were tested and compared with regard to their object tracking performance in 3D. Finally, the recording of pig pen was also processed with aforementioned AI model to test the possibility of 3D object detection. Results: Both AI successfully processed and provided a 3D bounding box, identification number, and distance away from camera for each individual human. The accurate detection model had better evidence than the fast detection model on 3D object tracking and showed the potential application onto pigs as a livestock. Conclusions: Preparing a custom dataset to train AI models in an appropriate farm is required for proper 3D object detection to operate object tracking for pigs at an ideal level. This will allow the farm to smoothly transit traditional methods to ASF-preventing precision livestock farming.