• Korean Chemical Engineering Research
• /
• v.61 no.1
• /
• pp.123-141
• /
• 2023

A sufficient amount of data with quality is needed for training artificial neural networks (ANNs). However, developing ANN models with a small amount of data often appears in engineering fields. This paper presented an ANN model to improve prediction performance of the ammonia emission amount with 83 data. The ammonia emission rate included eleven inputs and two outputs (maximum ammonia loss, N_max and time to reach half of N_max, K_m). Categorical input variables were transformed into multi-dimensional equal-distance variables, and 13 data were added into 66 training data using a generative adversarial network. Hyperparameters (number of layers, number of neurons, and activation function) of ANN were optimized using Gaussian process. Using 17 test data, the previous ANN model (Lim et al., 2007) showed the mean absolute error (MAE) of K_m and N_max to 0.0668 and 0.1860, respectively. The present ANN outperformed the previous model, reducing MAE by 38% and 56%.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.1
• /
• pp.1-7
• /
• 2023

An artificial intelligence (AI) method based on image deep learning is proposed to predict the entire displacement shape of a structure using the feature of partial displacements. The performance of the method was investigated through a structural test of a steel frame. An image-to-image regression (I2IR) training method was developed based on the U-Net layer for image recognition. In the I2IR method, the U-Net is modified to generate images of entire displacement shapes when images of partial displacement shapes of structures are input to the AI network. Furthermore, the training of displacements combined with the location feature was developed so that nodal displacement values with corresponding nodal coordinates could be used in AI training. The proposed training methods can consider correlations between nodal displacements in 3D space, and the accuracy of displacement predictions is improved compared with artificial neural network training methods. Displacements of the steel frame were predicted during the structural tests using the proposed methods and compared with 3D scanning data of displacement shapes. The results show that the proposed AI prediction properly follows the measured displacements using 3D scanning.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.166-172
• /
• 2022

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.2
• /
• pp.149-156
• /
• 2023

Recently, concerns about natural disasters such as earthquakes, tsunamis and typhoons have increased. As the magnitude and frequency of earthquakes increase, research is needed to prevent structures from collapsing due to earthquake loads. Research is needed to increase the ductility of columns to prevent the collapse of structures. In this study, the ductility improvement of square columns achieved by applying spiral stirrups to square columns. Square columns reinforced with spiral stirrups are more resistant to repetitive loads such as seismic loads than columns reinforced with tie stirrups. Also, the spiral stirrups can apply better confinement to the concrete. In this study, an uniaxial compression test was conducted to evaluate the performance of columns reinforced with spiral stirrups. The results showed that the columns reinforced with spiral stirrups in both the circular and square columns showed higher compressive strength than the columns reinforced with the tie stirrups. In addition, the columns reinforced with spiral stirrups for both the square and circle columns, showed a tendency to endure the load even after the initial cracking and rebar yielding.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.2
• /
• pp.107-114
• /
• 2022

In order to classify 3D film images as right or wrong, it is necessary to detect the pattern in a 3D film image. However, if the contrast of the pixels in the 3D film image is low, it is not easy to classify as the right and wrong 3D film images because the pattern in the image might not be clear. In this paper, we propose a method of classifying 3D film images as right or wrong by comparing the width at a specific frequency of each histogram after obtaining the histogram. Since, it is classified using the width of the histogram, the analysis process is not complicated. From the experiment, the histograms of right and wrong 3D film images were distinctly different, and the proposed algorithm reflects these features, and showed that all 3D film images were accurately classified at a specific frequency of the histogram. The performance of the proposed algorithm was verified to be the best through the comparison test with the other methods such as image subtraction, otsu thresholding, canny edge detection, morphological geodesic active contour, and support vector machines, and it was shown that excellent classification accuracy could be obtained without detecting the patterns in 3D film images.

• Journal of the Korea Institute of Building Construction
• /
• v.23 no.2
• /
• pp.153-164
• /
• 2023

The objective of this study is to examine the removal rate of air pollutants, specifically sulfur oxides (SO_x) and nitrogen oxides(NO_x), using concrete permeable blocks containing zeolite beads coated with materials capable of eliminating these pollutants. Titanium dioxide(TiO₂) powder and coconut shell powder were utilized for the removal of SO_x and NO_x and were applied as coatings on the zeolite beads. Concrete permeable block specimens embedded with the coated zeolite beads were produced using an actual factory production line. Test results demonstrated that the concrete permeable block containing zeolite beads coated with coconut shell powder in the surface layer achieved SO_x and NO_x removal rates of 12.5% and 99%, respectively, exhibiting superior performance compared to other blocks. Additionally, the flexural strength and slip resistance were 5.3MPa and 65BPN or higher, respectively, satisfying the requirements specified in KS F 4419 and KS F 4561. Conversely, the permeability coefficient exhibited low permeability, with grades 2 and 3 before and after contaminant pollution, according to the standard for 'design, construction, and maintenance of pavement using permeable block'. In conclusion, incorporating zeolite beads coated with coconut shell powder in the surface layer enables simultaneous removal of SO_x and NO_x, irrespective of ultraviolet rays, while maintaining adequate flexural strength and slip resistance. However, the permeability is significantly reduced, necessitating further improvements.

• Tribology and Lubricants
• /
• v.39 no.2
• /
• pp.49-55
• /
• 2023

Currently, the demand for green technologies toward a sustainable future is rapidly increasing due to growing concern over environmental issues. Methanol is biodegradable and can provide clean combustion to reduce sulfur oxide and nitrogen oxide emissions, and therefore it is a candidate fuel for marine engines. However, the effect of methanol on tribological characteristic degradation should be addressed for methanol-fueled engines. In this study, the methanol addition effects on tribological characteristic degradation is experimentally assessed using a pin-on-disk tribo-tester. Ni-based alloy is used as a target material due to its broad applicability as an engine component material. For a lubricant, engine oil with and without methanol are used. The tests are conducted for up to 10,000 cycles under boundary lubrication while the change in friction force is monitored. Additionally, the wear rate is determined based on laser scanning confocal microscope data. An additional test in which methanol is added at regular intervals is performed with an aim to directly observe its effect on friction. Overall, the friction coefficient increases slightly with increasing methanol concentration. Furthermore, the wear rate of the pin and disk increase significantly with methanol addition. The results also indicate that the friction increases instantaneously with methanol addition at the contacting interface. These findings may be useful for better understanding the methanol effect on the tribological characteristics of Ni-based alloys for methanol-fueled engines with improved performance.

• The Journal of KAIRB
• /
• v.5 no.1
• /
• pp.14-20
• /
• 2023

Purpose: To obtain fundamental data on selection tools for an internal audit and develop a new guideline. We scored the indicated points from the internal audit, identified the research progress and problems that occurred, and confirmed the validity of the risk factors involved. Methods: Of the 63 internal audits conducted by Keimyung University Dongsan Hospital from 2014 to 2021, we analyzed 55 clinical trials with an inspection checklist. We excluded 8 that failed to transfer data and refused to comply with the internal audit. The statistical summary of the collected data was verified and interpreted by using frequency analysis and a chi-square test. Result: Of total 55 cases included in the internal audit, sponsor-initiated trial (SIT) was 63.6% (vs. investigator-initiated trial [IIT]), clinical trial for investigational drug was 71.0% (vs. nonclinical or clinical trial for investigational device), domestic multicenter trial was 60.0% (vs. single center or multinational multicenter trial), and trial requisition for MFDS approval was 69.1% (vs. exception for MFDS approval). The 10 areas of the clinical trial inspection checklist (reports, protection of subjects, compliance with protocols, records, management of investigational drug and/or device, delegation of duties, qualification of investigators, management of specimen, contract-agreement and approval of protocols, and preservation of recorded documents) were weighted between 2 to 5 points. The average of the total points was 16.09±13.2 and 20 clinical trials were above the average. As a result of comparing the average of the total points weighted by year, the highest score was in 2020. The 4 factors that play significant roles in determining the internal quality were (1) principal subjects that initiated the clinical trials (p=0.049), (2) type (p=0.003), (3) phase of clinical trials (p=0.024), and (4) number of registered subjects reported at the time of continuing deliberation (p=0.019). Of the 10 areas of the clinical trial inspection checklist, 'record' was the most inappropriate and insufficient. We found more indicated points; the quality of performance declined in IIT, nonclinical trials, and other clinical trials that were not in phase I1-IV4, and the study of more than 30 registered subjects at the time of continuing review. Conclusion: If an institution has an internal audit selection tool that reflects the aforementioned risk factors, it will be possible to effectively manage high-risk studies; thereby, contributing to an efficient internal audit and improving the quality of clinical trials.

• Geophysics and Geophysical Exploration
• /
• v.26 no.2
• /
• pp.84-93
• /
• 2023

The supervised learning-based deep-learning seismic inversion techniques have demonstrated successful performance in synthetic data examples targeting small-scale areas. The supervised learning-based deep-learning seismic inversion uses time-domain wavefields as input and subsurface velocity models as output. Because the time-domain wavefields contain various types of wave information, the data size is considerably large. Therefore, research applying supervised learning-based deep-learning seismic inversion trained with a significant amount of field-scale data has not yet been conducted. In this study, we predict subsurface velocity models using Laplace-domain wavefields as input instead of time-domain wavefields to apply a supervised learning-based deep-learning seismic inversion technique to field-scale data. Using Laplace-domain wavefields instead of time-domain wavefields significantly reduces the size of the input data, thereby accelerating the neural network training, although the resolution of the results is reduced. Additionally, a large grid interval can be used to efficiently predict the velocity model of the field data size, and the results obtained can be used as the initial model for subsequent inversions. The neural network is trained using only synthetic data by generating a massive synthetic velocity model and Laplace-domain wavefields of the same size as the field-scale data. In addition, we adopt a towed-streamer acquisition geometry to simulate a marine seismic survey. Testing the trained network on numerical examples using the test data and a benchmark model yielded appropriate background velocity models.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.2
• /
• pp.104-108
• /
• 2023

Because of recent expansion of the electric car market. it is highly growing that should be supplemented its performance and safely issue. The EMI problem due to the interlocking of electrical components that causes various safety problems such as fire in electric vehicles is emerging every time. We strive to achieve optimal charging efficiency by combining various technologies and reduce radioactive noise among the EMI noise of a weirless charging control module, one of the important parts of an electric vehicle was designed and tested. In order to analyze the EMI problems occurring in the wireless charging control module, the optimized wireless charging control module by applying the optimization design technology by learning the accumulated test data for critical factors by utilizing the Python-based script function in the Ansys simulation tool. It showed an EMI noise improvement effect of 25 dBu V/m compared to the charge control module. These results not only contribute to the development of a more stable and reliable weirless charging function in electric vehicles, but also increase the usability and efficiency of electric vehicles. This allows electric vehicles to be more usable and efficient, making them an environmentally friendly alternative.