• Wind and Structures
• /
• v.36 no.6
• /
• pp.423-434
• /
• 2023

Aerodynamic force coefficients are generally obtained from traditional wind tunnel tests or computational fluid dynamics (CFD). Unfortunately, the techniques mentioned above can sometimes be cumbersome because of the cost involved, such as the computational cost and the use of heavy equipment, to name only two examples. This study proposed to build a deep neural network model to predict the aerodynamic force coefficients based on data collected from CFD simulations to overcome these drawbacks. Therefore, a series of CFD simulations were conducted using different geometric parameters to obtain the aerodynamic force coefficients, validated with wind tunnel tests. The results obtained from CFD simulations were used to create a dataset to train a multilayer perceptron artificial neural network (ANN) model. The models were obtained using three optimization algorithms: scaled conjugate gradient (SCG), Bayesian regularization (BR), and Levenberg-Marquardt algorithms (LM). Furthermore, the performance of each neural network was verified using two performance metrics, including the mean square error and the R-squared coefficient of determination. Finally, the ANN model proved to be highly accurate in predicting the force coefficients of similar bridge sections, thus circumventing the computational burden associated with CFD simulation and the cost of traditional wind tunnel tests.

• Nuclear Engineering and Technology
• /
• v.56 no.8
• /
• pp.2958-2973
• /
• 2024

Sliding bearings are crucial rotating mechanical components in nuclear power plants, and their failures can result in severe economic losses and human casualties. Deep learning provides a new approach to bearing fault diagnosis, but there is currently a lack of a universal fault diagnosis model for studying bearing-rotor systems under various operating conditions, speeds and faults. Research on bearing-rotor systems supported by sliding bearings is limited, leading to insufficient fault data. To address these issues, this paper proposes a fault diagnosis model framework for bearing-rotor systems based on a deep convolutional generative adversarial network (TF-DLGAN). This model not only exhibits outstanding fault diagnosis performance but also addresses the issue of insufficient fault data. An experimental platform is constructed to conduct fault experiments under various operating conditions, speeds and faults, establishing a dataset for sliding bearing-rotor system faults. Finally, the model's effectiveness is validated using this dataset.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.5
• /
• pp.162-177
• /
• 2020

The perception of traffic environment based on various sensors in autonomous driving system has a direct relationship with driving safety. Recently, as the perception model based on deep neural network is used due to the development of machine learning/in-depth neural network technology, a the perception model training and high quality of a training dataset are required. However, there are several realistic difficulties to collect data on all situations that may occur in self-driving. The performance of the perception model may be deteriorated due to the difference between the overseas and domestic traffic environments, and data on bad weather where the sensors can not operate normally can not guarantee the qualitative part. Therefore, it is necessary to build a virtual road environment in the simulator rather than the actual road to collect the traning data. In this paper, a training dataset collection process is suggested by diversifying the weather, illumination, sensor position, type and counts of vehicles in the simulator environment that simulates the domestic road situation according to the domestic situation. In order to achieve better performance, the authors changed the domain of image to be closer to due diligence and diversified. And the performance evaluation was conducted on the test data collected in the actual road environment, and the performance was similar to that of the model learned only by the actual environmental data.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.23 no.6
• /
• pp.549-558
• /
• 2021

In order to keep infrastructures such as tunnels and underground facilities safe, cracks of concrete lining in tunnel should be detected by regular inspections. Since regular inspections are accomplished through manual efforts using maintenance lift vehicles, it brings about traffic jam, exposes works to dangerous circumstances, and deteriorates consistency of crack inspection data. This study aims to provide methodology to automatically extract cracks from tunnel concrete lining images generated by the existing tunnel image acquisition system. Specifically, we train a deep learning based semantic segmentation model with open dataset, and evaluate its performance with the dataset from the existing tunnel image acquisition system. In particular, we compare the model performance in case of using all of a public dataset, subset of the public dataset which are related to tunnel surfaces, and the tunnel-related subset with negative examples. As a result, the model trained using the tunnel-related subset with negative examples reached the best performance. In the future, we expect that this research can be used for planning efficient model training strategy for crack detection.

• Journal of Internet Computing and Services
• /
• v.25 no.1
• /
• pp.57-67
• /
• 2024

This research investigates training methods for large language models to accurately identify sentiments and comprehend information about increasing and decreasing fluctuations in the financial domain. The main goal is to identify suitable datasets that enable these models to effectively understand expressions related to financial increases and decreases. For this purpose, we selected sentences from Wall Street Journal that included relevant financial terms and sentences generated by GPT-3.5-turbo-1106 for post-training. We assessed the impact of these datasets on language model performance using Financial PhraseBank, a benchmark dataset for financial sentiment analysis. Our findings demonstrate that post-training FinBERT, a model specialized in finance, outperformed the similarly post-trained BERT, a general domain model. Moreover, post-training with actual financial news proved to be more effective than using generated sentences, though in scenarios requiring higher generalization, models trained on generated sentences performed better. This suggests that aligning the model's domain with the domain of the area intended for improvement and choosing the right dataset are crucial for enhancing a language model's understanding and sentiment prediction accuracy. These results offer a methodology for optimizing language model performance in financial sentiment analysis tasks and suggest future research directions for more nuanced language understanding and sentiment analysis in finance. This research provides valuable insights not only for the financial sector but also for language model training across various domains.

• Journal of Biomedical Engineering Research
• /
• v.24 no.5
• /
• pp.465-471
• /
• 2003

The purpose of this research was to evaluate chronic stress using physiological parameters. Wistar rats were exposed to the sound stress for 14 days. Biosignals were acquired hourly. To develop a fuzzy inference system which can integrate physiological parameters. the parameters of the system were adjusted by the adaptive neuro-fuzzy inference system. Of the training dataset, input dataset was the physiological parameters from the biosignals and output dataset was the target values from the cortisol production. Physiological parameters were integrated using the fuzzy inference system. then 24-hour results were analyzed by the Cosinor method. Chronic stress was evaluated from the degree of circadian rhythm disturbance. Suppose that the degree of stress for initial rest period is 1. Then. the degree of stress after 14-day sound stress increased to 1.37, and increased to 1.47 after the 7-day recovery period. That is, the rat was exposed to 37%-increased amount of stress by the 14-day sound and did not recover after the 7-day recovery period.

• Journal of computational fluids engineering
• /
• v.22 no.1
• /
• pp.59-66
• /
• 2017

The guideline of selecting the number of snapshot dataset, $N_s$ in proper orthogonal decomposition(POD) was presented via the analysis of Eigen values based on the singular value decomposition(SVD). In POD, snapshot datasets from the solutions of Euler or Navier-Stokes equations are utilized to SVD and a reduced order model(ROM) is constructed as the combination of Eigen vectors. The ROM is subsequently applied to reconstruct the flowfield data with new set of flow conditions, thereby enhancing the computational efficiency. The overall computational efficiency and accuracy of POD is dependent on the number of snapshot dataset; however, there is no reliable guideline of determining $N_s$. In order to resolve this problem, the order of maximum to minimum Eigen value ratio, O(R) from SVD was analyzed and presented for the decision of $N_s$; in case of steady flow, $N_s$ should be determined to make O(R) be $10^9$. For unsteady flow, $N_s$ should be increased to make O(R) be $10^{11\sim12}$. This strategy of selecting the snapshot dataset was applied to two dimensional NACA0012 airfoil and vortex flow problems including steady and unsteady cases and the numerical accuracies according to $N_s$ and O(R) were discussed.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.173-173
• /
• 2023

The Mekong River Basin (MRB) is a crucial watershed in Asia, impacting over 60 million people across six developing nations. Accurate satellite-based precipitation products (SPPs) are essential for effective hydrological and watershed management in this region. However, the performance of SPPs has been varied and limited. The APHRODITE product, a unique gauge-based dataset for MRB, is widely used but is only available until 2015. In this study, we present a novel framework for correcting SPPs in the MRB by employing a deep learning approach that combines convolutional neural networks and encoder-decoder architecture to address pixel-by-pixel bias and enhance accuracy. The DLF was applied to four widely used SPPs (TRMM, CMORPH, CHIRPS, and PERSIANN-CDR) in MRB. For the original SPPs, the TRMM product outperformed the other SPPs. Results revealed that the DLF effectively bridged the spatial-temporal gap between the SPPs and the gauge-based dataset (APHRODITE). Among the four corrected products, ADJ-TRMM demonstrated the best performance, followed by ADJ-CDR, ADJ-CHIRPS, and ADJ-CMORPH. The DLF offered a robust and adaptable solution for bias correction in the MRB and beyond, capable of detecting intricate patterns and learning from data to make appropriate adjustments. With the discontinuation of the APHRODITE product, DLF represents a promising solution for generating a more current and reliable dataset for MRB research. This research showcased the potential of deep learning-based methods for improving the accuracy of SPPs, particularly in regions like the MRB, where gauge-based datasets are limited or discontinued.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.1
• /
• pp.11-17
• /
• 2023

This paper proposes a lightweight deep learning network for detecting an image splicing forgery. The research on image forgery detection using CNN, a deep learning network, and research on detecting and localizing forgery in pixel units are in progress. Among them, CAT-Net, which learns the discrete cosine transform coefficients of images together with images, was released in 2022. The DCT coefficients presented by CAT-Net are combined with the JPEG artifact learning module and the backbone model as pre-learning, and the weights are fixed. The dataset used for pre-training is not included in the public dataset, and the backbone model has a relatively large number of network parameters, which causes overfitting in a small dataset, hindering generalization performance. In this paper, this learning module is designed to learn the characterization depending on the DCT domain in real-time during network training without pre-training. The DCT RRU-Net proposed in this paper is a network that combines RRU-Net which detects forgery by learning only images and JPEG artifact learning module. It is confirmed that the network parameters are less than those of CAT-Net, the detection performance of forgery is better than that of RRU-Net, and the generalization performance for various datasets improves through the network architecture and training method of DCT RRU-Net.

• Journal of The Geomorphological Association of Korea
• /
• v.27 no.3
• /
• pp.53-73
• /
• 2020

Morphology and grain size distribution of coastal dunes should be well documented because they are critical to dune's buffering capacity and resilience against storm surges. The nationwide coastal dune survey produced the dataset, including beach-dune topographic profiles and grain size parameters for frontal beaches, foredunes, and inland dunes. This research investigated the dataset to describe geomorphic and textural properties of coastal dunes: foredune slopes, dune heights above approximately highest high water, mean size, and sorting, together with associated variables of coastal setting that influence coastal dunes. It also explores the possibility of a dune type scheme based on gran size trends. The results are as follows. First, the coast in which dunes are developed is the primary control on foredune morphology and sediment texture. Coastal dunes on the east coast were developed more alongshore rather than inland, with gentler slopes on the higher ground and out of coarser sand. The shore aspect contributes to this pattern because the east coast cannot benefit from prevailing northwesterly. Second, grain size trends from beaches through foredunes to inland dunes were little identified. Third, 12 dune types were identified from 69 dunes, showing the indicative capability for the status of beaches and dunes. We confirmed that the dataset could increase our understanding of the overall characteristics of coastal dune morphology and texture, though there is something to be improved, for example, establishing the refined and comprehensive field survey protocol.