• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.49.2-49.2
• /
• 2019

We present results from our long-term observing campaign, using the NASA IRTF at Maunakea, to obtain 2 - 4 ㎛ spectra of 118 red point sources in the line of sight to the Galactic Center (GC). Our sample is largely composed of point sources selected from near- and mid-infrared photometry, but also includes a number of massive young stellar objects. Many of these sources show high foreground extinction as shown by deep 3.4 ㎛ aliphatic hydrocarbon absorption feature, which is a characteristic of the diffuse ISM and comes from the long line of sight through the diffuse medium toward the Central Molecular Zone (CMZ), the central 300 pc region of the GC. The deep 3.1 ㎛ H₂O ice absorption band coming from the local, dense material in the GC CMZ suggests that most sources are likely located in the GC CMZ. A few of these sources show weak CCH₃OH ice absorption at 3.535 ㎛, which can provide a strong constraint on the CCH₃OH ice formation in the unique environment of the CMZ. From the best-fitting models, the optical depths of these features are determined and used to generate a well-rounded view of the ice composition across the GC CMZ and the spectral characteristics of massive YSOs in the GC.

• Journal of Animal Science and Technology
• /
• v.65 no.6
• /
• pp.1254-1269
• /
• 2023

This study aims to predict the change in corn share according to the grazing of 20 gestational sows in a mature corn field by taking images with a camera-equipped unmanned air vehicle (UAV). Deep learning based on convolutional neural networks (CNNs) has been verified for its performance in various areas. It has also demonstrated high recognition accuracy and detection time in agricultural applications such as pest and disease diagnosis and prediction. A large amount of data is required to train CNNs effectively. Still, since UAVs capture only a limited number of images, we propose a data augmentation method that can effectively increase data. And most occupancy prediction predicts occupancy by designing a CNN-based object detector for an image and counting the number of recognized objects or calculating the number of pixels occupied by an object. These methods require complex occupancy rate calculations; the accuracy depends on whether the object features of interest are visible in the image. However, in this study, CNN is not approached as a corn object detection and classification problem but as a function approximation and regression problem so that the occupancy rate of corn objects in an image can be represented as the CNN output. The proposed method effectively estimates occupancy for a limited number of cornfield photos, shows excellent prediction accuracy, and confirms the potential and scalability of deep learning.

• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.673-687
• /
• 2023

Convolutional neural network-based deep learning technology is the most commonly used in image identification, but it requires large-scale data for training. Therefore, application in specific fields in which data acquisition is limited, such as in the military, may be challenging. In particular, the identification of ground weapon systems is a very important mission, and high identification accuracy is required. Accordingly, various studies have been conducted to achieve high performance using small-scale data. Among them, the ensemble method, which achieves excellent performance through the prediction average of the pre-trained models, is the most representative method; however, it requires considerable time and effort to find the optimal combination of ensemble models. In addition, there is a performance limitation in the prediction results obtained by using an ensemble method. Furthermore, it is difficult to obtain the ensemble effect using models with imbalanced classification accuracies. In this paper, we propose a transfer learning-based feature fusion technique for heterogeneous models that extracts and fuses features of pre-trained heterogeneous models and finally, fine-tunes hyperparameters of the fully connected layer to improve the classification accuracy. The experimental results of this study indicate that it is possible to overcome the limitations of the existing ensemble methods by improving the classification accuracy through feature fusion between heterogeneous models based on transfer learning.

• Wind and Structures
• /
• v.38 no.1
• /
• pp.75-91
• /
• 2024

Reliable wind signal reconstruction can be beneficial to the operational safety of long-span bridges. Non-Gaussian characteristics of wind signals make the reconstruction process challenging. In this paper, non-Gaussian wind signals are converted into a combined prediction of two kinds of features, actual wind speeds and wind angles of attack. First, two decomposition techniques, empirical mode decomposition (EMD) and variational mode decomposition (VMD), are introduced to decompose wind signals into intrinsic mode functions (IMFs) to reduce the randomness of wind signals. Their principles and applicability are also discussed. Then, four artificial intelligence (AI) algorithms are utilized for wind signal reconstruction by combining the particle swarm optimization (PSO) algorithm with back propagation neural network (BPNN), support vector regression (SVR), long short-term memory (LSTM) and bidirectional long short-term memory (Bi-LSTM), respectively. Measured wind signals from a bridge site in a deep-cutting gorge are taken as experimental subjects. The results showed that the reconstruction error of high-frequency components of EMD is too large. On the contrary, VMD fully extracts the multiscale rules of the signal, reduces the component complexity. The combination of VMD-PSO-Bi-LSTM is demonstrated to be the most effective among all hybrid models.

• Journal of information and communication convergence engineering
• /
• v.22 no.1
• /
• pp.44-55
• /
• 2024

High-utility itemset mining (HUIM) is a dominant technology that enables enterprises to make real-time decisions, including supply chain management, customer segmentation, and business analytics. However, classical support value-driven Apriori solutions are confined and unable to meet real-time enterprise demands, especially for large amounts of input data. This study introduces a groundbreaking model for top-N high utility itemset mining in real-time enterprise applications. Unlike traditional Apriori-based solutions, the proposed convolutional sequential embedding metrics-driven cosine-similarity-based multilayer perception learning model leverages global and contextual features, including semantic attributes, for enhanced top-N recommendations over sequential transactions. The MATLAB-based simulations of the model on diverse datasets, demonstrated an impressive precision (0.5632), mean absolute error (MAE) (0.7610), hit rate (HR)@K (0.5720), and normalized discounted cumulative gain (NDCG)@K (0.4268). The average MAE across different datasets and latent dimensions was 0.608. Additionally, the model achieved remarkable cumulative accuracy and precision of 97.94% and 97.04% in performance, respectively, surpassing existing state-of-the-art models. This affirms the robustness and effectiveness of the proposed model in real-time enterprise scenarios.

• Nuclear Engineering and Technology
• /
• v.55 no.11
• /
• pp.4083-4095
• /
• 2023

Currently, various research institutes in Korea are conducting research to develop a safety case for deep geological repository for high-level radioactive waste (HLW). In the past, low and intermediate-level waste (LILW) was approved by a regulatory body by performing a post-closure safety assessment, but HLW has different disposal characteristics and safety objectives are different. Therefore, in the case of HLW, safety assessment should be performed based on these changed conditions, and specific procedures are also under development. In this paper, the regulatory status of prior research institutes, feature, event and process (FEP) and scenario development cases were investigated for well-organized FEP and scenario development methodologies. In addition, through the results of these surveys, the requirements and procedures necessary for the FEP and scenario development stage during the safety assessment of repository for HLW were presented. These review results are expected to be used to identify the overall status of previous studies in conducting post-closure risk assessment for HLW repository, starting with identifying regulatory requirements, the most basic element.

• Journal of Web Engineering
• /
• v.21 no.1
• /
• pp.27-52
• /
• 2021

With recent increases in the number of network-connected devices, the number of edge computing services that provide similar functions has increased. Therefore, it is important to recommend an optimal edge computing service, based on quality-of-service (QoS). However, in the real world, there is a cold-start problem in QoS data: highly sparse invocation. Therefore, it is difficult to recommend a suitable service to the user. Deep learning techniques were applied to address this problem, or context information was used to extract deep features between users and services. However, edge computing environment has not been considered in previous studies. Our goal is to predict the QoS values in real edge computing environments with improved accuracy. To this end, we propose a GAIN-QoS technique. It clusters services based on their location information, calculates the distance between services and users in each cluster, and brings the QoS values of users within a certain distance. We apply a Generative Adversarial Imputation Nets (GAIN) model and perform QoS prediction based on this reconstructed user service invocation matrix. When the density is low, GAIN-QoS shows superior performance to other techniques. In addition, the distance between the service and user slightly affects performance. Thus, compared to other methods, the proposed method can significantly improve the accuracy of QoS prediction for edge computing, which suffers from cold-start problem.

• The Korean Journal of Food And Nutrition
• /
• v.37 no.4
• /
• pp.197-210
• /
• 2024

This study aims to develop a deep learning model to monitor rice serving amounts in institutional foodservice, enhancing personalized nutrition management. The goal is to identify the best convolutional neural network (CNN) for detecting rice quantities on serving trays, addressing balanced dietary intake challenges. Both a vanilla CNN and 12 pre-trained CNNs were tested, using features extracted from images of varying rice quantities on white trays. Configurations included optimizers, image generation, dropout, feature extraction, and fine-tuning, with top-1 validation accuracy as the evaluation metric. The vanilla CNN achieved 60% top-1 validation accuracy, while pre-trained CNNs significantly improved performance, reaching up to 90% accuracy. MobileNetV2, suitable for mobile devices, achieved a minimum 76% accuracy. These results suggest the model can effectively monitor rice servings, with potential for improvement through ongoing data collection and training. This development represents a significant advancement in personalized nutrition management, with high validation accuracy indicating its potential utility in dietary management. Continuous improvement based on expanding datasets promises enhanced precision and reliability, contributing to better health outcomes.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.327-334
• /
• 2024

Bridge inspection is crucial for infrastructure maintenance. Current inspections based on computer vision primarily focus on identifying simple defects such as cracks or corrosion. These detection results can serve merely as preliminary references for bridge inspection reports. To generate detailed reports, on-site engineers must still present the structural conditions through lengthy textual descriptions. This process is time-consuming, costly, and prone to human error. To bridge this gap, we propose a deep learning-based framework to generate detailed and accurate textual descriptions, laying the foundation for automating bridge inspection reports. This framework is built around an encoder-decoder architecture, utilizing Convolutional Neural Networks (CNN) for encoding image features and Gated Recurrent Units (GRU) as the decoder, combined with a dynamically adaptive attention mechanism. The experimental results demonstrate this approach's effectiveness, proving that the introduction of the attention mechanism contributes to improved generation results. Moreover, it is worth noting that, through comparative experiments on image restoration, we found that the model requires further improvement in terms of explainability. In summary, this study demonstrates the potential and practical application of image captioning techniques for bridge defect detection, and future research can further explore the integration of domain knowledge with artificial intelligence (AI).

• The Journal of Society for e-Business Studies
• /
• v.27 no.1
• /
• pp.63-79
• /
• 2022

Recently, various studies have been conducted on stock price prediction using machine learning and deep learning techniques. Among these studies, the latest studies have attempted to predict stock prices using limit order books, which contain buy and sell order information of stocks. However, most of the studies using limit order books consider only the trend of limit order books over the most recent period of a specified length, and few studies consider both the medium and short term trends of limit order books. Therefore, in this paper, we propose a deep learning-based prediction model that predicts stock price more accurately by considering both the medium and short term trends of limit order books. Moreover, the proposed model considers news headlines during the same period to reflect the qualitative status of the company in the stock price prediction. The proposed model extracts the features of changes in limit order books with CNNs and the features of news headlines using Word2vec, and combines these information to predict whether a particular company's stock will rise or fall the next day. We conducted experiments to predict the daily stock price fluctuations of five stocks (Amazon, Apple, Facebook, Google, Tesla) with the proposed model using the real NASDAQ limit order book data and news headline data, and the proposed model improved the accuracy by up to 17.66%p and the average by 14.47%p on average. In addition, we conducted a simulated investment with the proposed model and earned a minimum of $492.46 and a maximum of $2,840.93 depending on the stock for 21 business days.